Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b6422c763e | ||
|
|
22685f528a | ||
|
|
576884b199 | ||
|
|
9f5744d4c0 | ||
|
|
634bea21f5 | ||
|
|
42bcb91ca0 | ||
|
|
4709668995 | ||
|
|
79ee0ec264 | ||
|
|
d764b5cca2 | ||
|
|
b72b4c5a5f | ||
|
|
268c89f9a2 | ||
|
|
2907a7c678 | ||
|
|
fcd3e4336b | ||
|
|
48b3f119be | ||
|
|
efd507fb3b | ||
|
|
39238f077d | ||
|
|
5636e2be5e | ||
|
|
d25b42e41b | ||
|
|
3e419abf84 | ||
|
|
a55b148ecc | ||
|
|
cf077902d0 | ||
|
|
82908b3f67 | ||
|
|
b02f79b58b | ||
|
|
2b43d57d42 | ||
|
|
e95712a2ea | ||
|
|
ed4927fcd0 | ||
|
|
555504bd98 | ||
|
|
2ea4635ef7 | ||
|
|
76b63b5a71 | ||
|
|
e791039592 | ||
|
|
98f2f8c745 | ||
|
|
c2f319fa86 | ||
|
|
ebe95aac2f | ||
|
|
52df82917a | ||
|
|
0224d4705e | ||
|
|
123fe287b6 | ||
|
|
85394cf22b | ||
|
|
0c545eb724 | ||
|
|
f2c7a45e47 | ||
|
|
75d721adb9 | ||
|
|
e99ff6c15b | ||
|
|
cbd7865a79 | ||
|
|
a08056ed2a | ||
|
|
c9d110e543 | ||
|
|
7500af78eb | ||
|
|
5be1521294 | ||
|
|
b165cc32e6 | ||
|
|
2d5755d1ef | ||
|
|
90c26c8418 | ||
|
|
692041aa74 | ||
|
|
0618c2abc3 | ||
|
|
b2b76f8006 | ||
|
|
f1a55b3388 | ||
|
|
58a5ccfd6a | ||
|
|
bbd2c704f9 |
No files matched your search
+10
-13
@@ -15,7 +15,7 @@ static __device__ uint64_t cuda_swab32ll(uint64_t x) {
|
||||
return MAKE_ULONGLONG(cuda_swab32(_LODWORD(x)), cuda_swab32(_HIDWORD(x)));
|
||||
}
|
||||
|
||||
__constant__ static uint32_t c_data[20];
|
||||
__constant__ static uint32_t c_data[3+1];
|
||||
|
||||
__constant__ static uint32_t sigma[16][16];
|
||||
static uint32_t c_sigma[16][16] = {
|
||||
@@ -195,17 +195,16 @@ void blake256_gpu_hash_80(const uint32_t threads, const uint32_t startNonce, uin
|
||||
uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
{
|
||||
const uint32_t nonce = startNonce + thread;
|
||||
uint32_t h[8];
|
||||
uint32_t input[4];
|
||||
|
||||
#pragma unroll 8
|
||||
for (int i = 0; i<8; i++) { h[i] = cpu_h[i];}
|
||||
#pragma unroll
|
||||
for (int i = 0; i < 8; i++) h[i] = cpu_h[i];
|
||||
|
||||
#pragma unroll 3
|
||||
for (int i = 0; i < 3; ++i) input[i] = c_data[16 + i];
|
||||
#pragma unroll
|
||||
for (int i = 0; i < 3; ++i) input[i] = c_data[i];
|
||||
|
||||
input[3] = nonce;
|
||||
input[3] = startNonce + thread;
|
||||
blake256_compress2nd(h, input, 640);
|
||||
|
||||
#pragma unroll
|
||||
@@ -230,16 +229,14 @@ void blake256_cpu_hash_80(const int thr_id, const uint32_t threads, const uint32
|
||||
__host__
|
||||
void blake256_cpu_setBlock_80(uint32_t *pdata)
|
||||
{
|
||||
uint32_t h[8];
|
||||
uint32_t data[20];
|
||||
uint32_t h[8], data[20];
|
||||
|
||||
memcpy(data, pdata, 80);
|
||||
for (int i = 0; i<8; i++) {
|
||||
h[i] = c_IV256[i];
|
||||
}
|
||||
memcpy(h, c_IV256, sizeof(c_IV256));
|
||||
blake256_compress1st(h, pdata, 512);
|
||||
|
||||
cudaMemcpyToSymbol(cpu_h, h, sizeof(h), 0, cudaMemcpyHostToDevice);
|
||||
cudaMemcpyToSymbol(c_data, data, sizeof(data), 0, cudaMemcpyHostToDevice);
|
||||
cudaMemcpyToSymbol(c_data, &data[16], sizeof(c_data), 0, cudaMemcpyHostToDevice);
|
||||
}
|
||||
|
||||
__host__
|
||||
|
||||
+99
-116
@@ -20,21 +20,17 @@ static __constant__ uint2 vSKEIN_IV512_256[8] = {
|
||||
{ 0x33EDFC13, 0x3EEDBA18 }
|
||||
};
|
||||
|
||||
static __constant__ int ROT256[8][4] =
|
||||
{
|
||||
46,36, 19, 37,
|
||||
33,27, 14, 42,
|
||||
17,49, 36, 39,
|
||||
44, 9, 54, 56,
|
||||
39,30, 34, 24,
|
||||
13,50, 10, 17,
|
||||
25,29, 39, 43,
|
||||
8, 35, 56, 22,
|
||||
static __constant__ int8_t ROT256[8][4] = {
|
||||
46, 36, 19, 37,
|
||||
33, 27, 14, 42,
|
||||
17, 49, 36, 39,
|
||||
44, 9, 54, 56,
|
||||
39, 30, 34, 24,
|
||||
13, 50, 10, 17,
|
||||
25, 29, 39, 43,
|
||||
8, 35, 56, 22,
|
||||
};
|
||||
|
||||
static __constant__ uint2 skein_ks_parity = { 0xA9FC1A22,0x1BD11BDA};
|
||||
static __constant__ uint64_t skein_ks_parity64 = 0x1BD11BDAA9FC1A22ull;
|
||||
|
||||
static __constant__ uint2 t12[6] = {
|
||||
{ 0x20, 0 },
|
||||
{ 0, 0xf0000000 },
|
||||
@@ -44,25 +40,19 @@ static __constant__ uint2 t12[6] = {
|
||||
{ 0x08, 0xff000000 }
|
||||
};
|
||||
|
||||
static __constant__ uint64_t t12_30[6] = {
|
||||
0x20,
|
||||
0xf000000000000000,
|
||||
0xf000000000000020,
|
||||
0x08,
|
||||
0xff00000000000000,
|
||||
0xff00000000000008
|
||||
};
|
||||
static __constant__ uint2 skein_ks_parity = { 0xA9FC1A22, 0x1BD11BDA };
|
||||
static __constant__ uint64_t skein_ks_parity64 = 0x1BD11BDAA9FC1A22ull;
|
||||
|
||||
|
||||
static __forceinline__ __device__
|
||||
void Round512v35(uint2 &p0, uint2 &p1, uint2 &p2, uint2 &p3, uint2 &p4, uint2 &p5, uint2 &p6, uint2 &p7, int ROT)
|
||||
{
|
||||
p0 += p1; p1 = ROL2(p1, ROT256[ROT][0]); p1 ^= p0;
|
||||
p2 += p3; p3 = ROL2(p3, ROT256[ROT][1]); p3 ^= p2;
|
||||
p4 += p5; p5 = ROL2(p5, ROT256[ROT][2]); p5 ^= p4;
|
||||
p6 += p7; p7 = ROL2(p7, ROT256[ROT][3]); p7 ^= p6;
|
||||
p0 += p1; p1 = ROL2(p1, ROT256[ROT][0]) ^ p0;
|
||||
p2 += p3; p3 = ROL2(p3, ROT256[ROT][1]) ^ p2;
|
||||
p4 += p5; p5 = ROL2(p5, ROT256[ROT][2]) ^ p4;
|
||||
p6 += p7; p7 = ROL2(p7, ROT256[ROT][3]) ^ p6;
|
||||
}
|
||||
|
||||
|
||||
static __forceinline__ __device__
|
||||
void Round_8_512v35(uint2 *ks, uint2 *ts,
|
||||
uint2 &p0, uint2 &p1, uint2 &p2, uint2 &p3,
|
||||
@@ -72,39 +62,36 @@ void Round_8_512v35(uint2 *ks, uint2 *ts,
|
||||
Round512v35(p2, p1, p4, p7, p6, p5, p0, p3, 1);
|
||||
Round512v35(p4, p1, p6, p3, p0, p5, p2, p7, 2);
|
||||
Round512v35(p6, p1, p0, p7, p2, p5, p4, p3, 3);
|
||||
p0 += ks[((R)+0) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[((R)+1) % 9];
|
||||
p2 += ks[((R)+2) % 9];
|
||||
p3 += ks[((R)+3) % 9];
|
||||
p4 += ks[((R)+4) % 9];
|
||||
p5 += ks[((R)+5) % 9] + ts[((R)+0) % 3];
|
||||
p6 += ks[((R)+6) % 9] + ts[((R)+1) % 3];
|
||||
p7 += ks[((R)+7) % 9] + make_uint2((R),0);
|
||||
p0 += ks[(R+0) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[(R+1) % 9];
|
||||
p2 += ks[(R+2) % 9];
|
||||
p3 += ks[(R+3) % 9];
|
||||
p4 += ks[(R+4) % 9];
|
||||
p5 += ks[(R+5) % 9] + ts[(R+0) % 3];
|
||||
p6 += ks[(R+6) % 9] + ts[(R+1) % 3];
|
||||
p7 += ks[(R+7) % 9] + make_uint2((R),0);
|
||||
Round512v35(p0, p1, p2, p3, p4, p5, p6, p7, 4);
|
||||
Round512v35(p2, p1, p4, p7, p6, p5, p0, p3, 5);
|
||||
Round512v35(p4, p1, p6, p3, p0, p5, p2, p7, 6);
|
||||
Round512v35(p6, p1, p0, p7, p2, p5, p4, p3, 7);
|
||||
p0 += ks[((R)+1) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[((R)+2) % 9];
|
||||
p2 += ks[((R)+3) % 9];
|
||||
p3 += ks[((R)+4) % 9];
|
||||
p4 += ks[((R)+5) % 9];
|
||||
p5 += ks[((R)+6) % 9] + ts[((R)+1) % 3];
|
||||
p6 += ks[((R)+7) % 9] + ts[((R)+2) % 3];
|
||||
p7 += ks[((R)+8) % 9] + make_uint2((R)+1, 0);
|
||||
p0 += ks[(R+1) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[(R+2) % 9];
|
||||
p2 += ks[(R+3) % 9];
|
||||
p3 += ks[(R+4) % 9];
|
||||
p4 += ks[(R+5) % 9];
|
||||
p5 += ks[(R+6) % 9] + ts[(R+1) % 3];
|
||||
p6 += ks[(R+7) % 9] + ts[(R+2) % 3];
|
||||
p7 += ks[(R+8) % 9] + make_uint2(R+1, 0);
|
||||
}
|
||||
|
||||
|
||||
__global__ __launch_bounds__(256,3)
|
||||
void skein256_gpu_hash_32(uint32_t threads, uint32_t startNounce, uint64_t *outputHash)
|
||||
{
|
||||
uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
const uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
{
|
||||
uint2 h[9];
|
||||
uint2 t[3];
|
||||
uint2 dt0,dt1,dt2,dt3;
|
||||
uint2 p0, p1, p2, p3, p4, p5, p6, p7;
|
||||
uint2 h[9], t[3] = { t12[0], t12[1], t12[2] };
|
||||
|
||||
h[8] = skein_ks_parity;
|
||||
for (int i = 0; i<8; i++) {
|
||||
@@ -112,27 +99,23 @@ void skein256_gpu_hash_32(uint32_t threads, uint32_t startNounce, uint64_t *outp
|
||||
h[8] ^= h[i];
|
||||
}
|
||||
|
||||
t[0]=t12[0];
|
||||
t[1]=t12[1];
|
||||
t[2]=t12[2];
|
||||
uint2 dt0 = vectorize(outputHash[thread]);
|
||||
uint2 dt1 = vectorize(outputHash[threads + thread]);
|
||||
uint2 dt2 = vectorize(outputHash[threads*2 + thread]);
|
||||
uint2 dt3 = vectorize(outputHash[threads*3 + thread]);
|
||||
|
||||
LOHI(dt0.x,dt0.y,outputHash[thread]);
|
||||
LOHI(dt1.x,dt1.y,outputHash[threads+thread]);
|
||||
LOHI(dt2.x,dt2.y,outputHash[2*threads+thread]);
|
||||
LOHI(dt3.x,dt3.y,outputHash[3*threads+thread]);
|
||||
uint2 p0 = h[0] + dt0;
|
||||
uint2 p1 = h[1] + dt1;
|
||||
uint2 p2 = h[2] + dt2;
|
||||
uint2 p3 = h[3] + dt3;
|
||||
uint2 p4 = h[4];
|
||||
uint2 p5 = h[5] + t[0];
|
||||
uint2 p6 = h[6] + t[1];
|
||||
uint2 p7 = h[7];
|
||||
|
||||
p0 = h[0] + dt0;
|
||||
p1 = h[1] + dt1;
|
||||
p2 = h[2] + dt2;
|
||||
p3 = h[3] + dt3;
|
||||
p4 = h[4];
|
||||
p5 = h[5] + t[0];
|
||||
p6 = h[6] + t[1];
|
||||
p7 = h[7];
|
||||
|
||||
#pragma unroll
|
||||
#pragma unroll 9
|
||||
for (int i = 1; i<19; i+=2) {
|
||||
Round_8_512v35(h,t,p0,p1,p2,p3,p4,p5,p6,p7,i);
|
||||
Round_8_512v35(h, t, p0, p1, p2, p3, p4, p5, p6, p7, i);
|
||||
}
|
||||
|
||||
p0 ^= dt0;
|
||||
@@ -158,18 +141,19 @@ void skein256_gpu_hash_32(uint32_t threads, uint32_t startNounce, uint64_t *outp
|
||||
t[0] = t12[3];
|
||||
t[1] = t12[4];
|
||||
t[2] = t12[5];
|
||||
p5 += t[0]; //p5 already equal h[5]
|
||||
|
||||
p5 += t[0];
|
||||
p6 += t[1];
|
||||
|
||||
#pragma unroll
|
||||
#pragma unroll 9
|
||||
for (int i = 1; i<19; i+=2) {
|
||||
Round_8_512v35(h, t, p0, p1, p2, p3, p4, p5, p6, p7, i);
|
||||
}
|
||||
|
||||
outputHash[thread] = devectorize(p0);
|
||||
outputHash[threads+thread] = devectorize(p1);
|
||||
outputHash[2*threads+thread] = devectorize(p2);
|
||||
outputHash[3*threads+thread] = devectorize(p3);
|
||||
outputHash[thread] = devectorize(p0);
|
||||
outputHash[threads + thread] = devectorize(p1);
|
||||
outputHash[threads*2 + thread] = devectorize(p2);
|
||||
outputHash[threads*3 + thread] = devectorize(p3);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -177,10 +161,10 @@ static __forceinline__ __device__
|
||||
void Round512v30(uint64_t &p0, uint64_t &p1, uint64_t &p2, uint64_t &p3,
|
||||
uint64_t &p4, uint64_t &p5, uint64_t &p6, uint64_t &p7, int ROT)
|
||||
{
|
||||
p0 += p1; p1 = ROTL64(p1, ROT256[ROT][0]); p1 ^= p0;
|
||||
p2 += p3; p3 = ROTL64(p3, ROT256[ROT][1]); p3 ^= p2;
|
||||
p4 += p5; p5 = ROTL64(p5, ROT256[ROT][2]); p5 ^= p4;
|
||||
p6 += p7; p7 = ROTL64(p7, ROT256[ROT][3]); p7 ^= p6;
|
||||
p0 += p1; p1 = ROTL64(p1, ROT256[ROT][0]) ^ p0;
|
||||
p2 += p3; p3 = ROTL64(p3, ROT256[ROT][1]) ^ p2;
|
||||
p4 += p5; p5 = ROTL64(p5, ROT256[ROT][2]) ^ p4;
|
||||
p6 += p7; p7 = ROTL64(p7, ROT256[ROT][3]) ^ p6;
|
||||
}
|
||||
|
||||
static __forceinline__ __device__
|
||||
@@ -191,38 +175,36 @@ void Round_8_512v30(uint64_t *ks, uint64_t *ts, uint64_t &p0, uint64_t &p1, uint
|
||||
Round512v30(p2, p1, p4, p7, p6, p5, p0, p3, 1);
|
||||
Round512v30(p4, p1, p6, p3, p0, p5, p2, p7, 2);
|
||||
Round512v30(p6, p1, p0, p7, p2, p5, p4, p3, 3);
|
||||
p0 += ks[((R)+0) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[((R)+1) % 9];
|
||||
p2 += ks[((R)+2) % 9];
|
||||
p3 += ks[((R)+3) % 9];
|
||||
p4 += ks[((R)+4) % 9];
|
||||
p5 += ks[((R)+5) % 9] + ts[((R)+0) % 3];
|
||||
p6 += ks[((R)+6) % 9] + ts[((R)+1) % 3];
|
||||
p7 += ks[((R)+7) % 9] + R;
|
||||
p0 += ks[(R+0) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[(R+1) % 9];
|
||||
p2 += ks[(R+2) % 9];
|
||||
p3 += ks[(R+3) % 9];
|
||||
p4 += ks[(R+4) % 9];
|
||||
p5 += ks[(R+5) % 9] + ts[(R+0) % 3];
|
||||
p6 += ks[(R+6) % 9] + ts[(R+1) % 3];
|
||||
p7 += ks[(R+7) % 9] + R;
|
||||
Round512v30(p0, p1, p2, p3, p4, p5, p6, p7, 4);
|
||||
Round512v30(p2, p1, p4, p7, p6, p5, p0, p3, 5);
|
||||
Round512v30(p4, p1, p6, p3, p0, p5, p2, p7, 6);
|
||||
Round512v30(p6, p1, p0, p7, p2, p5, p4, p3, 7);
|
||||
p0 += ks[((R)+1) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[((R)+2) % 9];
|
||||
p2 += ks[((R)+3) % 9];
|
||||
p3 += ks[((R)+4) % 9];
|
||||
p4 += ks[((R)+5) % 9];
|
||||
p5 += ks[((R)+6) % 9] + ts[((R)+1) % 3];
|
||||
p6 += ks[((R)+7) % 9] + ts[((R)+2) % 3];
|
||||
p7 += ks[((R)+8) % 9] + (R)+1;
|
||||
p0 += ks[(R+1) % 9]; /* inject the key schedule value */
|
||||
p1 += ks[(R+2) % 9];
|
||||
p2 += ks[(R+3) % 9];
|
||||
p3 += ks[(R+4) % 9];
|
||||
p4 += ks[(R+5) % 9];
|
||||
p5 += ks[(R+6) % 9] + ts[(R+1) % 3];
|
||||
p6 += ks[(R+7) % 9] + ts[(R+2) % 3];
|
||||
p7 += ks[(R+8) % 9] + R+1;
|
||||
}
|
||||
|
||||
__global__ __launch_bounds__(256, 3)
|
||||
void skein256_gpu_hash_32_v30(uint32_t threads, uint32_t startNounce, uint64_t *outputHash)
|
||||
{
|
||||
uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
const uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
{
|
||||
uint64_t h[9];
|
||||
uint64_t t[3];
|
||||
uint64_t dt0, dt1, dt2, dt3;
|
||||
uint64_t p0, p1, p2, p3, p4, p5, p6, p7;
|
||||
uint64_t h[9], t[3];
|
||||
|
||||
h[8] = skein_ks_parity64;
|
||||
for (int i = 0; i<8; i++) {
|
||||
h[i] = SKEIN_IV512_256[i];
|
||||
@@ -233,21 +215,21 @@ void skein256_gpu_hash_32_v30(uint32_t threads, uint32_t startNounce, uint64_t *
|
||||
t[1] = devectorize(t12[1]);
|
||||
t[2] = devectorize(t12[2]);
|
||||
|
||||
dt0 = outputHash[thread];
|
||||
dt1 = outputHash[threads+thread];
|
||||
dt2 = outputHash[2*threads+thread];
|
||||
dt3 = outputHash[3*threads+thread];
|
||||
uint64_t dt0 = outputHash[thread];
|
||||
uint64_t dt1 = outputHash[threads + thread];
|
||||
uint64_t dt2 = outputHash[threads*2 + thread];
|
||||
uint64_t dt3 = outputHash[threads*3 + thread];
|
||||
|
||||
p0 = h[0] + dt0;
|
||||
p1 = h[1] + dt1;
|
||||
p2 = h[2] + dt2;
|
||||
p3 = h[3] + dt3;
|
||||
p4 = h[4];
|
||||
p5 = h[5] + t[0];
|
||||
p6 = h[6] + t[1];
|
||||
p7 = h[7];
|
||||
uint64_t p0 = h[0] + dt0;
|
||||
uint64_t p1 = h[1] + dt1;
|
||||
uint64_t p2 = h[2] + dt2;
|
||||
uint64_t p3 = h[3] + dt3;
|
||||
uint64_t p4 = h[4];
|
||||
uint64_t p5 = h[5] + t[0];
|
||||
uint64_t p6 = h[6] + t[1];
|
||||
uint64_t p7 = h[7];
|
||||
|
||||
#pragma unroll
|
||||
#pragma unroll 9
|
||||
for (int i = 1; i<19; i += 2) {
|
||||
Round_8_512v30(h, t, p0, p1, p2, p3, p4, p5, p6, p7, i);
|
||||
}
|
||||
@@ -272,22 +254,22 @@ void skein256_gpu_hash_32_v30(uint32_t threads, uint32_t startNounce, uint64_t *
|
||||
h[8] ^= h[i];
|
||||
}
|
||||
|
||||
t[0] = t12_30[3];
|
||||
t[1] = t12_30[4];
|
||||
t[2] = t12_30[5];
|
||||
t[0] = devectorize(t12[3]);
|
||||
t[1] = devectorize(t12[4]);
|
||||
t[2] = devectorize(t12[5]);
|
||||
|
||||
p5 += t[0]; //p5 already equal h[5]
|
||||
p6 += t[1];
|
||||
|
||||
#pragma unroll
|
||||
#pragma unroll 9
|
||||
for (int i = 1; i<19; i += 2) {
|
||||
Round_8_512v30(h, t, p0, p1, p2, p3, p4, p5, p6, p7, i);
|
||||
}
|
||||
|
||||
outputHash[thread] = p0;
|
||||
outputHash[threads + thread] = p1;
|
||||
outputHash[2 * threads + thread] = p2;
|
||||
outputHash[3 * threads + thread] = p3;
|
||||
outputHash[threads + thread] = p1;
|
||||
outputHash[threads*2 + thread] = p2;
|
||||
outputHash[threads*3 + thread] = p3;
|
||||
|
||||
} //thread
|
||||
}
|
||||
@@ -306,6 +288,7 @@ void skein256_cpu_hash_32(int thr_id, uint32_t threads, uint32_t startNounce, ui
|
||||
dim3 grid((threads + threadsperblock - 1) / threadsperblock);
|
||||
dim3 block(threadsperblock);
|
||||
|
||||
// only 1kH/s perf change between kernels on a 960...
|
||||
if (device_sm[device_map[thr_id]] > 300 && cuda_arch[device_map[thr_id]] > 300)
|
||||
skein256_gpu_hash_32<<<grid, block>>>(threads, startNounce, d_outputHash);
|
||||
else
|
||||
|
||||
@@ -8,4 +8,35 @@ need to be installed on your system for autogen.sh to work)
|
||||
where your CUDA 6.5 toolkit is installed (usually /usr/local/cuda,
|
||||
but some distros may have a different default location)
|
||||
|
||||
See README.txt
|
||||
|
||||
** How to compile on Fedora 22 (2015) **
|
||||
|
||||
# Step 1: gcc and dependencies
|
||||
dnf install gcc gcc-c++ automake
|
||||
dnf install jansson-devel openssl-devel libcurl-devel
|
||||
|
||||
# Step 2: nvidia drivers (Download common linux drivers from nvidia site)
|
||||
dnf install kernel-devel
|
||||
modprobe -r nouveau
|
||||
./NVIDIA-Linux-x86_64-346.72.run
|
||||
|
||||
# Step 3: CUDA SDK (Download from nvidia archive)
|
||||
dnf install cuda-repo-fedora20-6-5-prod-6.5-19.x86_64.rpm
|
||||
dnf install cuda-minimal-build-6-5.x86_64
|
||||
|
||||
# add the nvcc binary path to the system
|
||||
ln -s /usr/local/cuda-6.5 /usr/local/cuda
|
||||
echo 'export PATH=$PATH:/usr/local/cuda/bin' > /etc/profile.d/cuda.sh
|
||||
|
||||
# add the cudart library path to the system
|
||||
echo /usr/local/cuda/lib64 > /etc/ld.so.conf.d/cuda.conf
|
||||
ldconfig
|
||||
|
||||
# Step 4: Fix the toolkit warning with gcc 5.1
|
||||
edit the file /usr/local/cuda/include/host_config.h
|
||||
and comment/delete the line 82 : #error -- unsupported GNU version! gcc 4.9
|
||||
|
||||
./build.sh
|
||||
|
||||
./ccminer -n
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
#include <memory.h>
|
||||
|
||||
#include "cuda_helper.h"
|
||||
#include "miner.h"
|
||||
|
||||
// ZR5
|
||||
__constant__ uint32_t d_OriginalData[20];
|
||||
@@ -9,9 +10,6 @@ __constant__ uint32_t d_OriginalData[20];
|
||||
__constant__ uint32_t c_PaddedMessage[18];
|
||||
__constant__ uint64_t c_State[25];
|
||||
|
||||
#define POK_DATA_MASK 0xFFFF0000
|
||||
#define POK_VERSION 0x1
|
||||
|
||||
#define U32TO64_LE(p) \
|
||||
(((uint64_t)(*p)) | (((uint64_t)(*(p + 1))) << 32))
|
||||
|
||||
@@ -657,7 +655,7 @@ __host__
|
||||
void zr5_keccak512_cpu_hash_pok(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t* pdata, uint32_t *d_hash, uint16_t *d_poks)
|
||||
{
|
||||
const uint32_t threadsperblock = 256;
|
||||
const uint32_t version = pdata[0] & (~POK_DATA_MASK);
|
||||
const uint32_t version = (pdata[0] & (~POK_DATA_MASK)) | (use_pok ? POK_BOOL_MASK : 0);
|
||||
|
||||
dim3 grid((threads + threadsperblock-1)/threadsperblock);
|
||||
dim3 block(threadsperblock);
|
||||
|
||||
+12
-10
@@ -19,7 +19,7 @@ ccminer_SOURCES = elist.h miner.h compat.h \
|
||||
compat/inttypes.h compat/stdbool.h compat/unistd.h \
|
||||
compat/sys/time.h compat/getopt/getopt.h \
|
||||
crc32.c hefty1.c \
|
||||
ccminer.cpp util.cpp \
|
||||
ccminer.cpp pools.cpp util.cpp bignum.cpp \
|
||||
api.cpp hashlog.cpp nvml.cpp stats.cpp sysinfos.cpp cuda.cpp \
|
||||
heavy/heavy.cu \
|
||||
heavy/cuda_blake512.cu heavy/cuda_blake512.h \
|
||||
@@ -44,11 +44,13 @@ ccminer_SOURCES = elist.h miner.h compat.h \
|
||||
neoscrypt/neoscrypt.cpp neoscrypt/neoscrypt-cpu.c neoscrypt/cuda_neoscrypt.cu \
|
||||
cuda_nist5.cu pentablake.cu skein.cu cuda_skeincoin.cu skein2.cpp zr5.cu \
|
||||
sph/bmw.c sph/blake.c sph/groestl.c sph/jh.c sph/keccak.c sph/skein.c \
|
||||
sph/cubehash.c sph/echo.c sph/luffa.c sph/sha2.c sph/shavite.c sph/simd.c \
|
||||
sph/cubehash.c sph/echo.c sph/luffa.c sph/sha2.c sph/sha256d.c sph/shavite.c sph/simd.c \
|
||||
sph/hamsi.c sph/hamsi_helper.c sph/sph_hamsi.h \
|
||||
sph/shabal.c sph/whirlpool.c sph/sha2big.c sph/haval.c \
|
||||
sha256/bitcoin.cu sha256/cuda_bitcoin.cu \
|
||||
sha256/credits.cu sha256/cuda_credits.cu \
|
||||
pluck/pluck.cu pluck/cuda_pluck.cu \
|
||||
qubit/qubit.cu qubit/qubit_luffa512.cu qubit/deep.cu qubit/doom.cu \
|
||||
qubit/qubit.cu qubit/qubit_luffa512.cu qubit/deep.cu qubit/luffa.cu \
|
||||
x11/x11.cu x11/fresh.cu x11/cuda_x11_luffa512.cu x11/cuda_x11_cubehash512.cu \
|
||||
x11/cuda_x11_shavite512.cu x11/cuda_x11_simd512.cu x11/cuda_x11_echo.cu \
|
||||
x11/cuda_x11_luffa512_Cubehash.cu \
|
||||
@@ -79,7 +81,7 @@ ccminer_CPPFLAGS = @LIBCURL_CPPFLAGS@ @OPENMP_CFLAGS@ $(CPPFLAGS) $(PTHREAD_FLAG
|
||||
|
||||
nvcc_ARCH = -gencode=arch=compute_50,code=\"sm_50,compute_50\"
|
||||
|
||||
#nvcc_ARCH += -gencode=arch=compute_52,code=\"sm_52,compute_52\"
|
||||
nvcc_ARCH += -gencode=arch=compute_52,code=\"sm_52,compute_52\"
|
||||
#nvcc_ARCH += -gencode=arch=compute_35,code=\"sm_35,compute_35\"
|
||||
#nvcc_ARCH += -gencode=arch=compute_30,code=\"sm_30,compute_30\"
|
||||
#nvcc_ARCH += -gencode=arch=compute_20,code=\"sm_21,compute_20\"
|
||||
@@ -105,7 +107,7 @@ x11/cuda_x11_luffa512.o: x11/cuda_x11_luffa512.cu
|
||||
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
||||
|
||||
x11/cuda_x11_luffa512_Cubehash.o: x11/cuda_x11_luffa512_Cubehash.cu
|
||||
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
||||
$(NVCC) $(nvcc_FLAGS) --maxrregcount=76 -o $@ -c $<
|
||||
|
||||
x13/cuda_x13_hamsi512.o: x13/cuda_x13_hamsi512.cu
|
||||
$(NVCC) $(nvcc_FLAGS) --maxrregcount=72 -o $@ -c $<
|
||||
@@ -127,21 +129,21 @@ JHA/cuda_jha_compactionTest.o: JHA/cuda_jha_compactionTest.cu
|
||||
|
||||
# This object does not use cuda device code but call the different kernels (autotune)
|
||||
scrypt/salsa_kernel.o: scrypt/salsa_kernel.cu
|
||||
$(NVCC) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_21,compute_20\" -o $@ -c $<
|
||||
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_21,compute_20\" -o $@ -c $<
|
||||
|
||||
# These kernels are for older devices (SM)
|
||||
|
||||
scrypt/test_kernel.o: scrypt/test_kernel.cu
|
||||
$(NVCC) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_20,compute_20\" -o $@ -c $<
|
||||
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_20,compute_20\" -o $@ -c $<
|
||||
|
||||
scrypt/fermi_kernel.o: scrypt/fermi_kernel.cu
|
||||
$(NVCC) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_21,compute_20\" -o $@ -c $<
|
||||
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_21,compute_20\" -o $@ -c $<
|
||||
|
||||
scrypt/kepler_kernel.o: scrypt/kepler_kernel.cu
|
||||
$(NVCC) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_30,code=\"sm_30,compute_30\" -o $@ -c $<
|
||||
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_30,code=\"sm_30,compute_30\" -o $@ -c $<
|
||||
|
||||
scrypt/nv_kernel.o: scrypt/nv_kernel.cu
|
||||
$(NVCC) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_30,code=\"sm_30,compute_30\" -o $@ -c $<
|
||||
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_30,code=\"sm_30,compute_30\" -o $@ -c $<
|
||||
|
||||
scrypt/titan_kernel.o: scrypt/titan_kernel.cu
|
||||
$(NVCC) $(nvcc_FLAGS) -gencode=arch=compute_35,code=\"sm_35,compute_35\" -o $@ -c $<
|
||||
|
||||
+26
-6
@@ -1,5 +1,5 @@
|
||||
|
||||
ccMiner release 1.6.3-tpruvot (May 2015) - "Neoscrypt (SM5.0+)"
|
||||
ccMiner release 1.6.x-tpruvot (Jun 2015) - "SHA and ..."
|
||||
---------------------------------------------------------------
|
||||
|
||||
***************************************************************
|
||||
@@ -24,6 +24,7 @@ cbuchner v1.2:
|
||||
|
||||
This is a CUDA accelerated mining application which handle :
|
||||
|
||||
Credits
|
||||
HeavyCoin & MjollnirCoin
|
||||
FugueCoin
|
||||
GroestlCoin & Myriad-Groestl
|
||||
@@ -33,7 +34,8 @@ TalkCoin
|
||||
DarkCoin and other X11 coins
|
||||
Saffroncoin blake (256 14-rounds)
|
||||
BlakeCoin (256 8-rounds)
|
||||
Deep, Doom and Qubit
|
||||
Qubit (Digibyte, ...)
|
||||
Luffa (Joincoin)
|
||||
Keccak (Maxcoin)
|
||||
Pentablake (Blake 512 x5)
|
||||
1Coin Triple S
|
||||
@@ -63,8 +65,10 @@ its command line interface and options.
|
||||
|
||||
-a, --algo=ALGO specify the algorithm to use
|
||||
anime use to mine Animecoin
|
||||
bitcoin use to mine SHA-256d coins
|
||||
blake use to mine Saffroncoin (Blake 256)
|
||||
blakecoin use to mine Old Blake 256
|
||||
credits use to mine Credits [CRE]
|
||||
deep use to mine Deepcoin
|
||||
dmd-gr use to mine Diamond-Groestl
|
||||
fresh use to mine Freshcoin
|
||||
@@ -73,7 +77,7 @@ its command line interface and options.
|
||||
heavy use to mine Heavycoin
|
||||
jackpot use to mine Jackpotcoin
|
||||
keccak use to mine Maxcoin
|
||||
luffa use to mine Doomcoin
|
||||
luffa use to mine Joincoin
|
||||
lyra2 use to mine Vertcoin
|
||||
mjollnir use to mine Mjollnircoin
|
||||
myr-gr use to mine Myriad-Groest
|
||||
@@ -102,8 +106,10 @@ its command line interface and options.
|
||||
|
||||
-i, --intensity=N[,N] GPU threads per call 8-25 (2^N + F, default: 0=auto)
|
||||
Decimals and multiple values are allowed for fine tuning
|
||||
-f, --diff Divide difficulty by this factor (std is 1)
|
||||
-v, --vote Heavycoin block vote (default: 512)
|
||||
-f, --diff-factor Divide difficulty by this factor (default 1.0)
|
||||
-m, --diff-multiplier Multiply difficulty by this value (default 1.0)
|
||||
--vote=VOTE block reward vote (for HeavyCoin)
|
||||
--trust-pool trust the max block reward vote (maxvote) sent by the pool
|
||||
-o, --url=URL URL of mining server
|
||||
-O, --userpass=U:P username:password pair for mining server
|
||||
-u, --user=USERNAME username for mining server
|
||||
@@ -215,7 +221,21 @@ features.
|
||||
|
||||
>>> RELEASE HISTORY <<<
|
||||
|
||||
Try to compute network difficulty on pools too
|
||||
June 2015 v1.6.5
|
||||
Remove -v and -m short params specific to heavycoin
|
||||
Add --diff-multiplier (-m) and rename --diff to --diff-factor (-f)
|
||||
First steps to handle nvml application clocks and P0 on the GTX9xx
|
||||
Optimize qubit, deep and luffa algos
|
||||
Compatibility with CUDA 7.0 (but slower hashrate)
|
||||
Various improvements on multipool and cmdline parameters
|
||||
Import Credits (djm34) and Bitcoin (klaus) "SHA256" algos
|
||||
|
||||
May 26th 2015 v1.6.4
|
||||
Implement multi-pool support (failover and time rotate)
|
||||
try "ccminer -c pools.conf" to test the sample config
|
||||
Update the API to allow remote pool switching and pool stats
|
||||
Auto bind the api port to the first available when using default
|
||||
Try to compute network difficulty on pools too (for most algos)
|
||||
Drop Whirlpool and whirpoolx algos, no more used...
|
||||
|
||||
May 15th 2015 v1.6.3
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
* Software Foundation; either version 2 of the License, or (at your option)
|
||||
* any later version. See COPYING for more details.
|
||||
*/
|
||||
#define APIVERSION "1.4"
|
||||
#define APIVERSION "1.5"
|
||||
|
||||
#ifdef WIN32
|
||||
# define _WINSOCK_DEPRECATED_NO_WARNINGS
|
||||
@@ -92,13 +92,12 @@ static int bye = 0;
|
||||
extern char *opt_api_allow;
|
||||
extern int opt_api_listen; /* port */
|
||||
extern int opt_api_remote;
|
||||
extern uint32_t accepted_count;
|
||||
extern uint32_t rejected_count;
|
||||
extern int num_cpus;
|
||||
|
||||
// current stratum...
|
||||
extern struct stratum_ctx stratum;
|
||||
extern char* rpc_user;
|
||||
|
||||
// sysinfos.cpp
|
||||
extern int num_cpus;
|
||||
extern float cpu_temp(int);
|
||||
extern uint32_t cpu_clock(int);
|
||||
// cuda.cpp
|
||||
@@ -111,6 +110,8 @@ char driver_version[32] = { 0 };
|
||||
|
||||
static void gpustatus(int thr_id)
|
||||
{
|
||||
struct pool_infos *p = &pools[cur_pooln];
|
||||
|
||||
if (thr_id >= 0 && thr_id < opt_n_threads) {
|
||||
struct cgpu_info *cgpu = &thr_info[thr_id].gpu;
|
||||
int gpuid = cgpu->gpu_id;
|
||||
@@ -127,8 +128,8 @@ static void gpustatus(int thr_id)
|
||||
cuda_gpu_clocks(cgpu);
|
||||
|
||||
// todo: per gpu
|
||||
cgpu->accepted = accepted_count;
|
||||
cgpu->rejected = rejected_count;
|
||||
cgpu->accepted = p->accepted_count;
|
||||
cgpu->rejected = p->rejected_count;
|
||||
|
||||
cgpu->khashes = stats_get_speed(thr_id, 0.0) / 1000.0;
|
||||
|
||||
@@ -165,19 +166,27 @@ static char *getsummary(char *params)
|
||||
{
|
||||
char algo[64]; *algo = '\0';
|
||||
time_t ts = time(NULL);
|
||||
double uptime = difftime(ts, startup);
|
||||
double accps = (60.0 * accepted_count) / (uptime ? uptime : 1.0);
|
||||
double accps, uptime = difftime(ts, startup);
|
||||
uint32_t wait_time = 0, accepted_count = 0, rejected_count = 0;
|
||||
for (int p = 0; p < num_pools; p++) {
|
||||
wait_time += pools[p].wait_time;
|
||||
accepted_count += pools[p].accepted_count;
|
||||
rejected_count += pools[p].rejected_count;
|
||||
}
|
||||
accps = (60.0 * accepted_count) / (uptime ? uptime : 1.0);
|
||||
|
||||
get_currentalgo(algo, sizeof(algo));
|
||||
|
||||
*buffer = '\0';
|
||||
sprintf(buffer, "NAME=%s;VER=%s;API=%s;"
|
||||
"ALGO=%s;GPUS=%d;KHS=%.2f;ACC=%d;REJ=%d;"
|
||||
"ACCMN=%.3f;DIFF=%.6f;UPTIME=%.0f;TS=%u|",
|
||||
"ACCMN=%.3f;DIFF=%.6f;NETKHS=%.0f;"
|
||||
"POOLS=%u;WAIT=%u;UPTIME=%.0f;TS=%u|",
|
||||
PACKAGE_NAME, PACKAGE_VERSION, APIVERSION,
|
||||
algo, active_gpus, (double)global_hashrate / 1000.0,
|
||||
algo, active_gpus, (double)global_hashrate / 1000.,
|
||||
accepted_count, rejected_count,
|
||||
accps, net_diff > 0. ? net_diff : stratum_diff, uptime, (uint32_t) ts);
|
||||
accps, net_diff > 1e-6 ? net_diff : stratum_diff, (double)net_hashrate / 1000.,
|
||||
num_pools, wait_time, uptime, (uint32_t) ts);
|
||||
return buffer;
|
||||
}
|
||||
|
||||
@@ -186,31 +195,31 @@ static char *getsummary(char *params)
|
||||
*/
|
||||
static char *getpoolnfo(char *params)
|
||||
{
|
||||
char *p = buffer;
|
||||
char *s = buffer;
|
||||
char jobid[128] = { 0 };
|
||||
char nonce[128] = { 0 };
|
||||
*p = '\0';
|
||||
int pooln = params ? atoi(params) % num_pools : cur_pooln;
|
||||
struct pool_infos *p = &pools[pooln];
|
||||
|
||||
if (!stratum.url) {
|
||||
sprintf(p, "|");
|
||||
return p;
|
||||
}
|
||||
*s = '\0';
|
||||
|
||||
if (stratum.job.job_id)
|
||||
strncpy(jobid, stratum.job.job_id, sizeof(stratum.job.job_id));
|
||||
|
||||
if (stratum.job.xnonce2) {
|
||||
/* used temporary to be sure all is ok */
|
||||
cbin2hex(nonce, (const char*) stratum.job.xnonce2, stratum.xnonce2_size);
|
||||
sprintf(nonce, "0x");
|
||||
cbin2hex(&nonce[2], (const char*) stratum.job.xnonce2, stratum.xnonce2_size);
|
||||
}
|
||||
|
||||
snprintf(p, MYBUFSIZ, "URL=%s;USER=%s;H=%u;JOB=%s;DIFF=%.6f;N2SZ=%d;N2=0x%s;PING=%u;DISCO=%u;UPTIME=%u|",
|
||||
stratum.url, rpc_user ? rpc_user : "",
|
||||
stratum.job.height, jobid, stratum.job.diff,
|
||||
snprintf(s, MYBUFSIZ, "URL=%s;USER=%s;ACC=%d;REJ=%d;H=%u;JOB=%s;DIFF=%.6f;"
|
||||
"N2SZ=%d;N2=%s;PING=%u;DISCO=%u;WAIT=%u;UPTIME=%u|",
|
||||
p->url, p->type & POOL_STRATUM ? p->user : "",
|
||||
p->accepted_count, p->rejected_count,
|
||||
stratum.job.height, jobid, stratum_diff,
|
||||
(int) stratum.xnonce2_size, nonce, stratum.answer_msec,
|
||||
stratum.disconnects, (uint32_t) (time(NULL) - stratum.tm_connected));
|
||||
p->disconnects, p->wait_time, p->work_time);
|
||||
|
||||
return p;
|
||||
return s;
|
||||
}
|
||||
|
||||
/*****************************************************************************/
|
||||
@@ -238,7 +247,7 @@ static void gpuhwinfos(int gpu_id)
|
||||
cgpu->gpu_temp = gpu_temp(cgpu);
|
||||
cgpu->gpu_fan = (uint16_t) gpu_fanpercent(cgpu);
|
||||
cgpu->gpu_fan_rpm = (uint16_t) gpu_fanrpm(cgpu);
|
||||
cgpu->gpu_pstate = gpu_pstate(cgpu);
|
||||
cgpu->gpu_pstate = (int16_t) gpu_pstate(cgpu);
|
||||
gpu_info(cgpu);
|
||||
#endif
|
||||
|
||||
@@ -246,7 +255,7 @@ static void gpuhwinfos(int gpu_id)
|
||||
|
||||
memset(pstate, 0, sizeof(pstate));
|
||||
if (cgpu->gpu_pstate != -1)
|
||||
snprintf(pstate, sizeof(pstate), "P%hu", cgpu->gpu_pstate);
|
||||
snprintf(pstate, sizeof(pstate), "P%d", (int) cgpu->gpu_pstate);
|
||||
|
||||
card = device_name[gpu_id];
|
||||
|
||||
@@ -342,9 +351,9 @@ static char *getscanlog(char *params)
|
||||
*buffer = '\0';
|
||||
for (int i = 0; i < records; i++) {
|
||||
time_t ts = data[i].tm_upd;
|
||||
p += sprintf(p, "H=%u;JOB=%u;N=%u;FROM=0x%x;SCANTO=0x%x;"
|
||||
p += sprintf(p, "H=%u;P=%u;JOB=%u;N=%u;FROM=0x%x;SCANTO=0x%x;"
|
||||
"COUNT=0x%x;FOUND=%u;TS=%u|",
|
||||
data[i].height, data[i].njobid, data[i].nonce, data[i].scanned_from, data[i].scanned_to,
|
||||
data[i].height, data[i].npool, data[i].njobid, data[i].nonce, data[i].scanned_from, data[i].scanned_to,
|
||||
(data[i].scanned_to - data[i].scanned_from), data[i].tm_sent ? 1 : 0, (uint32_t)ts);
|
||||
}
|
||||
return buffer;
|
||||
@@ -381,18 +390,46 @@ static bool check_remote_access(void)
|
||||
}
|
||||
|
||||
/**
|
||||
* Change pool url (see --url parameter)
|
||||
* seturl|stratum+tcp://Danila.1:X@pool.ipominer.com:3335|
|
||||
* Set pool by index (pools array in json config)
|
||||
* switchpool|1|
|
||||
*/
|
||||
extern bool stratum_need_reset;
|
||||
static char *remote_seturl(char *params)
|
||||
static char *remote_switchpool(char *params)
|
||||
{
|
||||
bool ret = false;
|
||||
*buffer = '\0';
|
||||
if (!check_remote_access())
|
||||
return buffer;
|
||||
parse_arg('o', params);
|
||||
stratum_need_reset = true;
|
||||
sprintf(buffer, "%s", "ok|");
|
||||
if (!params || strlen(params) == 0) {
|
||||
// rotate pool test
|
||||
ret = pool_switch_next();
|
||||
} else {
|
||||
int n = atoi(params);
|
||||
if (n == cur_pooln)
|
||||
ret = true;
|
||||
else if (n < num_pools)
|
||||
ret = pool_switch(n);
|
||||
}
|
||||
sprintf(buffer, "%s|", ret ? "ok" : "fail");
|
||||
return buffer;
|
||||
}
|
||||
|
||||
/**
|
||||
* Change pool url (see --url parameter)
|
||||
* seturl|stratum+tcp://<user>:<pass>@mine.xpool.ca:1131|
|
||||
*/
|
||||
static char *remote_seturl(char *params)
|
||||
{
|
||||
bool ret;
|
||||
*buffer = '\0';
|
||||
if (!check_remote_access())
|
||||
return buffer;
|
||||
if (!params || strlen(params) == 0) {
|
||||
// rotate pool test
|
||||
ret = pool_switch_next();
|
||||
} else {
|
||||
ret = pool_switch_url(params);
|
||||
}
|
||||
sprintf(buffer, "%s|", ret ? "ok" : "fail");
|
||||
return buffer;
|
||||
}
|
||||
|
||||
@@ -425,7 +462,8 @@ struct CMDS {
|
||||
{ "scanlog", getscanlog },
|
||||
|
||||
/* remote functions */
|
||||
{ "seturl", remote_seturl },
|
||||
{ "seturl", remote_seturl }, /* prefer switchpool, deprecated */
|
||||
{ "switchpool", remote_switchpool },
|
||||
{ "quit", remote_quit },
|
||||
|
||||
/* keep it the last */
|
||||
|
||||
+9
-3
@@ -1,5 +1,5 @@
|
||||
<?php
|
||||
/* ccminer API sample UI */
|
||||
/* ccminer API sample UI (API 1.5) */
|
||||
|
||||
$host = 'http://localhost/api/'; // 'http://'.$_SERVER['SERVER_NAME'].'/api/';
|
||||
$configs = array(
|
||||
@@ -27,7 +27,7 @@ function getdataFromPeers()
|
||||
function ignoreField($key)
|
||||
{
|
||||
$ignored = array(
|
||||
'API','VER','GPU','BUS',
|
||||
'API','VER','GPU','BUS','POOLS',
|
||||
'CARD','GPUS','CPU','TS',
|
||||
);
|
||||
return in_array($key, $ignored);
|
||||
@@ -47,13 +47,17 @@ function translateField($key)
|
||||
$intl['ACCMN'] = 'Accepted / mn';
|
||||
$intl['REJ'] = 'Rejected';
|
||||
$intl['DIFF'] = 'Difficulty';
|
||||
$intl['NETKHS'] = 'Net Rate';
|
||||
$intl['UPTIME'] = 'Miner up time';
|
||||
$intl['TS'] = 'Last update';
|
||||
$intl['THR'] = 'Throughput';
|
||||
$intl['WAIT'] = 'Wait time';
|
||||
|
||||
|
||||
$intl['H'] = 'Bloc height';
|
||||
$intl['I'] = 'Intensity';
|
||||
$intl['HWF'] = 'Failures';
|
||||
$intl['POOLS'] = 'Pools';
|
||||
|
||||
$intl['TEMP'] = 'T°c';
|
||||
$intl['FAN'] = 'Fan %';
|
||||
@@ -76,6 +80,7 @@ function translateValue($key,$val,$data=array())
|
||||
{
|
||||
switch ($key) {
|
||||
case 'UPTIME':
|
||||
case 'WAIT':
|
||||
$min = floor(intval($val) / 60);
|
||||
$sec = intval($val) % 60;
|
||||
$val = "${min}mn${sec}s";
|
||||
@@ -95,6 +100,7 @@ function translateValue($key,$val,$data=array())
|
||||
$val = strftime("%H:%M:%S", (int) $val);
|
||||
break;
|
||||
case 'KHS':
|
||||
case 'NETKHS':
|
||||
$val = '<span class="bold">'.$val.'</span> kH/s';
|
||||
break;
|
||||
case 'NAME':
|
||||
@@ -246,7 +252,7 @@ span.elipsis { display: inline-block; max-width: 130px; overflow: hidden; }
|
||||
</div>
|
||||
|
||||
<div id="footer">
|
||||
<p>© 2014 <a href="http://github.com/tpruvot/ccminer">tpruvot@github</a></p>
|
||||
<p>© 2014-2015 <a href="http://github.com/tpruvot/ccminer">tpruvot@github</a></p>
|
||||
</div>
|
||||
|
||||
</body>
|
||||
|
||||
+26
@@ -0,0 +1,26 @@
|
||||
/**
|
||||
* Wrapper to OpenSSL BIGNUM used by net diff (nBits)
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
#include "uint256.h"
|
||||
#include "bignum.hpp"
|
||||
|
||||
#include "miner.h" // hex2bin
|
||||
|
||||
extern "C" double bn_convert_nbits(const uint32_t nBits)
|
||||
{
|
||||
uint256 bn = CBigNum().SetCompact(nBits).getuint256();
|
||||
return bn.getdouble();
|
||||
}
|
||||
|
||||
// copy the big number to 32-bytes uchar
|
||||
extern "C" void bn_nbits_to_uchar(const uint32_t nBits, unsigned char *target)
|
||||
{
|
||||
char buff[65];
|
||||
uint256 bn = CBigNum().SetCompact(nBits).getuint256();
|
||||
|
||||
snprintf(buff, 65, "%s\n", bn.ToString().c_str()); buff[64] = '\0';
|
||||
hex2bin(target, buff, 32);
|
||||
}
|
||||
+602
@@ -0,0 +1,602 @@
|
||||
// Copyright (c) 2009-2010 Satoshi Nakamoto
|
||||
// Copyright (c) 2009-2012 The Bitcoin developers
|
||||
// Distributed under the MIT/X11 software license, see the accompanying
|
||||
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
|
||||
#ifndef BITCOIN_BIGNUM_H
|
||||
#define BITCOIN_BIGNUM_H
|
||||
|
||||
#ifndef PROTOCOL_VERSION
|
||||
#define PROTOCOL_VERSION 70001
|
||||
#endif
|
||||
|
||||
#include <map>
|
||||
#include <limits>
|
||||
#include <algorithm>
|
||||
#include <stdexcept>
|
||||
#include <vector>
|
||||
|
||||
#include "uint256.h"
|
||||
|
||||
#include <openssl/bn.h>
|
||||
|
||||
#include "serialize.hpp"
|
||||
|
||||
using namespace std;
|
||||
|
||||
/** Errors thrown by the bignum class */
|
||||
class bignum_error : public std::runtime_error
|
||||
{
|
||||
public:
|
||||
explicit bignum_error(const std::string& str) : std::runtime_error(str) {}
|
||||
};
|
||||
|
||||
|
||||
/** RAII encapsulated BN_CTX (OpenSSL bignum context) */
|
||||
class CAutoBN_CTX
|
||||
{
|
||||
protected:
|
||||
BN_CTX* pctx;
|
||||
BN_CTX* operator=(BN_CTX* pnew) { return pctx = pnew; }
|
||||
|
||||
public:
|
||||
CAutoBN_CTX()
|
||||
{
|
||||
pctx = BN_CTX_new();
|
||||
if (pctx == NULL)
|
||||
throw bignum_error("CAutoBN_CTX : BN_CTX_new() returned NULL");
|
||||
}
|
||||
|
||||
~CAutoBN_CTX()
|
||||
{
|
||||
if (pctx != NULL)
|
||||
BN_CTX_free(pctx);
|
||||
}
|
||||
|
||||
operator BN_CTX*() { return pctx; }
|
||||
BN_CTX& operator*() { return *pctx; }
|
||||
BN_CTX** operator&() { return &pctx; }
|
||||
bool operator!() { return (pctx == NULL); }
|
||||
};
|
||||
|
||||
|
||||
/** C++ wrapper for BIGNUM (OpenSSL bignum) */
|
||||
class CBigNum : public BIGNUM
|
||||
{
|
||||
public:
|
||||
CBigNum()
|
||||
{
|
||||
BN_init(this);
|
||||
}
|
||||
|
||||
CBigNum(const CBigNum& b)
|
||||
{
|
||||
BN_init(this);
|
||||
if (!BN_copy(this, &b))
|
||||
{
|
||||
BN_clear_free(this);
|
||||
throw bignum_error("CBigNum::CBigNum(const CBigNum&) : BN_copy failed");
|
||||
}
|
||||
}
|
||||
|
||||
CBigNum& operator=(const CBigNum& b)
|
||||
{
|
||||
if (!BN_copy(this, &b))
|
||||
throw bignum_error("CBigNum::operator= : BN_copy failed");
|
||||
return (*this);
|
||||
}
|
||||
|
||||
~CBigNum()
|
||||
{
|
||||
BN_clear_free(this);
|
||||
}
|
||||
|
||||
//CBigNum(char n) is not portable. Use 'signed char' or 'unsigned char'.
|
||||
CBigNum(signed char n) { BN_init(this); if (n >= 0) setulong(n); else setint64(n); }
|
||||
CBigNum(short n) { BN_init(this); if (n >= 0) setulong(n); else setint64(n); }
|
||||
CBigNum(int n) { BN_init(this); if (n >= 0) setulong(n); else setint64(n); }
|
||||
CBigNum(long n) { BN_init(this); if (n >= 0) setulong(n); else setint64(n); }
|
||||
CBigNum(int64 n) { BN_init(this); setint64(n); }
|
||||
CBigNum(unsigned char n) { BN_init(this); setulong(n); }
|
||||
CBigNum(unsigned short n) { BN_init(this); setulong(n); }
|
||||
CBigNum(unsigned int n) { BN_init(this); setulong(n); }
|
||||
CBigNum(unsigned long n) { BN_init(this); setulong(n); }
|
||||
CBigNum(uint64 n) { BN_init(this); setuint64(n); }
|
||||
explicit CBigNum(uint256 n) { BN_init(this); setuint256(n); }
|
||||
|
||||
explicit CBigNum(const std::vector<unsigned char>& vch)
|
||||
{
|
||||
BN_init(this);
|
||||
setvch(vch);
|
||||
}
|
||||
|
||||
void setulong(unsigned long n)
|
||||
{
|
||||
if (!BN_set_word(this, n))
|
||||
throw bignum_error("CBigNum conversion from unsigned long : BN_set_word failed");
|
||||
}
|
||||
|
||||
unsigned long getulong() const
|
||||
{
|
||||
return BN_get_word(this);
|
||||
}
|
||||
|
||||
unsigned int getuint() const
|
||||
{
|
||||
return BN_get_word(this);
|
||||
}
|
||||
|
||||
int getint() const
|
||||
{
|
||||
unsigned long n = BN_get_word(this);
|
||||
if (!BN_is_negative(this))
|
||||
return (n > (unsigned long)std::numeric_limits<int>::max() ? std::numeric_limits<int>::max() : n);
|
||||
else
|
||||
return (n > (unsigned long)std::numeric_limits<int>::max() ? std::numeric_limits<int>::min() : -(int)n);
|
||||
}
|
||||
|
||||
void setint64(int64 sn)
|
||||
{
|
||||
unsigned char pch[sizeof(sn) + 6];
|
||||
unsigned char* p = pch + 4;
|
||||
bool fNegative;
|
||||
uint64 n;
|
||||
|
||||
if (sn < (int64)0)
|
||||
{
|
||||
// Since the minimum signed integer cannot be represented as positive so long as its type is signed,
|
||||
// and it's not well-defined what happens if you make it unsigned before negating it,
|
||||
// we instead increment the negative integer by 1, convert it, then increment the (now positive) unsigned integer by 1 to compensate
|
||||
n = -(sn + 1);
|
||||
++n;
|
||||
fNegative = true;
|
||||
} else {
|
||||
n = sn;
|
||||
fNegative = false;
|
||||
}
|
||||
|
||||
bool fLeadingZeroes = true;
|
||||
for (int i = 0; i < 8; i++)
|
||||
{
|
||||
unsigned char c = (n >> 56) & 0xff;
|
||||
n <<= 8;
|
||||
if (fLeadingZeroes)
|
||||
{
|
||||
if (c == 0)
|
||||
continue;
|
||||
if (c & 0x80)
|
||||
*p++ = (fNegative ? 0x80 : 0);
|
||||
else if (fNegative)
|
||||
c |= 0x80;
|
||||
fLeadingZeroes = false;
|
||||
}
|
||||
*p++ = c;
|
||||
}
|
||||
unsigned int nSize = p - (pch + 4);
|
||||
pch[0] = (nSize >> 24) & 0xff;
|
||||
pch[1] = (nSize >> 16) & 0xff;
|
||||
pch[2] = (nSize >> 8) & 0xff;
|
||||
pch[3] = (nSize) & 0xff;
|
||||
BN_mpi2bn(pch, p - pch, this);
|
||||
}
|
||||
|
||||
void setuint64(uint64 n)
|
||||
{
|
||||
unsigned char pch[sizeof(n) + 6];
|
||||
unsigned char* p = pch + 4;
|
||||
bool fLeadingZeroes = true;
|
||||
for (int i = 0; i < 8; i++)
|
||||
{
|
||||
unsigned char c = (n >> 56) & 0xff;
|
||||
n <<= 8;
|
||||
if (fLeadingZeroes)
|
||||
{
|
||||
if (c == 0)
|
||||
continue;
|
||||
if (c & 0x80)
|
||||
*p++ = 0;
|
||||
fLeadingZeroes = false;
|
||||
}
|
||||
*p++ = c;
|
||||
}
|
||||
unsigned int nSize = p - (pch + 4);
|
||||
pch[0] = (nSize >> 24) & 0xff;
|
||||
pch[1] = (nSize >> 16) & 0xff;
|
||||
pch[2] = (nSize >> 8) & 0xff;
|
||||
pch[3] = (nSize) & 0xff;
|
||||
BN_mpi2bn(pch, p - pch, this);
|
||||
}
|
||||
|
||||
void setuint256(uint256 n)
|
||||
{
|
||||
unsigned char pch[sizeof(n) + 6];
|
||||
unsigned char* p = pch + 4;
|
||||
bool fLeadingZeroes = true;
|
||||
unsigned char* pbegin = (unsigned char*)&n;
|
||||
unsigned char* psrc = pbegin + sizeof(n);
|
||||
while (psrc != pbegin)
|
||||
{
|
||||
unsigned char c = *(--psrc);
|
||||
if (fLeadingZeroes)
|
||||
{
|
||||
if (c == 0)
|
||||
continue;
|
||||
if (c & 0x80)
|
||||
*p++ = 0;
|
||||
fLeadingZeroes = false;
|
||||
}
|
||||
*p++ = c;
|
||||
}
|
||||
unsigned int nSize = p - (pch + 4);
|
||||
pch[0] = (nSize >> 24) & 0xff;
|
||||
pch[1] = (nSize >> 16) & 0xff;
|
||||
pch[2] = (nSize >> 8) & 0xff;
|
||||
pch[3] = (nSize >> 0) & 0xff;
|
||||
BN_mpi2bn(pch, p - pch, this);
|
||||
}
|
||||
|
||||
uint256 getuint256() const
|
||||
{
|
||||
unsigned int nSize = BN_bn2mpi(this, NULL);
|
||||
if (nSize < 4)
|
||||
return 0;
|
||||
std::vector<unsigned char> vch(nSize);
|
||||
BN_bn2mpi(this, &vch[0]);
|
||||
if (vch.size() > 4)
|
||||
vch[4] &= 0x7f;
|
||||
uint256 n = 0;
|
||||
for (unsigned int i = 0, j = vch.size()-1; i < sizeof(n) && j >= 4; i++, j--)
|
||||
((unsigned char*)&n)[i] = vch[j];
|
||||
return n;
|
||||
}
|
||||
|
||||
void setvch(const std::vector<unsigned char>& vch)
|
||||
{
|
||||
std::vector<unsigned char> vch2(vch.size() + 4);
|
||||
unsigned int nSize = vch.size();
|
||||
// BIGNUM's byte stream format expects 4 bytes of
|
||||
// big endian size data info at the front
|
||||
vch2[0] = (nSize >> 24) & 0xff;
|
||||
vch2[1] = (nSize >> 16) & 0xff;
|
||||
vch2[2] = (nSize >> 8) & 0xff;
|
||||
vch2[3] = (nSize >> 0) & 0xff;
|
||||
// swap data to big endian
|
||||
reverse_copy(vch.begin(), vch.end(), vch2.begin() + 4);
|
||||
BN_mpi2bn(&vch2[0], vch2.size(), this);
|
||||
}
|
||||
|
||||
std::vector<unsigned char> getvch() const
|
||||
{
|
||||
unsigned int nSize = BN_bn2mpi(this, NULL);
|
||||
if (nSize <= 4)
|
||||
return std::vector<unsigned char>();
|
||||
std::vector<unsigned char> vch(nSize);
|
||||
BN_bn2mpi(this, &vch[0]);
|
||||
vch.erase(vch.begin(), vch.begin() + 4);
|
||||
reverse(vch.begin(), vch.end());
|
||||
return vch;
|
||||
}
|
||||
|
||||
// The "compact" format is a representation of a whole
|
||||
// number N using an unsigned 32bit number similar to a
|
||||
// floating point format.
|
||||
// The most significant 8 bits are the unsigned exponent of base 256.
|
||||
// This exponent can be thought of as "number of bytes of N".
|
||||
// The lower 23 bits are the mantissa.
|
||||
// Bit number 24 (0x800000) represents the sign of N.
|
||||
// N = (-1^sign) * mantissa * 256^(exponent-3)
|
||||
//
|
||||
// Satoshi's original implementation used BN_bn2mpi() and BN_mpi2bn().
|
||||
// MPI uses the most significant bit of the first byte as sign.
|
||||
// Thus 0x1234560000 is compact (0x05123456)
|
||||
// and 0xc0de000000 is compact (0x0600c0de)
|
||||
// (0x05c0de00) would be -0x40de000000
|
||||
//
|
||||
// Bitcoin only uses this "compact" format for encoding difficulty
|
||||
// targets, which are unsigned 256bit quantities. Thus, all the
|
||||
// complexities of the sign bit and using base 256 are probably an
|
||||
// implementation accident.
|
||||
//
|
||||
// This implementation directly uses shifts instead of going
|
||||
// through an intermediate MPI representation.
|
||||
CBigNum& SetCompact(unsigned int nCompact)
|
||||
{
|
||||
unsigned int nSize = nCompact >> 24;
|
||||
bool fNegative =(nCompact & 0x00800000) != 0;
|
||||
unsigned int nWord = nCompact & 0x007fffff;
|
||||
if (nSize <= 3)
|
||||
{
|
||||
nWord >>= 8*(3-nSize);
|
||||
BN_set_word(this, nWord);
|
||||
}
|
||||
else
|
||||
{
|
||||
BN_set_word(this, nWord);
|
||||
BN_lshift(this, this, 8*(nSize-3));
|
||||
}
|
||||
BN_set_negative(this, fNegative);
|
||||
return *this;
|
||||
}
|
||||
|
||||
unsigned int GetCompact() const
|
||||
{
|
||||
unsigned int nSize = BN_num_bytes(this);
|
||||
unsigned int nCompact = 0;
|
||||
if (nSize <= 3)
|
||||
nCompact = BN_get_word(this) << 8*(3-nSize);
|
||||
else
|
||||
{
|
||||
CBigNum bn;
|
||||
BN_rshift(&bn, this, 8*(nSize-3));
|
||||
nCompact = BN_get_word(&bn);
|
||||
}
|
||||
// The 0x00800000 bit denotes the sign.
|
||||
// Thus, if it is already set, divide the mantissa by 256 and increase the exponent.
|
||||
if (nCompact & 0x00800000)
|
||||
{
|
||||
nCompact >>= 8;
|
||||
nSize++;
|
||||
}
|
||||
nCompact |= nSize << 24;
|
||||
nCompact |= (BN_is_negative(this) ? 0x00800000 : 0);
|
||||
return nCompact;
|
||||
}
|
||||
|
||||
void SetHex(const std::string& str)
|
||||
{
|
||||
// skip 0x
|
||||
const char* psz = str.c_str();
|
||||
while (isspace(*psz))
|
||||
psz++;
|
||||
bool fNegative = false;
|
||||
if (*psz == '-')
|
||||
{
|
||||
fNegative = true;
|
||||
psz++;
|
||||
}
|
||||
if (psz[0] == '0' && tolower(psz[1]) == 'x')
|
||||
psz += 2;
|
||||
while (isspace(*psz))
|
||||
psz++;
|
||||
|
||||
// hex string to bignum
|
||||
static const signed char phexdigit[256] = { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,1,2,3,4,5,6,7,8,9,0,0,0,0,0,0, 0,0xa,0xb,0xc,0xd,0xe,0xf,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0xa,0xb,0xc,0xd,0xe,0xf,0,0,0,0,0,0,0,0,0 };
|
||||
*this = 0;
|
||||
while (isxdigit(*psz))
|
||||
{
|
||||
*this <<= 4;
|
||||
int n = phexdigit[(unsigned char)*psz++];
|
||||
*this += n;
|
||||
}
|
||||
if (fNegative)
|
||||
*this = 0 - *this;
|
||||
}
|
||||
|
||||
std::string ToString(int nBase=10) const
|
||||
{
|
||||
CAutoBN_CTX pctx;
|
||||
CBigNum bnBase = nBase;
|
||||
CBigNum bn0 = 0;
|
||||
std::string str;
|
||||
CBigNum bn = *this;
|
||||
BN_set_negative(&bn, false);
|
||||
CBigNum dv;
|
||||
CBigNum rem;
|
||||
if (BN_cmp(&bn, &bn0) == 0)
|
||||
return "0";
|
||||
while (BN_cmp(&bn, &bn0) > 0)
|
||||
{
|
||||
if (!BN_div(&dv, &rem, &bn, &bnBase, pctx))
|
||||
throw bignum_error("CBigNum::ToString() : BN_div failed");
|
||||
bn = dv;
|
||||
unsigned int c = rem.getulong();
|
||||
str += "0123456789abcdef"[c];
|
||||
}
|
||||
if (BN_is_negative(this))
|
||||
str += "-";
|
||||
reverse(str.begin(), str.end());
|
||||
return str;
|
||||
}
|
||||
|
||||
std::string GetHex() const
|
||||
{
|
||||
return ToString(16);
|
||||
}
|
||||
|
||||
unsigned int GetSerializeSize(int nType=0, int nVersion=PROTOCOL_VERSION) const
|
||||
{
|
||||
return ::GetSerializeSize(getvch(), nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Serialize(Stream& s, int nType=0, int nVersion=PROTOCOL_VERSION) const
|
||||
{
|
||||
::Serialize(s, getvch(), nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Unserialize(Stream& s, int nType=0, int nVersion=PROTOCOL_VERSION)
|
||||
{
|
||||
std::vector<unsigned char> vch;
|
||||
::Unserialize(s, vch, nType, nVersion);
|
||||
setvch(vch);
|
||||
}
|
||||
|
||||
|
||||
bool operator!() const
|
||||
{
|
||||
return BN_is_zero(this);
|
||||
}
|
||||
|
||||
CBigNum& operator+=(const CBigNum& b)
|
||||
{
|
||||
if (!BN_add(this, this, &b))
|
||||
throw bignum_error("CBigNum::operator+= : BN_add failed");
|
||||
return *this;
|
||||
}
|
||||
|
||||
CBigNum& operator-=(const CBigNum& b)
|
||||
{
|
||||
*this = *this - b;
|
||||
return *this;
|
||||
}
|
||||
|
||||
CBigNum& operator*=(const CBigNum& b)
|
||||
{
|
||||
CAutoBN_CTX pctx;
|
||||
if (!BN_mul(this, this, &b, pctx))
|
||||
throw bignum_error("CBigNum::operator*= : BN_mul failed");
|
||||
return *this;
|
||||
}
|
||||
|
||||
CBigNum& operator/=(const CBigNum& b)
|
||||
{
|
||||
*this = *this / b;
|
||||
return *this;
|
||||
}
|
||||
|
||||
CBigNum& operator%=(const CBigNum& b)
|
||||
{
|
||||
*this = *this % b;
|
||||
return *this;
|
||||
}
|
||||
|
||||
CBigNum& operator<<=(unsigned int shift)
|
||||
{
|
||||
if (!BN_lshift(this, this, shift))
|
||||
throw bignum_error("CBigNum:operator<<= : BN_lshift failed");
|
||||
return *this;
|
||||
}
|
||||
|
||||
CBigNum& operator>>=(unsigned int shift)
|
||||
{
|
||||
// Note: BN_rshift segfaults on 64-bit if 2^shift is greater than the number
|
||||
// if built on ubuntu 9.04 or 9.10, probably depends on version of OpenSSL
|
||||
CBigNum a = 1;
|
||||
a <<= shift;
|
||||
if (BN_cmp(&a, this) > 0)
|
||||
{
|
||||
*this = 0;
|
||||
return *this;
|
||||
}
|
||||
|
||||
if (!BN_rshift(this, this, shift))
|
||||
throw bignum_error("CBigNum:operator>>= : BN_rshift failed");
|
||||
return *this;
|
||||
}
|
||||
|
||||
|
||||
CBigNum& operator++()
|
||||
{
|
||||
// prefix operator
|
||||
if (!BN_add(this, this, BN_value_one()))
|
||||
throw bignum_error("CBigNum::operator++ : BN_add failed");
|
||||
return *this;
|
||||
}
|
||||
|
||||
const CBigNum operator++(int)
|
||||
{
|
||||
// postfix operator
|
||||
const CBigNum ret = *this;
|
||||
++(*this);
|
||||
return ret;
|
||||
}
|
||||
|
||||
CBigNum& operator--()
|
||||
{
|
||||
// prefix operator
|
||||
CBigNum r;
|
||||
if (!BN_sub(&r, this, BN_value_one()))
|
||||
throw bignum_error("CBigNum::operator-- : BN_sub failed");
|
||||
*this = r;
|
||||
return *this;
|
||||
}
|
||||
|
||||
const CBigNum operator--(int)
|
||||
{
|
||||
// postfix operator
|
||||
const CBigNum ret = *this;
|
||||
--(*this);
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
||||
friend inline const CBigNum operator-(const CBigNum& a, const CBigNum& b);
|
||||
friend inline const CBigNum operator/(const CBigNum& a, const CBigNum& b);
|
||||
friend inline const CBigNum operator%(const CBigNum& a, const CBigNum& b);
|
||||
};
|
||||
|
||||
|
||||
|
||||
inline const CBigNum operator+(const CBigNum& a, const CBigNum& b)
|
||||
{
|
||||
CBigNum r;
|
||||
if (!BN_add(&r, &a, &b))
|
||||
throw bignum_error("CBigNum::operator+ : BN_add failed");
|
||||
return r;
|
||||
}
|
||||
|
||||
inline const CBigNum operator-(const CBigNum& a, const CBigNum& b)
|
||||
{
|
||||
CBigNum r;
|
||||
if (!BN_sub(&r, &a, &b))
|
||||
throw bignum_error("CBigNum::operator- : BN_sub failed");
|
||||
return r;
|
||||
}
|
||||
|
||||
inline const CBigNum operator-(const CBigNum& a)
|
||||
{
|
||||
CBigNum r(a);
|
||||
BN_set_negative(&r, !BN_is_negative(&r));
|
||||
return r;
|
||||
}
|
||||
|
||||
inline const CBigNum operator*(const CBigNum& a, const CBigNum& b)
|
||||
{
|
||||
CAutoBN_CTX pctx;
|
||||
CBigNum r;
|
||||
if (!BN_mul(&r, &a, &b, pctx))
|
||||
throw bignum_error("CBigNum::operator* : BN_mul failed");
|
||||
return r;
|
||||
}
|
||||
|
||||
inline const CBigNum operator/(const CBigNum& a, const CBigNum& b)
|
||||
{
|
||||
CAutoBN_CTX pctx;
|
||||
CBigNum r;
|
||||
if (!BN_div(&r, NULL, &a, &b, pctx))
|
||||
throw bignum_error("CBigNum::operator/ : BN_div failed");
|
||||
return r;
|
||||
}
|
||||
|
||||
inline const CBigNum operator%(const CBigNum& a, const CBigNum& b)
|
||||
{
|
||||
CAutoBN_CTX pctx;
|
||||
CBigNum r;
|
||||
if (!BN_mod(&r, &a, &b, pctx))
|
||||
throw bignum_error("CBigNum::operator% : BN_div failed");
|
||||
return r;
|
||||
}
|
||||
|
||||
inline const CBigNum operator<<(const CBigNum& a, unsigned int shift)
|
||||
{
|
||||
CBigNum r;
|
||||
if (!BN_lshift(&r, &a, shift))
|
||||
throw bignum_error("CBigNum:operator<< : BN_lshift failed");
|
||||
return r;
|
||||
}
|
||||
|
||||
inline const CBigNum operator>>(const CBigNum& a, unsigned int shift)
|
||||
{
|
||||
CBigNum r = a;
|
||||
r >>= shift;
|
||||
return r;
|
||||
}
|
||||
|
||||
inline bool operator==(const CBigNum& a, const CBigNum& b) { return (BN_cmp(&a, &b) == 0); }
|
||||
inline bool operator!=(const CBigNum& a, const CBigNum& b) { return (BN_cmp(&a, &b) != 0); }
|
||||
inline bool operator<=(const CBigNum& a, const CBigNum& b) { return (BN_cmp(&a, &b) <= 0); }
|
||||
inline bool operator>=(const CBigNum& a, const CBigNum& b) { return (BN_cmp(&a, &b) >= 0); }
|
||||
inline bool operator<(const CBigNum& a, const CBigNum& b) { return (BN_cmp(&a, &b) < 0); }
|
||||
inline bool operator>(const CBigNum& a, const CBigNum& b) { return (BN_cmp(&a, &b) > 0); }
|
||||
|
||||
#endif
|
||||
+649
-268
File diff suppressed because it is too large.
Load diff
+36
-52
@@ -23,34 +23,22 @@
|
||||
<RootNamespace>ccminer</RootNamespace>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Release'" Label="Configuration">
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<UseDebugLibraries>false</UseDebugLibraries>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v120</PlatformToolset>
|
||||
<CLRSupport>false</CLRSupport>
|
||||
<LinkIncremental>false</LinkIncremental>
|
||||
<WholeProgramOptimization>true</WholeProgramOptimization>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<UseDebugLibraries>true</UseDebugLibraries>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v120</PlatformToolset>
|
||||
<CLRSupport>false</CLRSupport>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<UseDebugLibraries>false</UseDebugLibraries>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v120</PlatformToolset>
|
||||
<CLRSupport>false</CLRSupport>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
|
||||
<PropertyGroup Condition="'$(Configuration)'=='Debug'" Label="Configuration">
|
||||
<ConfigurationType>Application</ConfigurationType>
|
||||
<UseDebugLibraries>true</UseDebugLibraries>
|
||||
<CharacterSet>MultiByte</CharacterSet>
|
||||
<PlatformToolset>v120</PlatformToolset>
|
||||
<CLRSupport>false</CLRSupport>
|
||||
<LinkIncremental>false</LinkIncremental>
|
||||
</PropertyGroup>
|
||||
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
|
||||
<ImportGroup Label="ExtensionSettings">
|
||||
@@ -68,19 +56,6 @@
|
||||
<ImportGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="PropertySheets">
|
||||
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
|
||||
</ImportGroup>
|
||||
<PropertyGroup Label="UserMacros" />
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
|
||||
<LinkIncremental>true</LinkIncremental>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
|
||||
<LinkIncremental>false</LinkIncremental>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
|
||||
<LinkIncremental>false</LinkIncremental>
|
||||
</PropertyGroup>
|
||||
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
|
||||
<LinkIncremental>false</LinkIncremental>
|
||||
</PropertyGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
|
||||
<ClCompile>
|
||||
<WarningLevel>Level3</WarningLevel>
|
||||
@@ -91,6 +66,7 @@
|
||||
<AdditionalIncludeDirectories>.;compat;compat\curl-for-windows\curl\include;compat\jansson;compat\getopt;compat\pthreads;compat\curl-for-windows\openssl\openssl\include;compat\curl-for-windows\zlib;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir)</AdditionalIncludeDirectories>
|
||||
<EnableParallelCodeGeneration>true</EnableParallelCodeGeneration>
|
||||
<MultiProcessorCompilation>true</MultiProcessorCompilation>
|
||||
<OpenMPSupport>true</OpenMPSupport>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>true</GenerateDebugInformation>
|
||||
@@ -108,6 +84,7 @@
|
||||
<PtxAsOptionV>true</PtxAsOptionV>
|
||||
<Keep>true</Keep>
|
||||
<CodeGeneration>compute_50,sm_50</CodeGeneration>
|
||||
<Include>$(NVTOOLSEXT_PATH)\include;..\..\..\Common\C99</Include>
|
||||
</CudaCompile>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
|
||||
@@ -121,6 +98,7 @@
|
||||
<StructMemberAlignment>8Bytes</StructMemberAlignment>
|
||||
<EnableParallelCodeGeneration>true</EnableParallelCodeGeneration>
|
||||
<MultiProcessorCompilation>true</MultiProcessorCompilation>
|
||||
<OpenMPSupport>true</OpenMPSupport>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>true</GenerateDebugInformation>
|
||||
@@ -159,7 +137,7 @@
|
||||
<AdditionalIncludeDirectories>.;compat;compat\curl-for-windows\curl\include;compat\jansson;compat\getopt;compat\pthreads;compat\curl-for-windows\openssl\openssl\include;compat\curl-for-windows\zlib;%(AdditionalIncludeDirectories);$(CudaToolkitIncludeDir)</AdditionalIncludeDirectories>
|
||||
<EnableParallelCodeGeneration>true</EnableParallelCodeGeneration>
|
||||
<MultiProcessorCompilation>true</MultiProcessorCompilation>
|
||||
<ExceptionHandling>SyncCThrow</ExceptionHandling>
|
||||
<OpenMPSupport>true</OpenMPSupport>
|
||||
</ClCompile>
|
||||
<Link>
|
||||
<GenerateDebugInformation>false</GenerateDebugInformation>
|
||||
@@ -181,15 +159,11 @@
|
||||
<Keep>true</Keep>
|
||||
<CodeGeneration>compute_35,sm_35;compute_50,sm_50;compute_52,sm_52</CodeGeneration>
|
||||
<AdditionalOptions>--ptxas-options="-O2" %(AdditionalOptions)</AdditionalOptions>
|
||||
<Defines>
|
||||
</Defines>
|
||||
<Optimization>O3</Optimization>
|
||||
<Optimization>O2</Optimization>
|
||||
</CudaCompile>
|
||||
<CudaLink>
|
||||
<GPUDebugInfo>false</GPUDebugInfo>
|
||||
</CudaLink>
|
||||
<CudaLink>
|
||||
<Optimization>O2</Optimization>
|
||||
<Optimization>O3</Optimization>
|
||||
</CudaLink>
|
||||
</ItemDefinitionGroup>
|
||||
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
|
||||
@@ -198,7 +172,9 @@
|
||||
<Optimization>MaxSpeed</Optimization>
|
||||
<RuntimeLibrary>MultiThreaded</RuntimeLibrary>
|
||||
<FavorSizeOrSpeed>Speed</FavorSizeOrSpeed>
|
||||
<EnableEnhancedInstructionSet>AdvancedVectorExtensions</EnableEnhancedInstructionSet>
|
||||
<EnableEnhancedInstructionSet>
|
||||
</EnableEnhancedInstructionSet>
|
||||
<OpenMPSupport>true</OpenMPSupport>
|
||||
<CompileAsManaged>false</CompileAsManaged>
|
||||
<FunctionLevelLinking>true</FunctionLevelLinking>
|
||||
<IntrinsicFunctions>true</IntrinsicFunctions>
|
||||
@@ -222,13 +198,14 @@
|
||||
<CInterleavedPTX>false</CInterleavedPTX>
|
||||
<MaxRegCount>80</MaxRegCount>
|
||||
<PtxAsOptionV>true</PtxAsOptionV>
|
||||
<Keep>false</Keep>
|
||||
<Keep>true</Keep>
|
||||
<CodeGeneration>compute_35,sm_35;compute_50,sm_50;compute_52,sm_52</CodeGeneration>
|
||||
<Include>
|
||||
</Include>
|
||||
<Include>$(NVTOOLSEXT_PATH)\include;..\..\..\Common\C99</Include>
|
||||
<Optimization>O3</Optimization>
|
||||
<TargetMachinePlatform>64</TargetMachinePlatform>
|
||||
</CudaCompile>
|
||||
<CudaLink>
|
||||
<Optimization>O3</Optimization>
|
||||
<PerformDeviceLink>false</PerformDeviceLink>
|
||||
</CudaLink>
|
||||
</ItemDefinitionGroup>
|
||||
@@ -250,9 +227,10 @@
|
||||
<TreatWChar_tAsBuiltInType>false</TreatWChar_tAsBuiltInType>
|
||||
<Optimization Condition="'$(Configuration)'=='Release'">Full</Optimization>
|
||||
</ClCompile>
|
||||
<ClCompile Include="scrypt-jane.cpp" />
|
||||
<ClCompile Include="scrypt.cpp" />
|
||||
<ClCompile Include="pools.cpp" />
|
||||
<ClCompile Include="util.cpp" />
|
||||
<ClCompile Include="bignum.cpp" />
|
||||
<ClInclude Include="bignum.hpp" />
|
||||
<ClCompile Include="fuguecoin.cpp" />
|
||||
<ClCompile Include="groestlcoin.cpp" />
|
||||
<ClCompile Include="hashlog.cpp" />
|
||||
@@ -270,6 +248,8 @@
|
||||
<ClCompile Include="neoscrypt\neoscrypt-cpu.c" />
|
||||
<ClInclude Include="neoscrypt\cuda_vectors.h" />
|
||||
<CudaCompile Include="neoscrypt\cuda_neoscrypt.cu" />
|
||||
<ClCompile Include="scrypt-jane.cpp" />
|
||||
<ClCompile Include="scrypt.cpp" />
|
||||
<ClCompile Include="skein2.cpp" />
|
||||
<ClCompile Include="sph\aes_helper.c" />
|
||||
<ClCompile Include="sph\blake.c" />
|
||||
@@ -289,6 +269,7 @@
|
||||
<ExcludedFromBuild>true</ExcludedFromBuild>
|
||||
</ClCompile>
|
||||
<ClCompile Include="sph\sha2.c" />
|
||||
<ClCompile Include="sph\sha256d.c" />
|
||||
<ClCompile Include="sph\sha2big.c" />
|
||||
<ClCompile Include="sph\shabal.c" />
|
||||
<ClCompile Include="sph\shavite.c" />
|
||||
@@ -355,8 +336,11 @@
|
||||
<CudaCompile Include="cuda.cpp" />
|
||||
<CudaCompile Include="cuda_groestlcoin.cu" />
|
||||
<CudaCompile Include="cuda_myriadgroestl.cu" />
|
||||
<CudaCompile Include="cuda_nist5.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="cuda_nist5.cu" />
|
||||
<CudaCompile Include="sha256\bitcoin.cu" />
|
||||
<CudaCompile Include="sha256\cuda_bitcoin.cu" />
|
||||
<CudaCompile Include="sha256\credits.cu" />
|
||||
<CudaCompile Include="sha256\cuda_credits.cu" />
|
||||
<CudaCompile Include="scrypt\blake.cu" />
|
||||
<CudaCompile Include="scrypt\keccak.cu" />
|
||||
<CudaCompile Include="scrypt\sha256.cu" />
|
||||
@@ -454,7 +438,7 @@
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="qubit\deep.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="qubit\doom.cu">
|
||||
<CudaCompile Include="qubit\luffa.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="qubit\qubit.cu">
|
||||
</CudaCompile>
|
||||
@@ -476,7 +460,7 @@
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x11\cuda_x11_luffa512.cu" />
|
||||
<CudaCompile Include="x11\cuda_x11_luffa512_Cubehash.cu">
|
||||
<MaxRegCount>80</MaxRegCount>
|
||||
<MaxRegCount>76</MaxRegCount>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x11\cuda_x11_shavite512.cu">
|
||||
<MaxRegCount>128</MaxRegCount>
|
||||
@@ -499,21 +483,21 @@
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x13\x13.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x15\x14.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x15\cuda_x14_shabal512.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x15\x15.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x15\cuda_x15_whirlpool.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x17\x17.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x17\cuda_x17_haval512.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x17\cuda_x17_sha512.cu">
|
||||
<MaxRegCount>80</MaxRegCount>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x15\x14.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x15\x15.cu">
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="x17\x17.cu">
|
||||
</CudaCompile>
|
||||
</ItemGroup>
|
||||
<ItemGroup>
|
||||
<Image Include="res\ccminer.ico" />
|
||||
|
||||
+28
-1
@@ -79,6 +79,9 @@
|
||||
<Filter Include="Source Files\neoscrypt">
|
||||
<UniqueIdentifier>{2037fd0d-e7a2-4da8-956c-150aec726a99}</UniqueIdentifier>
|
||||
</Filter>
|
||||
<Filter Include="Source Files\CUDA\sha256">
|
||||
<UniqueIdentifier>{6def248f-bf21-43b0-8fd7-f2c749b73e9e}</UniqueIdentifier>
|
||||
</Filter>
|
||||
</ItemGroup>
|
||||
<ItemGroup>
|
||||
<ClCompile Include="compat\jansson\dump.c">
|
||||
@@ -111,6 +114,9 @@
|
||||
<ClCompile Include="ccminer.cpp">
|
||||
<Filter>Source Files</Filter>
|
||||
</ClCompile>
|
||||
<ClCompile Include="pools.cpp">
|
||||
<Filter>Source Files</Filter>
|
||||
</ClCompile>
|
||||
<ClCompile Include="crc32.c">
|
||||
<Filter>Source Files</Filter>
|
||||
</ClCompile>
|
||||
@@ -177,6 +183,9 @@
|
||||
<ClCompile Include="sph\haval_helper.c">
|
||||
<Filter>Source Files\sph</Filter>
|
||||
</ClCompile>
|
||||
<ClCompile Include="sph\sha256d.c">
|
||||
<Filter>Source Files\sph</Filter>
|
||||
</ClCompile>
|
||||
<ClCompile Include="sph\sha2big.c">
|
||||
<Filter>Source Files\sph</Filter>
|
||||
</ClCompile>
|
||||
@@ -243,6 +252,9 @@
|
||||
<ClCompile Include="hefty1.c">
|
||||
<Filter>Source Files\CUDA\heavy</Filter>
|
||||
</ClCompile>
|
||||
<ClCompile Include="bignum.cpp">
|
||||
<Filter>Source Files</Filter>
|
||||
</ClCompile>
|
||||
</ItemGroup>
|
||||
<ItemGroup>
|
||||
<ClInclude Include="compat.h">
|
||||
@@ -404,6 +416,9 @@
|
||||
<ClInclude Include="hefty1.h">
|
||||
<Filter>Source Files\CUDA\heavy</Filter>
|
||||
</ClInclude>
|
||||
<ClInclude Include="bignum.hpp">
|
||||
<Filter>Header Files</Filter>
|
||||
</ClInclude>
|
||||
</ItemGroup>
|
||||
<ItemGroup>
|
||||
<CudaCompile Include="cuda.cpp">
|
||||
@@ -481,7 +496,7 @@
|
||||
<CudaCompile Include="qubit\deep.cu">
|
||||
<Filter>Source Files\CUDA\qubit</Filter>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="qubit\doom.cu">
|
||||
<CudaCompile Include="qubit\luffa.cu">
|
||||
<Filter>Source Files\CUDA\qubit</Filter>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="qubit\qubit.cu">
|
||||
@@ -631,6 +646,18 @@
|
||||
<CudaCompile Include="neoscrypt\cuda_neoscrypt.cu">
|
||||
<Filter>Source Files\neoscrypt</Filter>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="sha256\bitcoin.cu">
|
||||
<Filter>Source Files\CUDA\sha256</Filter>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="sha256\cuda_bitcoin.cu">
|
||||
<Filter>Source Files\CUDA\sha256</Filter>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="sha256\credits.cu">
|
||||
<Filter>Source Files\CUDA\sha256</Filter>
|
||||
</CudaCompile>
|
||||
<CudaCompile Include="sha256\cuda_credits.cu">
|
||||
<Filter>Source Files\CUDA\sha256</Filter>
|
||||
</CudaCompile>
|
||||
</ItemGroup>
|
||||
<ItemGroup>
|
||||
<Image Include="res\ccminer.ico">
|
||||
|
||||
@@ -0,0 +1,902 @@
|
||||
/* crypto/bn/bn.h */
|
||||
/* Copyright (C) 1995-1997 Eric Young (eay@cryptsoft.com)
|
||||
* All rights reserved.
|
||||
*
|
||||
* This package is an SSL implementation written
|
||||
* by Eric Young (eay@cryptsoft.com).
|
||||
* The implementation was written so as to conform with Netscapes SSL.
|
||||
*
|
||||
* This library is free for commercial and non-commercial use as long as
|
||||
* the following conditions are aheared to. The following conditions
|
||||
* apply to all code found in this distribution, be it the RC4, RSA,
|
||||
* lhash, DES, etc., code; not just the SSL code. The SSL documentation
|
||||
* included with this distribution is covered by the same copyright terms
|
||||
* except that the holder is Tim Hudson (tjh@cryptsoft.com).
|
||||
*
|
||||
* Copyright remains Eric Young's, and as such any Copyright notices in
|
||||
* the code are not to be removed.
|
||||
* If this package is used in a product, Eric Young should be given attribution
|
||||
* as the author of the parts of the library used.
|
||||
* This can be in the form of a textual message at program startup or
|
||||
* in documentation (online or textual) provided with the package.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* 1. Redistributions of source code must retain the copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* 3. All advertising materials mentioning features or use of this software
|
||||
* must display the following acknowledgement:
|
||||
* "This product includes cryptographic software written by
|
||||
* Eric Young (eay@cryptsoft.com)"
|
||||
* The word 'cryptographic' can be left out if the rouines from the library
|
||||
* being used are not cryptographic related :-).
|
||||
* 4. If you include any Windows specific code (or a derivative thereof) from
|
||||
* the apps directory (application code) you must include an acknowledgement:
|
||||
* "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
|
||||
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
||||
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
||||
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
||||
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
||||
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||
* SUCH DAMAGE.
|
||||
*
|
||||
* The licence and distribution terms for any publically available version or
|
||||
* derivative of this code cannot be changed. i.e. this code cannot simply be
|
||||
* copied and put under another distribution licence
|
||||
* [including the GNU Public Licence.]
|
||||
*/
|
||||
/* ====================================================================
|
||||
* Copyright (c) 1998-2006 The OpenSSL Project. All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
*
|
||||
* 1. Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
*
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in
|
||||
* the documentation and/or other materials provided with the
|
||||
* distribution.
|
||||
*
|
||||
* 3. All advertising materials mentioning features or use of this
|
||||
* software must display the following acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit. (http://www.openssl.org/)"
|
||||
*
|
||||
* 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
|
||||
* endorse or promote products derived from this software without
|
||||
* prior written permission. For written permission, please contact
|
||||
* openssl-core@openssl.org.
|
||||
*
|
||||
* 5. Products derived from this software may not be called "OpenSSL"
|
||||
* nor may "OpenSSL" appear in their names without prior written
|
||||
* permission of the OpenSSL Project.
|
||||
*
|
||||
* 6. Redistributions of any form whatsoever must retain the following
|
||||
* acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit (http://www.openssl.org/)"
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
|
||||
* EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE OpenSSL PROJECT OR
|
||||
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
||||
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
||||
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
||||
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
||||
* OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
* ====================================================================
|
||||
*
|
||||
* This product includes cryptographic software written by Eric Young
|
||||
* (eay@cryptsoft.com). This product includes software written by Tim
|
||||
* Hudson (tjh@cryptsoft.com).
|
||||
*
|
||||
*/
|
||||
/* ====================================================================
|
||||
* Copyright 2002 Sun Microsystems, Inc. ALL RIGHTS RESERVED.
|
||||
*
|
||||
* Portions of the attached software ("Contribution") are developed by
|
||||
* SUN MICROSYSTEMS, INC., and are contributed to the OpenSSL project.
|
||||
*
|
||||
* The Contribution is licensed pursuant to the Eric Young open source
|
||||
* license provided above.
|
||||
*
|
||||
* The binary polynomial arithmetic software is originally written by
|
||||
* Sheueling Chang Shantz and Douglas Stebila of Sun Microsystems Laboratories.
|
||||
*
|
||||
*/
|
||||
|
||||
#ifndef HEADER_BN_H
|
||||
#define HEADER_BN_H
|
||||
|
||||
#include <openssl/e_os2.h>
|
||||
#ifndef OPENSSL_NO_FP_API
|
||||
#include <stdio.h> /* FILE */
|
||||
#endif
|
||||
#include <openssl/ossl_typ.h>
|
||||
#include <openssl/crypto.h>
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* These preprocessor symbols control various aspects of the bignum headers and
|
||||
* library code. They're not defined by any "normal" configuration, as they are
|
||||
* intended for development and testing purposes. NB: defining all three can be
|
||||
* useful for debugging application code as well as openssl itself.
|
||||
*
|
||||
* BN_DEBUG - turn on various debugging alterations to the bignum code
|
||||
* BN_DEBUG_RAND - uses random poisoning of unused words to trip up
|
||||
* mismanagement of bignum internals. You must also define BN_DEBUG.
|
||||
*/
|
||||
/* #define BN_DEBUG */
|
||||
/* #define BN_DEBUG_RAND */
|
||||
|
||||
#ifndef OPENSSL_SMALL_FOOTPRINT
|
||||
#define BN_MUL_COMBA
|
||||
#define BN_SQR_COMBA
|
||||
#define BN_RECURSION
|
||||
#endif
|
||||
|
||||
/* This next option uses the C libraries (2 word)/(1 word) function.
|
||||
* If it is not defined, I use my C version (which is slower).
|
||||
* The reason for this flag is that when the particular C compiler
|
||||
* library routine is used, and the library is linked with a different
|
||||
* compiler, the library is missing. This mostly happens when the
|
||||
* library is built with gcc and then linked using normal cc. This would
|
||||
* be a common occurrence because gcc normally produces code that is
|
||||
* 2 times faster than system compilers for the big number stuff.
|
||||
* For machines with only one compiler (or shared libraries), this should
|
||||
* be on. Again this in only really a problem on machines
|
||||
* using "long long's", are 32bit, and are not using my assembler code. */
|
||||
#if defined(OPENSSL_SYS_MSDOS) || defined(OPENSSL_SYS_WINDOWS) || \
|
||||
defined(OPENSSL_SYS_WIN32) || defined(linux)
|
||||
# ifndef BN_DIV2W
|
||||
# define BN_DIV2W
|
||||
# endif
|
||||
#endif
|
||||
|
||||
/* assuming long is 64bit - this is the DEC Alpha
|
||||
* unsigned long long is only 64 bits :-(, don't define
|
||||
* BN_LLONG for the DEC Alpha */
|
||||
#ifdef SIXTY_FOUR_BIT_LONG
|
||||
#define BN_ULLONG unsigned long long
|
||||
#define BN_ULONG unsigned long
|
||||
#define BN_LONG long
|
||||
#define BN_BITS 128
|
||||
#define BN_BYTES 8
|
||||
#define BN_BITS2 64
|
||||
#define BN_BITS4 32
|
||||
#define BN_MASK (0xffffffffffffffffffffffffffffffffLL)
|
||||
#define BN_MASK2 (0xffffffffffffffffL)
|
||||
#define BN_MASK2l (0xffffffffL)
|
||||
#define BN_MASK2h (0xffffffff00000000L)
|
||||
#define BN_MASK2h1 (0xffffffff80000000L)
|
||||
#define BN_TBIT (0x8000000000000000L)
|
||||
#define BN_DEC_CONV (10000000000000000000UL)
|
||||
#define BN_DEC_FMT1 "%lu"
|
||||
#define BN_DEC_FMT2 "%019lu"
|
||||
#define BN_DEC_NUM 19
|
||||
#define BN_HEX_FMT1 "%lX"
|
||||
#define BN_HEX_FMT2 "%016lX"
|
||||
#endif
|
||||
|
||||
/* This is where the long long data type is 64 bits, but long is 32.
|
||||
* For machines where there are 64bit registers, this is the mode to use.
|
||||
* IRIX, on R4000 and above should use this mode, along with the relevant
|
||||
* assembler code :-). Do NOT define BN_LLONG.
|
||||
*/
|
||||
#ifdef SIXTY_FOUR_BIT
|
||||
#undef BN_LLONG
|
||||
#undef BN_ULLONG
|
||||
#define BN_ULONG unsigned long long
|
||||
#define BN_LONG long long
|
||||
#define BN_BITS 128
|
||||
#define BN_BYTES 8
|
||||
#define BN_BITS2 64
|
||||
#define BN_BITS4 32
|
||||
#define BN_MASK2 (0xffffffffffffffffLL)
|
||||
#define BN_MASK2l (0xffffffffL)
|
||||
#define BN_MASK2h (0xffffffff00000000LL)
|
||||
#define BN_MASK2h1 (0xffffffff80000000LL)
|
||||
#define BN_TBIT (0x8000000000000000LL)
|
||||
#define BN_DEC_CONV (10000000000000000000ULL)
|
||||
#define BN_DEC_FMT1 "%llu"
|
||||
#define BN_DEC_FMT2 "%019llu"
|
||||
#define BN_DEC_NUM 19
|
||||
#define BN_HEX_FMT1 "%llX"
|
||||
#define BN_HEX_FMT2 "%016llX"
|
||||
#endif
|
||||
|
||||
#ifdef THIRTY_TWO_BIT
|
||||
#ifdef BN_LLONG
|
||||
# if defined(_WIN32) && !defined(__GNUC__)
|
||||
# define BN_ULLONG unsigned __int64
|
||||
# define BN_MASK (0xffffffffffffffffI64)
|
||||
# else
|
||||
# define BN_ULLONG unsigned long long
|
||||
# define BN_MASK (0xffffffffffffffffLL)
|
||||
# endif
|
||||
#endif
|
||||
#define BN_ULONG unsigned int
|
||||
#define BN_LONG int
|
||||
#define BN_BITS 64
|
||||
#define BN_BYTES 4
|
||||
#define BN_BITS2 32
|
||||
#define BN_BITS4 16
|
||||
#define BN_MASK2 (0xffffffffL)
|
||||
#define BN_MASK2l (0xffff)
|
||||
#define BN_MASK2h1 (0xffff8000L)
|
||||
#define BN_MASK2h (0xffff0000L)
|
||||
#define BN_TBIT (0x80000000L)
|
||||
#define BN_DEC_CONV (1000000000L)
|
||||
#define BN_DEC_FMT1 "%u"
|
||||
#define BN_DEC_FMT2 "%09u"
|
||||
#define BN_DEC_NUM 9
|
||||
#define BN_HEX_FMT1 "%X"
|
||||
#define BN_HEX_FMT2 "%08X"
|
||||
#endif
|
||||
|
||||
/* 2011-02-22 SMS.
|
||||
* In various places, a size_t variable or a type cast to size_t was
|
||||
* used to perform integer-only operations on pointers. This failed on
|
||||
* VMS with 64-bit pointers (CC /POINTER_SIZE = 64) because size_t is
|
||||
* still only 32 bits. What's needed in these cases is an integer type
|
||||
* with the same size as a pointer, which size_t is not certain to be.
|
||||
* The only fix here is VMS-specific.
|
||||
*/
|
||||
#if defined(OPENSSL_SYS_VMS)
|
||||
# if __INITIAL_POINTER_SIZE == 64
|
||||
# define PTR_SIZE_INT long long
|
||||
# else /* __INITIAL_POINTER_SIZE == 64 */
|
||||
# define PTR_SIZE_INT int
|
||||
# endif /* __INITIAL_POINTER_SIZE == 64 [else] */
|
||||
#else /* defined(OPENSSL_SYS_VMS) */
|
||||
# define PTR_SIZE_INT size_t
|
||||
#endif /* defined(OPENSSL_SYS_VMS) [else] */
|
||||
|
||||
#define BN_DEFAULT_BITS 1280
|
||||
|
||||
#define BN_FLG_MALLOCED 0x01
|
||||
#define BN_FLG_STATIC_DATA 0x02
|
||||
#define BN_FLG_CONSTTIME 0x04 /* avoid leaking exponent information through timing,
|
||||
* BN_mod_exp_mont() will call BN_mod_exp_mont_consttime,
|
||||
* BN_div() will call BN_div_no_branch,
|
||||
* BN_mod_inverse() will call BN_mod_inverse_no_branch.
|
||||
*/
|
||||
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
#define BN_FLG_EXP_CONSTTIME BN_FLG_CONSTTIME /* deprecated name for the flag */
|
||||
/* avoid leaking exponent information through timings
|
||||
* (BN_mod_exp_mont() will call BN_mod_exp_mont_consttime) */
|
||||
#endif
|
||||
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
#define BN_FLG_FREE 0x8000 /* used for debuging */
|
||||
#endif
|
||||
#define BN_set_flags(b,n) ((b)->flags|=(n))
|
||||
#define BN_get_flags(b,n) ((b)->flags&(n))
|
||||
|
||||
/* get a clone of a BIGNUM with changed flags, for *temporary* use only
|
||||
* (the two BIGNUMs cannot not be used in parallel!) */
|
||||
#define BN_with_flags(dest,b,n) ((dest)->d=(b)->d, \
|
||||
(dest)->top=(b)->top, \
|
||||
(dest)->dmax=(b)->dmax, \
|
||||
(dest)->neg=(b)->neg, \
|
||||
(dest)->flags=(((dest)->flags & BN_FLG_MALLOCED) \
|
||||
| ((b)->flags & ~BN_FLG_MALLOCED) \
|
||||
| BN_FLG_STATIC_DATA \
|
||||
| (n)))
|
||||
|
||||
/* Already declared in ossl_typ.h */
|
||||
#if 0
|
||||
typedef struct bignum_st BIGNUM;
|
||||
/* Used for temp variables (declaration hidden in bn_lcl.h) */
|
||||
typedef struct bignum_ctx BN_CTX;
|
||||
typedef struct bn_blinding_st BN_BLINDING;
|
||||
typedef struct bn_mont_ctx_st BN_MONT_CTX;
|
||||
typedef struct bn_recp_ctx_st BN_RECP_CTX;
|
||||
typedef struct bn_gencb_st BN_GENCB;
|
||||
#endif
|
||||
|
||||
struct bignum_st
|
||||
{
|
||||
BN_ULONG *d; /* Pointer to an array of 'BN_BITS2' bit chunks. */
|
||||
int top; /* Index of last used d +1. */
|
||||
/* The next are internal book keeping for bn_expand. */
|
||||
int dmax; /* Size of the d array. */
|
||||
int neg; /* one if the number is negative */
|
||||
int flags;
|
||||
};
|
||||
|
||||
/* Used for montgomery multiplication */
|
||||
struct bn_mont_ctx_st
|
||||
{
|
||||
int ri; /* number of bits in R */
|
||||
BIGNUM RR; /* used to convert to montgomery form */
|
||||
BIGNUM N; /* The modulus */
|
||||
BIGNUM Ni; /* R*(1/R mod N) - N*Ni = 1
|
||||
* (Ni is only stored for bignum algorithm) */
|
||||
BN_ULONG n0[2];/* least significant word(s) of Ni;
|
||||
(type changed with 0.9.9, was "BN_ULONG n0;" before) */
|
||||
int flags;
|
||||
};
|
||||
|
||||
/* Used for reciprocal division/mod functions
|
||||
* It cannot be shared between threads
|
||||
*/
|
||||
struct bn_recp_ctx_st
|
||||
{
|
||||
BIGNUM N; /* the divisor */
|
||||
BIGNUM Nr; /* the reciprocal */
|
||||
int num_bits;
|
||||
int shift;
|
||||
int flags;
|
||||
};
|
||||
|
||||
/* Used for slow "generation" functions. */
|
||||
struct bn_gencb_st
|
||||
{
|
||||
unsigned int ver; /* To handle binary (in)compatibility */
|
||||
void *arg; /* callback-specific data */
|
||||
union
|
||||
{
|
||||
/* if(ver==1) - handles old style callbacks */
|
||||
void (*cb_1)(int, int, void *);
|
||||
/* if(ver==2) - new callback style */
|
||||
int (*cb_2)(int, int, BN_GENCB *);
|
||||
} cb;
|
||||
};
|
||||
/* Wrapper function to make using BN_GENCB easier, */
|
||||
int BN_GENCB_call(BN_GENCB *cb, int a, int b);
|
||||
/* Macro to populate a BN_GENCB structure with an "old"-style callback */
|
||||
#define BN_GENCB_set_old(gencb, callback, cb_arg) { \
|
||||
BN_GENCB *tmp_gencb = (gencb); \
|
||||
tmp_gencb->ver = 1; \
|
||||
tmp_gencb->arg = (cb_arg); \
|
||||
tmp_gencb->cb.cb_1 = (callback); }
|
||||
/* Macro to populate a BN_GENCB structure with a "new"-style callback */
|
||||
#define BN_GENCB_set(gencb, callback, cb_arg) { \
|
||||
BN_GENCB *tmp_gencb = (gencb); \
|
||||
tmp_gencb->ver = 2; \
|
||||
tmp_gencb->arg = (cb_arg); \
|
||||
tmp_gencb->cb.cb_2 = (callback); }
|
||||
|
||||
#define BN_prime_checks 0 /* default: select number of iterations
|
||||
based on the size of the number */
|
||||
|
||||
/* number of Miller-Rabin iterations for an error rate of less than 2^-80
|
||||
* for random 'b'-bit input, b >= 100 (taken from table 4.4 in the Handbook
|
||||
* of Applied Cryptography [Menezes, van Oorschot, Vanstone; CRC Press 1996];
|
||||
* original paper: Damgaard, Landrock, Pomerance: Average case error estimates
|
||||
* for the strong probable prime test. -- Math. Comp. 61 (1993) 177-194) */
|
||||
#define BN_prime_checks_for_size(b) ((b) >= 1300 ? 2 : \
|
||||
(b) >= 850 ? 3 : \
|
||||
(b) >= 650 ? 4 : \
|
||||
(b) >= 550 ? 5 : \
|
||||
(b) >= 450 ? 6 : \
|
||||
(b) >= 400 ? 7 : \
|
||||
(b) >= 350 ? 8 : \
|
||||
(b) >= 300 ? 9 : \
|
||||
(b) >= 250 ? 12 : \
|
||||
(b) >= 200 ? 15 : \
|
||||
(b) >= 150 ? 18 : \
|
||||
/* b >= 100 */ 27)
|
||||
|
||||
#define BN_num_bytes(a) ((BN_num_bits(a)+7)/8)
|
||||
|
||||
/* Note that BN_abs_is_word didn't work reliably for w == 0 until 0.9.8 */
|
||||
#define BN_abs_is_word(a,w) ((((a)->top == 1) && ((a)->d[0] == (BN_ULONG)(w))) || \
|
||||
(((w) == 0) && ((a)->top == 0)))
|
||||
#define BN_is_zero(a) ((a)->top == 0)
|
||||
#define BN_is_one(a) (BN_abs_is_word((a),1) && !(a)->neg)
|
||||
#define BN_is_word(a,w) (BN_abs_is_word((a),(w)) && (!(w) || !(a)->neg))
|
||||
#define BN_is_odd(a) (((a)->top > 0) && ((a)->d[0] & 1))
|
||||
|
||||
#define BN_one(a) (BN_set_word((a),1))
|
||||
#define BN_zero_ex(a) \
|
||||
do { \
|
||||
BIGNUM *_tmp_bn = (a); \
|
||||
_tmp_bn->top = 0; \
|
||||
_tmp_bn->neg = 0; \
|
||||
} while(0)
|
||||
#ifdef OPENSSL_NO_DEPRECATED
|
||||
#define BN_zero(a) BN_zero_ex(a)
|
||||
#else
|
||||
#define BN_zero(a) (BN_set_word((a),0))
|
||||
#endif
|
||||
|
||||
const BIGNUM *BN_value_one(void);
|
||||
char * BN_options(void);
|
||||
BN_CTX *BN_CTX_new(void);
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
void BN_CTX_init(BN_CTX *c);
|
||||
#endif
|
||||
void BN_CTX_free(BN_CTX *c);
|
||||
void BN_CTX_start(BN_CTX *ctx);
|
||||
BIGNUM *BN_CTX_get(BN_CTX *ctx);
|
||||
void BN_CTX_end(BN_CTX *ctx);
|
||||
int BN_rand(BIGNUM *rnd, int bits, int top,int bottom);
|
||||
int BN_pseudo_rand(BIGNUM *rnd, int bits, int top,int bottom);
|
||||
int BN_rand_range(BIGNUM *rnd, const BIGNUM *range);
|
||||
int BN_pseudo_rand_range(BIGNUM *rnd, const BIGNUM *range);
|
||||
int BN_num_bits(const BIGNUM *a);
|
||||
int BN_num_bits_word(BN_ULONG);
|
||||
BIGNUM *BN_new(void);
|
||||
void BN_init(BIGNUM *);
|
||||
void BN_clear_free(BIGNUM *a);
|
||||
BIGNUM *BN_copy(BIGNUM *a, const BIGNUM *b);
|
||||
void BN_swap(BIGNUM *a, BIGNUM *b);
|
||||
BIGNUM *BN_bin2bn(const unsigned char *s,int len,BIGNUM *ret);
|
||||
int BN_bn2bin(const BIGNUM *a, unsigned char *to);
|
||||
BIGNUM *BN_mpi2bn(const unsigned char *s,int len,BIGNUM *ret);
|
||||
int BN_bn2mpi(const BIGNUM *a, unsigned char *to);
|
||||
int BN_sub(BIGNUM *r, const BIGNUM *a, const BIGNUM *b);
|
||||
int BN_usub(BIGNUM *r, const BIGNUM *a, const BIGNUM *b);
|
||||
int BN_uadd(BIGNUM *r, const BIGNUM *a, const BIGNUM *b);
|
||||
int BN_add(BIGNUM *r, const BIGNUM *a, const BIGNUM *b);
|
||||
int BN_mul(BIGNUM *r, const BIGNUM *a, const BIGNUM *b, BN_CTX *ctx);
|
||||
int BN_sqr(BIGNUM *r, const BIGNUM *a,BN_CTX *ctx);
|
||||
/** BN_set_negative sets sign of a BIGNUM
|
||||
* \param b pointer to the BIGNUM object
|
||||
* \param n 0 if the BIGNUM b should be positive and a value != 0 otherwise
|
||||
*/
|
||||
void BN_set_negative(BIGNUM *b, int n);
|
||||
/** BN_is_negative returns 1 if the BIGNUM is negative
|
||||
* \param a pointer to the BIGNUM object
|
||||
* \return 1 if a < 0 and 0 otherwise
|
||||
*/
|
||||
#define BN_is_negative(a) ((a)->neg != 0)
|
||||
|
||||
int BN_div(BIGNUM *dv, BIGNUM *rem, const BIGNUM *m, const BIGNUM *d,
|
||||
BN_CTX *ctx);
|
||||
#define BN_mod(rem,m,d,ctx) BN_div(NULL,(rem),(m),(d),(ctx))
|
||||
int BN_nnmod(BIGNUM *r, const BIGNUM *m, const BIGNUM *d, BN_CTX *ctx);
|
||||
int BN_mod_add(BIGNUM *r, const BIGNUM *a, const BIGNUM *b, const BIGNUM *m, BN_CTX *ctx);
|
||||
int BN_mod_add_quick(BIGNUM *r, const BIGNUM *a, const BIGNUM *b, const BIGNUM *m);
|
||||
int BN_mod_sub(BIGNUM *r, const BIGNUM *a, const BIGNUM *b, const BIGNUM *m, BN_CTX *ctx);
|
||||
int BN_mod_sub_quick(BIGNUM *r, const BIGNUM *a, const BIGNUM *b, const BIGNUM *m);
|
||||
int BN_mod_mul(BIGNUM *r, const BIGNUM *a, const BIGNUM *b,
|
||||
const BIGNUM *m, BN_CTX *ctx);
|
||||
int BN_mod_sqr(BIGNUM *r, const BIGNUM *a, const BIGNUM *m, BN_CTX *ctx);
|
||||
int BN_mod_lshift1(BIGNUM *r, const BIGNUM *a, const BIGNUM *m, BN_CTX *ctx);
|
||||
int BN_mod_lshift1_quick(BIGNUM *r, const BIGNUM *a, const BIGNUM *m);
|
||||
int BN_mod_lshift(BIGNUM *r, const BIGNUM *a, int n, const BIGNUM *m, BN_CTX *ctx);
|
||||
int BN_mod_lshift_quick(BIGNUM *r, const BIGNUM *a, int n, const BIGNUM *m);
|
||||
|
||||
BN_ULONG BN_mod_word(const BIGNUM *a, BN_ULONG w);
|
||||
BN_ULONG BN_div_word(BIGNUM *a, BN_ULONG w);
|
||||
int BN_mul_word(BIGNUM *a, BN_ULONG w);
|
||||
int BN_add_word(BIGNUM *a, BN_ULONG w);
|
||||
int BN_sub_word(BIGNUM *a, BN_ULONG w);
|
||||
int BN_set_word(BIGNUM *a, BN_ULONG w);
|
||||
BN_ULONG BN_get_word(const BIGNUM *a);
|
||||
|
||||
int BN_cmp(const BIGNUM *a, const BIGNUM *b);
|
||||
void BN_free(BIGNUM *a);
|
||||
int BN_is_bit_set(const BIGNUM *a, int n);
|
||||
int BN_lshift(BIGNUM *r, const BIGNUM *a, int n);
|
||||
int BN_lshift1(BIGNUM *r, const BIGNUM *a);
|
||||
int BN_exp(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,BN_CTX *ctx);
|
||||
|
||||
int BN_mod_exp(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
const BIGNUM *m,BN_CTX *ctx);
|
||||
int BN_mod_exp_mont(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
const BIGNUM *m, BN_CTX *ctx, BN_MONT_CTX *m_ctx);
|
||||
int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
|
||||
const BIGNUM *m, BN_CTX *ctx, BN_MONT_CTX *in_mont);
|
||||
int BN_mod_exp_mont_word(BIGNUM *r, BN_ULONG a, const BIGNUM *p,
|
||||
const BIGNUM *m, BN_CTX *ctx, BN_MONT_CTX *m_ctx);
|
||||
int BN_mod_exp2_mont(BIGNUM *r, const BIGNUM *a1, const BIGNUM *p1,
|
||||
const BIGNUM *a2, const BIGNUM *p2,const BIGNUM *m,
|
||||
BN_CTX *ctx,BN_MONT_CTX *m_ctx);
|
||||
int BN_mod_exp_simple(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
const BIGNUM *m,BN_CTX *ctx);
|
||||
|
||||
int BN_mask_bits(BIGNUM *a,int n);
|
||||
#ifndef OPENSSL_NO_FP_API
|
||||
int BN_print_fp(FILE *fp, const BIGNUM *a);
|
||||
#endif
|
||||
#ifdef HEADER_BIO_H
|
||||
int BN_print(BIO *fp, const BIGNUM *a);
|
||||
#else
|
||||
int BN_print(void *fp, const BIGNUM *a);
|
||||
#endif
|
||||
int BN_reciprocal(BIGNUM *r, const BIGNUM *m, int len, BN_CTX *ctx);
|
||||
int BN_rshift(BIGNUM *r, const BIGNUM *a, int n);
|
||||
int BN_rshift1(BIGNUM *r, const BIGNUM *a);
|
||||
void BN_clear(BIGNUM *a);
|
||||
BIGNUM *BN_dup(const BIGNUM *a);
|
||||
int BN_ucmp(const BIGNUM *a, const BIGNUM *b);
|
||||
int BN_set_bit(BIGNUM *a, int n);
|
||||
int BN_clear_bit(BIGNUM *a, int n);
|
||||
char * BN_bn2hex(const BIGNUM *a);
|
||||
char * BN_bn2dec(const BIGNUM *a);
|
||||
int BN_hex2bn(BIGNUM **a, const char *str);
|
||||
int BN_dec2bn(BIGNUM **a, const char *str);
|
||||
int BN_asc2bn(BIGNUM **a, const char *str);
|
||||
int BN_gcd(BIGNUM *r,const BIGNUM *a,const BIGNUM *b,BN_CTX *ctx);
|
||||
int BN_kronecker(const BIGNUM *a,const BIGNUM *b,BN_CTX *ctx); /* returns -2 for error */
|
||||
BIGNUM *BN_mod_inverse(BIGNUM *ret,
|
||||
const BIGNUM *a, const BIGNUM *n,BN_CTX *ctx);
|
||||
BIGNUM *BN_mod_sqrt(BIGNUM *ret,
|
||||
const BIGNUM *a, const BIGNUM *n,BN_CTX *ctx);
|
||||
|
||||
void BN_consttime_swap(BN_ULONG swap, BIGNUM *a, BIGNUM *b, int nwords);
|
||||
|
||||
/* Deprecated versions */
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
BIGNUM *BN_generate_prime(BIGNUM *ret,int bits,int safe,
|
||||
const BIGNUM *add, const BIGNUM *rem,
|
||||
void (*callback)(int,int,void *),void *cb_arg);
|
||||
int BN_is_prime(const BIGNUM *p,int nchecks,
|
||||
void (*callback)(int,int,void *),
|
||||
BN_CTX *ctx,void *cb_arg);
|
||||
int BN_is_prime_fasttest(const BIGNUM *p,int nchecks,
|
||||
void (*callback)(int,int,void *),BN_CTX *ctx,void *cb_arg,
|
||||
int do_trial_division);
|
||||
#endif /* !defined(OPENSSL_NO_DEPRECATED) */
|
||||
|
||||
/* Newer versions */
|
||||
int BN_generate_prime_ex(BIGNUM *ret,int bits,int safe, const BIGNUM *add,
|
||||
const BIGNUM *rem, BN_GENCB *cb);
|
||||
int BN_is_prime_ex(const BIGNUM *p,int nchecks, BN_CTX *ctx, BN_GENCB *cb);
|
||||
int BN_is_prime_fasttest_ex(const BIGNUM *p,int nchecks, BN_CTX *ctx,
|
||||
int do_trial_division, BN_GENCB *cb);
|
||||
|
||||
int BN_X931_generate_Xpq(BIGNUM *Xp, BIGNUM *Xq, int nbits, BN_CTX *ctx);
|
||||
|
||||
int BN_X931_derive_prime_ex(BIGNUM *p, BIGNUM *p1, BIGNUM *p2,
|
||||
const BIGNUM *Xp, const BIGNUM *Xp1, const BIGNUM *Xp2,
|
||||
const BIGNUM *e, BN_CTX *ctx, BN_GENCB *cb);
|
||||
int BN_X931_generate_prime_ex(BIGNUM *p, BIGNUM *p1, BIGNUM *p2,
|
||||
BIGNUM *Xp1, BIGNUM *Xp2,
|
||||
const BIGNUM *Xp,
|
||||
const BIGNUM *e, BN_CTX *ctx,
|
||||
BN_GENCB *cb);
|
||||
|
||||
BN_MONT_CTX *BN_MONT_CTX_new(void );
|
||||
void BN_MONT_CTX_init(BN_MONT_CTX *ctx);
|
||||
int BN_mod_mul_montgomery(BIGNUM *r,const BIGNUM *a,const BIGNUM *b,
|
||||
BN_MONT_CTX *mont, BN_CTX *ctx);
|
||||
#define BN_to_montgomery(r,a,mont,ctx) BN_mod_mul_montgomery(\
|
||||
(r),(a),&((mont)->RR),(mont),(ctx))
|
||||
int BN_from_montgomery(BIGNUM *r,const BIGNUM *a,
|
||||
BN_MONT_CTX *mont, BN_CTX *ctx);
|
||||
void BN_MONT_CTX_free(BN_MONT_CTX *mont);
|
||||
int BN_MONT_CTX_set(BN_MONT_CTX *mont,const BIGNUM *mod,BN_CTX *ctx);
|
||||
BN_MONT_CTX *BN_MONT_CTX_copy(BN_MONT_CTX *to,BN_MONT_CTX *from);
|
||||
BN_MONT_CTX *BN_MONT_CTX_set_locked(BN_MONT_CTX **pmont, int lock,
|
||||
const BIGNUM *mod, BN_CTX *ctx);
|
||||
|
||||
/* BN_BLINDING flags */
|
||||
#define BN_BLINDING_NO_UPDATE 0x00000001
|
||||
#define BN_BLINDING_NO_RECREATE 0x00000002
|
||||
|
||||
BN_BLINDING *BN_BLINDING_new(const BIGNUM *A, const BIGNUM *Ai, BIGNUM *mod);
|
||||
void BN_BLINDING_free(BN_BLINDING *b);
|
||||
int BN_BLINDING_update(BN_BLINDING *b,BN_CTX *ctx);
|
||||
int BN_BLINDING_convert(BIGNUM *n, BN_BLINDING *b, BN_CTX *ctx);
|
||||
int BN_BLINDING_invert(BIGNUM *n, BN_BLINDING *b, BN_CTX *ctx);
|
||||
int BN_BLINDING_convert_ex(BIGNUM *n, BIGNUM *r, BN_BLINDING *b, BN_CTX *);
|
||||
int BN_BLINDING_invert_ex(BIGNUM *n, const BIGNUM *r, BN_BLINDING *b, BN_CTX *);
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
unsigned long BN_BLINDING_get_thread_id(const BN_BLINDING *);
|
||||
void BN_BLINDING_set_thread_id(BN_BLINDING *, unsigned long);
|
||||
#endif
|
||||
CRYPTO_THREADID *BN_BLINDING_thread_id(BN_BLINDING *);
|
||||
unsigned long BN_BLINDING_get_flags(const BN_BLINDING *);
|
||||
void BN_BLINDING_set_flags(BN_BLINDING *, unsigned long);
|
||||
BN_BLINDING *BN_BLINDING_create_param(BN_BLINDING *b,
|
||||
const BIGNUM *e, BIGNUM *m, BN_CTX *ctx,
|
||||
int (*bn_mod_exp)(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
const BIGNUM *m, BN_CTX *ctx, BN_MONT_CTX *m_ctx),
|
||||
BN_MONT_CTX *m_ctx);
|
||||
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
void BN_set_params(int mul,int high,int low,int mont);
|
||||
int BN_get_params(int which); /* 0, mul, 1 high, 2 low, 3 mont */
|
||||
#endif
|
||||
|
||||
void BN_RECP_CTX_init(BN_RECP_CTX *recp);
|
||||
BN_RECP_CTX *BN_RECP_CTX_new(void);
|
||||
void BN_RECP_CTX_free(BN_RECP_CTX *recp);
|
||||
int BN_RECP_CTX_set(BN_RECP_CTX *recp,const BIGNUM *rdiv,BN_CTX *ctx);
|
||||
int BN_mod_mul_reciprocal(BIGNUM *r, const BIGNUM *x, const BIGNUM *y,
|
||||
BN_RECP_CTX *recp,BN_CTX *ctx);
|
||||
int BN_mod_exp_recp(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
const BIGNUM *m, BN_CTX *ctx);
|
||||
int BN_div_recp(BIGNUM *dv, BIGNUM *rem, const BIGNUM *m,
|
||||
BN_RECP_CTX *recp, BN_CTX *ctx);
|
||||
|
||||
#ifndef OPENSSL_NO_EC2M
|
||||
|
||||
/* Functions for arithmetic over binary polynomials represented by BIGNUMs.
|
||||
*
|
||||
* The BIGNUM::neg property of BIGNUMs representing binary polynomials is
|
||||
* ignored.
|
||||
*
|
||||
* Note that input arguments are not const so that their bit arrays can
|
||||
* be expanded to the appropriate size if needed.
|
||||
*/
|
||||
|
||||
int BN_GF2m_add(BIGNUM *r, const BIGNUM *a, const BIGNUM *b); /*r = a + b*/
|
||||
#define BN_GF2m_sub(r, a, b) BN_GF2m_add(r, a, b)
|
||||
int BN_GF2m_mod(BIGNUM *r, const BIGNUM *a, const BIGNUM *p); /*r=a mod p*/
|
||||
int BN_GF2m_mod_mul(BIGNUM *r, const BIGNUM *a, const BIGNUM *b,
|
||||
const BIGNUM *p, BN_CTX *ctx); /* r = (a * b) mod p */
|
||||
int BN_GF2m_mod_sqr(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
BN_CTX *ctx); /* r = (a * a) mod p */
|
||||
int BN_GF2m_mod_inv(BIGNUM *r, const BIGNUM *b, const BIGNUM *p,
|
||||
BN_CTX *ctx); /* r = (1 / b) mod p */
|
||||
int BN_GF2m_mod_div(BIGNUM *r, const BIGNUM *a, const BIGNUM *b,
|
||||
const BIGNUM *p, BN_CTX *ctx); /* r = (a / b) mod p */
|
||||
int BN_GF2m_mod_exp(BIGNUM *r, const BIGNUM *a, const BIGNUM *b,
|
||||
const BIGNUM *p, BN_CTX *ctx); /* r = (a ^ b) mod p */
|
||||
int BN_GF2m_mod_sqrt(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
BN_CTX *ctx); /* r = sqrt(a) mod p */
|
||||
int BN_GF2m_mod_solve_quad(BIGNUM *r, const BIGNUM *a, const BIGNUM *p,
|
||||
BN_CTX *ctx); /* r^2 + r = a mod p */
|
||||
#define BN_GF2m_cmp(a, b) BN_ucmp((a), (b))
|
||||
/* Some functions allow for representation of the irreducible polynomials
|
||||
* as an unsigned int[], say p. The irreducible f(t) is then of the form:
|
||||
* t^p[0] + t^p[1] + ... + t^p[k]
|
||||
* where m = p[0] > p[1] > ... > p[k] = 0.
|
||||
*/
|
||||
int BN_GF2m_mod_arr(BIGNUM *r, const BIGNUM *a, const int p[]);
|
||||
/* r = a mod p */
|
||||
int BN_GF2m_mod_mul_arr(BIGNUM *r, const BIGNUM *a, const BIGNUM *b,
|
||||
const int p[], BN_CTX *ctx); /* r = (a * b) mod p */
|
||||
int BN_GF2m_mod_sqr_arr(BIGNUM *r, const BIGNUM *a, const int p[],
|
||||
BN_CTX *ctx); /* r = (a * a) mod p */
|
||||
int BN_GF2m_mod_inv_arr(BIGNUM *r, const BIGNUM *b, const int p[],
|
||||
BN_CTX *ctx); /* r = (1 / b) mod p */
|
||||
int BN_GF2m_mod_div_arr(BIGNUM *r, const BIGNUM *a, const BIGNUM *b,
|
||||
const int p[], BN_CTX *ctx); /* r = (a / b) mod p */
|
||||
int BN_GF2m_mod_exp_arr(BIGNUM *r, const BIGNUM *a, const BIGNUM *b,
|
||||
const int p[], BN_CTX *ctx); /* r = (a ^ b) mod p */
|
||||
int BN_GF2m_mod_sqrt_arr(BIGNUM *r, const BIGNUM *a,
|
||||
const int p[], BN_CTX *ctx); /* r = sqrt(a) mod p */
|
||||
int BN_GF2m_mod_solve_quad_arr(BIGNUM *r, const BIGNUM *a,
|
||||
const int p[], BN_CTX *ctx); /* r^2 + r = a mod p */
|
||||
int BN_GF2m_poly2arr(const BIGNUM *a, int p[], int max);
|
||||
int BN_GF2m_arr2poly(const int p[], BIGNUM *a);
|
||||
|
||||
#endif
|
||||
|
||||
/* faster mod functions for the 'NIST primes'
|
||||
* 0 <= a < p^2 */
|
||||
int BN_nist_mod_192(BIGNUM *r, const BIGNUM *a, const BIGNUM *p, BN_CTX *ctx);
|
||||
int BN_nist_mod_224(BIGNUM *r, const BIGNUM *a, const BIGNUM *p, BN_CTX *ctx);
|
||||
int BN_nist_mod_256(BIGNUM *r, const BIGNUM *a, const BIGNUM *p, BN_CTX *ctx);
|
||||
int BN_nist_mod_384(BIGNUM *r, const BIGNUM *a, const BIGNUM *p, BN_CTX *ctx);
|
||||
int BN_nist_mod_521(BIGNUM *r, const BIGNUM *a, const BIGNUM *p, BN_CTX *ctx);
|
||||
|
||||
const BIGNUM *BN_get0_nist_prime_192(void);
|
||||
const BIGNUM *BN_get0_nist_prime_224(void);
|
||||
const BIGNUM *BN_get0_nist_prime_256(void);
|
||||
const BIGNUM *BN_get0_nist_prime_384(void);
|
||||
const BIGNUM *BN_get0_nist_prime_521(void);
|
||||
|
||||
/* library internal functions */
|
||||
|
||||
#define bn_expand(a,bits) ((((((bits+BN_BITS2-1))/BN_BITS2)) <= (a)->dmax)?\
|
||||
(a):bn_expand2((a),(bits+BN_BITS2-1)/BN_BITS2))
|
||||
#define bn_wexpand(a,words) (((words) <= (a)->dmax)?(a):bn_expand2((a),(words)))
|
||||
BIGNUM *bn_expand2(BIGNUM *a, int words);
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
BIGNUM *bn_dup_expand(const BIGNUM *a, int words); /* unused */
|
||||
#endif
|
||||
|
||||
/* Bignum consistency macros
|
||||
* There is one "API" macro, bn_fix_top(), for stripping leading zeroes from
|
||||
* bignum data after direct manipulations on the data. There is also an
|
||||
* "internal" macro, bn_check_top(), for verifying that there are no leading
|
||||
* zeroes. Unfortunately, some auditing is required due to the fact that
|
||||
* bn_fix_top() has become an overabused duct-tape because bignum data is
|
||||
* occasionally passed around in an inconsistent state. So the following
|
||||
* changes have been made to sort this out;
|
||||
* - bn_fix_top()s implementation has been moved to bn_correct_top()
|
||||
* - if BN_DEBUG isn't defined, bn_fix_top() maps to bn_correct_top(), and
|
||||
* bn_check_top() is as before.
|
||||
* - if BN_DEBUG *is* defined;
|
||||
* - bn_check_top() tries to pollute unused words even if the bignum 'top' is
|
||||
* consistent. (ed: only if BN_DEBUG_RAND is defined)
|
||||
* - bn_fix_top() maps to bn_check_top() rather than "fixing" anything.
|
||||
* The idea is to have debug builds flag up inconsistent bignums when they
|
||||
* occur. If that occurs in a bn_fix_top(), we examine the code in question; if
|
||||
* the use of bn_fix_top() was appropriate (ie. it follows directly after code
|
||||
* that manipulates the bignum) it is converted to bn_correct_top(), and if it
|
||||
* was not appropriate, we convert it permanently to bn_check_top() and track
|
||||
* down the cause of the bug. Eventually, no internal code should be using the
|
||||
* bn_fix_top() macro. External applications and libraries should try this with
|
||||
* their own code too, both in terms of building against the openssl headers
|
||||
* with BN_DEBUG defined *and* linking with a version of OpenSSL built with it
|
||||
* defined. This not only improves external code, it provides more test
|
||||
* coverage for openssl's own code.
|
||||
*/
|
||||
|
||||
#ifdef BN_DEBUG
|
||||
|
||||
/* We only need assert() when debugging */
|
||||
#include <assert.h>
|
||||
|
||||
#ifdef BN_DEBUG_RAND
|
||||
/* To avoid "make update" cvs wars due to BN_DEBUG, use some tricks */
|
||||
#ifndef RAND_pseudo_bytes
|
||||
int RAND_pseudo_bytes(unsigned char *buf,int num);
|
||||
#define BN_DEBUG_TRIX
|
||||
#endif
|
||||
#define bn_pollute(a) \
|
||||
do { \
|
||||
const BIGNUM *_bnum1 = (a); \
|
||||
if(_bnum1->top < _bnum1->dmax) { \
|
||||
unsigned char _tmp_char; \
|
||||
/* We cast away const without the compiler knowing, any \
|
||||
* *genuinely* constant variables that aren't mutable \
|
||||
* wouldn't be constructed with top!=dmax. */ \
|
||||
BN_ULONG *_not_const; \
|
||||
memcpy(&_not_const, &_bnum1->d, sizeof(BN_ULONG*)); \
|
||||
RAND_pseudo_bytes(&_tmp_char, 1); \
|
||||
memset((unsigned char *)(_not_const + _bnum1->top), _tmp_char, \
|
||||
(_bnum1->dmax - _bnum1->top) * sizeof(BN_ULONG)); \
|
||||
} \
|
||||
} while(0)
|
||||
#ifdef BN_DEBUG_TRIX
|
||||
#undef RAND_pseudo_bytes
|
||||
#endif
|
||||
#else
|
||||
#define bn_pollute(a)
|
||||
#endif
|
||||
#define bn_check_top(a) \
|
||||
do { \
|
||||
const BIGNUM *_bnum2 = (a); \
|
||||
if (_bnum2 != NULL) { \
|
||||
assert((_bnum2->top == 0) || \
|
||||
(_bnum2->d[_bnum2->top - 1] != 0)); \
|
||||
bn_pollute(_bnum2); \
|
||||
} \
|
||||
} while(0)
|
||||
|
||||
#define bn_fix_top(a) bn_check_top(a)
|
||||
|
||||
#define bn_check_size(bn, bits) bn_wcheck_size(bn, ((bits+BN_BITS2-1))/BN_BITS2)
|
||||
#define bn_wcheck_size(bn, words) \
|
||||
do { \
|
||||
const BIGNUM *_bnum2 = (bn); \
|
||||
assert(words <= (_bnum2)->dmax && words >= (_bnum2)->top); \
|
||||
} while(0)
|
||||
|
||||
#else /* !BN_DEBUG */
|
||||
|
||||
#define bn_pollute(a)
|
||||
#define bn_check_top(a)
|
||||
#define bn_fix_top(a) bn_correct_top(a)
|
||||
#define bn_check_size(bn, bits)
|
||||
#define bn_wcheck_size(bn, words)
|
||||
|
||||
#endif
|
||||
|
||||
#define bn_correct_top(a) \
|
||||
{ \
|
||||
BN_ULONG *ftl; \
|
||||
int tmp_top = (a)->top; \
|
||||
if (tmp_top > 0) \
|
||||
{ \
|
||||
for (ftl= &((a)->d[tmp_top-1]); tmp_top > 0; tmp_top--) \
|
||||
if (*(ftl--)) break; \
|
||||
(a)->top = tmp_top; \
|
||||
} \
|
||||
bn_pollute(a); \
|
||||
}
|
||||
|
||||
BN_ULONG bn_mul_add_words(BN_ULONG *rp, const BN_ULONG *ap, int num, BN_ULONG w);
|
||||
BN_ULONG bn_mul_words(BN_ULONG *rp, const BN_ULONG *ap, int num, BN_ULONG w);
|
||||
void bn_sqr_words(BN_ULONG *rp, const BN_ULONG *ap, int num);
|
||||
BN_ULONG bn_div_words(BN_ULONG h, BN_ULONG l, BN_ULONG d);
|
||||
BN_ULONG bn_add_words(BN_ULONG *rp, const BN_ULONG *ap, const BN_ULONG *bp,int num);
|
||||
BN_ULONG bn_sub_words(BN_ULONG *rp, const BN_ULONG *ap, const BN_ULONG *bp,int num);
|
||||
|
||||
/* Primes from RFC 2409 */
|
||||
BIGNUM *get_rfc2409_prime_768(BIGNUM *bn);
|
||||
BIGNUM *get_rfc2409_prime_1024(BIGNUM *bn);
|
||||
|
||||
/* Primes from RFC 3526 */
|
||||
BIGNUM *get_rfc3526_prime_1536(BIGNUM *bn);
|
||||
BIGNUM *get_rfc3526_prime_2048(BIGNUM *bn);
|
||||
BIGNUM *get_rfc3526_prime_3072(BIGNUM *bn);
|
||||
BIGNUM *get_rfc3526_prime_4096(BIGNUM *bn);
|
||||
BIGNUM *get_rfc3526_prime_6144(BIGNUM *bn);
|
||||
BIGNUM *get_rfc3526_prime_8192(BIGNUM *bn);
|
||||
|
||||
int BN_bntest_rand(BIGNUM *rnd, int bits, int top,int bottom);
|
||||
|
||||
/* BEGIN ERROR CODES */
|
||||
/* The following lines are auto generated by the script mkerr.pl. Any changes
|
||||
* made after this point may be overwritten when the script is next run.
|
||||
*/
|
||||
void ERR_load_BN_strings(void);
|
||||
|
||||
/* Error codes for the BN functions. */
|
||||
|
||||
/* Function codes. */
|
||||
#define BN_F_BNRAND 127
|
||||
#define BN_F_BN_BLINDING_CONVERT_EX 100
|
||||
#define BN_F_BN_BLINDING_CREATE_PARAM 128
|
||||
#define BN_F_BN_BLINDING_INVERT_EX 101
|
||||
#define BN_F_BN_BLINDING_NEW 102
|
||||
#define BN_F_BN_BLINDING_UPDATE 103
|
||||
#define BN_F_BN_BN2DEC 104
|
||||
#define BN_F_BN_BN2HEX 105
|
||||
#define BN_F_BN_CTX_GET 116
|
||||
#define BN_F_BN_CTX_NEW 106
|
||||
#define BN_F_BN_CTX_START 129
|
||||
#define BN_F_BN_DIV 107
|
||||
#define BN_F_BN_DIV_NO_BRANCH 138
|
||||
#define BN_F_BN_DIV_RECP 130
|
||||
#define BN_F_BN_EXP 123
|
||||
#define BN_F_BN_EXPAND2 108
|
||||
#define BN_F_BN_EXPAND_INTERNAL 120
|
||||
#define BN_F_BN_GF2M_MOD 131
|
||||
#define BN_F_BN_GF2M_MOD_EXP 132
|
||||
#define BN_F_BN_GF2M_MOD_MUL 133
|
||||
#define BN_F_BN_GF2M_MOD_SOLVE_QUAD 134
|
||||
#define BN_F_BN_GF2M_MOD_SOLVE_QUAD_ARR 135
|
||||
#define BN_F_BN_GF2M_MOD_SQR 136
|
||||
#define BN_F_BN_GF2M_MOD_SQRT 137
|
||||
#define BN_F_BN_MOD_EXP2_MONT 118
|
||||
#define BN_F_BN_MOD_EXP_MONT 109
|
||||
#define BN_F_BN_MOD_EXP_MONT_CONSTTIME 124
|
||||
#define BN_F_BN_MOD_EXP_MONT_WORD 117
|
||||
#define BN_F_BN_MOD_EXP_RECP 125
|
||||
#define BN_F_BN_MOD_EXP_SIMPLE 126
|
||||
#define BN_F_BN_MOD_INVERSE 110
|
||||
#define BN_F_BN_MOD_INVERSE_NO_BRANCH 139
|
||||
#define BN_F_BN_MOD_LSHIFT_QUICK 119
|
||||
#define BN_F_BN_MOD_MUL_RECIPROCAL 111
|
||||
#define BN_F_BN_MOD_SQRT 121
|
||||
#define BN_F_BN_MPI2BN 112
|
||||
#define BN_F_BN_NEW 113
|
||||
#define BN_F_BN_RAND 114
|
||||
#define BN_F_BN_RAND_RANGE 122
|
||||
#define BN_F_BN_USUB 115
|
||||
|
||||
/* Reason codes. */
|
||||
#define BN_R_ARG2_LT_ARG3 100
|
||||
#define BN_R_BAD_RECIPROCAL 101
|
||||
#define BN_R_BIGNUM_TOO_LONG 114
|
||||
#define BN_R_CALLED_WITH_EVEN_MODULUS 102
|
||||
#define BN_R_DIV_BY_ZERO 103
|
||||
#define BN_R_ENCODING_ERROR 104
|
||||
#define BN_R_EXPAND_ON_STATIC_BIGNUM_DATA 105
|
||||
#define BN_R_INPUT_NOT_REDUCED 110
|
||||
#define BN_R_INVALID_LENGTH 106
|
||||
#define BN_R_INVALID_RANGE 115
|
||||
#define BN_R_NOT_A_SQUARE 111
|
||||
#define BN_R_NOT_INITIALIZED 107
|
||||
#define BN_R_NO_INVERSE 108
|
||||
#define BN_R_NO_SOLUTION 116
|
||||
#define BN_R_P_IS_NOT_PRIME 112
|
||||
#define BN_R_TOO_MANY_ITERATIONS 113
|
||||
#define BN_R_TOO_MANY_TEMPORARY_VARIABLES 109
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
#endif
|
||||
@@ -0,0 +1,611 @@
|
||||
/* crypto/crypto.h */
|
||||
/* ====================================================================
|
||||
* Copyright (c) 1998-2006 The OpenSSL Project. All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
*
|
||||
* 1. Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
*
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in
|
||||
* the documentation and/or other materials provided with the
|
||||
* distribution.
|
||||
*
|
||||
* 3. All advertising materials mentioning features or use of this
|
||||
* software must display the following acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit. (http://www.openssl.org/)"
|
||||
*
|
||||
* 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
|
||||
* endorse or promote products derived from this software without
|
||||
* prior written permission. For written permission, please contact
|
||||
* openssl-core@openssl.org.
|
||||
*
|
||||
* 5. Products derived from this software may not be called "OpenSSL"
|
||||
* nor may "OpenSSL" appear in their names without prior written
|
||||
* permission of the OpenSSL Project.
|
||||
*
|
||||
* 6. Redistributions of any form whatsoever must retain the following
|
||||
* acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit (http://www.openssl.org/)"
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
|
||||
* EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE OpenSSL PROJECT OR
|
||||
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
||||
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
||||
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
||||
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
||||
* OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
* ====================================================================
|
||||
*
|
||||
* This product includes cryptographic software written by Eric Young
|
||||
* (eay@cryptsoft.com). This product includes software written by Tim
|
||||
* Hudson (tjh@cryptsoft.com).
|
||||
*
|
||||
*/
|
||||
/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
|
||||
* All rights reserved.
|
||||
*
|
||||
* This package is an SSL implementation written
|
||||
* by Eric Young (eay@cryptsoft.com).
|
||||
* The implementation was written so as to conform with Netscapes SSL.
|
||||
*
|
||||
* This library is free for commercial and non-commercial use as long as
|
||||
* the following conditions are aheared to. The following conditions
|
||||
* apply to all code found in this distribution, be it the RC4, RSA,
|
||||
* lhash, DES, etc., code; not just the SSL code. The SSL documentation
|
||||
* included with this distribution is covered by the same copyright terms
|
||||
* except that the holder is Tim Hudson (tjh@cryptsoft.com).
|
||||
*
|
||||
* Copyright remains Eric Young's, and as such any Copyright notices in
|
||||
* the code are not to be removed.
|
||||
* If this package is used in a product, Eric Young should be given attribution
|
||||
* as the author of the parts of the library used.
|
||||
* This can be in the form of a textual message at program startup or
|
||||
* in documentation (online or textual) provided with the package.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* 1. Redistributions of source code must retain the copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* 3. All advertising materials mentioning features or use of this software
|
||||
* must display the following acknowledgement:
|
||||
* "This product includes cryptographic software written by
|
||||
* Eric Young (eay@cryptsoft.com)"
|
||||
* The word 'cryptographic' can be left out if the rouines from the library
|
||||
* being used are not cryptographic related :-).
|
||||
* 4. If you include any Windows specific code (or a derivative thereof) from
|
||||
* the apps directory (application code) you must include an acknowledgement:
|
||||
* "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
|
||||
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
||||
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
||||
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
||||
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
||||
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||
* SUCH DAMAGE.
|
||||
*
|
||||
* The licence and distribution terms for any publically available version or
|
||||
* derivative of this code cannot be changed. i.e. this code cannot simply be
|
||||
* copied and put under another distribution licence
|
||||
* [including the GNU Public Licence.]
|
||||
*/
|
||||
/* ====================================================================
|
||||
* Copyright 2002 Sun Microsystems, Inc. ALL RIGHTS RESERVED.
|
||||
* ECDH support in OpenSSL originally developed by
|
||||
* SUN MICROSYSTEMS, INC., and contributed to the OpenSSL project.
|
||||
*/
|
||||
|
||||
#ifndef HEADER_CRYPTO_H
|
||||
#define HEADER_CRYPTO_H
|
||||
|
||||
#include <stdlib.h>
|
||||
|
||||
#include <openssl/e_os2.h>
|
||||
|
||||
#ifndef OPENSSL_NO_FP_API
|
||||
#include <stdio.h>
|
||||
#endif
|
||||
|
||||
#include <openssl/stack.h>
|
||||
#include <openssl/safestack.h>
|
||||
#include <openssl/opensslv.h>
|
||||
#include <openssl/ossl_typ.h>
|
||||
|
||||
#ifdef CHARSET_EBCDIC
|
||||
#include <openssl/ebcdic.h>
|
||||
#endif
|
||||
|
||||
/* Resolve problems on some operating systems with symbol names that clash
|
||||
one way or another */
|
||||
#include <openssl/symhacks.h>
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* Backward compatibility to SSLeay */
|
||||
/* This is more to be used to check the correct DLL is being used
|
||||
* in the MS world. */
|
||||
#define SSLEAY_VERSION_NUMBER OPENSSL_VERSION_NUMBER
|
||||
#define SSLEAY_VERSION 0
|
||||
/* #define SSLEAY_OPTIONS 1 no longer supported */
|
||||
#define SSLEAY_CFLAGS 2
|
||||
#define SSLEAY_BUILT_ON 3
|
||||
#define SSLEAY_PLATFORM 4
|
||||
#define SSLEAY_DIR 5
|
||||
|
||||
/* Already declared in ossl_typ.h */
|
||||
#if 0
|
||||
typedef struct crypto_ex_data_st CRYPTO_EX_DATA;
|
||||
/* Called when a new object is created */
|
||||
typedef int CRYPTO_EX_new(void *parent, void *ptr, CRYPTO_EX_DATA *ad,
|
||||
int idx, long argl, void *argp);
|
||||
/* Called when an object is free()ed */
|
||||
typedef void CRYPTO_EX_free(void *parent, void *ptr, CRYPTO_EX_DATA *ad,
|
||||
int idx, long argl, void *argp);
|
||||
/* Called when we need to dup an object */
|
||||
typedef int CRYPTO_EX_dup(CRYPTO_EX_DATA *to, CRYPTO_EX_DATA *from, void *from_d,
|
||||
int idx, long argl, void *argp);
|
||||
#endif
|
||||
|
||||
/* A generic structure to pass assorted data in a expandable way */
|
||||
typedef struct openssl_item_st
|
||||
{
|
||||
int code;
|
||||
void *value; /* Not used for flag attributes */
|
||||
size_t value_size; /* Max size of value for output, length for input */
|
||||
size_t *value_length; /* Returned length of value for output */
|
||||
} OPENSSL_ITEM;
|
||||
|
||||
|
||||
/* When changing the CRYPTO_LOCK_* list, be sure to maintin the text lock
|
||||
* names in cryptlib.c
|
||||
*/
|
||||
|
||||
#define CRYPTO_LOCK_ERR 1
|
||||
#define CRYPTO_LOCK_EX_DATA 2
|
||||
#define CRYPTO_LOCK_X509 3
|
||||
#define CRYPTO_LOCK_X509_INFO 4
|
||||
#define CRYPTO_LOCK_X509_PKEY 5
|
||||
#define CRYPTO_LOCK_X509_CRL 6
|
||||
#define CRYPTO_LOCK_X509_REQ 7
|
||||
#define CRYPTO_LOCK_DSA 8
|
||||
#define CRYPTO_LOCK_RSA 9
|
||||
#define CRYPTO_LOCK_EVP_PKEY 10
|
||||
#define CRYPTO_LOCK_X509_STORE 11
|
||||
#define CRYPTO_LOCK_SSL_CTX 12
|
||||
#define CRYPTO_LOCK_SSL_CERT 13
|
||||
#define CRYPTO_LOCK_SSL_SESSION 14
|
||||
#define CRYPTO_LOCK_SSL_SESS_CERT 15
|
||||
#define CRYPTO_LOCK_SSL 16
|
||||
#define CRYPTO_LOCK_SSL_METHOD 17
|
||||
#define CRYPTO_LOCK_RAND 18
|
||||
#define CRYPTO_LOCK_RAND2 19
|
||||
#define CRYPTO_LOCK_MALLOC 20
|
||||
#define CRYPTO_LOCK_BIO 21
|
||||
#define CRYPTO_LOCK_GETHOSTBYNAME 22
|
||||
#define CRYPTO_LOCK_GETSERVBYNAME 23
|
||||
#define CRYPTO_LOCK_READDIR 24
|
||||
#define CRYPTO_LOCK_RSA_BLINDING 25
|
||||
#define CRYPTO_LOCK_DH 26
|
||||
#define CRYPTO_LOCK_MALLOC2 27
|
||||
#define CRYPTO_LOCK_DSO 28
|
||||
#define CRYPTO_LOCK_DYNLOCK 29
|
||||
#define CRYPTO_LOCK_ENGINE 30
|
||||
#define CRYPTO_LOCK_UI 31
|
||||
#define CRYPTO_LOCK_ECDSA 32
|
||||
#define CRYPTO_LOCK_EC 33
|
||||
#define CRYPTO_LOCK_ECDH 34
|
||||
#define CRYPTO_LOCK_BN 35
|
||||
#define CRYPTO_LOCK_EC_PRE_COMP 36
|
||||
#define CRYPTO_LOCK_STORE 37
|
||||
#define CRYPTO_LOCK_COMP 38
|
||||
#define CRYPTO_LOCK_FIPS 39
|
||||
#define CRYPTO_LOCK_FIPS2 40
|
||||
#define CRYPTO_NUM_LOCKS 41
|
||||
|
||||
#define CRYPTO_LOCK 1
|
||||
#define CRYPTO_UNLOCK 2
|
||||
#define CRYPTO_READ 4
|
||||
#define CRYPTO_WRITE 8
|
||||
|
||||
#ifndef OPENSSL_NO_LOCKING
|
||||
#ifndef CRYPTO_w_lock
|
||||
#define CRYPTO_w_lock(type) \
|
||||
CRYPTO_lock(CRYPTO_LOCK|CRYPTO_WRITE,type,__FILE__,__LINE__)
|
||||
#define CRYPTO_w_unlock(type) \
|
||||
CRYPTO_lock(CRYPTO_UNLOCK|CRYPTO_WRITE,type,__FILE__,__LINE__)
|
||||
#define CRYPTO_r_lock(type) \
|
||||
CRYPTO_lock(CRYPTO_LOCK|CRYPTO_READ,type,__FILE__,__LINE__)
|
||||
#define CRYPTO_r_unlock(type) \
|
||||
CRYPTO_lock(CRYPTO_UNLOCK|CRYPTO_READ,type,__FILE__,__LINE__)
|
||||
#define CRYPTO_add(addr,amount,type) \
|
||||
CRYPTO_add_lock(addr,amount,type,__FILE__,__LINE__)
|
||||
#endif
|
||||
#else
|
||||
#define CRYPTO_w_lock(a)
|
||||
#define CRYPTO_w_unlock(a)
|
||||
#define CRYPTO_r_lock(a)
|
||||
#define CRYPTO_r_unlock(a)
|
||||
#define CRYPTO_add(a,b,c) ((*(a))+=(b))
|
||||
#endif
|
||||
|
||||
/* Some applications as well as some parts of OpenSSL need to allocate
|
||||
and deallocate locks in a dynamic fashion. The following typedef
|
||||
makes this possible in a type-safe manner. */
|
||||
/* struct CRYPTO_dynlock_value has to be defined by the application. */
|
||||
typedef struct
|
||||
{
|
||||
int references;
|
||||
struct CRYPTO_dynlock_value *data;
|
||||
} CRYPTO_dynlock;
|
||||
|
||||
|
||||
/* The following can be used to detect memory leaks in the SSLeay library.
|
||||
* It used, it turns on malloc checking */
|
||||
|
||||
#define CRYPTO_MEM_CHECK_OFF 0x0 /* an enume */
|
||||
#define CRYPTO_MEM_CHECK_ON 0x1 /* a bit */
|
||||
#define CRYPTO_MEM_CHECK_ENABLE 0x2 /* a bit */
|
||||
#define CRYPTO_MEM_CHECK_DISABLE 0x3 /* an enume */
|
||||
|
||||
/* The following are bit values to turn on or off options connected to the
|
||||
* malloc checking functionality */
|
||||
|
||||
/* Adds time to the memory checking information */
|
||||
#define V_CRYPTO_MDEBUG_TIME 0x1 /* a bit */
|
||||
/* Adds thread number to the memory checking information */
|
||||
#define V_CRYPTO_MDEBUG_THREAD 0x2 /* a bit */
|
||||
|
||||
#define V_CRYPTO_MDEBUG_ALL (V_CRYPTO_MDEBUG_TIME | V_CRYPTO_MDEBUG_THREAD)
|
||||
|
||||
|
||||
/* predec of the BIO type */
|
||||
typedef struct bio_st BIO_dummy;
|
||||
|
||||
struct crypto_ex_data_st
|
||||
{
|
||||
STACK_OF(void) *sk;
|
||||
int dummy; /* gcc is screwing up this data structure :-( */
|
||||
};
|
||||
DECLARE_STACK_OF(void)
|
||||
|
||||
/* This stuff is basically class callback functions
|
||||
* The current classes are SSL_CTX, SSL, SSL_SESSION, and a few more */
|
||||
|
||||
typedef struct crypto_ex_data_func_st
|
||||
{
|
||||
long argl; /* Arbitary long */
|
||||
void *argp; /* Arbitary void * */
|
||||
CRYPTO_EX_new *new_func;
|
||||
CRYPTO_EX_free *free_func;
|
||||
CRYPTO_EX_dup *dup_func;
|
||||
} CRYPTO_EX_DATA_FUNCS;
|
||||
|
||||
DECLARE_STACK_OF(CRYPTO_EX_DATA_FUNCS)
|
||||
|
||||
/* Per class, we have a STACK of CRYPTO_EX_DATA_FUNCS for each CRYPTO_EX_DATA
|
||||
* entry.
|
||||
*/
|
||||
|
||||
#define CRYPTO_EX_INDEX_BIO 0
|
||||
#define CRYPTO_EX_INDEX_SSL 1
|
||||
#define CRYPTO_EX_INDEX_SSL_CTX 2
|
||||
#define CRYPTO_EX_INDEX_SSL_SESSION 3
|
||||
#define CRYPTO_EX_INDEX_X509_STORE 4
|
||||
#define CRYPTO_EX_INDEX_X509_STORE_CTX 5
|
||||
#define CRYPTO_EX_INDEX_RSA 6
|
||||
#define CRYPTO_EX_INDEX_DSA 7
|
||||
#define CRYPTO_EX_INDEX_DH 8
|
||||
#define CRYPTO_EX_INDEX_ENGINE 9
|
||||
#define CRYPTO_EX_INDEX_X509 10
|
||||
#define CRYPTO_EX_INDEX_UI 11
|
||||
#define CRYPTO_EX_INDEX_ECDSA 12
|
||||
#define CRYPTO_EX_INDEX_ECDH 13
|
||||
#define CRYPTO_EX_INDEX_COMP 14
|
||||
#define CRYPTO_EX_INDEX_STORE 15
|
||||
|
||||
/* Dynamically assigned indexes start from this value (don't use directly, use
|
||||
* via CRYPTO_ex_data_new_class). */
|
||||
#define CRYPTO_EX_INDEX_USER 100
|
||||
|
||||
|
||||
/* This is the default callbacks, but we can have others as well:
|
||||
* this is needed in Win32 where the application malloc and the
|
||||
* library malloc may not be the same.
|
||||
*/
|
||||
#define CRYPTO_malloc_init() CRYPTO_set_mem_functions(\
|
||||
malloc, realloc, free)
|
||||
|
||||
#if defined CRYPTO_MDEBUG_ALL || defined CRYPTO_MDEBUG_TIME || defined CRYPTO_MDEBUG_THREAD
|
||||
# ifndef CRYPTO_MDEBUG /* avoid duplicate #define */
|
||||
# define CRYPTO_MDEBUG
|
||||
# endif
|
||||
#endif
|
||||
|
||||
/* Set standard debugging functions (not done by default
|
||||
* unless CRYPTO_MDEBUG is defined) */
|
||||
#define CRYPTO_malloc_debug_init() do {\
|
||||
CRYPTO_set_mem_debug_functions(\
|
||||
CRYPTO_dbg_malloc,\
|
||||
CRYPTO_dbg_realloc,\
|
||||
CRYPTO_dbg_free,\
|
||||
CRYPTO_dbg_set_options,\
|
||||
CRYPTO_dbg_get_options);\
|
||||
} while(0)
|
||||
|
||||
int CRYPTO_mem_ctrl(int mode);
|
||||
int CRYPTO_is_mem_check_on(void);
|
||||
|
||||
/* for applications */
|
||||
#define MemCheck_start() CRYPTO_mem_ctrl(CRYPTO_MEM_CHECK_ON)
|
||||
#define MemCheck_stop() CRYPTO_mem_ctrl(CRYPTO_MEM_CHECK_OFF)
|
||||
|
||||
/* for library-internal use */
|
||||
#define MemCheck_on() CRYPTO_mem_ctrl(CRYPTO_MEM_CHECK_ENABLE)
|
||||
#define MemCheck_off() CRYPTO_mem_ctrl(CRYPTO_MEM_CHECK_DISABLE)
|
||||
#define is_MemCheck_on() CRYPTO_is_mem_check_on()
|
||||
|
||||
#define OPENSSL_malloc(num) CRYPTO_malloc((int)num,__FILE__,__LINE__)
|
||||
#define OPENSSL_strdup(str) CRYPTO_strdup((str),__FILE__,__LINE__)
|
||||
#define OPENSSL_realloc(addr,num) \
|
||||
CRYPTO_realloc((char *)addr,(int)num,__FILE__,__LINE__)
|
||||
#define OPENSSL_realloc_clean(addr,old_num,num) \
|
||||
CRYPTO_realloc_clean(addr,old_num,num,__FILE__,__LINE__)
|
||||
#define OPENSSL_remalloc(addr,num) \
|
||||
CRYPTO_remalloc((char **)addr,(int)num,__FILE__,__LINE__)
|
||||
#define OPENSSL_freeFunc CRYPTO_free
|
||||
#define OPENSSL_free(addr) CRYPTO_free(addr)
|
||||
|
||||
#define OPENSSL_malloc_locked(num) \
|
||||
CRYPTO_malloc_locked((int)num,__FILE__,__LINE__)
|
||||
#define OPENSSL_free_locked(addr) CRYPTO_free_locked(addr)
|
||||
|
||||
|
||||
const char *SSLeay_version(int type);
|
||||
unsigned long SSLeay(void);
|
||||
|
||||
int OPENSSL_issetugid(void);
|
||||
|
||||
/* An opaque type representing an implementation of "ex_data" support */
|
||||
typedef struct st_CRYPTO_EX_DATA_IMPL CRYPTO_EX_DATA_IMPL;
|
||||
/* Return an opaque pointer to the current "ex_data" implementation */
|
||||
const CRYPTO_EX_DATA_IMPL *CRYPTO_get_ex_data_implementation(void);
|
||||
/* Sets the "ex_data" implementation to be used (if it's not too late) */
|
||||
int CRYPTO_set_ex_data_implementation(const CRYPTO_EX_DATA_IMPL *i);
|
||||
/* Get a new "ex_data" class, and return the corresponding "class_index" */
|
||||
int CRYPTO_ex_data_new_class(void);
|
||||
/* Within a given class, get/register a new index */
|
||||
int CRYPTO_get_ex_new_index(int class_index, long argl, void *argp,
|
||||
CRYPTO_EX_new *new_func, CRYPTO_EX_dup *dup_func,
|
||||
CRYPTO_EX_free *free_func);
|
||||
/* Initialise/duplicate/free CRYPTO_EX_DATA variables corresponding to a given
|
||||
* class (invokes whatever per-class callbacks are applicable) */
|
||||
int CRYPTO_new_ex_data(int class_index, void *obj, CRYPTO_EX_DATA *ad);
|
||||
int CRYPTO_dup_ex_data(int class_index, CRYPTO_EX_DATA *to,
|
||||
CRYPTO_EX_DATA *from);
|
||||
void CRYPTO_free_ex_data(int class_index, void *obj, CRYPTO_EX_DATA *ad);
|
||||
/* Get/set data in a CRYPTO_EX_DATA variable corresponding to a particular index
|
||||
* (relative to the class type involved) */
|
||||
int CRYPTO_set_ex_data(CRYPTO_EX_DATA *ad, int idx, void *val);
|
||||
void *CRYPTO_get_ex_data(const CRYPTO_EX_DATA *ad,int idx);
|
||||
/* This function cleans up all "ex_data" state. It mustn't be called under
|
||||
* potential race-conditions. */
|
||||
void CRYPTO_cleanup_all_ex_data(void);
|
||||
|
||||
int CRYPTO_get_new_lockid(char *name);
|
||||
|
||||
int CRYPTO_num_locks(void); /* return CRYPTO_NUM_LOCKS (shared libs!) */
|
||||
void CRYPTO_lock(int mode, int type,const char *file,int line);
|
||||
void CRYPTO_set_locking_callback(void (*func)(int mode,int type,
|
||||
const char *file,int line));
|
||||
void (*CRYPTO_get_locking_callback(void))(int mode,int type,const char *file,
|
||||
int line);
|
||||
void CRYPTO_set_add_lock_callback(int (*func)(int *num,int mount,int type,
|
||||
const char *file, int line));
|
||||
int (*CRYPTO_get_add_lock_callback(void))(int *num,int mount,int type,
|
||||
const char *file,int line);
|
||||
|
||||
/* Don't use this structure directly. */
|
||||
typedef struct crypto_threadid_st
|
||||
{
|
||||
void *ptr;
|
||||
unsigned long val;
|
||||
} CRYPTO_THREADID;
|
||||
/* Only use CRYPTO_THREADID_set_[numeric|pointer]() within callbacks */
|
||||
void CRYPTO_THREADID_set_numeric(CRYPTO_THREADID *id, unsigned long val);
|
||||
void CRYPTO_THREADID_set_pointer(CRYPTO_THREADID *id, void *ptr);
|
||||
int CRYPTO_THREADID_set_callback(void (*threadid_func)(CRYPTO_THREADID *));
|
||||
void (*CRYPTO_THREADID_get_callback(void))(CRYPTO_THREADID *);
|
||||
void CRYPTO_THREADID_current(CRYPTO_THREADID *id);
|
||||
int CRYPTO_THREADID_cmp(const CRYPTO_THREADID *a, const CRYPTO_THREADID *b);
|
||||
void CRYPTO_THREADID_cpy(CRYPTO_THREADID *dest, const CRYPTO_THREADID *src);
|
||||
unsigned long CRYPTO_THREADID_hash(const CRYPTO_THREADID *id);
|
||||
#ifndef OPENSSL_NO_DEPRECATED
|
||||
void CRYPTO_set_id_callback(unsigned long (*func)(void));
|
||||
unsigned long (*CRYPTO_get_id_callback(void))(void);
|
||||
unsigned long CRYPTO_thread_id(void);
|
||||
#endif
|
||||
|
||||
const char *CRYPTO_get_lock_name(int type);
|
||||
int CRYPTO_add_lock(int *pointer,int amount,int type, const char *file,
|
||||
int line);
|
||||
|
||||
int CRYPTO_get_new_dynlockid(void);
|
||||
void CRYPTO_destroy_dynlockid(int i);
|
||||
struct CRYPTO_dynlock_value *CRYPTO_get_dynlock_value(int i);
|
||||
void CRYPTO_set_dynlock_create_callback(struct CRYPTO_dynlock_value *(*dyn_create_function)(const char *file, int line));
|
||||
void CRYPTO_set_dynlock_lock_callback(void (*dyn_lock_function)(int mode, struct CRYPTO_dynlock_value *l, const char *file, int line));
|
||||
void CRYPTO_set_dynlock_destroy_callback(void (*dyn_destroy_function)(struct CRYPTO_dynlock_value *l, const char *file, int line));
|
||||
struct CRYPTO_dynlock_value *(*CRYPTO_get_dynlock_create_callback(void))(const char *file,int line);
|
||||
void (*CRYPTO_get_dynlock_lock_callback(void))(int mode, struct CRYPTO_dynlock_value *l, const char *file,int line);
|
||||
void (*CRYPTO_get_dynlock_destroy_callback(void))(struct CRYPTO_dynlock_value *l, const char *file,int line);
|
||||
|
||||
/* CRYPTO_set_mem_functions includes CRYPTO_set_locked_mem_functions --
|
||||
* call the latter last if you need different functions */
|
||||
int CRYPTO_set_mem_functions(void *(*m)(size_t),void *(*r)(void *,size_t), void (*f)(void *));
|
||||
int CRYPTO_set_locked_mem_functions(void *(*m)(size_t), void (*free_func)(void *));
|
||||
int CRYPTO_set_mem_ex_functions(void *(*m)(size_t,const char *,int),
|
||||
void *(*r)(void *,size_t,const char *,int),
|
||||
void (*f)(void *));
|
||||
int CRYPTO_set_locked_mem_ex_functions(void *(*m)(size_t,const char *,int),
|
||||
void (*free_func)(void *));
|
||||
int CRYPTO_set_mem_debug_functions(void (*m)(void *,int,const char *,int,int),
|
||||
void (*r)(void *,void *,int,const char *,int,int),
|
||||
void (*f)(void *,int),
|
||||
void (*so)(long),
|
||||
long (*go)(void));
|
||||
void CRYPTO_get_mem_functions(void *(**m)(size_t),void *(**r)(void *, size_t), void (**f)(void *));
|
||||
void CRYPTO_get_locked_mem_functions(void *(**m)(size_t), void (**f)(void *));
|
||||
void CRYPTO_get_mem_ex_functions(void *(**m)(size_t,const char *,int),
|
||||
void *(**r)(void *, size_t,const char *,int),
|
||||
void (**f)(void *));
|
||||
void CRYPTO_get_locked_mem_ex_functions(void *(**m)(size_t,const char *,int),
|
||||
void (**f)(void *));
|
||||
void CRYPTO_get_mem_debug_functions(void (**m)(void *,int,const char *,int,int),
|
||||
void (**r)(void *,void *,int,const char *,int,int),
|
||||
void (**f)(void *,int),
|
||||
void (**so)(long),
|
||||
long (**go)(void));
|
||||
|
||||
void *CRYPTO_malloc_locked(int num, const char *file, int line);
|
||||
void CRYPTO_free_locked(void *ptr);
|
||||
void *CRYPTO_malloc(int num, const char *file, int line);
|
||||
char *CRYPTO_strdup(const char *str, const char *file, int line);
|
||||
void CRYPTO_free(void *ptr);
|
||||
void *CRYPTO_realloc(void *addr,int num, const char *file, int line);
|
||||
void *CRYPTO_realloc_clean(void *addr,int old_num,int num,const char *file,
|
||||
int line);
|
||||
void *CRYPTO_remalloc(void *addr,int num, const char *file, int line);
|
||||
|
||||
void OPENSSL_cleanse(void *ptr, size_t len);
|
||||
|
||||
void CRYPTO_set_mem_debug_options(long bits);
|
||||
long CRYPTO_get_mem_debug_options(void);
|
||||
|
||||
#define CRYPTO_push_info(info) \
|
||||
CRYPTO_push_info_(info, __FILE__, __LINE__);
|
||||
int CRYPTO_push_info_(const char *info, const char *file, int line);
|
||||
int CRYPTO_pop_info(void);
|
||||
int CRYPTO_remove_all_info(void);
|
||||
|
||||
|
||||
/* Default debugging functions (enabled by CRYPTO_malloc_debug_init() macro;
|
||||
* used as default in CRYPTO_MDEBUG compilations): */
|
||||
/* The last argument has the following significance:
|
||||
*
|
||||
* 0: called before the actual memory allocation has taken place
|
||||
* 1: called after the actual memory allocation has taken place
|
||||
*/
|
||||
void CRYPTO_dbg_malloc(void *addr,int num,const char *file,int line,int before_p);
|
||||
void CRYPTO_dbg_realloc(void *addr1,void *addr2,int num,const char *file,int line,int before_p);
|
||||
void CRYPTO_dbg_free(void *addr,int before_p);
|
||||
/* Tell the debugging code about options. By default, the following values
|
||||
* apply:
|
||||
*
|
||||
* 0: Clear all options.
|
||||
* V_CRYPTO_MDEBUG_TIME (1): Set the "Show Time" option.
|
||||
* V_CRYPTO_MDEBUG_THREAD (2): Set the "Show Thread Number" option.
|
||||
* V_CRYPTO_MDEBUG_ALL (3): 1 + 2
|
||||
*/
|
||||
void CRYPTO_dbg_set_options(long bits);
|
||||
long CRYPTO_dbg_get_options(void);
|
||||
|
||||
|
||||
#ifndef OPENSSL_NO_FP_API
|
||||
void CRYPTO_mem_leaks_fp(FILE *);
|
||||
#endif
|
||||
void CRYPTO_mem_leaks(struct bio_st *bio);
|
||||
/* unsigned long order, char *file, int line, int num_bytes, char *addr */
|
||||
typedef void *CRYPTO_MEM_LEAK_CB(unsigned long, const char *, int, int, void *);
|
||||
void CRYPTO_mem_leaks_cb(CRYPTO_MEM_LEAK_CB *cb);
|
||||
|
||||
/* die if we have to */
|
||||
void OpenSSLDie(const char *file,int line,const char *assertion);
|
||||
#define OPENSSL_assert(e) (void)((e) ? 0 : (OpenSSLDie(__FILE__, __LINE__, #e),1))
|
||||
|
||||
unsigned long *OPENSSL_ia32cap_loc(void);
|
||||
#define OPENSSL_ia32cap (*(OPENSSL_ia32cap_loc()))
|
||||
int OPENSSL_isservice(void);
|
||||
|
||||
int FIPS_mode(void);
|
||||
int FIPS_mode_set(int r);
|
||||
|
||||
void OPENSSL_init(void);
|
||||
|
||||
#define fips_md_init(alg) fips_md_init_ctx(alg, alg)
|
||||
|
||||
#ifdef OPENSSL_FIPS
|
||||
#define fips_md_init_ctx(alg, cx) \
|
||||
int alg##_Init(cx##_CTX *c) \
|
||||
{ \
|
||||
if (FIPS_mode()) OpenSSLDie(__FILE__, __LINE__, \
|
||||
"Low level API call to digest " #alg " forbidden in FIPS mode!"); \
|
||||
return private_##alg##_Init(c); \
|
||||
} \
|
||||
int private_##alg##_Init(cx##_CTX *c)
|
||||
|
||||
#define fips_cipher_abort(alg) \
|
||||
if (FIPS_mode()) OpenSSLDie(__FILE__, __LINE__, \
|
||||
"Low level API call to cipher " #alg " forbidden in FIPS mode!")
|
||||
|
||||
#else
|
||||
#define fips_md_init_ctx(alg, cx) \
|
||||
int alg##_Init(cx##_CTX *c)
|
||||
#define fips_cipher_abort(alg) while(0)
|
||||
#endif
|
||||
|
||||
/* CRYPTO_memcmp returns zero iff the |len| bytes at |a| and |b| are equal. It
|
||||
* takes an amount of time dependent on |len|, but independent of the contents
|
||||
* of |a| and |b|. Unlike memcmp, it cannot be used to put elements into a
|
||||
* defined order as the return value when a != b is undefined, other than to be
|
||||
* non-zero. */
|
||||
int CRYPTO_memcmp(const void *a, const void *b, size_t len);
|
||||
|
||||
/* BEGIN ERROR CODES */
|
||||
/* The following lines are auto generated by the script mkerr.pl. Any changes
|
||||
* made after this point may be overwritten when the script is next run.
|
||||
*/
|
||||
void ERR_load_CRYPTO_strings(void);
|
||||
|
||||
/* Error codes for the CRYPTO functions. */
|
||||
|
||||
/* Function codes. */
|
||||
#define CRYPTO_F_CRYPTO_GET_EX_NEW_INDEX 100
|
||||
#define CRYPTO_F_CRYPTO_GET_NEW_DYNLOCKID 103
|
||||
#define CRYPTO_F_CRYPTO_GET_NEW_LOCKID 101
|
||||
#define CRYPTO_F_CRYPTO_SET_EX_DATA 102
|
||||
#define CRYPTO_F_DEF_ADD_INDEX 104
|
||||
#define CRYPTO_F_DEF_GET_CLASS 105
|
||||
#define CRYPTO_F_FIPS_MODE_SET 109
|
||||
#define CRYPTO_F_INT_DUP_EX_DATA 106
|
||||
#define CRYPTO_F_INT_FREE_EX_DATA 107
|
||||
#define CRYPTO_F_INT_NEW_EX_DATA 108
|
||||
|
||||
/* Reason codes. */
|
||||
#define CRYPTO_R_FIPS_MODE_NOT_SUPPORTED 101
|
||||
#define CRYPTO_R_NO_DYNLOCK_CREATE_CALLBACK 100
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
#endif
|
||||
@@ -0,0 +1,89 @@
|
||||
#ifndef HEADER_OPENSSLV_H
|
||||
#define HEADER_OPENSSLV_H
|
||||
|
||||
/* Numeric release version identifier:
|
||||
* MNNFFPPS: major minor fix patch status
|
||||
* The status nibble has one of the values 0 for development, 1 to e for betas
|
||||
* 1 to 14, and f for release. The patch level is exactly that.
|
||||
* For example:
|
||||
* 0.9.3-dev 0x00903000
|
||||
* 0.9.3-beta1 0x00903001
|
||||
* 0.9.3-beta2-dev 0x00903002
|
||||
* 0.9.3-beta2 0x00903002 (same as ...beta2-dev)
|
||||
* 0.9.3 0x0090300f
|
||||
* 0.9.3a 0x0090301f
|
||||
* 0.9.4 0x0090400f
|
||||
* 1.2.3z 0x102031af
|
||||
*
|
||||
* For continuity reasons (because 0.9.5 is already out, and is coded
|
||||
* 0x00905100), between 0.9.5 and 0.9.6 the coding of the patch level
|
||||
* part is slightly different, by setting the highest bit. This means
|
||||
* that 0.9.5a looks like this: 0x0090581f. At 0.9.6, we can start
|
||||
* with 0x0090600S...
|
||||
*
|
||||
* (Prior to 0.9.3-dev a different scheme was used: 0.9.2b is 0x0922.)
|
||||
* (Prior to 0.9.5a beta1, a different scheme was used: MMNNFFRBB for
|
||||
* major minor fix final patch/beta)
|
||||
*/
|
||||
#define OPENSSL_VERSION_NUMBER 0x1000109fL
|
||||
#ifdef OPENSSL_FIPS
|
||||
#define OPENSSL_VERSION_TEXT "OpenSSL 1.0.1i-fips 6 Aug 2014"
|
||||
#else
|
||||
#define OPENSSL_VERSION_TEXT "OpenSSL 1.0.1i 6 Aug 2014"
|
||||
#endif
|
||||
#define OPENSSL_VERSION_PTEXT " part of " OPENSSL_VERSION_TEXT
|
||||
|
||||
|
||||
/* The macros below are to be used for shared library (.so, .dll, ...)
|
||||
* versioning. That kind of versioning works a bit differently between
|
||||
* operating systems. The most usual scheme is to set a major and a minor
|
||||
* number, and have the runtime loader check that the major number is equal
|
||||
* to what it was at application link time, while the minor number has to
|
||||
* be greater or equal to what it was at application link time. With this
|
||||
* scheme, the version number is usually part of the file name, like this:
|
||||
*
|
||||
* libcrypto.so.0.9
|
||||
*
|
||||
* Some unixen also make a softlink with the major verson number only:
|
||||
*
|
||||
* libcrypto.so.0
|
||||
*
|
||||
* On Tru64 and IRIX 6.x it works a little bit differently. There, the
|
||||
* shared library version is stored in the file, and is actually a series
|
||||
* of versions, separated by colons. The rightmost version present in the
|
||||
* library when linking an application is stored in the application to be
|
||||
* matched at run time. When the application is run, a check is done to
|
||||
* see if the library version stored in the application matches any of the
|
||||
* versions in the version string of the library itself.
|
||||
* This version string can be constructed in any way, depending on what
|
||||
* kind of matching is desired. However, to implement the same scheme as
|
||||
* the one used in the other unixen, all compatible versions, from lowest
|
||||
* to highest, should be part of the string. Consecutive builds would
|
||||
* give the following versions strings:
|
||||
*
|
||||
* 3.0
|
||||
* 3.0:3.1
|
||||
* 3.0:3.1:3.2
|
||||
* 4.0
|
||||
* 4.0:4.1
|
||||
*
|
||||
* Notice how version 4 is completely incompatible with version, and
|
||||
* therefore give the breach you can see.
|
||||
*
|
||||
* There may be other schemes as well that I haven't yet discovered.
|
||||
*
|
||||
* So, here's the way it works here: first of all, the library version
|
||||
* number doesn't need at all to match the overall OpenSSL version.
|
||||
* However, it's nice and more understandable if it actually does.
|
||||
* The current library version is stored in the macro SHLIB_VERSION_NUMBER,
|
||||
* which is just a piece of text in the format "M.m.e" (Major, minor, edit).
|
||||
* For the sake of Tru64, IRIX, and any other OS that behaves in similar ways,
|
||||
* we need to keep a history of version numbers, which is done in the
|
||||
* macro SHLIB_VERSION_HISTORY. The numbers are separated by colons and
|
||||
* should only keep the versions that are binary compatible with the current.
|
||||
*/
|
||||
#define SHLIB_VERSION_HISTORY ""
|
||||
#define SHLIB_VERSION_NUMBER "1.0.0"
|
||||
|
||||
|
||||
#endif /* HEADER_OPENSSLV_H */
|
||||
@@ -0,0 +1,202 @@
|
||||
/* ====================================================================
|
||||
* Copyright (c) 1998-2001 The OpenSSL Project. All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
*
|
||||
* 1. Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
*
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in
|
||||
* the documentation and/or other materials provided with the
|
||||
* distribution.
|
||||
*
|
||||
* 3. All advertising materials mentioning features or use of this
|
||||
* software must display the following acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit. (http://www.openssl.org/)"
|
||||
*
|
||||
* 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
|
||||
* endorse or promote products derived from this software without
|
||||
* prior written permission. For written permission, please contact
|
||||
* openssl-core@openssl.org.
|
||||
*
|
||||
* 5. Products derived from this software may not be called "OpenSSL"
|
||||
* nor may "OpenSSL" appear in their names without prior written
|
||||
* permission of the OpenSSL Project.
|
||||
*
|
||||
* 6. Redistributions of any form whatsoever must retain the following
|
||||
* acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit (http://www.openssl.org/)"
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
|
||||
* EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE OpenSSL PROJECT OR
|
||||
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
||||
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
||||
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
||||
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
||||
* OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
* ====================================================================
|
||||
*
|
||||
* This product includes cryptographic software written by Eric Young
|
||||
* (eay@cryptsoft.com). This product includes software written by Tim
|
||||
* Hudson (tjh@cryptsoft.com).
|
||||
*
|
||||
*/
|
||||
|
||||
#ifndef HEADER_OPENSSL_TYPES_H
|
||||
#define HEADER_OPENSSL_TYPES_H
|
||||
|
||||
#include <openssl/e_os2.h>
|
||||
|
||||
#ifdef NO_ASN1_TYPEDEFS
|
||||
#define ASN1_INTEGER ASN1_STRING
|
||||
#define ASN1_ENUMERATED ASN1_STRING
|
||||
#define ASN1_BIT_STRING ASN1_STRING
|
||||
#define ASN1_OCTET_STRING ASN1_STRING
|
||||
#define ASN1_PRINTABLESTRING ASN1_STRING
|
||||
#define ASN1_T61STRING ASN1_STRING
|
||||
#define ASN1_IA5STRING ASN1_STRING
|
||||
#define ASN1_UTCTIME ASN1_STRING
|
||||
#define ASN1_GENERALIZEDTIME ASN1_STRING
|
||||
#define ASN1_TIME ASN1_STRING
|
||||
#define ASN1_GENERALSTRING ASN1_STRING
|
||||
#define ASN1_UNIVERSALSTRING ASN1_STRING
|
||||
#define ASN1_BMPSTRING ASN1_STRING
|
||||
#define ASN1_VISIBLESTRING ASN1_STRING
|
||||
#define ASN1_UTF8STRING ASN1_STRING
|
||||
#define ASN1_BOOLEAN int
|
||||
#define ASN1_NULL int
|
||||
#else
|
||||
typedef struct asn1_string_st ASN1_INTEGER;
|
||||
typedef struct asn1_string_st ASN1_ENUMERATED;
|
||||
typedef struct asn1_string_st ASN1_BIT_STRING;
|
||||
typedef struct asn1_string_st ASN1_OCTET_STRING;
|
||||
typedef struct asn1_string_st ASN1_PRINTABLESTRING;
|
||||
typedef struct asn1_string_st ASN1_T61STRING;
|
||||
typedef struct asn1_string_st ASN1_IA5STRING;
|
||||
typedef struct asn1_string_st ASN1_GENERALSTRING;
|
||||
typedef struct asn1_string_st ASN1_UNIVERSALSTRING;
|
||||
typedef struct asn1_string_st ASN1_BMPSTRING;
|
||||
typedef struct asn1_string_st ASN1_UTCTIME;
|
||||
typedef struct asn1_string_st ASN1_TIME;
|
||||
typedef struct asn1_string_st ASN1_GENERALIZEDTIME;
|
||||
typedef struct asn1_string_st ASN1_VISIBLESTRING;
|
||||
typedef struct asn1_string_st ASN1_UTF8STRING;
|
||||
typedef struct asn1_string_st ASN1_STRING;
|
||||
typedef int ASN1_BOOLEAN;
|
||||
typedef int ASN1_NULL;
|
||||
#endif
|
||||
|
||||
typedef struct ASN1_ITEM_st ASN1_ITEM;
|
||||
typedef struct asn1_pctx_st ASN1_PCTX;
|
||||
|
||||
#ifdef OPENSSL_SYS_WIN32
|
||||
#undef X509_NAME
|
||||
#undef X509_EXTENSIONS
|
||||
#undef X509_CERT_PAIR
|
||||
#undef PKCS7_ISSUER_AND_SERIAL
|
||||
#undef OCSP_REQUEST
|
||||
#undef OCSP_RESPONSE
|
||||
#endif
|
||||
|
||||
#ifdef BIGNUM
|
||||
#undef BIGNUM
|
||||
#endif
|
||||
typedef struct bignum_st BIGNUM;
|
||||
typedef struct bignum_ctx BN_CTX;
|
||||
typedef struct bn_blinding_st BN_BLINDING;
|
||||
typedef struct bn_mont_ctx_st BN_MONT_CTX;
|
||||
typedef struct bn_recp_ctx_st BN_RECP_CTX;
|
||||
typedef struct bn_gencb_st BN_GENCB;
|
||||
|
||||
typedef struct buf_mem_st BUF_MEM;
|
||||
|
||||
typedef struct evp_cipher_st EVP_CIPHER;
|
||||
typedef struct evp_cipher_ctx_st EVP_CIPHER_CTX;
|
||||
typedef struct env_md_st EVP_MD;
|
||||
typedef struct env_md_ctx_st EVP_MD_CTX;
|
||||
typedef struct evp_pkey_st EVP_PKEY;
|
||||
|
||||
typedef struct evp_pkey_asn1_method_st EVP_PKEY_ASN1_METHOD;
|
||||
|
||||
typedef struct evp_pkey_method_st EVP_PKEY_METHOD;
|
||||
typedef struct evp_pkey_ctx_st EVP_PKEY_CTX;
|
||||
|
||||
typedef struct dh_st DH;
|
||||
typedef struct dh_method DH_METHOD;
|
||||
|
||||
typedef struct dsa_st DSA;
|
||||
typedef struct dsa_method DSA_METHOD;
|
||||
|
||||
typedef struct rsa_st RSA;
|
||||
typedef struct rsa_meth_st RSA_METHOD;
|
||||
|
||||
typedef struct rand_meth_st RAND_METHOD;
|
||||
|
||||
typedef struct ecdh_method ECDH_METHOD;
|
||||
typedef struct ecdsa_method ECDSA_METHOD;
|
||||
|
||||
typedef struct x509_st X509;
|
||||
typedef struct X509_algor_st X509_ALGOR;
|
||||
typedef struct X509_crl_st X509_CRL;
|
||||
typedef struct x509_crl_method_st X509_CRL_METHOD;
|
||||
typedef struct x509_revoked_st X509_REVOKED;
|
||||
typedef struct X509_name_st X509_NAME;
|
||||
typedef struct X509_pubkey_st X509_PUBKEY;
|
||||
typedef struct x509_store_st X509_STORE;
|
||||
typedef struct x509_store_ctx_st X509_STORE_CTX;
|
||||
|
||||
typedef struct pkcs8_priv_key_info_st PKCS8_PRIV_KEY_INFO;
|
||||
|
||||
typedef struct v3_ext_ctx X509V3_CTX;
|
||||
typedef struct conf_st CONF;
|
||||
|
||||
typedef struct store_st STORE;
|
||||
typedef struct store_method_st STORE_METHOD;
|
||||
|
||||
typedef struct ui_st UI;
|
||||
typedef struct ui_method_st UI_METHOD;
|
||||
|
||||
typedef struct st_ERR_FNS ERR_FNS;
|
||||
|
||||
typedef struct engine_st ENGINE;
|
||||
typedef struct ssl_st SSL;
|
||||
typedef struct ssl_ctx_st SSL_CTX;
|
||||
|
||||
typedef struct X509_POLICY_NODE_st X509_POLICY_NODE;
|
||||
typedef struct X509_POLICY_LEVEL_st X509_POLICY_LEVEL;
|
||||
typedef struct X509_POLICY_TREE_st X509_POLICY_TREE;
|
||||
typedef struct X509_POLICY_CACHE_st X509_POLICY_CACHE;
|
||||
|
||||
typedef struct AUTHORITY_KEYID_st AUTHORITY_KEYID;
|
||||
typedef struct DIST_POINT_st DIST_POINT;
|
||||
typedef struct ISSUING_DIST_POINT_st ISSUING_DIST_POINT;
|
||||
typedef struct NAME_CONSTRAINTS_st NAME_CONSTRAINTS;
|
||||
|
||||
/* If placed in pkcs12.h, we end up with a circular depency with pkcs7.h */
|
||||
#define DECLARE_PKCS12_STACK_OF(type) /* Nothing */
|
||||
#define IMPLEMENT_PKCS12_STACK_OF(type) /* Nothing */
|
||||
|
||||
typedef struct crypto_ex_data_st CRYPTO_EX_DATA;
|
||||
/* Callback types for crypto.h */
|
||||
typedef int CRYPTO_EX_new(void *parent, void *ptr, CRYPTO_EX_DATA *ad,
|
||||
int idx, long argl, void *argp);
|
||||
typedef void CRYPTO_EX_free(void *parent, void *ptr, CRYPTO_EX_DATA *ad,
|
||||
int idx, long argl, void *argp);
|
||||
typedef int CRYPTO_EX_dup(CRYPTO_EX_DATA *to, CRYPTO_EX_DATA *from, void *from_d,
|
||||
int idx, long argl, void *argp);
|
||||
|
||||
typedef struct ocsp_req_ctx_st OCSP_REQ_CTX;
|
||||
typedef struct ocsp_response_st OCSP_RESPONSE;
|
||||
typedef struct ocsp_responder_id_st OCSP_RESPID;
|
||||
|
||||
#endif /* def HEADER_OPENSSL_TYPES_H */
|
||||
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,108 @@
|
||||
/* crypto/stack/stack.h */
|
||||
/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
|
||||
* All rights reserved.
|
||||
*
|
||||
* This package is an SSL implementation written
|
||||
* by Eric Young (eay@cryptsoft.com).
|
||||
* The implementation was written so as to conform with Netscapes SSL.
|
||||
*
|
||||
* This library is free for commercial and non-commercial use as long as
|
||||
* the following conditions are aheared to. The following conditions
|
||||
* apply to all code found in this distribution, be it the RC4, RSA,
|
||||
* lhash, DES, etc., code; not just the SSL code. The SSL documentation
|
||||
* included with this distribution is covered by the same copyright terms
|
||||
* except that the holder is Tim Hudson (tjh@cryptsoft.com).
|
||||
*
|
||||
* Copyright remains Eric Young's, and as such any Copyright notices in
|
||||
* the code are not to be removed.
|
||||
* If this package is used in a product, Eric Young should be given attribution
|
||||
* as the author of the parts of the library used.
|
||||
* This can be in the form of a textual message at program startup or
|
||||
* in documentation (online or textual) provided with the package.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
* 1. Redistributions of source code must retain the copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in the
|
||||
* documentation and/or other materials provided with the distribution.
|
||||
* 3. All advertising materials mentioning features or use of this software
|
||||
* must display the following acknowledgement:
|
||||
* "This product includes cryptographic software written by
|
||||
* Eric Young (eay@cryptsoft.com)"
|
||||
* The word 'cryptographic' can be left out if the rouines from the library
|
||||
* being used are not cryptographic related :-).
|
||||
* 4. If you include any Windows specific code (or a derivative thereof) from
|
||||
* the apps directory (application code) you must include an acknowledgement:
|
||||
* "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
|
||||
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
||||
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
||||
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
||||
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
||||
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
||||
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
||||
* SUCH DAMAGE.
|
||||
*
|
||||
* The licence and distribution terms for any publically available version or
|
||||
* derivative of this code cannot be changed. i.e. this code cannot simply be
|
||||
* copied and put under another distribution licence
|
||||
* [including the GNU Public Licence.]
|
||||
*/
|
||||
|
||||
#ifndef HEADER_STACK_H
|
||||
#define HEADER_STACK_H
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
typedef struct stack_st
|
||||
{
|
||||
int num;
|
||||
char **data;
|
||||
int sorted;
|
||||
|
||||
int num_alloc;
|
||||
int (*comp)(const void *, const void *);
|
||||
} _STACK; /* Use STACK_OF(...) instead */
|
||||
|
||||
#define M_sk_num(sk) ((sk) ? (sk)->num:-1)
|
||||
#define M_sk_value(sk,n) ((sk) ? (sk)->data[n] : NULL)
|
||||
|
||||
int sk_num(const _STACK *);
|
||||
void *sk_value(const _STACK *, int);
|
||||
|
||||
void *sk_set(_STACK *, int, void *);
|
||||
|
||||
_STACK *sk_new(int (*cmp)(const void *, const void *));
|
||||
_STACK *sk_new_null(void);
|
||||
void sk_free(_STACK *);
|
||||
void sk_pop_free(_STACK *st, void (*func)(void *));
|
||||
int sk_insert(_STACK *sk, void *data, int where);
|
||||
void *sk_delete(_STACK *st, int loc);
|
||||
void *sk_delete_ptr(_STACK *st, void *p);
|
||||
int sk_find(_STACK *st, void *data);
|
||||
int sk_find_ex(_STACK *st, void *data);
|
||||
int sk_push(_STACK *st, void *data);
|
||||
int sk_unshift(_STACK *st, void *data);
|
||||
void *sk_shift(_STACK *st);
|
||||
void *sk_pop(_STACK *st);
|
||||
void sk_zero(_STACK *st);
|
||||
int (*sk_set_cmp_func(_STACK *sk, int (*c)(const void *, const void *)))
|
||||
(const void *, const void *);
|
||||
_STACK *sk_dup(_STACK *st);
|
||||
void sk_sort(_STACK *st);
|
||||
int sk_is_sorted(const _STACK *st);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif
|
||||
@@ -0,0 +1,481 @@
|
||||
/* ====================================================================
|
||||
* Copyright (c) 1999 The OpenSSL Project. All rights reserved.
|
||||
*
|
||||
* Redistribution and use in source and binary forms, with or without
|
||||
* modification, are permitted provided that the following conditions
|
||||
* are met:
|
||||
*
|
||||
* 1. Redistributions of source code must retain the above copyright
|
||||
* notice, this list of conditions and the following disclaimer.
|
||||
*
|
||||
* 2. Redistributions in binary form must reproduce the above copyright
|
||||
* notice, this list of conditions and the following disclaimer in
|
||||
* the documentation and/or other materials provided with the
|
||||
* distribution.
|
||||
*
|
||||
* 3. All advertising materials mentioning features or use of this
|
||||
* software must display the following acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit. (http://www.openssl.org/)"
|
||||
*
|
||||
* 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
|
||||
* endorse or promote products derived from this software without
|
||||
* prior written permission. For written permission, please contact
|
||||
* openssl-core@openssl.org.
|
||||
*
|
||||
* 5. Products derived from this software may not be called "OpenSSL"
|
||||
* nor may "OpenSSL" appear in their names without prior written
|
||||
* permission of the OpenSSL Project.
|
||||
*
|
||||
* 6. Redistributions of any form whatsoever must retain the following
|
||||
* acknowledgment:
|
||||
* "This product includes software developed by the OpenSSL Project
|
||||
* for use in the OpenSSL Toolkit (http://www.openssl.org/)"
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
|
||||
* EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
||||
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE OpenSSL PROJECT OR
|
||||
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
||||
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
||||
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
||||
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
|
||||
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
|
||||
* OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
* ====================================================================
|
||||
*
|
||||
* This product includes cryptographic software written by Eric Young
|
||||
* (eay@cryptsoft.com). This product includes software written by Tim
|
||||
* Hudson (tjh@cryptsoft.com).
|
||||
*
|
||||
*/
|
||||
|
||||
#ifndef HEADER_SYMHACKS_H
|
||||
#define HEADER_SYMHACKS_H
|
||||
|
||||
#include <openssl/e_os2.h>
|
||||
|
||||
/* Hacks to solve the problem with linkers incapable of handling very long
|
||||
symbol names. In the case of VMS, the limit is 31 characters on VMS for
|
||||
VAX. */
|
||||
/* Note that this affects util/libeay.num and util/ssleay.num... you may
|
||||
change those manually, but that's not recommended, as those files are
|
||||
controlled centrally and updated on Unix, and the central definition
|
||||
may disagree with yours, which in turn may come with shareable library
|
||||
incompatibilities. */
|
||||
#ifdef OPENSSL_SYS_VMS
|
||||
|
||||
/* Hack a long name in crypto/ex_data.c */
|
||||
#undef CRYPTO_get_ex_data_implementation
|
||||
#define CRYPTO_get_ex_data_implementation CRYPTO_get_ex_data_impl
|
||||
#undef CRYPTO_set_ex_data_implementation
|
||||
#define CRYPTO_set_ex_data_implementation CRYPTO_set_ex_data_impl
|
||||
|
||||
/* Hack a long name in crypto/asn1/a_mbstr.c */
|
||||
#undef ASN1_STRING_set_default_mask_asc
|
||||
#define ASN1_STRING_set_default_mask_asc ASN1_STRING_set_def_mask_asc
|
||||
|
||||
#if 0 /* No longer needed, since safestack macro magic does the job */
|
||||
/* Hack the names created with DECLARE_ASN1_SET_OF(PKCS7_SIGNER_INFO) */
|
||||
#undef i2d_ASN1_SET_OF_PKCS7_SIGNER_INFO
|
||||
#define i2d_ASN1_SET_OF_PKCS7_SIGNER_INFO i2d_ASN1_SET_OF_PKCS7_SIGINF
|
||||
#undef d2i_ASN1_SET_OF_PKCS7_SIGNER_INFO
|
||||
#define d2i_ASN1_SET_OF_PKCS7_SIGNER_INFO d2i_ASN1_SET_OF_PKCS7_SIGINF
|
||||
#endif
|
||||
|
||||
#if 0 /* No longer needed, since safestack macro magic does the job */
|
||||
/* Hack the names created with DECLARE_ASN1_SET_OF(PKCS7_RECIP_INFO) */
|
||||
#undef i2d_ASN1_SET_OF_PKCS7_RECIP_INFO
|
||||
#define i2d_ASN1_SET_OF_PKCS7_RECIP_INFO i2d_ASN1_SET_OF_PKCS7_RECINF
|
||||
#undef d2i_ASN1_SET_OF_PKCS7_RECIP_INFO
|
||||
#define d2i_ASN1_SET_OF_PKCS7_RECIP_INFO d2i_ASN1_SET_OF_PKCS7_RECINF
|
||||
#endif
|
||||
|
||||
#if 0 /* No longer needed, since safestack macro magic does the job */
|
||||
/* Hack the names created with DECLARE_ASN1_SET_OF(ACCESS_DESCRIPTION) */
|
||||
#undef i2d_ASN1_SET_OF_ACCESS_DESCRIPTION
|
||||
#define i2d_ASN1_SET_OF_ACCESS_DESCRIPTION i2d_ASN1_SET_OF_ACC_DESC
|
||||
#undef d2i_ASN1_SET_OF_ACCESS_DESCRIPTION
|
||||
#define d2i_ASN1_SET_OF_ACCESS_DESCRIPTION d2i_ASN1_SET_OF_ACC_DESC
|
||||
#endif
|
||||
|
||||
/* Hack the names created with DECLARE_PEM_rw(NETSCAPE_CERT_SEQUENCE) */
|
||||
#undef PEM_read_NETSCAPE_CERT_SEQUENCE
|
||||
#define PEM_read_NETSCAPE_CERT_SEQUENCE PEM_read_NS_CERT_SEQ
|
||||
#undef PEM_write_NETSCAPE_CERT_SEQUENCE
|
||||
#define PEM_write_NETSCAPE_CERT_SEQUENCE PEM_write_NS_CERT_SEQ
|
||||
#undef PEM_read_bio_NETSCAPE_CERT_SEQUENCE
|
||||
#define PEM_read_bio_NETSCAPE_CERT_SEQUENCE PEM_read_bio_NS_CERT_SEQ
|
||||
#undef PEM_write_bio_NETSCAPE_CERT_SEQUENCE
|
||||
#define PEM_write_bio_NETSCAPE_CERT_SEQUENCE PEM_write_bio_NS_CERT_SEQ
|
||||
#undef PEM_write_cb_bio_NETSCAPE_CERT_SEQUENCE
|
||||
#define PEM_write_cb_bio_NETSCAPE_CERT_SEQUENCE PEM_write_cb_bio_NS_CERT_SEQ
|
||||
|
||||
/* Hack the names created with DECLARE_PEM_rw(PKCS8_PRIV_KEY_INFO) */
|
||||
#undef PEM_read_PKCS8_PRIV_KEY_INFO
|
||||
#define PEM_read_PKCS8_PRIV_KEY_INFO PEM_read_P8_PRIV_KEY_INFO
|
||||
#undef PEM_write_PKCS8_PRIV_KEY_INFO
|
||||
#define PEM_write_PKCS8_PRIV_KEY_INFO PEM_write_P8_PRIV_KEY_INFO
|
||||
#undef PEM_read_bio_PKCS8_PRIV_KEY_INFO
|
||||
#define PEM_read_bio_PKCS8_PRIV_KEY_INFO PEM_read_bio_P8_PRIV_KEY_INFO
|
||||
#undef PEM_write_bio_PKCS8_PRIV_KEY_INFO
|
||||
#define PEM_write_bio_PKCS8_PRIV_KEY_INFO PEM_write_bio_P8_PRIV_KEY_INFO
|
||||
#undef PEM_write_cb_bio_PKCS8_PRIV_KEY_INFO
|
||||
#define PEM_write_cb_bio_PKCS8_PRIV_KEY_INFO PEM_wrt_cb_bio_P8_PRIV_KEY_INFO
|
||||
|
||||
/* Hack other PEM names */
|
||||
#undef PEM_write_bio_PKCS8PrivateKey_nid
|
||||
#define PEM_write_bio_PKCS8PrivateKey_nid PEM_write_bio_PKCS8PrivKey_nid
|
||||
|
||||
/* Hack some long X509 names */
|
||||
#undef X509_REVOKED_get_ext_by_critical
|
||||
#define X509_REVOKED_get_ext_by_critical X509_REVOKED_get_ext_by_critic
|
||||
#undef X509_policy_tree_get0_user_policies
|
||||
#define X509_policy_tree_get0_user_policies X509_pcy_tree_get0_usr_policies
|
||||
#undef X509_policy_node_get0_qualifiers
|
||||
#define X509_policy_node_get0_qualifiers X509_pcy_node_get0_qualifiers
|
||||
#undef X509_STORE_CTX_get_explicit_policy
|
||||
#define X509_STORE_CTX_get_explicit_policy X509_STORE_CTX_get_expl_policy
|
||||
#undef X509_STORE_CTX_get0_current_issuer
|
||||
#define X509_STORE_CTX_get0_current_issuer X509_STORE_CTX_get0_cur_issuer
|
||||
|
||||
/* Hack some long CRYPTO names */
|
||||
#undef CRYPTO_set_dynlock_destroy_callback
|
||||
#define CRYPTO_set_dynlock_destroy_callback CRYPTO_set_dynlock_destroy_cb
|
||||
#undef CRYPTO_set_dynlock_create_callback
|
||||
#define CRYPTO_set_dynlock_create_callback CRYPTO_set_dynlock_create_cb
|
||||
#undef CRYPTO_set_dynlock_lock_callback
|
||||
#define CRYPTO_set_dynlock_lock_callback CRYPTO_set_dynlock_lock_cb
|
||||
#undef CRYPTO_get_dynlock_lock_callback
|
||||
#define CRYPTO_get_dynlock_lock_callback CRYPTO_get_dynlock_lock_cb
|
||||
#undef CRYPTO_get_dynlock_destroy_callback
|
||||
#define CRYPTO_get_dynlock_destroy_callback CRYPTO_get_dynlock_destroy_cb
|
||||
#undef CRYPTO_get_dynlock_create_callback
|
||||
#define CRYPTO_get_dynlock_create_callback CRYPTO_get_dynlock_create_cb
|
||||
#undef CRYPTO_set_locked_mem_ex_functions
|
||||
#define CRYPTO_set_locked_mem_ex_functions CRYPTO_set_locked_mem_ex_funcs
|
||||
#undef CRYPTO_get_locked_mem_ex_functions
|
||||
#define CRYPTO_get_locked_mem_ex_functions CRYPTO_get_locked_mem_ex_funcs
|
||||
|
||||
/* Hack some long SSL names */
|
||||
#undef SSL_CTX_set_default_verify_paths
|
||||
#define SSL_CTX_set_default_verify_paths SSL_CTX_set_def_verify_paths
|
||||
#undef SSL_get_ex_data_X509_STORE_CTX_idx
|
||||
#define SSL_get_ex_data_X509_STORE_CTX_idx SSL_get_ex_d_X509_STORE_CTX_idx
|
||||
#undef SSL_add_file_cert_subjects_to_stack
|
||||
#define SSL_add_file_cert_subjects_to_stack SSL_add_file_cert_subjs_to_stk
|
||||
#undef SSL_add_dir_cert_subjects_to_stack
|
||||
#define SSL_add_dir_cert_subjects_to_stack SSL_add_dir_cert_subjs_to_stk
|
||||
#undef SSL_CTX_use_certificate_chain_file
|
||||
#define SSL_CTX_use_certificate_chain_file SSL_CTX_use_cert_chain_file
|
||||
#undef SSL_CTX_set_cert_verify_callback
|
||||
#define SSL_CTX_set_cert_verify_callback SSL_CTX_set_cert_verify_cb
|
||||
#undef SSL_CTX_set_default_passwd_cb_userdata
|
||||
#define SSL_CTX_set_default_passwd_cb_userdata SSL_CTX_set_def_passwd_cb_ud
|
||||
#undef SSL_COMP_get_compression_methods
|
||||
#define SSL_COMP_get_compression_methods SSL_COMP_get_compress_methods
|
||||
#undef ssl_add_clienthello_renegotiate_ext
|
||||
#define ssl_add_clienthello_renegotiate_ext ssl_add_clienthello_reneg_ext
|
||||
#undef ssl_add_serverhello_renegotiate_ext
|
||||
#define ssl_add_serverhello_renegotiate_ext ssl_add_serverhello_reneg_ext
|
||||
#undef ssl_parse_clienthello_renegotiate_ext
|
||||
#define ssl_parse_clienthello_renegotiate_ext ssl_parse_clienthello_reneg_ext
|
||||
#undef ssl_parse_serverhello_renegotiate_ext
|
||||
#define ssl_parse_serverhello_renegotiate_ext ssl_parse_serverhello_reneg_ext
|
||||
#undef SSL_srp_server_param_with_username
|
||||
#define SSL_srp_server_param_with_username SSL_srp_server_param_with_un
|
||||
#undef SSL_CTX_set_srp_client_pwd_callback
|
||||
#define SSL_CTX_set_srp_client_pwd_callback SSL_CTX_set_srp_client_pwd_cb
|
||||
#undef SSL_CTX_set_srp_verify_param_callback
|
||||
#define SSL_CTX_set_srp_verify_param_callback SSL_CTX_set_srp_vfy_param_cb
|
||||
#undef SSL_CTX_set_srp_username_callback
|
||||
#define SSL_CTX_set_srp_username_callback SSL_CTX_set_srp_un_cb
|
||||
#undef ssl_add_clienthello_use_srtp_ext
|
||||
#define ssl_add_clienthello_use_srtp_ext ssl_add_clihello_use_srtp_ext
|
||||
#undef ssl_add_serverhello_use_srtp_ext
|
||||
#define ssl_add_serverhello_use_srtp_ext ssl_add_serhello_use_srtp_ext
|
||||
#undef ssl_parse_clienthello_use_srtp_ext
|
||||
#define ssl_parse_clienthello_use_srtp_ext ssl_parse_clihello_use_srtp_ext
|
||||
#undef ssl_parse_serverhello_use_srtp_ext
|
||||
#define ssl_parse_serverhello_use_srtp_ext ssl_parse_serhello_use_srtp_ext
|
||||
#undef SSL_CTX_set_next_protos_advertised_cb
|
||||
#define SSL_CTX_set_next_protos_advertised_cb SSL_CTX_set_next_protos_adv_cb
|
||||
#undef SSL_CTX_set_next_proto_select_cb
|
||||
#define SSL_CTX_set_next_proto_select_cb SSL_CTX_set_next_proto_sel_cb
|
||||
#undef ssl3_cbc_record_digest_supported
|
||||
#define ssl3_cbc_record_digest_supported ssl3_cbc_record_digest_support
|
||||
#undef ssl_check_clienthello_tlsext_late
|
||||
#define ssl_check_clienthello_tlsext_late ssl_check_clihello_tlsext_late
|
||||
#undef ssl_check_clienthello_tlsext_early
|
||||
#define ssl_check_clienthello_tlsext_early ssl_check_clihello_tlsext_early
|
||||
|
||||
/* Hack some long ENGINE names */
|
||||
#undef ENGINE_get_default_BN_mod_exp_crt
|
||||
#define ENGINE_get_default_BN_mod_exp_crt ENGINE_get_def_BN_mod_exp_crt
|
||||
#undef ENGINE_set_default_BN_mod_exp_crt
|
||||
#define ENGINE_set_default_BN_mod_exp_crt ENGINE_set_def_BN_mod_exp_crt
|
||||
#undef ENGINE_set_load_privkey_function
|
||||
#define ENGINE_set_load_privkey_function ENGINE_set_load_privkey_fn
|
||||
#undef ENGINE_get_load_privkey_function
|
||||
#define ENGINE_get_load_privkey_function ENGINE_get_load_privkey_fn
|
||||
#undef ENGINE_unregister_pkey_asn1_meths
|
||||
#define ENGINE_unregister_pkey_asn1_meths ENGINE_unreg_pkey_asn1_meths
|
||||
#undef ENGINE_register_all_pkey_asn1_meths
|
||||
#define ENGINE_register_all_pkey_asn1_meths ENGINE_reg_all_pkey_asn1_meths
|
||||
#undef ENGINE_set_default_pkey_asn1_meths
|
||||
#define ENGINE_set_default_pkey_asn1_meths ENGINE_set_def_pkey_asn1_meths
|
||||
#undef ENGINE_get_pkey_asn1_meth_engine
|
||||
#define ENGINE_get_pkey_asn1_meth_engine ENGINE_get_pkey_asn1_meth_eng
|
||||
#undef ENGINE_set_load_ssl_client_cert_function
|
||||
#define ENGINE_set_load_ssl_client_cert_function \
|
||||
ENGINE_set_ld_ssl_clnt_cert_fn
|
||||
#undef ENGINE_get_ssl_client_cert_function
|
||||
#define ENGINE_get_ssl_client_cert_function ENGINE_get_ssl_client_cert_fn
|
||||
|
||||
/* Hack some long OCSP names */
|
||||
#undef OCSP_REQUEST_get_ext_by_critical
|
||||
#define OCSP_REQUEST_get_ext_by_critical OCSP_REQUEST_get_ext_by_crit
|
||||
#undef OCSP_BASICRESP_get_ext_by_critical
|
||||
#define OCSP_BASICRESP_get_ext_by_critical OCSP_BASICRESP_get_ext_by_crit
|
||||
#undef OCSP_SINGLERESP_get_ext_by_critical
|
||||
#define OCSP_SINGLERESP_get_ext_by_critical OCSP_SINGLERESP_get_ext_by_crit
|
||||
|
||||
/* Hack some long DES names */
|
||||
#undef _ossl_old_des_ede3_cfb64_encrypt
|
||||
#define _ossl_old_des_ede3_cfb64_encrypt _ossl_odes_ede3_cfb64_encrypt
|
||||
#undef _ossl_old_des_ede3_ofb64_encrypt
|
||||
#define _ossl_old_des_ede3_ofb64_encrypt _ossl_odes_ede3_ofb64_encrypt
|
||||
|
||||
/* Hack some long EVP names */
|
||||
#undef OPENSSL_add_all_algorithms_noconf
|
||||
#define OPENSSL_add_all_algorithms_noconf OPENSSL_add_all_algo_noconf
|
||||
#undef OPENSSL_add_all_algorithms_conf
|
||||
#define OPENSSL_add_all_algorithms_conf OPENSSL_add_all_algo_conf
|
||||
#undef EVP_PKEY_meth_set_verify_recover
|
||||
#define EVP_PKEY_meth_set_verify_recover EVP_PKEY_meth_set_vrfy_recover
|
||||
|
||||
/* Hack some long EC names */
|
||||
#undef EC_GROUP_set_point_conversion_form
|
||||
#define EC_GROUP_set_point_conversion_form EC_GROUP_set_point_conv_form
|
||||
#undef EC_GROUP_get_point_conversion_form
|
||||
#define EC_GROUP_get_point_conversion_form EC_GROUP_get_point_conv_form
|
||||
#undef EC_GROUP_clear_free_all_extra_data
|
||||
#define EC_GROUP_clear_free_all_extra_data EC_GROUP_clr_free_all_xtra_data
|
||||
#undef EC_KEY_set_public_key_affine_coordinates
|
||||
#define EC_KEY_set_public_key_affine_coordinates \
|
||||
EC_KEY_set_pub_key_aff_coords
|
||||
#undef EC_POINT_set_Jprojective_coordinates_GFp
|
||||
#define EC_POINT_set_Jprojective_coordinates_GFp \
|
||||
EC_POINT_set_Jproj_coords_GFp
|
||||
#undef EC_POINT_get_Jprojective_coordinates_GFp
|
||||
#define EC_POINT_get_Jprojective_coordinates_GFp \
|
||||
EC_POINT_get_Jproj_coords_GFp
|
||||
#undef EC_POINT_set_affine_coordinates_GFp
|
||||
#define EC_POINT_set_affine_coordinates_GFp EC_POINT_set_affine_coords_GFp
|
||||
#undef EC_POINT_get_affine_coordinates_GFp
|
||||
#define EC_POINT_get_affine_coordinates_GFp EC_POINT_get_affine_coords_GFp
|
||||
#undef EC_POINT_set_compressed_coordinates_GFp
|
||||
#define EC_POINT_set_compressed_coordinates_GFp EC_POINT_set_compr_coords_GFp
|
||||
#undef EC_POINT_set_affine_coordinates_GF2m
|
||||
#define EC_POINT_set_affine_coordinates_GF2m EC_POINT_set_affine_coords_GF2m
|
||||
#undef EC_POINT_get_affine_coordinates_GF2m
|
||||
#define EC_POINT_get_affine_coordinates_GF2m EC_POINT_get_affine_coords_GF2m
|
||||
#undef EC_POINT_set_compressed_coordinates_GF2m
|
||||
#define EC_POINT_set_compressed_coordinates_GF2m \
|
||||
EC_POINT_set_compr_coords_GF2m
|
||||
#undef ec_GF2m_simple_group_clear_finish
|
||||
#define ec_GF2m_simple_group_clear_finish ec_GF2m_simple_grp_clr_finish
|
||||
#undef ec_GF2m_simple_group_check_discriminant
|
||||
#define ec_GF2m_simple_group_check_discriminant ec_GF2m_simple_grp_chk_discrim
|
||||
#undef ec_GF2m_simple_point_clear_finish
|
||||
#define ec_GF2m_simple_point_clear_finish ec_GF2m_simple_pt_clr_finish
|
||||
#undef ec_GF2m_simple_point_set_to_infinity
|
||||
#define ec_GF2m_simple_point_set_to_infinity ec_GF2m_simple_pt_set_to_inf
|
||||
#undef ec_GF2m_simple_points_make_affine
|
||||
#define ec_GF2m_simple_points_make_affine ec_GF2m_simple_pts_make_affine
|
||||
#undef ec_GF2m_simple_point_set_affine_coordinates
|
||||
#define ec_GF2m_simple_point_set_affine_coordinates \
|
||||
ec_GF2m_smp_pt_set_af_coords
|
||||
#undef ec_GF2m_simple_point_get_affine_coordinates
|
||||
#define ec_GF2m_simple_point_get_affine_coordinates \
|
||||
ec_GF2m_smp_pt_get_af_coords
|
||||
#undef ec_GF2m_simple_set_compressed_coordinates
|
||||
#define ec_GF2m_simple_set_compressed_coordinates \
|
||||
ec_GF2m_smp_set_compr_coords
|
||||
#undef ec_GFp_simple_group_set_curve_GFp
|
||||
#define ec_GFp_simple_group_set_curve_GFp ec_GFp_simple_grp_set_curve_GFp
|
||||
#undef ec_GFp_simple_group_get_curve_GFp
|
||||
#define ec_GFp_simple_group_get_curve_GFp ec_GFp_simple_grp_get_curve_GFp
|
||||
#undef ec_GFp_simple_group_clear_finish
|
||||
#define ec_GFp_simple_group_clear_finish ec_GFp_simple_grp_clear_finish
|
||||
#undef ec_GFp_simple_group_set_generator
|
||||
#define ec_GFp_simple_group_set_generator ec_GFp_simple_grp_set_generator
|
||||
#undef ec_GFp_simple_group_get0_generator
|
||||
#define ec_GFp_simple_group_get0_generator ec_GFp_simple_grp_gt0_generator
|
||||
#undef ec_GFp_simple_group_get_cofactor
|
||||
#define ec_GFp_simple_group_get_cofactor ec_GFp_simple_grp_get_cofactor
|
||||
#undef ec_GFp_simple_point_clear_finish
|
||||
#define ec_GFp_simple_point_clear_finish ec_GFp_simple_pt_clear_finish
|
||||
#undef ec_GFp_simple_point_set_to_infinity
|
||||
#define ec_GFp_simple_point_set_to_infinity ec_GFp_simple_pt_set_to_inf
|
||||
#undef ec_GFp_simple_points_make_affine
|
||||
#define ec_GFp_simple_points_make_affine ec_GFp_simple_pts_make_affine
|
||||
#undef ec_GFp_simple_set_Jprojective_coordinates_GFp
|
||||
#define ec_GFp_simple_set_Jprojective_coordinates_GFp \
|
||||
ec_GFp_smp_set_Jproj_coords_GFp
|
||||
#undef ec_GFp_simple_get_Jprojective_coordinates_GFp
|
||||
#define ec_GFp_simple_get_Jprojective_coordinates_GFp \
|
||||
ec_GFp_smp_get_Jproj_coords_GFp
|
||||
#undef ec_GFp_simple_point_set_affine_coordinates_GFp
|
||||
#define ec_GFp_simple_point_set_affine_coordinates_GFp \
|
||||
ec_GFp_smp_pt_set_af_coords_GFp
|
||||
#undef ec_GFp_simple_point_get_affine_coordinates_GFp
|
||||
#define ec_GFp_simple_point_get_affine_coordinates_GFp \
|
||||
ec_GFp_smp_pt_get_af_coords_GFp
|
||||
#undef ec_GFp_simple_set_compressed_coordinates_GFp
|
||||
#define ec_GFp_simple_set_compressed_coordinates_GFp \
|
||||
ec_GFp_smp_set_compr_coords_GFp
|
||||
#undef ec_GFp_simple_point_set_affine_coordinates
|
||||
#define ec_GFp_simple_point_set_affine_coordinates \
|
||||
ec_GFp_smp_pt_set_af_coords
|
||||
#undef ec_GFp_simple_point_get_affine_coordinates
|
||||
#define ec_GFp_simple_point_get_affine_coordinates \
|
||||
ec_GFp_smp_pt_get_af_coords
|
||||
#undef ec_GFp_simple_set_compressed_coordinates
|
||||
#define ec_GFp_simple_set_compressed_coordinates \
|
||||
ec_GFp_smp_set_compr_coords
|
||||
#undef ec_GFp_simple_group_check_discriminant
|
||||
#define ec_GFp_simple_group_check_discriminant ec_GFp_simple_grp_chk_discrim
|
||||
|
||||
/* Hack som long STORE names */
|
||||
#undef STORE_method_set_initialise_function
|
||||
#define STORE_method_set_initialise_function STORE_meth_set_initialise_fn
|
||||
#undef STORE_method_set_cleanup_function
|
||||
#define STORE_method_set_cleanup_function STORE_meth_set_cleanup_fn
|
||||
#undef STORE_method_set_generate_function
|
||||
#define STORE_method_set_generate_function STORE_meth_set_generate_fn
|
||||
#undef STORE_method_set_modify_function
|
||||
#define STORE_method_set_modify_function STORE_meth_set_modify_fn
|
||||
#undef STORE_method_set_revoke_function
|
||||
#define STORE_method_set_revoke_function STORE_meth_set_revoke_fn
|
||||
#undef STORE_method_set_delete_function
|
||||
#define STORE_method_set_delete_function STORE_meth_set_delete_fn
|
||||
#undef STORE_method_set_list_start_function
|
||||
#define STORE_method_set_list_start_function STORE_meth_set_list_start_fn
|
||||
#undef STORE_method_set_list_next_function
|
||||
#define STORE_method_set_list_next_function STORE_meth_set_list_next_fn
|
||||
#undef STORE_method_set_list_end_function
|
||||
#define STORE_method_set_list_end_function STORE_meth_set_list_end_fn
|
||||
#undef STORE_method_set_update_store_function
|
||||
#define STORE_method_set_update_store_function STORE_meth_set_update_store_fn
|
||||
#undef STORE_method_set_lock_store_function
|
||||
#define STORE_method_set_lock_store_function STORE_meth_set_lock_store_fn
|
||||
#undef STORE_method_set_unlock_store_function
|
||||
#define STORE_method_set_unlock_store_function STORE_meth_set_unlock_store_fn
|
||||
#undef STORE_method_get_initialise_function
|
||||
#define STORE_method_get_initialise_function STORE_meth_get_initialise_fn
|
||||
#undef STORE_method_get_cleanup_function
|
||||
#define STORE_method_get_cleanup_function STORE_meth_get_cleanup_fn
|
||||
#undef STORE_method_get_generate_function
|
||||
#define STORE_method_get_generate_function STORE_meth_get_generate_fn
|
||||
#undef STORE_method_get_modify_function
|
||||
#define STORE_method_get_modify_function STORE_meth_get_modify_fn
|
||||
#undef STORE_method_get_revoke_function
|
||||
#define STORE_method_get_revoke_function STORE_meth_get_revoke_fn
|
||||
#undef STORE_method_get_delete_function
|
||||
#define STORE_method_get_delete_function STORE_meth_get_delete_fn
|
||||
#undef STORE_method_get_list_start_function
|
||||
#define STORE_method_get_list_start_function STORE_meth_get_list_start_fn
|
||||
#undef STORE_method_get_list_next_function
|
||||
#define STORE_method_get_list_next_function STORE_meth_get_list_next_fn
|
||||
#undef STORE_method_get_list_end_function
|
||||
#define STORE_method_get_list_end_function STORE_meth_get_list_end_fn
|
||||
#undef STORE_method_get_update_store_function
|
||||
#define STORE_method_get_update_store_function STORE_meth_get_update_store_fn
|
||||
#undef STORE_method_get_lock_store_function
|
||||
#define STORE_method_get_lock_store_function STORE_meth_get_lock_store_fn
|
||||
#undef STORE_method_get_unlock_store_function
|
||||
#define STORE_method_get_unlock_store_function STORE_meth_get_unlock_store_fn
|
||||
|
||||
/* Hack some long TS names */
|
||||
#undef TS_RESP_CTX_set_status_info_cond
|
||||
#define TS_RESP_CTX_set_status_info_cond TS_RESP_CTX_set_stat_info_cond
|
||||
#undef TS_RESP_CTX_set_clock_precision_digits
|
||||
#define TS_RESP_CTX_set_clock_precision_digits TS_RESP_CTX_set_clk_prec_digits
|
||||
#undef TS_CONF_set_clock_precision_digits
|
||||
#define TS_CONF_set_clock_precision_digits TS_CONF_set_clk_prec_digits
|
||||
|
||||
/* Hack some long CMS names */
|
||||
#undef CMS_RecipientInfo_ktri_get0_algs
|
||||
#define CMS_RecipientInfo_ktri_get0_algs CMS_RecipInfo_ktri_get0_algs
|
||||
#undef CMS_RecipientInfo_ktri_get0_signer_id
|
||||
#define CMS_RecipientInfo_ktri_get0_signer_id CMS_RecipInfo_ktri_get0_sigr_id
|
||||
#undef CMS_OtherRevocationInfoFormat_it
|
||||
#define CMS_OtherRevocationInfoFormat_it CMS_OtherRevocInfoFormat_it
|
||||
#undef CMS_KeyAgreeRecipientIdentifier_it
|
||||
#define CMS_KeyAgreeRecipientIdentifier_it CMS_KeyAgreeRecipIdentifier_it
|
||||
#undef CMS_OriginatorIdentifierOrKey_it
|
||||
#define CMS_OriginatorIdentifierOrKey_it CMS_OriginatorIdOrKey_it
|
||||
#undef cms_SignerIdentifier_get0_signer_id
|
||||
#define cms_SignerIdentifier_get0_signer_id cms_SignerId_get0_signer_id
|
||||
|
||||
/* Hack some long DTLS1 names */
|
||||
#undef dtls1_retransmit_buffered_messages
|
||||
#define dtls1_retransmit_buffered_messages dtls1_retransmit_buffered_msgs
|
||||
|
||||
/* Hack some long SRP names */
|
||||
#undef SRP_generate_server_master_secret
|
||||
#define SRP_generate_server_master_secret SRP_gen_server_master_secret
|
||||
#undef SRP_generate_client_master_secret
|
||||
#define SRP_generate_client_master_secret SRP_gen_client_master_secret
|
||||
|
||||
/* Hack some long UI names */
|
||||
#undef UI_method_get_prompt_constructor
|
||||
#define UI_method_get_prompt_constructor UI_method_get_prompt_constructr
|
||||
#undef UI_method_set_prompt_constructor
|
||||
#define UI_method_set_prompt_constructor UI_method_set_prompt_constructr
|
||||
|
||||
#endif /* defined OPENSSL_SYS_VMS */
|
||||
|
||||
|
||||
/* Case insensitive linking causes problems.... */
|
||||
#if defined(OPENSSL_SYS_VMS) || defined(OPENSSL_SYS_OS2)
|
||||
#undef ERR_load_CRYPTO_strings
|
||||
#define ERR_load_CRYPTO_strings ERR_load_CRYPTOlib_strings
|
||||
#undef OCSP_crlID_new
|
||||
#define OCSP_crlID_new OCSP_crlID2_new
|
||||
|
||||
#undef d2i_ECPARAMETERS
|
||||
#define d2i_ECPARAMETERS d2i_UC_ECPARAMETERS
|
||||
#undef i2d_ECPARAMETERS
|
||||
#define i2d_ECPARAMETERS i2d_UC_ECPARAMETERS
|
||||
#undef d2i_ECPKPARAMETERS
|
||||
#define d2i_ECPKPARAMETERS d2i_UC_ECPKPARAMETERS
|
||||
#undef i2d_ECPKPARAMETERS
|
||||
#define i2d_ECPKPARAMETERS i2d_UC_ECPKPARAMETERS
|
||||
|
||||
/* These functions do not seem to exist! However, I'm paranoid...
|
||||
Original command in x509v3.h:
|
||||
These functions are being redefined in another directory,
|
||||
and clash when the linker is case-insensitive, so let's
|
||||
hide them a little, by giving them an extra 'o' at the
|
||||
beginning of the name... */
|
||||
#undef X509v3_cleanup_extensions
|
||||
#define X509v3_cleanup_extensions oX509v3_cleanup_extensions
|
||||
#undef X509v3_add_extension
|
||||
#define X509v3_add_extension oX509v3_add_extension
|
||||
#undef X509v3_add_netscape_extensions
|
||||
#define X509v3_add_netscape_extensions oX509v3_add_netscape_extensions
|
||||
#undef X509v3_add_standard_extensions
|
||||
#define X509v3_add_standard_extensions oX509v3_add_standard_extensions
|
||||
|
||||
/* This one clashes with CMS_data_create */
|
||||
#undef cms_Data_create
|
||||
#define cms_Data_create priv_cms_Data_create
|
||||
|
||||
#endif
|
||||
|
||||
|
||||
#endif /* ! defined HEADER_VMS_IDHACKS_H */
|
||||
+1
-1
@@ -1,4 +1,4 @@
|
||||
AC_INIT([ccminer], [1.6.4-git])
|
||||
AC_INIT([ccminer], [1.6.5-git])
|
||||
|
||||
AC_PREREQ([2.59c])
|
||||
AC_CANONICAL_SYSTEM
|
||||
|
||||
+3
-3
@@ -159,7 +159,7 @@
|
||||
#define PACKAGE_NAME "ccminer"
|
||||
|
||||
/* Define to the full name and version of this package. */
|
||||
#define PACKAGE_STRING "ccminer 1.6.4-git"
|
||||
#define PACKAGE_STRING "ccminer 1.6.5-git"
|
||||
|
||||
/* Define to the one symbol short name of this package. */
|
||||
#define PACKAGE_TARNAME "ccminer"
|
||||
@@ -168,7 +168,7 @@
|
||||
#define PACKAGE_URL "http://github.com/tpruvot/ccminer"
|
||||
|
||||
/* Define to the version of this package. */
|
||||
#define PACKAGE_VERSION "1.6.4-git"
|
||||
#define PACKAGE_VERSION "1.6.5-git"
|
||||
|
||||
/* If using the C implementation of alloca, define if you know the
|
||||
direction of stack growth for your system; otherwise it will be
|
||||
@@ -182,7 +182,7 @@
|
||||
#define STDC_HEADERS 1
|
||||
|
||||
/* Version number of package */
|
||||
#define VERSION "1.6.4-git"
|
||||
#define VERSION "1.6.5-git"
|
||||
|
||||
/* Define curl_free() as free() if our version of curl lacks curl_free. */
|
||||
/* #undef curl_free */
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
#include <stdio.h>
|
||||
#include <memory.h>
|
||||
#include <string.h>
|
||||
#include <unistd.h>
|
||||
#include <map>
|
||||
|
||||
#ifndef _WIN32
|
||||
@@ -60,6 +61,7 @@ void cuda_devicenames()
|
||||
exit(1);
|
||||
}
|
||||
|
||||
GPU_N = min(MAX_GPUS, GPU_N);
|
||||
for (int i=0; i < GPU_N; i++)
|
||||
{
|
||||
cudaDeviceProp props;
|
||||
@@ -177,13 +179,20 @@ int cuda_gpu_clocks(struct cgpu_info *gpu)
|
||||
void cuda_reset_device(int thr_id, bool *init)
|
||||
{
|
||||
int dev_id = device_map[thr_id];
|
||||
for (int i=0; i < MAX_GPUS; i++) {
|
||||
if (device_map[i] == dev_id) {
|
||||
init[i] = false;
|
||||
cudaSetDevice(dev_id);
|
||||
if (init != NULL) {
|
||||
// with init array, its meant to be used in algo's scan code...
|
||||
for (int i=0; i < MAX_GPUS; i++) {
|
||||
if (device_map[i] == dev_id) {
|
||||
init[i] = false;
|
||||
}
|
||||
}
|
||||
// force exit from algo's scan loops/function
|
||||
restart_threads();
|
||||
cudaDeviceSynchronize();
|
||||
while (cudaStreamQuery(NULL) == cudaErrorNotReady)
|
||||
usleep(1000);
|
||||
}
|
||||
restart_threads();
|
||||
cudaDeviceSynchronize();
|
||||
cudaDeviceReset();
|
||||
}
|
||||
|
||||
|
||||
@@ -13,12 +13,14 @@ __constant__ uint32_t pTarget[8]; // 32 bytes
|
||||
// store MAX_GPUS device arrays of 8 nonces
|
||||
static uint32_t* h_resNonces[MAX_GPUS];
|
||||
static uint32_t* d_resNonces[MAX_GPUS];
|
||||
static bool init_done = false;
|
||||
|
||||
__host__
|
||||
void cuda_check_cpu_init(int thr_id, uint32_t threads)
|
||||
{
|
||||
CUDA_CALL_OR_RET(cudaMallocHost(&h_resNonces[thr_id], 32));
|
||||
CUDA_CALL_OR_RET(cudaMalloc(&d_resNonces[thr_id], 32));
|
||||
init_done = true;
|
||||
}
|
||||
|
||||
// Target Difficulty
|
||||
@@ -97,6 +99,11 @@ uint32_t cuda_check_hash(int thr_id, uint32_t threads, uint32_t startNounce, uin
|
||||
dim3 grid((threads + threadsperblock - 1) / threadsperblock);
|
||||
dim3 block(threadsperblock);
|
||||
|
||||
if (!init_done) {
|
||||
applog(LOG_ERR, "missing call to cuda_check_cpu_init");
|
||||
return UINT32_MAX;
|
||||
}
|
||||
|
||||
cuda_checkhash_64 <<<grid, block>>> (threads, startNounce, d_inputHash, d_resNonces[thr_id]);
|
||||
cudaThreadSynchronize();
|
||||
|
||||
@@ -130,6 +137,11 @@ uint32_t cuda_check_hash_suppl(int thr_id, uint32_t threads, uint32_t startNounc
|
||||
dim3 grid((threads + threadsperblock - 1) / threadsperblock);
|
||||
dim3 block(threadsperblock);
|
||||
|
||||
if (!init_done) {
|
||||
applog(LOG_ERR, "missing call to cuda_check_cpu_init");
|
||||
return 0;
|
||||
}
|
||||
|
||||
// first element stores the count of found nonces
|
||||
cudaMemset(d_resNonces[thr_id], 0, sizeof(uint32_t));
|
||||
|
||||
@@ -180,6 +192,12 @@ uint32_t cuda_check_hash_branch(int thr_id, uint32_t threads, uint32_t startNoun
|
||||
const uint32_t threadsperblock = 256;
|
||||
|
||||
uint32_t result = UINT32_MAX;
|
||||
|
||||
if (!init_done) {
|
||||
applog(LOG_ERR, "missing call to cuda_check_cpu_init");
|
||||
return UINT32_MAX;
|
||||
}
|
||||
|
||||
cudaMemset(d_resNonces[thr_id], 0xff, sizeof(uint32_t));
|
||||
|
||||
dim3 grid((threads + threadsperblock-1)/threadsperblock);
|
||||
|
||||
+35
-15
@@ -148,6 +148,13 @@ __device__ __forceinline__ uint64_t cuda_swab64(uint64_t x)
|
||||
(((uint64_t)(x) & 0x00000000000000ffULL) << 56)))
|
||||
#endif
|
||||
|
||||
// swap two uint32_t without extra registers
|
||||
__device__ __host__ __forceinline__ void xchg(uint32_t &x, uint32_t &y) {
|
||||
x ^= y; y = x ^ y; x ^= y;
|
||||
}
|
||||
// for other types...
|
||||
#define XCHG(x, y) { x ^= y; y = x ^ y; x ^= y; }
|
||||
|
||||
/*********************************************************************/
|
||||
// Macros to catch CUDA errors in CUDA runtime calls
|
||||
|
||||
@@ -480,7 +487,7 @@ uint64_t SWAPDWORDS(uint64_t value)
|
||||
#endif
|
||||
}
|
||||
|
||||
/* lyra2 - int2 operators */
|
||||
/* lyra2/bmw - uint2 vector's operators */
|
||||
|
||||
__device__ __forceinline__
|
||||
void LOHI(uint32_t &lo, uint32_t &hi, uint64_t x) {
|
||||
@@ -488,27 +495,41 @@ void LOHI(uint32_t &lo, uint32_t &hi, uint64_t x) {
|
||||
asm("mov.b64 {%0,%1},%2; \n\t"
|
||||
: "=r"(lo), "=r"(hi) : "l"(x));
|
||||
#else
|
||||
lo = _LODWORD(x);
|
||||
hi = _HIDWORD(x);
|
||||
lo = (uint32_t)(x);
|
||||
hi = (uint32_t)(x >> 32);
|
||||
#endif
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ uint2 vectorize(uint64_t v) {
|
||||
static __host__ __device__ __forceinline__ uint2 vectorize(uint64_t v) {
|
||||
uint2 result;
|
||||
LOHI(result.x, result.y, v);
|
||||
#ifdef __CUDA_ARCH__
|
||||
asm("mov.b64 {%0,%1},%2; \n\t"
|
||||
: "=r"(result.x), "=r"(result.y) : "l"(v));
|
||||
#else
|
||||
result.x = (uint32_t)(v);
|
||||
result.y = (uint32_t)(v >> 32);
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ uint64_t devectorize(uint2 v) { return MAKE_ULONGLONG(v.x, v.y); }
|
||||
static __host__ __device__ __forceinline__ uint64_t devectorize(uint2 v) {
|
||||
#ifdef __CUDA_ARCH__
|
||||
return MAKE_ULONGLONG(v.x, v.y);
|
||||
#else
|
||||
return (((uint64_t)v.y) << 32) + v.x;
|
||||
#endif
|
||||
}
|
||||
|
||||
/**
|
||||
* uint2 direct ops by c++ operator definitions
|
||||
*/
|
||||
static __device__ __forceinline__ uint2 operator^ (uint2 a, uint2 b) { return make_uint2(a.x ^ b.x, a.y ^ b.y); }
|
||||
static __device__ __forceinline__ uint2 operator& (uint2 a, uint2 b) { return make_uint2(a.x & b.x, a.y & b.y); }
|
||||
static __device__ __forceinline__ uint2 operator| (uint2 a, uint2 b) { return make_uint2(a.x | b.x, a.y | b.y); }
|
||||
static __device__ __forceinline__ uint2 operator~ (uint2 a) { return make_uint2(~a.x, ~a.y); }
|
||||
static __device__ __forceinline__ void operator^= (uint2 &a, uint2 b) { a = a ^ b; }
|
||||
|
||||
static __device__ __forceinline__ uint2 operator+ (uint2 a, uint2 b)
|
||||
{
|
||||
static __device__ __forceinline__ uint2 operator+ (uint2 a, uint2 b) {
|
||||
#ifdef __CUDA_ARCH__
|
||||
uint2 result;
|
||||
asm("{\n\t"
|
||||
@@ -518,15 +539,14 @@ static __device__ __forceinline__ uint2 operator+ (uint2 a, uint2 b)
|
||||
: "=r"(result.x), "=r"(result.y) : "r"(a.x), "r"(a.y), "r"(b.x), "r"(b.y));
|
||||
return result;
|
||||
#else
|
||||
// incorrect but unused host equiv
|
||||
return make_uint2(a.x + b.x, a.y + b.y);
|
||||
return vectorize(devectorize(a) + devectorize(b));
|
||||
#endif
|
||||
}
|
||||
static __device__ __forceinline__ void operator+= (uint2 &a, uint2 b) { a = a + b; }
|
||||
|
||||
static __device__ __forceinline__ uint2 operator- (uint2 a, uint2 b)
|
||||
{
|
||||
#ifdef __CUDA_ARCH__
|
||||
|
||||
static __device__ __forceinline__ uint2 operator- (uint2 a, uint2 b) {
|
||||
#if defined(__CUDA_ARCH__) && CUDA_VERSION < 7000
|
||||
uint2 result;
|
||||
asm("{\n\t"
|
||||
"sub.cc.u32 %0,%2,%4; \n\t"
|
||||
@@ -535,10 +555,10 @@ static __device__ __forceinline__ uint2 operator- (uint2 a, uint2 b)
|
||||
: "=r"(result.x), "=r"(result.y) : "r"(a.x), "r"(a.y), "r"(b.x), "r"(b.y));
|
||||
return result;
|
||||
#else
|
||||
// incorrect but unused host equiv
|
||||
return make_uint2(a.x - b.x, a.y - b.y);
|
||||
return vectorize(devectorize(a) - devectorize(b));
|
||||
#endif
|
||||
}
|
||||
static __device__ __forceinline__ void operator-= (uint2 &a, uint2 b) { a = a - b; }
|
||||
|
||||
/**
|
||||
* basic multiplication between 64bit no carry outside that range (ie mul.lo.b64(a*b))
|
||||
|
||||
@@ -2,7 +2,6 @@
|
||||
#include <stdint.h>
|
||||
#include <cuda_runtime.h>
|
||||
|
||||
#include "uint256.h"
|
||||
#include "sph/sph_fugue.h"
|
||||
|
||||
#include "miner.h"
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
#include <cuda_runtime.h>
|
||||
#include <openssl/sha.h>
|
||||
|
||||
#include "uint256.h"
|
||||
#include "sph/sph_groestl.h"
|
||||
#include "cuda_groestlcoin.h"
|
||||
|
||||
|
||||
+7
-1
@@ -18,13 +18,17 @@
|
||||
|
||||
/* from miner.h
|
||||
struct hashlog_data {
|
||||
uint32_t tm_sent;
|
||||
uint8_t npool;
|
||||
uint8_t pool_type;
|
||||
uint32_t height;
|
||||
uint32_t njobid;
|
||||
uint32_t nonce;
|
||||
uint32_t scanned_from;
|
||||
uint32_t scanned_to;
|
||||
uint32_t last_from;
|
||||
uint32_t tm_add;
|
||||
uint32_t tm_upd;
|
||||
uint32_t tm_sent;
|
||||
};
|
||||
*/
|
||||
|
||||
@@ -75,6 +79,8 @@ void hashlog_remember_submit(struct work* work, uint32_t nonce)
|
||||
data.height = work->height;
|
||||
data.njobid = (uint32_t) njobid;
|
||||
data.tm_add = data.tm_upd = data.tm_sent = (uint32_t) time(NULL);
|
||||
data.npool = (uint8_t) cur_pooln;
|
||||
data.pool_type = pools[cur_pooln].type;
|
||||
tlastshares[key] = data;
|
||||
}
|
||||
|
||||
|
||||
@@ -89,6 +89,9 @@ static void round_lyra(uint2 *s)
|
||||
__device__ __forceinline__
|
||||
void reduceDuplexRowSetup(const int rowIn, const int rowInOut, const int rowOut, uint2 state[16], uint2 Matrix[96][8])
|
||||
{
|
||||
#if __CUDA_ARCH__ > 500
|
||||
#pragma unroll
|
||||
#endif
|
||||
for (int i = 0; i < 8; i++)
|
||||
{
|
||||
#pragma unroll
|
||||
|
||||
@@ -258,6 +258,8 @@ void sha256d(unsigned char *hash, const unsigned char *data, int len);
|
||||
#define HAVE_SHA256_4WAY 0
|
||||
#define HAVE_SHA256_8WAY 0
|
||||
|
||||
struct work;
|
||||
|
||||
extern int scanhash_sha256d(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce, unsigned long *hashes_done);
|
||||
|
||||
@@ -265,7 +267,7 @@ extern int scanhash_deep(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done);
|
||||
|
||||
extern int scanhash_doom(int thr_id, uint32_t *pdata,
|
||||
extern int scanhash_luffa(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done);
|
||||
|
||||
@@ -301,10 +303,16 @@ extern int scanhash_anime(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done);
|
||||
|
||||
extern int scanhash_bitcoin(int thr_id, uint32_t *pdata,
|
||||
uint32_t *ptarget, uint32_t max_nonce, unsigned long *hashes_done);
|
||||
|
||||
extern int scanhash_blake256(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done, int8_t blakerounds);
|
||||
|
||||
extern int scanhash_credits(int thr_id, uint32_t *pdata, const uint32_t *ptarget,
|
||||
const uint32_t *midstate, uint32_t max_nonce, unsigned long *hashes_done);
|
||||
|
||||
extern int scanhash_fresh(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done);
|
||||
@@ -372,8 +380,7 @@ extern int scanhash_x17(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done);
|
||||
|
||||
extern int scanhash_zr5(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
extern int scanhash_zr5(int thr_id, struct work *work, uint32_t max_nonce,
|
||||
unsigned long *hashes_done);
|
||||
|
||||
/* api related */
|
||||
@@ -423,16 +430,25 @@ struct stats_data {
|
||||
uint32_t tm_stat;
|
||||
uint32_t hashcount;
|
||||
uint32_t height;
|
||||
|
||||
double difficulty;
|
||||
double hashrate;
|
||||
|
||||
uint8_t thr_id;
|
||||
uint8_t gpu_id;
|
||||
uint8_t hashfound;
|
||||
uint8_t ignored;
|
||||
|
||||
uint8_t npool;
|
||||
uint8_t pool_type;
|
||||
uint16_t align;
|
||||
};
|
||||
|
||||
struct hashlog_data {
|
||||
uint32_t tm_sent;
|
||||
uint8_t npool;
|
||||
uint8_t pool_type;
|
||||
uint16_t align;
|
||||
|
||||
uint32_t height;
|
||||
uint32_t njobid;
|
||||
uint32_t nonce;
|
||||
@@ -441,6 +457,7 @@ struct hashlog_data {
|
||||
uint32_t last_from;
|
||||
uint32_t tm_add;
|
||||
uint32_t tm_upd;
|
||||
uint32_t tm_sent;
|
||||
};
|
||||
|
||||
/* end of api */
|
||||
@@ -458,6 +475,18 @@ struct work_restart {
|
||||
char padding[128 - sizeof(uint32_t)];
|
||||
};
|
||||
|
||||
#ifdef HAVE_GETOPT_LONG
|
||||
#include <getopt.h>
|
||||
#else
|
||||
struct option {
|
||||
const char *name;
|
||||
int has_arg;
|
||||
int *flag;
|
||||
int val;
|
||||
};
|
||||
#endif
|
||||
extern int options_count();
|
||||
|
||||
extern bool opt_benchmark;
|
||||
extern bool opt_debug;
|
||||
extern bool opt_quiet;
|
||||
@@ -475,11 +504,13 @@ extern char *opt_proxy;
|
||||
extern long opt_proxy_type;
|
||||
extern bool use_syslog;
|
||||
extern bool use_colors;
|
||||
extern int use_pok;
|
||||
extern pthread_mutex_t applog_lock;
|
||||
extern struct thr_info *thr_info;
|
||||
extern int longpoll_thr_id;
|
||||
extern int stratum_thr_id;
|
||||
extern int api_thr_id;
|
||||
extern volatile bool abort_flag;
|
||||
extern struct work_restart *work_restart;
|
||||
extern bool opt_trust_pool;
|
||||
extern uint16_t opt_vote;
|
||||
@@ -529,8 +560,6 @@ extern uint32_t gpus_intensity[MAX_GPUS];
|
||||
extern void format_hashrate(double hashrate, char *output);
|
||||
extern void applog(int prio, const char *fmt, ...);
|
||||
void get_defconfig_path(char *out, size_t bufsize, char *argv0);
|
||||
extern json_t *json_rpc_call(CURL *curl, const char *url, const char *userpass,
|
||||
const char *rpc_req, bool, bool, int *);
|
||||
extern void cbin2hex(char *out, const char *in, size_t len);
|
||||
extern char *bin2hex(const unsigned char *in, size_t len);
|
||||
extern bool hex2bin(unsigned char *p, const char *hexstr, size_t len);
|
||||
@@ -541,6 +570,10 @@ extern void diff_to_target(uint32_t *target, double diff);
|
||||
extern void get_currentalgo(char* buf, int sz);
|
||||
extern uint32_t device_intensity(int thr_id, const char *func, uint32_t defcount);
|
||||
|
||||
// bignum
|
||||
double bn_convert_nbits(const uint32_t nbits);
|
||||
void bn_nbits_to_uchar(const uint32_t nBits, uchar *target);
|
||||
|
||||
struct stratum_job {
|
||||
char *job_id;
|
||||
unsigned char prevhash[32];
|
||||
@@ -567,7 +600,6 @@ struct stratum_ctx {
|
||||
curl_socket_t sock;
|
||||
size_t sockbuf_size;
|
||||
char *sockbuf;
|
||||
pthread_mutex_t sock_lock;
|
||||
|
||||
double next_diff;
|
||||
|
||||
@@ -576,18 +608,25 @@ struct stratum_ctx {
|
||||
unsigned char *xnonce1;
|
||||
size_t xnonce2_size;
|
||||
struct stratum_job job;
|
||||
pthread_mutex_t work_lock;
|
||||
|
||||
struct timeval tv_submit;
|
||||
uint32_t answer_msec;
|
||||
uint32_t disconnects;
|
||||
int pooln;
|
||||
time_t tm_connected;
|
||||
|
||||
int srvtime_diff;
|
||||
};
|
||||
|
||||
#define POK_MAX_TXS 4
|
||||
#define POK_MAX_TX_SZ 16384U
|
||||
struct tx {
|
||||
uint8_t data[POK_MAX_TX_SZ];
|
||||
uint32_t len;
|
||||
};
|
||||
|
||||
struct work {
|
||||
uint32_t data[32];
|
||||
uint32_t data[48]; /* 168 bytes req */
|
||||
uint32_t midstate[8];
|
||||
uint32_t target[8];
|
||||
uint32_t maxvote;
|
||||
|
||||
@@ -602,11 +641,79 @@ struct work {
|
||||
|
||||
double difficulty;
|
||||
uint32_t height;
|
||||
uint8_t pooln;
|
||||
|
||||
uint32_t scanned_from;
|
||||
uint32_t scanned_to;
|
||||
|
||||
/* pok getwork txs */
|
||||
uint32_t tx_count;
|
||||
struct tx txs[POK_MAX_TXS];
|
||||
};
|
||||
|
||||
#define POK_BOOL_MASK 0x00008000
|
||||
#define POK_DATA_MASK 0xFFFF0000
|
||||
|
||||
|
||||
#define MAX_POOLS 8
|
||||
struct pool_infos {
|
||||
uint8_t id;
|
||||
#define POOL_UNUSED 0
|
||||
#define POOL_GETWORK 1
|
||||
#define POOL_STRATUM 2
|
||||
#define POOL_LONGPOLL 4
|
||||
uint8_t type;
|
||||
#define POOL_ST_DEFINED 1
|
||||
#define POOL_ST_VALID 2
|
||||
#define POOL_ST_DISABLED 4
|
||||
#define POOL_ST_REMOVED 8
|
||||
uint16_t status;
|
||||
char name[64];
|
||||
// credentials
|
||||
char url[256];
|
||||
char short_url[64];
|
||||
char user[64];
|
||||
char pass[128];
|
||||
// config options
|
||||
double max_diff;
|
||||
double max_rate;
|
||||
int time_limit;
|
||||
int scantime;
|
||||
// connection
|
||||
struct stratum_ctx stratum;
|
||||
uint8_t allow_gbt;
|
||||
uint8_t allow_mininginfo;
|
||||
uint16_t check_dups; // 16_t for align
|
||||
int retries;
|
||||
int fail_pause;
|
||||
int timeout;
|
||||
// stats
|
||||
uint32_t work_time;
|
||||
uint32_t wait_time;
|
||||
uint32_t accepted_count;
|
||||
uint32_t rejected_count;
|
||||
uint32_t disconnects;
|
||||
};
|
||||
|
||||
extern struct pool_infos pools[MAX_POOLS];
|
||||
extern int num_pools;
|
||||
extern volatile int cur_pooln;
|
||||
|
||||
void pool_init_defaults(void);
|
||||
void pool_set_creds(int pooln);
|
||||
void pool_set_attr(int pooln, const char* key, char* arg);
|
||||
bool pool_switch_url(char *params);
|
||||
bool pool_switch(int pooln);
|
||||
bool pool_switch_next(void);
|
||||
int pool_get_first_valid(int startfrom);
|
||||
bool parse_pool_array(json_t *obj);
|
||||
void pool_dump_infos(void);
|
||||
|
||||
json_t * json_rpc_call_pool(CURL *curl, struct pool_infos*,
|
||||
const char *req, bool lp_scan, bool lp, int *err);
|
||||
json_t * json_rpc_longpoll(CURL *curl, char *lp_url, struct pool_infos*,
|
||||
const char *req, int *err);
|
||||
|
||||
bool stratum_socket_full(struct stratum_ctx *sctx, int timeout);
|
||||
bool stratum_send_line(struct stratum_ctx *sctx, char *s);
|
||||
char *stratum_recv_line(struct stratum_ctx *sctx);
|
||||
@@ -615,6 +722,7 @@ void stratum_disconnect(struct stratum_ctx *sctx);
|
||||
bool stratum_subscribe(struct stratum_ctx *sctx);
|
||||
bool stratum_authorize(struct stratum_ctx *sctx, const char *user, const char *pass);
|
||||
bool stratum_handle_method(struct stratum_ctx *sctx, const char *s);
|
||||
void stratum_free_job(struct stratum_ctx *sctx);
|
||||
|
||||
void hashlog_remember_submit(struct work* work, uint32_t nonce);
|
||||
void hashlog_remember_scan_range(struct work* work);
|
||||
@@ -666,9 +774,11 @@ void applog_compare_hash(unsigned char *hash, unsigned char *hash2);
|
||||
|
||||
void print_hash_tests(void);
|
||||
void animehash(void *state, const void *input);
|
||||
void bitcoin_hash(uint32_t *output, const uint32_t *data, uint32_t nonce, const uint32_t *midstate);
|
||||
void blake256hash(void *output, const void *input, int8_t rounds);
|
||||
void creditshash(void *state, const void *input);
|
||||
void deephash(void *state, const void *input);
|
||||
void doomhash(void *state, const void *input);
|
||||
void luffa_hash(void *state, const void *input);
|
||||
void fresh_hash(void *state, const void *input);
|
||||
void fugue256_hash(unsigned char* output, const unsigned char* input, int len);
|
||||
void heavycoin_hash(unsigned char* output, const unsigned char* input, int len);
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
#include <cuda_runtime.h>
|
||||
#include <openssl/sha.h>
|
||||
|
||||
#include "uint256.h"
|
||||
#include "sph/sph_groestl.h"
|
||||
|
||||
#include "miner.h"
|
||||
|
||||
@@ -18,6 +18,7 @@
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <unistd.h>
|
||||
|
||||
#include "miner.h"
|
||||
#include "nvml.h"
|
||||
@@ -33,6 +34,11 @@ extern char driver_version[32];
|
||||
|
||||
static uint32_t device_bus_ids[MAX_GPUS] = { 0 };
|
||||
|
||||
extern uint32_t device_gpu_clocks[MAX_GPUS];
|
||||
extern uint32_t device_mem_clocks[MAX_GPUS];
|
||||
|
||||
uint8_t gpu_clocks_changed[MAX_GPUS] = { 0 };
|
||||
|
||||
/*
|
||||
* Wrappers to emulate dlopen() on other systems like Windows
|
||||
*/
|
||||
@@ -127,6 +133,17 @@ nvml_handle * nvml_create()
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetApplicationsClock");
|
||||
nvmlh->nvmlDeviceSetApplicationsClocks = (nvmlReturn_t (*)(nvmlDevice_t, unsigned int mem, unsigned int gpu))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceSetApplicationsClocks");
|
||||
nvmlh->nvmlDeviceResetApplicationsClocks = (nvmlReturn_t (*)(nvmlDevice_t))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceResetApplicationsClocks");
|
||||
nvmlh->nvmlDeviceGetSupportedGraphicsClocks = (nvmlReturn_t (*)(nvmlDevice_t, uint32_t mem, uint32_t *num, uint32_t *))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetSupportedGraphicsClocks");
|
||||
nvmlh->nvmlDeviceGetSupportedMemoryClocks = (nvmlReturn_t (*)(nvmlDevice_t, unsigned int *count, unsigned int *clocksMHz))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetSupportedMemoryClocks");
|
||||
/* NVML_ERROR_NOT_SUPPORTED
|
||||
nvmlh->nvmlDeviceGetAutoBoostedClocksEnabled = (nvmlReturn_t (*)(nvmlDevice_t, nvmlEnableState_t *isEnabled, nvmlEnableState_t *defaultIsEnabled))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetAutoBoostedClocksEnabled");
|
||||
nvmlh->nvmlDeviceSetAutoBoostedClocksEnabled = (nvmlReturn_t (*)(nvmlDevice_t, nvmlEnableState_t enabled))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceSetAutoBoostedClocksEnabled"); */
|
||||
nvmlh->nvmlDeviceGetClockInfo = (nvmlReturn_t (*)(nvmlDevice_t, nvmlClockType_t, unsigned int *clock))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetClockInfo");
|
||||
nvmlh->nvmlDeviceGetPciInfo = (nvmlReturn_t (*)(nvmlDevice_t, nvmlPciInfo_t *))
|
||||
@@ -138,7 +155,7 @@ nvml_handle * nvml_create()
|
||||
nvmlh->nvmlDeviceGetFanSpeed = (nvmlReturn_t (*)(nvmlDevice_t, unsigned int *))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetFanSpeed");
|
||||
nvmlh->nvmlDeviceGetPerformanceState = (nvmlReturn_t (*)(nvmlDevice_t, int *))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetPowerUsage");
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetPerformanceState"); /* or nvmlDeviceGetPowerState */
|
||||
nvmlh->nvmlDeviceGetSerial = (nvmlReturn_t (*)(nvmlDevice_t, char *, unsigned int))
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlDeviceGetSerial");
|
||||
nvmlh->nvmlDeviceGetUUID = (nvmlReturn_t (*)(nvmlDevice_t, char *, unsigned int))
|
||||
@@ -152,6 +169,14 @@ nvml_handle * nvml_create()
|
||||
nvmlh->nvmlShutdown = (nvmlReturn_t (*)())
|
||||
wrap_dlsym(nvmlh->nvml_dll, "nvmlShutdown");
|
||||
|
||||
/*
|
||||
nvmlDeviceGetBrand(nvmlDevice_t device, nvmlBrandType_t *type)
|
||||
nvmlDeviceGetMaxPcieLinkWidth(nvmlDevice_t device, unsigned int *maxLinkWidth)
|
||||
nvmlDeviceGetMaxPcieLinkGeneration(nvmlDevice_t device, unsigned int *maxLinkGen)
|
||||
nvmlDeviceGetCurrPcieLinkWidth(nvmlDevice_t device, unsigned int *currLinkWidth)
|
||||
nvmlDeviceGetCurrPcieLinkGeneration(nvmlDevice_t device, unsigned int *currLinkGen)
|
||||
*/
|
||||
|
||||
if (nvmlh->nvmlInit == NULL ||
|
||||
nvmlh->nvmlShutdown == NULL ||
|
||||
nvmlh->nvmlErrorString == NULL ||
|
||||
@@ -218,21 +243,6 @@ nvml_handle * nvml_create()
|
||||
if (nvmlh->nvmlDeviceGetAPIRestriction) {
|
||||
nvmlh->nvmlDeviceGetAPIRestriction(nvmlh->devs[i], NVML_RESTRICTED_API_SET_APPLICATION_CLOCKS,
|
||||
&nvmlh->app_clocks[i]);
|
||||
if (nvmlh->app_clocks[i] == NVML_FEATURE_ENABLED && opt_debug) {
|
||||
applog(LOG_DEBUG, "NVML application clock feature is allowed");
|
||||
#if 0
|
||||
uint32_t mem;
|
||||
nvmlReturn_t rc;
|
||||
rc = nvmlh->nvmlDeviceGetDefaultApplicationsClock(nvmlh->devs[i], NVML_CLOCK_MEM, &mem);
|
||||
if (rc == NVML_SUCCESS)
|
||||
applog(LOG_DEBUG, "nvmlDeviceGetDefaultApplicationsClock: mem %u", mem);
|
||||
else
|
||||
applog(LOG_DEBUG, "nvmlDeviceGetDefaultApplicationsClock: %s", nvmlh->nvmlErrorString(rc));
|
||||
rc = nvmlh->nvmlDeviceSetApplicationsClocks(nvmlh->devs[i], mem, 1228000);
|
||||
if (rc != NVML_SUCCESS)
|
||||
applog(LOG_DEBUG, "nvmlDeviceSetApplicationsClocks: %s", nvmlh->nvmlErrorString(rc));
|
||||
#endif
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -251,7 +261,7 @@ nvml_handle * nvml_create()
|
||||
(nvmlh->nvml_pci_bus_id[j] == (uint32_t) props.pciBusID) &&
|
||||
(nvmlh->nvml_pci_device_id[j] == (uint32_t) props.pciDeviceID)) {
|
||||
if (opt_debug)
|
||||
applog(LOG_DEBUG, "CUDA GPU#%d matches NVML GPU %d by busId %u",
|
||||
applog(LOG_DEBUG, "CUDA GPU %d matches NVML GPU %d by busId %u",
|
||||
i, j, (uint32_t) props.pciBusID);
|
||||
nvmlh->nvml_cuda_device_id[j] = i;
|
||||
nvmlh->cuda_nvml_device_id[i] = j;
|
||||
@@ -263,6 +273,99 @@ nvml_handle * nvml_create()
|
||||
return nvmlh;
|
||||
}
|
||||
|
||||
/* apply config clocks to an used device */
|
||||
int nvml_set_clocks(nvml_handle *nvmlh, int dev_id)
|
||||
{
|
||||
nvmlReturn_t rc;
|
||||
uint32_t gpu_clk = 0, mem_clk = 0;
|
||||
int n = nvmlh->cuda_nvml_device_id[dev_id];
|
||||
if (n < 0 || n >= nvmlh->nvml_gpucount)
|
||||
return -1;
|
||||
|
||||
// prevent double operations on the same gpu... to enhance
|
||||
if (gpu_clocks_changed[dev_id])
|
||||
return 0;
|
||||
|
||||
if (!device_gpu_clocks[dev_id] && !device_mem_clocks[dev_id])
|
||||
return 0; // nothing to do
|
||||
|
||||
if (nvmlh->app_clocks[n] != NVML_FEATURE_ENABLED) {
|
||||
applog(LOG_WARNING, "GPU #%d: NVML application clock feature is not allowed!", dev_id);
|
||||
return -1;
|
||||
}
|
||||
|
||||
nvmlh->nvmlDeviceGetDefaultApplicationsClock(nvmlh->devs[n], NVML_CLOCK_MEM, &mem_clk);
|
||||
rc = nvmlh->nvmlDeviceGetDefaultApplicationsClock(nvmlh->devs[n], NVML_CLOCK_GRAPHICS, &gpu_clk);
|
||||
if (rc != NVML_SUCCESS) {
|
||||
applog(LOG_WARNING, "GPU #%d: unable to query application clocks", dev_id);
|
||||
return -1;
|
||||
}
|
||||
|
||||
if (opt_debug)
|
||||
applog(LOG_DEBUG, "GPU #%d: default clocks are %u/%u", dev_id, mem_clk, gpu_clk);
|
||||
|
||||
// get application config values
|
||||
if (device_mem_clocks[dev_id]) mem_clk = device_mem_clocks[dev_id];
|
||||
if (device_gpu_clocks[dev_id]) gpu_clk = device_gpu_clocks[dev_id];
|
||||
|
||||
// these functions works for the 960 and the 970 (346.72+), not for the 750 Ti
|
||||
uint32_t nclocks = 0, clocks[128] = { 0 };
|
||||
nvmlh->nvmlDeviceGetSupportedMemoryClocks(nvmlh->devs[n], &nclocks, NULL);
|
||||
nclocks = min(nclocks, 128);
|
||||
nvmlh->nvmlDeviceGetSupportedMemoryClocks(nvmlh->devs[n], &nclocks, clocks);
|
||||
for (uint8_t u=0; u < nclocks; u++) {
|
||||
// ordered desc, so get first
|
||||
if (clocks[u] <= mem_clk) {
|
||||
mem_clk = clocks[u];
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
nclocks = 0;
|
||||
nvmlh->nvmlDeviceGetSupportedGraphicsClocks(nvmlh->devs[n], mem_clk, &nclocks, NULL);
|
||||
nclocks = min(nclocks, 128);
|
||||
nvmlh->nvmlDeviceGetSupportedGraphicsClocks(nvmlh->devs[n], mem_clk, &nclocks, clocks);
|
||||
for (uint8_t u=0; u < nclocks; u++) {
|
||||
// ordered desc, so get first
|
||||
if (clocks[u] <= gpu_clk) {
|
||||
gpu_clk = clocks[u];
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
rc = nvmlh->nvmlDeviceSetApplicationsClocks(nvmlh->devs[n], mem_clk, gpu_clk);
|
||||
if (rc == NVML_SUCCESS)
|
||||
applog(LOG_INFO, "GPU #%d: application clocks set to %u/%u", dev_id, mem_clk, gpu_clk);
|
||||
else {
|
||||
applog(LOG_ERR, "GPU #%d: %u/%u - %s", dev_id, mem_clk, gpu_clk, nvmlh->nvmlErrorString(rc));
|
||||
return -1;
|
||||
}
|
||||
|
||||
gpu_clocks_changed[dev_id] = 1;
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* reset default app clocks to an used device */
|
||||
int nvml_reset_clocks(nvml_handle *nvmlh, int dev_id)
|
||||
{
|
||||
nvmlReturn_t rc;
|
||||
uint32_t gpu_clk = 0, mem_clk = 0;
|
||||
int n = nvmlh->cuda_nvml_device_id[dev_id];
|
||||
if (n < 0 || n >= nvmlh->nvml_gpucount)
|
||||
return -1;
|
||||
|
||||
if (!gpu_clocks_changed[dev_id])
|
||||
return 0; // nothing to do
|
||||
|
||||
rc = nvmlh->nvmlDeviceResetApplicationsClocks(nvmlh->devs[n]);
|
||||
if (rc != NVML_SUCCESS) {
|
||||
applog(LOG_WARNING, "GPU #%d: unable to reset application clocks", dev_id);
|
||||
return -1;
|
||||
}
|
||||
gpu_clocks_changed[dev_id] = 0;
|
||||
return 1;
|
||||
}
|
||||
|
||||
int nvml_get_gpucount(nvml_handle *nvmlh, int *gpucount)
|
||||
{
|
||||
*gpucount = nvmlh->nvml_gpucount;
|
||||
|
||||
@@ -94,6 +94,11 @@ typedef struct {
|
||||
nvmlReturn_t (*nvmlDeviceGetDefaultApplicationsClock)(nvmlDevice_t, nvmlClockType_t, unsigned int *);
|
||||
nvmlReturn_t (*nvmlDeviceGetApplicationsClock)(nvmlDevice_t, nvmlClockType_t, unsigned int *);
|
||||
nvmlReturn_t (*nvmlDeviceSetApplicationsClocks)(nvmlDevice_t, unsigned int, unsigned int);
|
||||
nvmlReturn_t (*nvmlDeviceResetApplicationsClocks)(nvmlDevice_t);
|
||||
nvmlReturn_t (*nvmlDeviceGetSupportedGraphicsClocks)(nvmlDevice_t, uint32_t mem, uint32_t *num, uint32_t *arr);
|
||||
nvmlReturn_t (*nvmlDeviceGetSupportedMemoryClocks)(nvmlDevice_t, unsigned int *count, unsigned int *clocksMHz);
|
||||
nvmlReturn_t (*nvmlDeviceGetAutoBoostedClocksEnabled)(nvmlDevice_t, nvmlEnableState_t *isEnabled, nvmlEnableState_t *defaultIsEnabled);
|
||||
nvmlReturn_t (*nvmlDeviceSetAutoBoostedClocksEnabled)(nvmlDevice_t, nvmlEnableState_t enabled);
|
||||
nvmlReturn_t (*nvmlDeviceGetClockInfo)(nvmlDevice_t, nvmlClockType_t, unsigned int *);
|
||||
nvmlReturn_t (*nvmlDeviceGetPciInfo)(nvmlDevice_t, nvmlPciInfo_t *);
|
||||
nvmlReturn_t (*nvmlDeviceGetName)(nvmlDevice_t, char *, int);
|
||||
@@ -156,6 +161,9 @@ int nvml_get_power_usage(nvml_handle *nvmlh,
|
||||
int gpuindex,
|
||||
unsigned int *milliwatts);
|
||||
|
||||
int nvml_set_clocks(nvml_handle *nvmlh, int dev_id);
|
||||
int nvml_reset_clocks(nvml_handle *nvmlh, int dev_id);
|
||||
|
||||
/* api functions */
|
||||
|
||||
unsigned int gpu_fanpercent(struct cgpu_info *gpu);
|
||||
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_note": "Sample rotation of 2 pools",
|
||||
|
||||
"pools":[{
|
||||
"name": "Longpoll sample",
|
||||
"url": "http://ziftr.suprnova.cc:9991",
|
||||
"user": "tpruvot.win",
|
||||
"pass": "x",
|
||||
"max-diff": 0.0,
|
||||
"scantime": 40,
|
||||
"time-limit": 180,
|
||||
"disabled": false
|
||||
},
|
||||
{
|
||||
"name": "Stratum sample",
|
||||
"url": "stratum+tcp://zrc-stratum.suprnova.cc:2257",
|
||||
"user": "tpruvot.elite",
|
||||
"pass": "x",
|
||||
"time-limit": 300
|
||||
}],
|
||||
|
||||
"algo" : "zr5",
|
||||
|
||||
"api-bind" : "0.0.0.0",
|
||||
"api-remote" : true,
|
||||
|
||||
"no-gbt": true
|
||||
}
|
||||
@@ -0,0 +1,357 @@
|
||||
/**
|
||||
* Functions which handle multiple pools data
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <unistd.h>
|
||||
|
||||
#include "miner.h"
|
||||
#include "compat.h"
|
||||
|
||||
// to move in miner.h
|
||||
extern bool allow_gbt;
|
||||
extern bool allow_mininginfo;
|
||||
extern bool check_dups;
|
||||
|
||||
extern double opt_max_diff;
|
||||
extern double opt_max_rate;
|
||||
extern int opt_scantime;
|
||||
extern int opt_time_limit;
|
||||
|
||||
extern char* rpc_url;
|
||||
extern char* rpc_user;
|
||||
extern char* rpc_pass;
|
||||
extern char* short_url;
|
||||
|
||||
extern struct work _ALIGN(64) g_work;
|
||||
extern struct stratum_ctx stratum;
|
||||
extern pthread_mutex_t stratum_work_lock;
|
||||
extern bool get_work(struct thr_info *thr, struct work *work);
|
||||
extern bool stratum_need_reset;
|
||||
extern time_t firstwork_time;
|
||||
|
||||
extern volatile time_t g_work_time;
|
||||
extern volatile int pool_switch_count;
|
||||
extern volatile bool pool_is_switching;
|
||||
|
||||
extern struct option options[];
|
||||
|
||||
#define CFG_NULL 0
|
||||
#define CFG_POOL 1
|
||||
struct opt_config_array {
|
||||
int cat;
|
||||
const char *name; // json key
|
||||
const char *longname; // global opt name if different
|
||||
} cfg_array_keys[] = {
|
||||
{ CFG_POOL, "url", NULL }, /* let this key first, increment pools */
|
||||
{ CFG_POOL, "user", NULL },
|
||||
{ CFG_POOL, "pass", NULL },
|
||||
{ CFG_POOL, "userpass", NULL },
|
||||
{ CFG_POOL, "name", "pool-name" },
|
||||
{ CFG_POOL, "scantime", "pool-scantime" },
|
||||
{ CFG_POOL, "max-diff", "pool-max-diff" },
|
||||
{ CFG_POOL, "max-rate", "pool-max-rate" },
|
||||
{ CFG_POOL, "removed", "pool-removed" },
|
||||
{ CFG_POOL, "disabled", "pool-removed" }, // sample alias
|
||||
{ CFG_POOL, "time-limit", "pool-time-limit" },
|
||||
{ CFG_NULL, NULL, NULL }
|
||||
};
|
||||
|
||||
// store current credentials in pools container
|
||||
void pool_set_creds(int pooln)
|
||||
{
|
||||
struct pool_infos *p = &pools[pooln];
|
||||
|
||||
snprintf(p->url, sizeof(p->url), "%s", rpc_url);
|
||||
snprintf(p->short_url, sizeof(p->short_url), "%s", short_url);
|
||||
snprintf(p->user, sizeof(p->user), "%s", rpc_user);
|
||||
snprintf(p->pass, sizeof(p->pass), "%s", rpc_pass);
|
||||
|
||||
if (!(p->status & POOL_ST_DEFINED)) {
|
||||
p->id = pooln;
|
||||
p->status |= POOL_ST_DEFINED;
|
||||
// init pool options as "unset"
|
||||
// until cmdline is not fully parsed...
|
||||
p->max_diff = -1.;
|
||||
p->max_rate = -1.;
|
||||
p->scantime = -1;
|
||||
p->time_limit = -1;
|
||||
|
||||
p->allow_mininginfo = allow_mininginfo;
|
||||
p->allow_gbt = allow_gbt;
|
||||
p->check_dups = check_dups;
|
||||
|
||||
p->status |= POOL_ST_DEFINED;
|
||||
}
|
||||
|
||||
if (strlen(rpc_url)) {
|
||||
if (!strncasecmp(rpc_url, "stratum", 7))
|
||||
p->type = POOL_STRATUM;
|
||||
else /* if (!strncasecmp(rpc_url, "http", 4)) */
|
||||
p->type = POOL_GETWORK; // todo: or longpoll
|
||||
p->status |= POOL_ST_VALID;
|
||||
}
|
||||
}
|
||||
|
||||
// fill the unset pools options with cmdline ones
|
||||
void pool_init_defaults()
|
||||
{
|
||||
struct pool_infos *p;
|
||||
for (int i=0; i<num_pools; i++) {
|
||||
p = &pools[i];
|
||||
if (p->max_diff == -1.) p->max_diff = opt_max_diff;
|
||||
if (p->max_rate == -1.) p->max_rate = opt_max_rate;
|
||||
if (p->scantime == -1) p->scantime = opt_scantime;
|
||||
if (p->time_limit == -1) p->time_limit = opt_time_limit;
|
||||
}
|
||||
}
|
||||
|
||||
// attributes only set by a json pools config
|
||||
void pool_set_attr(int pooln, const char* key, char* arg)
|
||||
{
|
||||
struct pool_infos *p = &pools[pooln];
|
||||
|
||||
if (!strcasecmp(key, "name")) {
|
||||
snprintf(p->name, sizeof(p->name), "%s", arg);
|
||||
return;
|
||||
}
|
||||
if (!strcasecmp(key, "scantime")) {
|
||||
p->scantime = atoi(arg);
|
||||
return;
|
||||
}
|
||||
if (!strcasecmp(key, "max-diff")) {
|
||||
p->max_diff = atof(arg);
|
||||
return;
|
||||
}
|
||||
if (!strcasecmp(key, "max-rate")) {
|
||||
p->max_rate = atof(arg);
|
||||
return;
|
||||
}
|
||||
if (!strcasecmp(key, "time-limit")) {
|
||||
p->time_limit = atoi(arg);
|
||||
return;
|
||||
}
|
||||
if (!strcasecmp(key, "removed")) {
|
||||
int removed = atoi(arg);
|
||||
if (removed) {
|
||||
p->status |= POOL_ST_REMOVED;
|
||||
}
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
// pool switching code
|
||||
bool pool_switch(int pooln)
|
||||
{
|
||||
int prevn = cur_pooln;
|
||||
struct pool_infos *prev = &pools[cur_pooln];
|
||||
struct pool_infos* p = NULL;
|
||||
|
||||
// save prev stratum connection infos (struct)
|
||||
if (prev->type & POOL_STRATUM) {
|
||||
// may not be the right moment to free,
|
||||
// to check if required on submit...
|
||||
stratum_free_job(&stratum);
|
||||
prev->stratum = stratum;
|
||||
}
|
||||
|
||||
if (pooln < num_pools) {
|
||||
cur_pooln = pooln;
|
||||
p = &pools[cur_pooln];
|
||||
} else {
|
||||
applog(LOG_ERR, "Switch to inexistant pool %d!", pooln);
|
||||
return false;
|
||||
}
|
||||
|
||||
// save global attributes
|
||||
prev->allow_mininginfo = allow_mininginfo;
|
||||
prev->allow_gbt = allow_gbt;
|
||||
prev->check_dups = check_dups;
|
||||
|
||||
pthread_mutex_lock(&stratum_work_lock);
|
||||
|
||||
free(rpc_user); rpc_user = strdup(p->user);
|
||||
free(rpc_pass); rpc_pass = strdup(p->pass);
|
||||
free(rpc_url); rpc_url = strdup(p->url);
|
||||
|
||||
short_url = p->short_url; // just a pointer, no alloc
|
||||
|
||||
opt_scantime = p->scantime;
|
||||
opt_max_diff = p->max_diff;
|
||||
opt_max_rate = p->max_rate;
|
||||
opt_time_limit = p->time_limit;
|
||||
|
||||
want_stratum = have_stratum = (p->type & POOL_STRATUM) != 0;
|
||||
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
|
||||
if (prevn != cur_pooln) {
|
||||
|
||||
pool_switch_count++;
|
||||
g_work_time = 0;
|
||||
g_work.data[0] = 0;
|
||||
pool_is_switching = true;
|
||||
stratum_need_reset = true;
|
||||
// used to get the pool uptime
|
||||
firstwork_time = time(NULL);
|
||||
restart_threads();
|
||||
|
||||
// restore flags
|
||||
allow_gbt = p->allow_gbt;
|
||||
allow_mininginfo = p->allow_mininginfo;
|
||||
check_dups = p->check_dups;
|
||||
|
||||
if (want_stratum) {
|
||||
|
||||
// temporary... until stratum code cleanup
|
||||
stratum = p->stratum;
|
||||
stratum.pooln = cur_pooln;
|
||||
|
||||
// unlock the stratum thread
|
||||
tq_push(thr_info[stratum_thr_id].q, strdup(rpc_url));
|
||||
applog(LOG_BLUE, "Switch to stratum pool %d: %s", cur_pooln,
|
||||
strlen(p->name) ? p->name : p->short_url);
|
||||
} else {
|
||||
applog(LOG_BLUE, "Switch to pool %d: %s", cur_pooln,
|
||||
strlen(p->name) ? p->name : p->short_url);
|
||||
}
|
||||
|
||||
// will unlock the longpoll thread on /LP url receive
|
||||
want_longpoll = (p->type & POOL_LONGPOLL) || !(p->type & POOL_STRATUM);
|
||||
if (want_longpoll) {
|
||||
pthread_mutex_lock(&stratum_work_lock);
|
||||
// will issue a lp_url request to unlock the longpoll thread
|
||||
have_longpoll = false;
|
||||
get_work(&thr_info[0], &g_work);
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
}
|
||||
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
// search available pool
|
||||
int pool_get_first_valid(int startfrom)
|
||||
{
|
||||
int next = 0;
|
||||
struct pool_infos *p;
|
||||
for (int i=0; i<num_pools; i++) {
|
||||
int pooln = (startfrom + i) % num_pools;
|
||||
p = &pools[pooln];
|
||||
if (!(p->status & POOL_ST_VALID))
|
||||
continue;
|
||||
if (p->status & (POOL_ST_DISABLED | POOL_ST_REMOVED))
|
||||
continue;
|
||||
next = pooln;
|
||||
break;
|
||||
}
|
||||
return next;
|
||||
}
|
||||
|
||||
// switch to next available pool
|
||||
bool pool_switch_next()
|
||||
{
|
||||
if (num_pools > 1) {
|
||||
int pooln = pool_get_first_valid(cur_pooln+1);
|
||||
return pool_switch(pooln);
|
||||
} else {
|
||||
// no switch possible
|
||||
if (!opt_quiet)
|
||||
applog(LOG_DEBUG, "No other pools to try...");
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// seturl from api remote (deprecated)
|
||||
bool pool_switch_url(char *params)
|
||||
{
|
||||
int prevn = cur_pooln, nextn;
|
||||
parse_arg('o', params);
|
||||
// cur_pooln modified by parse_arg('o'), get new pool num
|
||||
nextn = cur_pooln;
|
||||
// and to handle the "hot swap" from current one...
|
||||
cur_pooln = prevn;
|
||||
if (nextn == prevn)
|
||||
return false;
|
||||
return pool_switch(nextn);
|
||||
}
|
||||
|
||||
// Parse pools array in json config
|
||||
bool parse_pool_array(json_t *obj)
|
||||
{
|
||||
size_t idx;
|
||||
json_t *p, *val;
|
||||
|
||||
if (!json_is_array(obj))
|
||||
return false;
|
||||
|
||||
// array of objects [ {}, {} ]
|
||||
json_array_foreach(obj, idx, p)
|
||||
{
|
||||
if (!json_is_object(p))
|
||||
continue;
|
||||
|
||||
for (int i = 0; i < ARRAY_SIZE(cfg_array_keys); i++)
|
||||
{
|
||||
int opt = -1;
|
||||
char *s = NULL;
|
||||
if (cfg_array_keys[i].cat != CFG_POOL)
|
||||
continue;
|
||||
|
||||
val = json_object_get(p, cfg_array_keys[i].name);
|
||||
if (!val)
|
||||
continue;
|
||||
|
||||
for (int k = 0; k < options_count(); k++)
|
||||
{
|
||||
const char *alias = cfg_array_keys[i].longname;
|
||||
if (alias && !strcasecmp(options[k].name, alias)) {
|
||||
opt = k;
|
||||
break;
|
||||
}
|
||||
if (!alias && !strcasecmp(options[k].name, cfg_array_keys[i].name)) {
|
||||
opt = k;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (opt == -1)
|
||||
continue;
|
||||
|
||||
if (json_is_string(val)) {
|
||||
s = strdup(json_string_value(val));
|
||||
if (!s)
|
||||
continue;
|
||||
|
||||
// applog(LOG_DEBUG, "pool key %s '%s'", options[opt].name, s);
|
||||
parse_arg(options[opt].val, s);
|
||||
free(s);
|
||||
} else {
|
||||
// numeric or bool
|
||||
char buf[32] = { 0 };
|
||||
double d = 0.;
|
||||
if (json_is_true(val)) d = 1.;
|
||||
else if (json_is_integer(val))
|
||||
d = 1.0 * json_integer_value(val);
|
||||
else if (json_is_real(val))
|
||||
d = json_real_value(val);
|
||||
snprintf(buf, sizeof(buf)-1, "%f", d);
|
||||
// applog(LOG_DEBUG, "pool key %s '%f'", options[opt].name, d);
|
||||
parse_arg(options[opt].val, buf);
|
||||
}
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
// debug stuff
|
||||
void pool_dump_infos()
|
||||
{
|
||||
struct pool_infos *p;
|
||||
for (int i=0; i<num_pools; i++) {
|
||||
p = &pools[i];
|
||||
applog(LOG_DEBUG, "POOL %01d: %s USER %s -s %d", i,
|
||||
p->short_url, p->user, p->scantime);
|
||||
}
|
||||
}
|
||||
+191
-193
@@ -11,20 +11,15 @@ __constant__ uint64_t c_PaddedMessage80[16]; // padded message (80 bytes + paddi
|
||||
#undef SHR
|
||||
#undef CONST_EXP2
|
||||
|
||||
//#define SHL(x, n) ((x) << (n))
|
||||
//#define SHR(x, n) ((x) >> (n))
|
||||
#define SHR(x, n) SHR2(x, n)
|
||||
#define SHL(x, n) SHL2(x, n)
|
||||
|
||||
#undef ROTL64
|
||||
#define ROTL64 ROL2
|
||||
|
||||
#define ROL(x, n) ROL2(x, n)
|
||||
|
||||
#define CONST_EXP2(i) \
|
||||
q[i+0] + ROTL64(q[i+1], 5) + q[i+2] + ROTL64(q[i+3], 11) + \
|
||||
q[i+4] + ROTL64(q[i+5], 27) + q[i+6] + SWAPUINT2(q[i+7]) + \
|
||||
q[i+8] + ROTL64(q[i+9], 37) + q[i+10] + ROTL64(q[i+11], 43) + \
|
||||
q[i+12] + ROTL64(q[i+13], 53) + (SHR(q[i+14],1) ^ q[i+14]) + (SHR(q[i+15],2) ^ q[i+15])
|
||||
q[i+0] + ROL(q[i+1], 5) + q[i+2] + ROL(q[i+3], 11) + \
|
||||
q[i+4] + ROL(q[i+5], 27) + q[i+6] + SWAPUINT2(q[i+7]) + \
|
||||
q[i+8] + ROL(q[i+9], 37) + q[i+10] + ROL(q[i+11], 43) + \
|
||||
q[i+12] + ROL(q[i+13], 53) + (SHR(q[i+14],1) ^ q[i+14]) + (SHR(q[i+15],2) ^ q[i+15])
|
||||
|
||||
__device__ void Compression512_64_first(uint2 *msg, uint2 *hash)
|
||||
{
|
||||
@@ -33,136 +28,138 @@ __device__ void Compression512_64_first(uint2 *msg, uint2 *hash)
|
||||
uint2 tmp;
|
||||
|
||||
tmp = (msg[5] ^ hash[5]) - (msg[7] ^ hash[7]) + (hash[10]) + (hash[13]) + (hash[14]);
|
||||
q[0] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[1];
|
||||
q[0] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[1];
|
||||
|
||||
tmp = (msg[6] ^ hash[6]) - (msg[8] ^ hash[8]) + (hash[11]) + (hash[14]) - (msg[15] ^ hash[15]);
|
||||
q[1] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROTL64(tmp, 13) ^ ROTL64(tmp, 43)) + hash[2];
|
||||
q[1] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROL(tmp, 13) ^ ROL(tmp, 43)) + hash[2];
|
||||
tmp = (msg[0] ^ hash[0]) + (msg[7] ^ hash[7]) + (hash[9]) - (hash[12]) + (msg[15] ^ hash[15]);
|
||||
q[2] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROTL64(tmp, 19) ^ ROTL64(tmp, 53)) + hash[3];
|
||||
q[2] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROL(tmp, 19) ^ ROL(tmp, 53)) + hash[3];
|
||||
tmp = (msg[0] ^ hash[0]) - (msg[1] ^ hash[1]) + (msg[8] ^ hash[8]) - (hash[10]) + (hash[13]);
|
||||
q[3] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROTL64(tmp, 28) ^ ROTL64(tmp, 59)) + hash[4];
|
||||
q[3] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROL(tmp, 28) ^ ROL(tmp, 59)) + hash[4];
|
||||
tmp = (msg[1] ^ hash[1]) + (msg[2] ^ hash[2]) + (hash[9]) - (hash[11]) - (hash[14]);
|
||||
q[4] = (SHR(tmp, 1) ^ tmp) + hash[5];
|
||||
tmp = (msg[3] ^ hash[3]) - (msg[2] ^ hash[2]) + (hash[10]) - (hash[12]) + (msg[15] ^ hash[15]);
|
||||
q[5] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[6];
|
||||
q[5] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[6];
|
||||
tmp = (msg[4] ^ hash[4]) - (msg[0] ^ hash[0]) - (msg[3] ^ hash[3]) - (hash[11]) + (hash[13]);
|
||||
q[6] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROTL64(tmp, 13) ^ ROTL64(tmp, 43)) + hash[7];
|
||||
q[6] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROL(tmp, 13) ^ ROL(tmp, 43)) + hash[7];
|
||||
tmp = (msg[1] ^ hash[1]) - (msg[4] ^ hash[4]) - (msg[5] ^ hash[5]) - (hash[12]) - (hash[14]);
|
||||
q[7] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROTL64(tmp, 19) ^ ROTL64(tmp, 53)) + hash[8];
|
||||
q[7] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROL(tmp, 19) ^ ROL(tmp, 53)) + hash[8];
|
||||
|
||||
tmp = (msg[2] ^ hash[2]) - (msg[5] ^ hash[5]) - (msg[6] ^ hash[6]) + (hash[13]) - (msg[15] ^ hash[15]);
|
||||
q[8] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROTL64(tmp, 28) ^ ROTL64(tmp, 59)) + hash[9];
|
||||
q[8] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROL(tmp, 28) ^ ROL(tmp, 59)) + hash[9];
|
||||
tmp = (msg[0] ^ hash[0]) - (msg[3] ^ hash[3]) + (msg[6] ^ hash[6]) - (msg[7] ^ hash[7]) + (hash[14]);
|
||||
q[9] = (SHR(tmp, 1) ^ tmp) + hash[10];
|
||||
tmp = (msg[8] ^ hash[8]) - (msg[1] ^ hash[1]) - (msg[4] ^ hash[4]) - (msg[7] ^ hash[7]) + (msg[15] ^ hash[15]);
|
||||
q[10] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[11];
|
||||
q[10] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[11];
|
||||
tmp = (msg[8] ^ hash[8]) - (msg[0] ^ hash[0]) - (msg[2] ^ hash[2]) - (msg[5] ^ hash[5]) + (hash[9]);
|
||||
q[11] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROTL64(tmp, 13) ^ ROTL64(tmp, 43)) + hash[12];
|
||||
q[11] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROL(tmp, 13) ^ ROL(tmp, 43)) + hash[12];
|
||||
tmp = (msg[1] ^ hash[1]) + (msg[3] ^ hash[3]) - (msg[6] ^ hash[6]) - (hash[9]) + (hash[10]);
|
||||
q[12] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROTL64(tmp, 19) ^ ROTL64(tmp, 53)) + hash[13];
|
||||
q[12] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROL(tmp, 19) ^ ROL(tmp, 53)) + hash[13];
|
||||
tmp = (msg[2] ^ hash[2]) + (msg[4] ^ hash[4]) + (msg[7] ^ hash[7]) + (hash[10]) + (hash[11]);
|
||||
q[13] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROTL64(tmp, 28) ^ ROTL64(tmp, 59)) + hash[14];
|
||||
q[13] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROL(tmp, 28) ^ ROL(tmp, 59)) + hash[14];
|
||||
tmp = (msg[3] ^ hash[3]) - (msg[5] ^ hash[5]) + (msg[8] ^ hash[8]) - (hash[11]) - (hash[12]);
|
||||
q[14] = (SHR(tmp, 1) ^ tmp) + hash[15];
|
||||
tmp = (msg[12] ^ hash[12]) - (msg[4] ^ hash[4]) - (msg[6] ^ hash[6]) - (hash[9]) + (hash[13]);
|
||||
q[15] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[0];
|
||||
q[15] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[0];
|
||||
|
||||
q[0 + 16] =
|
||||
(SHR(q[0], 1) ^ SHL(q[0], 2) ^ ROTL64(q[0], 13) ^ ROTL64(q[0], 43)) +
|
||||
(SHR(q[0 + 1], 2) ^ SHL(q[0 + 1], 1) ^ ROTL64(q[0 + 1], 19) ^ ROTL64(q[0 + 1], 53)) +
|
||||
(SHR(q[0 + 2], 2) ^ SHL(q[0 + 2], 2) ^ ROTL64(q[0 + 2], 28) ^ ROTL64(q[0 + 2], 59)) +
|
||||
(SHR(q[0 + 3], 1) ^ SHL(q[0 + 3], 3) ^ ROTL64(q[0 + 3], 4) ^ ROTL64(q[0 + 3], 37)) +
|
||||
(SHR(q[0 + 4], 1) ^ SHL(q[0 + 4], 2) ^ ROTL64(q[0 + 4], 13) ^ ROTL64(q[0 + 4], 43)) +
|
||||
(SHR(q[0 + 5], 2) ^ SHL(q[0 + 5], 1) ^ ROTL64(q[0 + 5], 19) ^ ROTL64(q[0 + 5], 53)) +
|
||||
(SHR(q[0 + 6], 2) ^ SHL(q[0 + 6], 2) ^ ROTL64(q[0 + 6], 28) ^ ROTL64(q[0 + 6], 59)) +
|
||||
(SHR(q[0 + 7], 1) ^ SHL(q[0 + 7], 3) ^ ROTL64(q[0 + 7], 4) ^ ROTL64(q[0 + 7], 37)) +
|
||||
(SHR(q[0 + 8], 1) ^ SHL(q[0 + 8], 2) ^ ROTL64(q[0 + 8], 13) ^ ROTL64(q[0 + 8], 43)) +
|
||||
(SHR(q[0 + 9], 2) ^ SHL(q[0 + 9], 1) ^ ROTL64(q[0 + 9], 19) ^ ROTL64(q[0 + 9], 53)) +
|
||||
(SHR(q[0 + 10], 2) ^ SHL(q[0 + 10], 2) ^ ROTL64(q[0 + 10], 28) ^ ROTL64(q[0 + 10], 59)) +
|
||||
(SHR(q[0 + 11], 1) ^ SHL(q[0 + 11], 3) ^ ROTL64(q[0 + 11], 4) ^ ROTL64(q[0 + 11], 37)) +
|
||||
(SHR(q[0 + 12], 1) ^ SHL(q[0 + 12], 2) ^ ROTL64(q[0 + 12], 13) ^ ROTL64(q[0 + 12], 43)) +
|
||||
(SHR(q[0 + 13], 2) ^ SHL(q[0 + 13], 1) ^ ROTL64(q[0 + 13], 19) ^ ROTL64(q[0 + 13], 53)) +
|
||||
(SHR(q[0 + 14], 2) ^ SHL(q[0 + 14], 2) ^ ROTL64(q[0 + 14], 28) ^ ROTL64(q[0 + 14], 59)) +
|
||||
(SHR(q[0 + 15], 1) ^ SHL(q[0 + 15], 3) ^ ROTL64(q[0 + 15], 4) ^ ROTL64(q[0 + 15], 37)) +
|
||||
((make_uint2(0x55555550ul,0x55555555) + ROTL64(msg[0], 0 + 1) +
|
||||
ROTL64(msg[0 + 3], 0 + 4)) ^ hash[0 + 7]);
|
||||
(SHR(q[0], 1) ^ SHL(q[0], 2) ^ ROL(q[0], 13) ^ ROL(q[0], 43)) +
|
||||
(SHR(q[0 + 1], 2) ^ SHL(q[0 + 1], 1) ^ ROL(q[0 + 1], 19) ^ ROL(q[0 + 1], 53)) +
|
||||
(SHR(q[0 + 2], 2) ^ SHL(q[0 + 2], 2) ^ ROL(q[0 + 2], 28) ^ ROL(q[0 + 2], 59)) +
|
||||
(SHR(q[0 + 3], 1) ^ SHL(q[0 + 3], 3) ^ ROL(q[0 + 3], 4) ^ ROL(q[0 + 3], 37)) +
|
||||
(SHR(q[0 + 4], 1) ^ SHL(q[0 + 4], 2) ^ ROL(q[0 + 4], 13) ^ ROL(q[0 + 4], 43)) +
|
||||
(SHR(q[0 + 5], 2) ^ SHL(q[0 + 5], 1) ^ ROL(q[0 + 5], 19) ^ ROL(q[0 + 5], 53)) +
|
||||
(SHR(q[0 + 6], 2) ^ SHL(q[0 + 6], 2) ^ ROL(q[0 + 6], 28) ^ ROL(q[0 + 6], 59)) +
|
||||
(SHR(q[0 + 7], 1) ^ SHL(q[0 + 7], 3) ^ ROL(q[0 + 7], 4) ^ ROL(q[0 + 7], 37)) +
|
||||
(SHR(q[0 + 8], 1) ^ SHL(q[0 + 8], 2) ^ ROL(q[0 + 8], 13) ^ ROL(q[0 + 8], 43)) +
|
||||
(SHR(q[0 + 9], 2) ^ SHL(q[0 + 9], 1) ^ ROL(q[0 + 9], 19) ^ ROL(q[0 + 9], 53)) +
|
||||
(SHR(q[0 + 10], 2) ^ SHL(q[0 + 10], 2) ^ ROL(q[0 + 10], 28) ^ ROL(q[0 + 10], 59)) +
|
||||
(SHR(q[0 + 11], 1) ^ SHL(q[0 + 11], 3) ^ ROL(q[0 + 11], 4) ^ ROL(q[0 + 11], 37)) +
|
||||
(SHR(q[0 + 12], 1) ^ SHL(q[0 + 12], 2) ^ ROL(q[0 + 12], 13) ^ ROL(q[0 + 12], 43)) +
|
||||
(SHR(q[0 + 13], 2) ^ SHL(q[0 + 13], 1) ^ ROL(q[0 + 13], 19) ^ ROL(q[0 + 13], 53)) +
|
||||
(SHR(q[0 + 14], 2) ^ SHL(q[0 + 14], 2) ^ ROL(q[0 + 14], 28) ^ ROL(q[0 + 14], 59)) +
|
||||
(SHR(q[0 + 15], 1) ^ SHL(q[0 + 15], 3) ^ ROL(q[0 + 15], 4) ^ ROL(q[0 + 15], 37)) +
|
||||
((make_uint2(0x55555550ul,0x55555555) + ROL(msg[0], 0 + 1) +
|
||||
ROL(msg[0 + 3], 0 + 4)) ^ hash[0 + 7]);
|
||||
|
||||
q[1 + 16] =
|
||||
(SHR(q[1], 1) ^ SHL(q[1], 2) ^ ROTL64(q[1], 13) ^ ROTL64(q[1], 43)) +
|
||||
(SHR(q[1 + 1], 2) ^ SHL(q[1 + 1], 1) ^ ROTL64(q[1 + 1], 19) ^ ROTL64(q[1 + 1], 53)) +
|
||||
(SHR(q[1 + 2], 2) ^ SHL(q[1 + 2], 2) ^ ROTL64(q[1 + 2], 28) ^ ROTL64(q[1 + 2], 59)) +
|
||||
(SHR(q[1 + 3], 1) ^ SHL(q[1 + 3], 3) ^ ROTL64(q[1 + 3], 4) ^ ROTL64(q[1 + 3], 37)) +
|
||||
(SHR(q[1 + 4], 1) ^ SHL(q[1 + 4], 2) ^ ROTL64(q[1 + 4], 13) ^ ROTL64(q[1 + 4], 43)) +
|
||||
(SHR(q[1 + 5], 2) ^ SHL(q[1 + 5], 1) ^ ROTL64(q[1 + 5], 19) ^ ROTL64(q[1 + 5], 53)) +
|
||||
(SHR(q[1 + 6], 2) ^ SHL(q[1 + 6], 2) ^ ROTL64(q[1 + 6], 28) ^ ROTL64(q[1 + 6], 59)) +
|
||||
(SHR(q[1 + 7], 1) ^ SHL(q[1 + 7], 3) ^ ROTL64(q[1 + 7], 4) ^ ROTL64(q[1 + 7], 37)) +
|
||||
(SHR(q[1 + 8], 1) ^ SHL(q[1 + 8], 2) ^ ROTL64(q[1 + 8], 13) ^ ROTL64(q[1 + 8], 43)) +
|
||||
(SHR(q[1 + 9], 2) ^ SHL(q[1 + 9], 1) ^ ROTL64(q[1 + 9], 19) ^ ROTL64(q[1 + 9], 53)) +
|
||||
(SHR(q[1 + 10], 2) ^ SHL(q[1 + 10], 2) ^ ROTL64(q[1 + 10], 28) ^ ROTL64(q[1 + 10], 59)) +
|
||||
(SHR(q[1 + 11], 1) ^ SHL(q[1 + 11], 3) ^ ROTL64(q[1 + 11], 4) ^ ROTL64(q[1 + 11], 37)) +
|
||||
(SHR(q[1 + 12], 1) ^ SHL(q[1 + 12], 2) ^ ROTL64(q[1 + 12], 13) ^ ROTL64(q[1 + 12], 43)) +
|
||||
(SHR(q[1 + 13], 2) ^ SHL(q[1 + 13], 1) ^ ROTL64(q[1 + 13], 19) ^ ROTL64(q[1 + 13], 53)) +
|
||||
(SHR(q[1 + 14], 2) ^ SHL(q[1 + 14], 2) ^ ROTL64(q[1 + 14], 28) ^ ROTL64(q[1 + 14], 59)) +
|
||||
(SHR(q[1 + 15], 1) ^ SHL(q[1 + 15], 3) ^ ROTL64(q[1 + 15], 4) ^ ROTL64(q[1 + 15], 37)) +
|
||||
((make_uint2(0xAAAAAAA5, 0x5AAAAAAA) + ROTL64(msg[1], 1 + 1) +
|
||||
ROTL64(msg[1 + 3], 1 + 4)) ^ hash[1 + 7]);
|
||||
(SHR(q[1], 1) ^ SHL(q[1], 2) ^ ROL(q[1], 13) ^ ROL(q[1], 43)) +
|
||||
(SHR(q[1 + 1], 2) ^ SHL(q[1 + 1], 1) ^ ROL(q[1 + 1], 19) ^ ROL(q[1 + 1], 53)) +
|
||||
(SHR(q[1 + 2], 2) ^ SHL(q[1 + 2], 2) ^ ROL(q[1 + 2], 28) ^ ROL(q[1 + 2], 59)) +
|
||||
(SHR(q[1 + 3], 1) ^ SHL(q[1 + 3], 3) ^ ROL(q[1 + 3], 4) ^ ROL(q[1 + 3], 37)) +
|
||||
(SHR(q[1 + 4], 1) ^ SHL(q[1 + 4], 2) ^ ROL(q[1 + 4], 13) ^ ROL(q[1 + 4], 43)) +
|
||||
(SHR(q[1 + 5], 2) ^ SHL(q[1 + 5], 1) ^ ROL(q[1 + 5], 19) ^ ROL(q[1 + 5], 53)) +
|
||||
(SHR(q[1 + 6], 2) ^ SHL(q[1 + 6], 2) ^ ROL(q[1 + 6], 28) ^ ROL(q[1 + 6], 59)) +
|
||||
(SHR(q[1 + 7], 1) ^ SHL(q[1 + 7], 3) ^ ROL(q[1 + 7], 4) ^ ROL(q[1 + 7], 37)) +
|
||||
(SHR(q[1 + 8], 1) ^ SHL(q[1 + 8], 2) ^ ROL(q[1 + 8], 13) ^ ROL(q[1 + 8], 43)) +
|
||||
(SHR(q[1 + 9], 2) ^ SHL(q[1 + 9], 1) ^ ROL(q[1 + 9], 19) ^ ROL(q[1 + 9], 53)) +
|
||||
(SHR(q[1 + 10], 2) ^ SHL(q[1 + 10], 2) ^ ROL(q[1 + 10], 28) ^ ROL(q[1 + 10], 59)) +
|
||||
(SHR(q[1 + 11], 1) ^ SHL(q[1 + 11], 3) ^ ROL(q[1 + 11], 4) ^ ROL(q[1 + 11], 37)) +
|
||||
(SHR(q[1 + 12], 1) ^ SHL(q[1 + 12], 2) ^ ROL(q[1 + 12], 13) ^ ROL(q[1 + 12], 43)) +
|
||||
(SHR(q[1 + 13], 2) ^ SHL(q[1 + 13], 1) ^ ROL(q[1 + 13], 19) ^ ROL(q[1 + 13], 53)) +
|
||||
(SHR(q[1 + 14], 2) ^ SHL(q[1 + 14], 2) ^ ROL(q[1 + 14], 28) ^ ROL(q[1 + 14], 59)) +
|
||||
(SHR(q[1 + 15], 1) ^ SHL(q[1 + 15], 3) ^ ROL(q[1 + 15], 4) ^ ROL(q[1 + 15], 37)) +
|
||||
((make_uint2(0xAAAAAAA5, 0x5AAAAAAA) + ROL(msg[1], 1 + 1) +
|
||||
ROL(msg[1 + 3], 1 + 4)) ^ hash[1 + 7]);
|
||||
|
||||
q[2 + 16] = CONST_EXP2(2) +
|
||||
((make_uint2(0xFFFFFFFA, 0x5FFFFFFF) + ROTL64(msg[2], 2 + 1) +
|
||||
ROTL64(msg[2 + 3], 2 + 4) - ROTL64(msg[2 + 10], 2 + 11)) ^ hash[2 + 7]);
|
||||
((make_uint2(0xFFFFFFFA, 0x5FFFFFFF) + ROL(msg[2], 2 + 1) +
|
||||
ROL(msg[2 + 3], 2 + 4) - ROL(msg[2 + 10], 2 + 11)) ^ hash[2 + 7]);
|
||||
q[3 + 16] = CONST_EXP2(3) +
|
||||
((make_uint2(0x5555554F, 0x65555555) + ROTL64(msg[3], 3 + 1) +
|
||||
ROTL64(msg[3 + 3], 3 + 4) - ROTL64(msg[3 + 10], 3 + 11)) ^ hash[3 + 7]);
|
||||
((make_uint2(0x5555554F, 0x65555555) + ROL(msg[3], 3 + 1) +
|
||||
ROL(msg[3 + 3], 3 + 4) - ROL(msg[3 + 10], 3 + 11)) ^ hash[3 + 7]);
|
||||
q[4 + 16] = CONST_EXP2(4) +
|
||||
((make_uint2(0xAAAAAAA4, 0x6AAAAAAA) +ROTL64(msg[4], 4 + 1) +
|
||||
ROTL64(msg[4 + 3], 4 + 4) - ROTL64(msg[4 + 10], 4 + 11)) ^ hash[4 + 7]);
|
||||
((make_uint2(0xAAAAAAA4, 0x6AAAAAAA) +ROL(msg[4], 4 + 1) +
|
||||
ROL(msg[4 + 3], 4 + 4) - ROL(msg[4 + 10], 4 + 11)) ^ hash[4 + 7]);
|
||||
q[5 + 16] = CONST_EXP2(5) +
|
||||
((make_uint2(0xFFFFFFF9, 0x6FFFFFFF) + ROTL64(msg[5], 5 + 1) +
|
||||
ROTL64(msg[5 + 3], 5 + 4) - ROTL64(msg[5 + 10], 5 + 11)) ^ hash[5 + 7]);
|
||||
((make_uint2(0xFFFFFFF9, 0x6FFFFFFF) + ROL(msg[5], 5 + 1) +
|
||||
ROL(msg[5 + 3], 5 + 4) - ROL(msg[5 + 10], 5 + 11)) ^ hash[5 + 7]);
|
||||
|
||||
#pragma unroll 3
|
||||
for (int i = 6; i<9; i++) {
|
||||
q[i + 16] = CONST_EXP2(i) +
|
||||
((vectorize((i + 16)*(0x0555555555555555ull)) + ROTL64(msg[i], i + 1) -
|
||||
ROTL64(msg[i - 6], (i - 6) + 1)) ^ hash[i + 7]);
|
||||
((vectorize((i + 16)*(0x0555555555555555ull)) + ROL(msg[i], i + 1) -
|
||||
ROL(msg[i - 6], (i - 6) + 1)) ^ hash[i + 7]);
|
||||
}
|
||||
|
||||
#pragma unroll 4
|
||||
for (int i = 9; i<13; i++) {
|
||||
q[i + 16] = CONST_EXP2(i) +
|
||||
((vectorize((i + 16)*(0x0555555555555555ull)) +
|
||||
ROTL64(msg[i + 3], i + 4) - ROTL64(msg[i - 6], (i - 6) + 1)) ^ hash[i - 9]);
|
||||
ROL(msg[i + 3], i + 4) - ROL(msg[i - 6], (i - 6) + 1)) ^ hash[i - 9]);
|
||||
}
|
||||
|
||||
q[13 + 16] = CONST_EXP2(13) +
|
||||
((make_uint2(0xAAAAAAA1, 0x9AAAAAAA) + ROTL64(msg[13], 13 + 1) +
|
||||
ROTL64(msg[13 - 13], (13 - 13) + 1) - ROTL64(msg[13 - 6], (13 - 6) + 1)) ^ hash[13 - 9]);
|
||||
((make_uint2(0xAAAAAAA1, 0x9AAAAAAA) + ROL(msg[13], 13 + 1) +
|
||||
ROL(msg[13 - 13], (13 - 13) + 1) - ROL(msg[13 - 6], (13 - 6) + 1)) ^ hash[13 - 9]);
|
||||
q[14 + 16] = CONST_EXP2(14) +
|
||||
((make_uint2(0xFFFFFFF6, 0x9FFFFFFF) + ROTL64(msg[14], 14 + 1) +
|
||||
ROTL64(msg[14 - 13], (14 - 13) + 1) - ROTL64(msg[14 - 6], (14 - 6) + 1)) ^ hash[14 - 9]);
|
||||
((make_uint2(0xFFFFFFF6, 0x9FFFFFFF) + ROL(msg[14], 14 + 1) +
|
||||
ROL(msg[14 - 13], (14 - 13) + 1) - ROL(msg[14 - 6], (14 - 6) + 1)) ^ hash[14 - 9]);
|
||||
q[15 + 16] = CONST_EXP2(15) +
|
||||
((make_uint2(0x5555554B, 0xA5555555) + ROTL64(msg[15], 15 + 1) +
|
||||
ROTL64(msg[15 - 13], (15 - 13) + 1) - ROTL64(msg[15 - 6], (15 - 6) + 1)) ^ hash[15 - 9]);
|
||||
((make_uint2(0x5555554B, 0xA5555555) + ROL(msg[15], 15 + 1) +
|
||||
ROL(msg[15 - 13], (15 - 13) + 1) - ROL(msg[15 - 6], (15 - 6) + 1)) ^ hash[15 - 9]);
|
||||
|
||||
|
||||
uint2 XL64 = q[16] ^ q[17] ^ q[18] ^ q[19] ^ q[20] ^ q[21] ^ q[22] ^ q[23];
|
||||
uint2 XH64 = XL64^q[24] ^ q[25] ^ q[26] ^ q[27] ^ q[28] ^ q[29] ^ q[30] ^ q[31];
|
||||
|
||||
hash[0] = (SHL(XH64, 5) ^ SHR(q[16], 5) ^ msg[0]) + (XL64 ^ q[24] ^ q[0]);
|
||||
hash[1] = (SHR(XH64, 7) ^ SHL(q[17], 8) ^ msg[1]) + (XL64 ^ q[25] ^ q[1]);
|
||||
hash[2] = (SHR(XH64, 5) ^ SHL(q[18], 5) ^ msg[2]) + (XL64 ^ q[26] ^ q[2]);
|
||||
hash[3] = (SHR(XH64, 1) ^ SHL(q[19], 5) ^ msg[3]) + (XL64 ^ q[27] ^ q[3]);
|
||||
hash[4] = (SHR(XH64, 3) ^ q[20] ^ msg[4]) + (XL64 ^ q[28] ^ q[4]);
|
||||
hash[5] = (SHL(XH64, 6) ^ SHR(q[21], 6) ^ msg[5]) + (XL64 ^ q[29] ^ q[5]);
|
||||
hash[6] = (SHR(XH64, 4) ^ SHL(q[22], 6) ^ msg[6]) + (XL64 ^ q[30] ^ q[6]);
|
||||
hash[7] = (SHR(XH64, 11) ^ SHL(q[23], 2) ^ msg[7]) + (XL64 ^ q[31] ^ q[7]);
|
||||
hash[0] = (SHL(XH64, 5) ^ SHR(q[16], 5) ^ msg[0]) + (XL64 ^ q[24] ^ q[0]);
|
||||
hash[1] = (SHR(XH64, 7) ^ SHL(q[17], 8) ^ msg[1]) + (XL64 ^ q[25] ^ q[1]);
|
||||
hash[2] = (SHR(XH64, 5) ^ SHL(q[18], 5) ^ msg[2]) + (XL64 ^ q[26] ^ q[2]);
|
||||
hash[3] = (SHR(XH64, 1) ^ SHL(q[19], 5) ^ msg[3]) + (XL64 ^ q[27] ^ q[3]);
|
||||
hash[4] = (SHR(XH64, 3) ^ q[20] ^ msg[4]) + (XL64 ^ q[28] ^ q[4]);
|
||||
hash[5] = (SHL(XH64, 6) ^ SHR(q[21], 6) ^ msg[5]) + (XL64 ^ q[29] ^ q[5]);
|
||||
hash[6] = (SHR(XH64, 4) ^ SHL(q[22], 6) ^ msg[6]) + (XL64 ^ q[30] ^ q[6]);
|
||||
hash[7] = (SHR(XH64, 11) ^ SHL(q[23], 2) ^ msg[7]) + (XL64 ^ q[31] ^ q[7]);
|
||||
|
||||
hash[8] = ROTL64(hash[4], 9) + (XH64 ^ q[24] ^ msg[8]) + (SHL(XL64, 8) ^ q[23] ^ q[8]);
|
||||
hash[9] = ROTL64(hash[5], 10) + (XH64 ^ q[25]) + (SHR(XL64, 6) ^ q[16] ^ q[9]);
|
||||
hash[10] = ROTL64(hash[6], 11) + (XH64 ^ q[26]) + (SHL(XL64, 6) ^ q[17] ^ q[10]);
|
||||
hash[11] = ROTL64(hash[7], 12) + (XH64 ^ q[27]) + (SHL(XL64, 4) ^ q[18] ^ q[11]);
|
||||
hash[12] = ROTL64(hash[0], 13) + (XH64 ^ q[28]) + (SHR(XL64, 3) ^ q[19] ^ q[12]);
|
||||
hash[13] = ROTL64(hash[1], 14) + (XH64 ^ q[29]) + (SHR(XL64, 4) ^ q[20] ^ q[13]);
|
||||
hash[14] = ROTL64(hash[2], 15) + (XH64 ^ q[30]) + (SHR(XL64, 7) ^ q[21] ^ q[14]);
|
||||
hash[15] = ROTL64(hash[3], 16) + (XH64 ^ q[31] ^ msg[15]) + (SHR(XL64, 2) ^ q[22] ^ q[15]);
|
||||
hash[8] = ROL(hash[4], 9) + (XH64 ^ q[24] ^ msg[8]) + (SHL(XL64, 8) ^ q[23] ^ q[8]);
|
||||
hash[9] = ROL(hash[5], 10) + (XH64 ^ q[25]) + (SHR(XL64, 6) ^ q[16] ^ q[9]);
|
||||
hash[10] = ROL(hash[6], 11) + (XH64 ^ q[26]) + (SHL(XL64, 6) ^ q[17] ^ q[10]);
|
||||
hash[11] = ROL(hash[7], 12) + (XH64 ^ q[27]) + (SHL(XL64, 4) ^ q[18] ^ q[11]);
|
||||
hash[12] = ROL(hash[0], 13) + (XH64 ^ q[28]) + (SHR(XL64, 3) ^ q[19] ^ q[12]);
|
||||
hash[13] = ROL(hash[1], 14) + (XH64 ^ q[29]) + (SHR(XL64, 4) ^ q[20] ^ q[13]);
|
||||
hash[14] = ROL(hash[2], 15) + (XH64 ^ q[30]) + (SHR(XL64, 7) ^ q[21] ^ q[14]);
|
||||
hash[15] = ROL(hash[3], 16) + (XH64 ^ q[31] ^ msg[15]) + (SHR(XL64, 2) ^ q[22] ^ q[15]);
|
||||
}
|
||||
|
||||
__device__
|
||||
@@ -173,141 +170,141 @@ void Compression512(uint2 *msg, uint2 *hash)
|
||||
uint2 tmp;
|
||||
|
||||
tmp = (msg[ 5] ^ hash[ 5]) - (msg[ 7] ^ hash[ 7]) + (msg[10] ^ hash[10]) + (msg[13] ^ hash[13]) + (msg[14] ^ hash[14]);
|
||||
q[0] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[1];
|
||||
q[0] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[1];
|
||||
tmp = (msg[ 6] ^ hash[ 6]) - (msg[ 8] ^ hash[ 8]) + (msg[11] ^ hash[11]) + (msg[14] ^ hash[14]) - (msg[15] ^ hash[15]);
|
||||
q[1] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROTL64(tmp, 13) ^ ROTL64(tmp, 43)) + hash[2];
|
||||
q[1] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROL(tmp, 13) ^ ROL(tmp, 43)) + hash[2];
|
||||
tmp = (msg[ 0] ^ hash[ 0]) + (msg[ 7] ^ hash[ 7]) + (msg[ 9] ^ hash[ 9]) - (msg[12] ^ hash[12]) + (msg[15] ^ hash[15]);
|
||||
q[2] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROTL64(tmp, 19) ^ ROTL64(tmp, 53)) + hash[3];
|
||||
q[2] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROL(tmp, 19) ^ ROL(tmp, 53)) + hash[3];
|
||||
tmp = (msg[ 0] ^ hash[ 0]) - (msg[ 1] ^ hash[ 1]) + (msg[ 8] ^ hash[ 8]) - (msg[10] ^ hash[10]) + (msg[13] ^ hash[13]);
|
||||
q[3] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROTL64(tmp, 28) ^ ROTL64(tmp, 59)) + hash[4];
|
||||
q[3] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROL(tmp, 28) ^ ROL(tmp, 59)) + hash[4];
|
||||
tmp = (msg[ 1] ^ hash[ 1]) + (msg[ 2] ^ hash[ 2]) + (msg[ 9] ^ hash[ 9]) - (msg[11] ^ hash[11]) - (msg[14] ^ hash[14]);
|
||||
q[4] = (SHR(tmp, 1) ^ tmp) + hash[5];
|
||||
tmp = (msg[ 3] ^ hash[ 3]) - (msg[ 2] ^ hash[ 2]) + (msg[10] ^ hash[10]) - (msg[12] ^ hash[12]) + (msg[15] ^ hash[15]);
|
||||
q[5] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[6];
|
||||
q[5] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[6];
|
||||
tmp = (msg[ 4] ^ hash[ 4]) - (msg[ 0] ^ hash[ 0]) - (msg[ 3] ^ hash[ 3]) - (msg[11] ^ hash[11]) + (msg[13] ^ hash[13]);
|
||||
q[6] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROTL64(tmp, 13) ^ ROTL64(tmp, 43)) + hash[7];
|
||||
q[6] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROL(tmp, 13) ^ ROL(tmp, 43)) + hash[7];
|
||||
tmp = (msg[ 1] ^ hash[ 1]) - (msg[ 4] ^ hash[ 4]) - (msg[ 5] ^ hash[ 5]) - (msg[12] ^ hash[12]) - (msg[14] ^ hash[14]);
|
||||
q[7] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROTL64(tmp, 19) ^ ROTL64(tmp, 53)) + hash[8];
|
||||
q[7] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROL(tmp, 19) ^ ROL(tmp, 53)) + hash[8];
|
||||
tmp = (msg[ 2] ^ hash[ 2]) - (msg[ 5] ^ hash[ 5]) - (msg[ 6] ^ hash[ 6]) + (msg[13] ^ hash[13]) - (msg[15] ^ hash[15]);
|
||||
q[8] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROTL64(tmp, 28) ^ ROTL64(tmp, 59)) + hash[9];
|
||||
q[8] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROL(tmp, 28) ^ ROL(tmp, 59)) + hash[9];
|
||||
tmp = (msg[ 0] ^ hash[ 0]) - (msg[ 3] ^ hash[ 3]) + (msg[ 6] ^ hash[ 6]) - (msg[ 7] ^ hash[ 7]) + (msg[14] ^ hash[14]);
|
||||
q[9] = (SHR(tmp, 1) ^ tmp) + hash[10];
|
||||
tmp = (msg[ 8] ^ hash[ 8]) - (msg[ 1] ^ hash[ 1]) - (msg[ 4] ^ hash[ 4]) - (msg[ 7] ^ hash[ 7]) + (msg[15] ^ hash[15]);
|
||||
q[10] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[11];
|
||||
q[10] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[11];
|
||||
tmp = (msg[ 8] ^ hash[ 8]) - (msg[ 0] ^ hash[ 0]) - (msg[ 2] ^ hash[ 2]) - (msg[ 5] ^ hash[ 5]) + (msg[ 9] ^ hash[ 9]);
|
||||
q[11] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROTL64(tmp, 13) ^ ROTL64(tmp, 43)) + hash[12];
|
||||
q[11] = (SHR(tmp, 1) ^ SHL(tmp, 2) ^ ROL(tmp, 13) ^ ROL(tmp, 43)) + hash[12];
|
||||
tmp = (msg[ 1] ^ hash[ 1]) + (msg[ 3] ^ hash[ 3]) - (msg[ 6] ^ hash[ 6]) - (msg[ 9] ^ hash[ 9]) + (msg[10] ^ hash[10]);
|
||||
q[12] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROTL64(tmp, 19) ^ ROTL64(tmp, 53)) + hash[13];
|
||||
q[12] = (SHR(tmp, 2) ^ SHL(tmp, 1) ^ ROL(tmp, 19) ^ ROL(tmp, 53)) + hash[13];
|
||||
tmp = (msg[ 2] ^ hash[ 2]) + (msg[ 4] ^ hash[ 4]) + (msg[ 7] ^ hash[ 7]) + (msg[10] ^ hash[10]) + (msg[11] ^ hash[11]);
|
||||
q[13] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROTL64(tmp, 28) ^ ROTL64(tmp, 59)) + hash[14];
|
||||
q[13] = (SHR(tmp, 2) ^ SHL(tmp, 2) ^ ROL(tmp, 28) ^ ROL(tmp, 59)) + hash[14];
|
||||
tmp = (msg[ 3] ^ hash[ 3]) - (msg[ 5] ^ hash[ 5]) + (msg[ 8] ^ hash[ 8]) - (msg[11] ^ hash[11]) - (msg[12] ^ hash[12]);
|
||||
q[14] = (SHR(tmp, 1) ^ tmp) + hash[15];
|
||||
tmp = (msg[12] ^ hash[12]) - (msg[ 4] ^ hash[ 4]) - (msg[ 6] ^ hash[ 6]) - (msg[ 9] ^ hash[ 9]) + (msg[13] ^ hash[13]);
|
||||
q[15] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROTL64(tmp, 4) ^ ROTL64(tmp, 37)) + hash[0];
|
||||
q[15] = (SHR(tmp, 1) ^ SHL(tmp, 3) ^ ROL(tmp, 4) ^ ROL(tmp, 37)) + hash[0];
|
||||
|
||||
q[0+16] =
|
||||
(SHR(q[0], 1) ^ SHL(q[0], 2) ^ ROTL64(q[0], 13) ^ ROTL64(q[0], 43)) +
|
||||
(SHR(q[0+1], 2) ^ SHL(q[0+1], 1) ^ ROTL64(q[0+1], 19) ^ ROTL64(q[0+1], 53)) +
|
||||
(SHR(q[0+2], 2) ^ SHL(q[0+2], 2) ^ ROTL64(q[0+2], 28) ^ ROTL64(q[0+2], 59)) +
|
||||
(SHR(q[0+3], 1) ^ SHL(q[0+3], 3) ^ ROTL64(q[0+3], 4) ^ ROTL64(q[0+3], 37)) +
|
||||
(SHR(q[0+4], 1) ^ SHL(q[0+4], 2) ^ ROTL64(q[0+4], 13) ^ ROTL64(q[0+4], 43)) +
|
||||
(SHR(q[0+5], 2) ^ SHL(q[0+5], 1) ^ ROTL64(q[0+5], 19) ^ ROTL64(q[0+5], 53)) +
|
||||
(SHR(q[0+6], 2) ^ SHL(q[0+6], 2) ^ ROTL64(q[0+6], 28) ^ ROTL64(q[0+6], 59)) +
|
||||
(SHR(q[0+7], 1) ^ SHL(q[0+7], 3) ^ ROTL64(q[0+7], 4) ^ ROTL64(q[0+7], 37)) +
|
||||
(SHR(q[0+8], 1) ^ SHL(q[0+8], 2) ^ ROTL64(q[0+8], 13) ^ ROTL64(q[0+8], 43)) +
|
||||
(SHR(q[0+9], 2) ^ SHL(q[0+9], 1) ^ ROTL64(q[0+9], 19) ^ ROTL64(q[0+9], 53)) +
|
||||
(SHR(q[0+10], 2) ^ SHL(q[0+10], 2) ^ ROTL64(q[0+10], 28) ^ ROTL64(q[0+10], 59)) +
|
||||
(SHR(q[0+11], 1) ^ SHL(q[0+11], 3) ^ ROTL64(q[0+11], 4) ^ ROTL64(q[0+11], 37)) +
|
||||
(SHR(q[0+12], 1) ^ SHL(q[0+12], 2) ^ ROTL64(q[0+12], 13) ^ ROTL64(q[0+12], 43)) +
|
||||
(SHR(q[0+13], 2) ^ SHL(q[0+13], 1) ^ ROTL64(q[0+13], 19) ^ ROTL64(q[0+13], 53)) +
|
||||
(SHR(q[0+14], 2) ^ SHL(q[0+14], 2) ^ ROTL64(q[0+14], 28) ^ ROTL64(q[0+14], 59)) +
|
||||
(SHR(q[0+15], 1) ^ SHL(q[0+15], 3) ^ ROTL64(q[0+15], 4) ^ ROTL64(q[0+15], 37)) +
|
||||
((make_uint2(0x55555550ul, 0x55555555) + ROTL64(msg[0], 0 + 1) +
|
||||
ROTL64(msg[0+3], 0+4) - ROTL64(msg[0+10], 0+11) ) ^ hash[0+7]);
|
||||
(SHR(q[0], 1) ^ SHL(q[0], 2) ^ ROL(q[0], 13) ^ ROL(q[0], 43)) +
|
||||
(SHR(q[0+1], 2) ^ SHL(q[0+1], 1) ^ ROL(q[0+1], 19) ^ ROL(q[0+1], 53)) +
|
||||
(SHR(q[0+2], 2) ^ SHL(q[0+2], 2) ^ ROL(q[0+2], 28) ^ ROL(q[0+2], 59)) +
|
||||
(SHR(q[0+3], 1) ^ SHL(q[0+3], 3) ^ ROL(q[0+3], 4) ^ ROL(q[0+3], 37)) +
|
||||
(SHR(q[0+4], 1) ^ SHL(q[0+4], 2) ^ ROL(q[0+4], 13) ^ ROL(q[0+4], 43)) +
|
||||
(SHR(q[0+5], 2) ^ SHL(q[0+5], 1) ^ ROL(q[0+5], 19) ^ ROL(q[0+5], 53)) +
|
||||
(SHR(q[0+6], 2) ^ SHL(q[0+6], 2) ^ ROL(q[0+6], 28) ^ ROL(q[0+6], 59)) +
|
||||
(SHR(q[0+7], 1) ^ SHL(q[0+7], 3) ^ ROL(q[0+7], 4) ^ ROL(q[0+7], 37)) +
|
||||
(SHR(q[0+8], 1) ^ SHL(q[0+8], 2) ^ ROL(q[0+8], 13) ^ ROL(q[0+8], 43)) +
|
||||
(SHR(q[0+9], 2) ^ SHL(q[0+9], 1) ^ ROL(q[0+9], 19) ^ ROL(q[0+9], 53)) +
|
||||
(SHR(q[0+10], 2) ^ SHL(q[0+10], 2) ^ ROL(q[0+10], 28) ^ ROL(q[0+10], 59)) +
|
||||
(SHR(q[0+11], 1) ^ SHL(q[0+11], 3) ^ ROL(q[0+11], 4) ^ ROL(q[0+11], 37)) +
|
||||
(SHR(q[0+12], 1) ^ SHL(q[0+12], 2) ^ ROL(q[0+12], 13) ^ ROL(q[0+12], 43)) +
|
||||
(SHR(q[0+13], 2) ^ SHL(q[0+13], 1) ^ ROL(q[0+13], 19) ^ ROL(q[0+13], 53)) +
|
||||
(SHR(q[0+14], 2) ^ SHL(q[0+14], 2) ^ ROL(q[0+14], 28) ^ ROL(q[0+14], 59)) +
|
||||
(SHR(q[0+15], 1) ^ SHL(q[0+15], 3) ^ ROL(q[0+15], 4) ^ ROL(q[0+15], 37)) +
|
||||
((make_uint2(0x55555550ul, 0x55555555) + ROL(msg[0], 0 + 1) +
|
||||
ROL(msg[0+3], 0+4) - ROL(msg[0+10], 0+11) ) ^ hash[0+7]);
|
||||
|
||||
q[1 + 16] =
|
||||
(SHR(q[1], 1) ^ SHL(q[1], 2) ^ ROTL64(q[1], 13) ^ ROTL64(q[1], 43)) +
|
||||
(SHR(q[1 + 1], 2) ^ SHL(q[1 + 1], 1) ^ ROTL64(q[1 + 1], 19) ^ ROTL64(q[1 + 1], 53)) +
|
||||
(SHR(q[1 + 2], 2) ^ SHL(q[1 + 2], 2) ^ ROTL64(q[1 + 2], 28) ^ ROTL64(q[1 + 2], 59)) +
|
||||
(SHR(q[1 + 3], 1) ^ SHL(q[1 + 3], 3) ^ ROTL64(q[1 + 3], 4) ^ ROTL64(q[1 + 3], 37)) +
|
||||
(SHR(q[1 + 4], 1) ^ SHL(q[1 + 4], 2) ^ ROTL64(q[1 + 4], 13) ^ ROTL64(q[1 + 4], 43)) +
|
||||
(SHR(q[1 + 5], 2) ^ SHL(q[1 + 5], 1) ^ ROTL64(q[1 + 5], 19) ^ ROTL64(q[1 + 5], 53)) +
|
||||
(SHR(q[1 + 6], 2) ^ SHL(q[1 + 6], 2) ^ ROTL64(q[1 + 6], 28) ^ ROTL64(q[1 + 6], 59)) +
|
||||
(SHR(q[1 + 7], 1) ^ SHL(q[1 + 7], 3) ^ ROTL64(q[1 + 7], 4) ^ ROTL64(q[1 + 7], 37)) +
|
||||
(SHR(q[1 + 8], 1) ^ SHL(q[1 + 8], 2) ^ ROTL64(q[1 + 8], 13) ^ ROTL64(q[1 + 8], 43)) +
|
||||
(SHR(q[1 + 9], 2) ^ SHL(q[1 + 9], 1) ^ ROTL64(q[1 + 9], 19) ^ ROTL64(q[1 + 9], 53)) +
|
||||
(SHR(q[1 + 10], 2) ^ SHL(q[1 + 10], 2) ^ ROTL64(q[1 + 10], 28) ^ ROTL64(q[1 + 10], 59)) +
|
||||
(SHR(q[1 + 11], 1) ^ SHL(q[1 + 11], 3) ^ ROTL64(q[1 + 11], 4) ^ ROTL64(q[1 + 11], 37)) +
|
||||
(SHR(q[1 + 12], 1) ^ SHL(q[1 + 12], 2) ^ ROTL64(q[1 + 12], 13) ^ ROTL64(q[1 + 12], 43)) +
|
||||
(SHR(q[1 + 13], 2) ^ SHL(q[1 + 13], 1) ^ ROTL64(q[1 + 13], 19) ^ ROTL64(q[1 + 13], 53)) +
|
||||
(SHR(q[1 + 14], 2) ^ SHL(q[1 + 14], 2) ^ ROTL64(q[1 + 14], 28) ^ ROTL64(q[1 + 14], 59)) +
|
||||
(SHR(q[1 + 15], 1) ^ SHL(q[1 + 15], 3) ^ ROTL64(q[1 + 15], 4) ^ ROTL64(q[1 + 15], 37)) +
|
||||
((make_uint2(0xAAAAAAA5, 0x5AAAAAAA) + ROTL64(msg[1], 1 + 1) +
|
||||
ROTL64(msg[1 + 3], 1 + 4) - ROTL64(msg[1 + 10], 1 + 11)) ^ hash[1 + 7]);
|
||||
(SHR(q[1], 1) ^ SHL(q[1], 2) ^ ROL(q[1], 13) ^ ROL(q[1], 43)) +
|
||||
(SHR(q[1 + 1], 2) ^ SHL(q[1 + 1], 1) ^ ROL(q[1 + 1], 19) ^ ROL(q[1 + 1], 53)) +
|
||||
(SHR(q[1 + 2], 2) ^ SHL(q[1 + 2], 2) ^ ROL(q[1 + 2], 28) ^ ROL(q[1 + 2], 59)) +
|
||||
(SHR(q[1 + 3], 1) ^ SHL(q[1 + 3], 3) ^ ROL(q[1 + 3], 4) ^ ROL(q[1 + 3], 37)) +
|
||||
(SHR(q[1 + 4], 1) ^ SHL(q[1 + 4], 2) ^ ROL(q[1 + 4], 13) ^ ROL(q[1 + 4], 43)) +
|
||||
(SHR(q[1 + 5], 2) ^ SHL(q[1 + 5], 1) ^ ROL(q[1 + 5], 19) ^ ROL(q[1 + 5], 53)) +
|
||||
(SHR(q[1 + 6], 2) ^ SHL(q[1 + 6], 2) ^ ROL(q[1 + 6], 28) ^ ROL(q[1 + 6], 59)) +
|
||||
(SHR(q[1 + 7], 1) ^ SHL(q[1 + 7], 3) ^ ROL(q[1 + 7], 4) ^ ROL(q[1 + 7], 37)) +
|
||||
(SHR(q[1 + 8], 1) ^ SHL(q[1 + 8], 2) ^ ROL(q[1 + 8], 13) ^ ROL(q[1 + 8], 43)) +
|
||||
(SHR(q[1 + 9], 2) ^ SHL(q[1 + 9], 1) ^ ROL(q[1 + 9], 19) ^ ROL(q[1 + 9], 53)) +
|
||||
(SHR(q[1 + 10], 2) ^ SHL(q[1 + 10], 2) ^ ROL(q[1 + 10], 28) ^ ROL(q[1 + 10], 59)) +
|
||||
(SHR(q[1 + 11], 1) ^ SHL(q[1 + 11], 3) ^ ROL(q[1 + 11], 4) ^ ROL(q[1 + 11], 37)) +
|
||||
(SHR(q[1 + 12], 1) ^ SHL(q[1 + 12], 2) ^ ROL(q[1 + 12], 13) ^ ROL(q[1 + 12], 43)) +
|
||||
(SHR(q[1 + 13], 2) ^ SHL(q[1 + 13], 1) ^ ROL(q[1 + 13], 19) ^ ROL(q[1 + 13], 53)) +
|
||||
(SHR(q[1 + 14], 2) ^ SHL(q[1 + 14], 2) ^ ROL(q[1 + 14], 28) ^ ROL(q[1 + 14], 59)) +
|
||||
(SHR(q[1 + 15], 1) ^ SHL(q[1 + 15], 3) ^ ROL(q[1 + 15], 4) ^ ROL(q[1 + 15], 37)) +
|
||||
((make_uint2(0xAAAAAAA5, 0x5AAAAAAA) + ROL(msg[1], 1 + 1) +
|
||||
ROL(msg[1 + 3], 1 + 4) - ROL(msg[1 + 10], 1 + 11)) ^ hash[1 + 7]);
|
||||
|
||||
q[2 + 16] = CONST_EXP2(2) +
|
||||
((make_uint2(0xFFFFFFFA, 0x5FFFFFFF) + ROTL64(msg[2], 2 + 1) +
|
||||
ROTL64(msg[2+3], 2+4) - ROTL64(msg[2+10], 2+11) ) ^ hash[2+7]);
|
||||
((make_uint2(0xFFFFFFFA, 0x5FFFFFFF) + ROL(msg[2], 2 + 1) +
|
||||
ROL(msg[2+3], 2+4) - ROL(msg[2+10], 2+11) ) ^ hash[2+7]);
|
||||
q[3 + 16] = CONST_EXP2(3) +
|
||||
((make_uint2(0x5555554F, 0x65555555) + ROTL64(msg[3], 3 + 1) +
|
||||
ROTL64(msg[3 + 3], 3 + 4) - ROTL64(msg[3 + 10], 3 + 11)) ^ hash[3 + 7]);
|
||||
((make_uint2(0x5555554F, 0x65555555) + ROL(msg[3], 3 + 1) +
|
||||
ROL(msg[3 + 3], 3 + 4) - ROL(msg[3 + 10], 3 + 11)) ^ hash[3 + 7]);
|
||||
q[4 + 16] = CONST_EXP2(4) +
|
||||
((make_uint2(0xAAAAAAA4, 0x6AAAAAAA) + ROTL64(msg[4], 4 + 1) +
|
||||
ROTL64(msg[4 + 3], 4 + 4) - ROTL64(msg[4 + 10], 4 + 11)) ^ hash[4 + 7]);
|
||||
((make_uint2(0xAAAAAAA4, 0x6AAAAAAA) + ROL(msg[4], 4 + 1) +
|
||||
ROL(msg[4 + 3], 4 + 4) - ROL(msg[4 + 10], 4 + 11)) ^ hash[4 + 7]);
|
||||
q[5 + 16] = CONST_EXP2(5) +
|
||||
((make_uint2(0xFFFFFFF9, 0x6FFFFFFF) + ROTL64(msg[5], 5 + 1) +
|
||||
ROTL64(msg[5 + 3], 5 + 4) - ROTL64(msg[5 + 10], 5 + 11)) ^ hash[5 + 7]);
|
||||
((make_uint2(0xFFFFFFF9, 0x6FFFFFFF) + ROL(msg[5], 5 + 1) +
|
||||
ROL(msg[5 + 3], 5 + 4) - ROL(msg[5 + 10], 5 + 11)) ^ hash[5 + 7]);
|
||||
q[6 + 16] = CONST_EXP2(6) +
|
||||
((make_uint2(0x5555554E, 0x75555555)+ ROTL64(msg[6], 6 + 1) +
|
||||
ROTL64(msg[6 + 3], 6 + 4) - ROTL64(msg[6 - 6], (6 - 6) + 1)) ^ hash[6 + 7]);
|
||||
((make_uint2(0x5555554E, 0x75555555)+ ROL(msg[6], 6 + 1) +
|
||||
ROL(msg[6 + 3], 6 + 4) - ROL(msg[6 - 6], (6 - 6) + 1)) ^ hash[6 + 7]);
|
||||
q[7 + 16] = CONST_EXP2(7) +
|
||||
((make_uint2(0xAAAAAAA3, 0x7AAAAAAA) + ROTL64(msg[7], 7 + 1) +
|
||||
ROTL64(msg[7 + 3], 7 + 4) - ROTL64(msg[7 - 6], (7 - 6) + 1)) ^ hash[7 + 7]);
|
||||
((make_uint2(0xAAAAAAA3, 0x7AAAAAAA) + ROL(msg[7], 7 + 1) +
|
||||
ROL(msg[7 + 3], 7 + 4) - ROL(msg[7 - 6], (7 - 6) + 1)) ^ hash[7 + 7]);
|
||||
q[8 + 16] = CONST_EXP2(8) +
|
||||
((make_uint2(0xFFFFFFF8, 0x7FFFFFFF) + ROTL64(msg[8], 8 + 1) +
|
||||
ROTL64(msg[8 + 3], 8 + 4) - ROTL64(msg[8 - 6], (8 - 6) + 1)) ^ hash[8 + 7]);
|
||||
((make_uint2(0xFFFFFFF8, 0x7FFFFFFF) + ROL(msg[8], 8 + 1) +
|
||||
ROL(msg[8 + 3], 8 + 4) - ROL(msg[8 - 6], (8 - 6) + 1)) ^ hash[8 + 7]);
|
||||
q[9 + 16] = CONST_EXP2(9) +
|
||||
((make_uint2(0x5555554D, 0x85555555) + ROTL64(msg[9], 9 + 1) +
|
||||
ROTL64(msg[9 + 3], 9 + 4) - ROTL64(msg[9 - 6], (9 - 6) + 1)) ^ hash[9 - 9]);
|
||||
((make_uint2(0x5555554D, 0x85555555) + ROL(msg[9], 9 + 1) +
|
||||
ROL(msg[9 + 3], 9 + 4) - ROL(msg[9 - 6], (9 - 6) + 1)) ^ hash[9 - 9]);
|
||||
q[10 + 16] = CONST_EXP2(10) +
|
||||
((make_uint2(0xAAAAAAA2, 0x8AAAAAAA) + ROTL64(msg[10], 10 + 1) +
|
||||
ROTL64(msg[10 + 3], 10 + 4) - ROTL64(msg[10 - 6], (10 - 6) + 1)) ^ hash[10 - 9]);
|
||||
((make_uint2(0xAAAAAAA2, 0x8AAAAAAA) + ROL(msg[10], 10 + 1) +
|
||||
ROL(msg[10 + 3], 10 + 4) - ROL(msg[10 - 6], (10 - 6) + 1)) ^ hash[10 - 9]);
|
||||
q[11 + 16] = CONST_EXP2(11) +
|
||||
((make_uint2(0xFFFFFFF7, 0x8FFFFFFF) + ROTL64(msg[11], 11 + 1) +
|
||||
ROTL64(msg[11 + 3], 11 + 4) - ROTL64(msg[11 - 6], (11 - 6) + 1)) ^ hash[11 - 9]);
|
||||
((make_uint2(0xFFFFFFF7, 0x8FFFFFFF) + ROL(msg[11], 11 + 1) +
|
||||
ROL(msg[11 + 3], 11 + 4) - ROL(msg[11 - 6], (11 - 6) + 1)) ^ hash[11 - 9]);
|
||||
q[12 + 16] = CONST_EXP2(12) +
|
||||
((make_uint2(0x5555554C, 0x95555555) + ROTL64(msg[12], 12 + 1) +
|
||||
ROTL64(msg[12 + 3], 12 + 4) - ROTL64(msg[12 - 6], (12 - 6) + 1)) ^ hash[12 - 9]);
|
||||
((make_uint2(0x5555554C, 0x95555555) + ROL(msg[12], 12 + 1) +
|
||||
ROL(msg[12 + 3], 12 + 4) - ROL(msg[12 - 6], (12 - 6) + 1)) ^ hash[12 - 9]);
|
||||
q[13 + 16] = CONST_EXP2(13) +
|
||||
((make_uint2(0xAAAAAAA1, 0x9AAAAAAA) + ROTL64(msg[13], 13 + 1) +
|
||||
ROTL64(msg[13 - 13], (13 - 13) + 1) - ROTL64(msg[13 - 6], (13 - 6) + 1)) ^ hash[13 - 9]);
|
||||
((make_uint2(0xAAAAAAA1, 0x9AAAAAAA) + ROL(msg[13], 13 + 1) +
|
||||
ROL(msg[13 - 13], (13 - 13) + 1) - ROL(msg[13 - 6], (13 - 6) + 1)) ^ hash[13 - 9]);
|
||||
q[14 + 16] = CONST_EXP2(14) +
|
||||
((make_uint2(0xFFFFFFF6, 0x9FFFFFFF) + ROTL64(msg[14], 14 + 1) +
|
||||
ROTL64(msg[14 - 13], (14 - 13) + 1) - ROTL64(msg[14 - 6], (14 - 6) + 1)) ^ hash[14 - 9]);
|
||||
((make_uint2(0xFFFFFFF6, 0x9FFFFFFF) + ROL(msg[14], 14 + 1) +
|
||||
ROL(msg[14 - 13], (14 - 13) + 1) - ROL(msg[14 - 6], (14 - 6) + 1)) ^ hash[14 - 9]);
|
||||
q[15 + 16] = CONST_EXP2(15) +
|
||||
((make_uint2(0x5555554B, 0xA5555555) + ROTL64(msg[15], 15 + 1) +
|
||||
ROTL64(msg[15 - 13], (15 - 13) + 1) - ROTL64(msg[15 - 6], (15 - 6) + 1)) ^ hash[15 - 9]);
|
||||
((make_uint2(0x5555554B, 0xA5555555) + ROL(msg[15], 15 + 1) +
|
||||
ROL(msg[15 - 13], (15 - 13) + 1) - ROL(msg[15 - 6], (15 - 6) + 1)) ^ hash[15 - 9]);
|
||||
|
||||
uint2 XL64 = q[16]^q[17]^q[18]^q[19]^q[20]^q[21]^q[22]^q[23];
|
||||
uint2 XH64 = XL64^q[24] ^ q[25] ^ q[26] ^ q[27] ^ q[28] ^ q[29] ^ q[30] ^ q[31];
|
||||
|
||||
hash[0] = (SHL(XH64, 5) ^ SHR(q[16],5) ^ msg[ 0]) + ( XL64 ^ q[24] ^ q[ 0]);
|
||||
hash[1] = (SHR(XH64, 7) ^ SHL(q[17],8) ^ msg[ 1]) + ( XL64 ^ q[25] ^ q[ 1]);
|
||||
hash[2] = (SHR(XH64, 5) ^ SHL(q[18],5) ^ msg[ 2]) + ( XL64 ^ q[26] ^ q[ 2]);
|
||||
hash[3] = (SHR(XH64, 1) ^ SHL(q[19],5) ^ msg[ 3]) + ( XL64 ^ q[27] ^ q[ 3]);
|
||||
hash[4] = (SHR(XH64, 3) ^ q[20] ^ msg[ 4]) + ( XL64 ^ q[28] ^ q[ 4]);
|
||||
hash[5] = (SHL(XH64, 6) ^ SHR(q[21],6) ^ msg[ 5]) + ( XL64 ^ q[29] ^ q[ 5]);
|
||||
hash[6] = (SHR(XH64, 4) ^ SHL(q[22],6) ^ msg[ 6]) + ( XL64 ^ q[30] ^ q[ 6]);
|
||||
hash[7] = (SHR(XH64,11) ^ SHL(q[23],2) ^ msg[ 7]) + ( XL64 ^ q[31] ^ q[ 7]);
|
||||
hash[0] = (SHL(XH64, 5) ^ SHR(q[16],5) ^ msg[ 0]) + (XL64 ^ q[24] ^ q[ 0]);
|
||||
hash[1] = (SHR(XH64, 7) ^ SHL(q[17],8) ^ msg[ 1]) + (XL64 ^ q[25] ^ q[ 1]);
|
||||
hash[2] = (SHR(XH64, 5) ^ SHL(q[18],5) ^ msg[ 2]) + (XL64 ^ q[26] ^ q[ 2]);
|
||||
hash[3] = (SHR(XH64, 1) ^ SHL(q[19],5) ^ msg[ 3]) + (XL64 ^ q[27] ^ q[ 3]);
|
||||
hash[4] = (SHR(XH64, 3) ^ q[20] ^ msg[ 4]) + (XL64 ^ q[28] ^ q[ 4]);
|
||||
hash[5] = (SHL(XH64, 6) ^ SHR(q[21],6) ^ msg[ 5]) + (XL64 ^ q[29] ^ q[ 5]);
|
||||
hash[6] = (SHR(XH64, 4) ^ SHL(q[22],6) ^ msg[ 6]) + (XL64 ^ q[30] ^ q[ 6]);
|
||||
hash[7] = (SHR(XH64,11) ^ SHL(q[23],2) ^ msg[ 7]) + (XL64 ^ q[31] ^ q[ 7]);
|
||||
|
||||
hash[ 8] = ROTL64(hash[4], 9) + ( XH64 ^ q[24] ^ msg[ 8]) + (SHL(XL64,8) ^ q[23] ^ q[ 8]);
|
||||
hash[ 9] = ROTL64(hash[5],10) + ( XH64 ^ q[25] ^ msg[ 9]) + (SHR(XL64,6) ^ q[16] ^ q[ 9]);
|
||||
hash[10] = ROTL64(hash[6],11) + ( XH64 ^ q[26] ^ msg[10]) + (SHL(XL64,6) ^ q[17] ^ q[10]);
|
||||
hash[11] = ROTL64(hash[7],12) + ( XH64 ^ q[27] ^ msg[11]) + (SHL(XL64,4) ^ q[18] ^ q[11]);
|
||||
hash[12] = ROTL64(hash[0],13) + ( XH64 ^ q[28] ^ msg[12]) + (SHR(XL64,3) ^ q[19] ^ q[12]);
|
||||
hash[13] = ROTL64(hash[1],14) + ( XH64 ^ q[29] ^ msg[13]) + (SHR(XL64,4) ^ q[20] ^ q[13]);
|
||||
hash[14] = ROTL64(hash[2],15) + ( XH64 ^ q[30] ^ msg[14]) + (SHR(XL64,7) ^ q[21] ^ q[14]);
|
||||
hash[15] = ROTL64(hash[3],16) + (XH64 ^ q[31] ^ msg[15]) + (SHR(XL64, 2) ^ q[22] ^ q[15]);
|
||||
hash[ 8] = ROL(hash[4], 9) + (XH64 ^ q[24] ^ msg[ 8]) + (SHL(XL64,8) ^ q[23] ^ q[ 8]);
|
||||
hash[ 9] = ROL(hash[5],10) + (XH64 ^ q[25] ^ msg[ 9]) + (SHR(XL64,6) ^ q[16] ^ q[ 9]);
|
||||
hash[10] = ROL(hash[6],11) + (XH64 ^ q[26] ^ msg[10]) + (SHL(XL64,6) ^ q[17] ^ q[10]);
|
||||
hash[11] = ROL(hash[7],12) + (XH64 ^ q[27] ^ msg[11]) + (SHL(XL64,4) ^ q[18] ^ q[11]);
|
||||
hash[12] = ROL(hash[0],13) + (XH64 ^ q[28] ^ msg[12]) + (SHR(XL64,3) ^ q[19] ^ q[12]);
|
||||
hash[13] = ROL(hash[1],14) + (XH64 ^ q[29] ^ msg[13]) + (SHR(XL64,4) ^ q[20] ^ q[13]);
|
||||
hash[14] = ROL(hash[2],15) + (XH64 ^ q[30] ^ msg[14]) + (SHR(XL64,7) ^ q[21] ^ q[14]);
|
||||
hash[15] = ROL(hash[3],16) + (XH64 ^ q[31] ^ msg[15]) + (SHR(XL64, 2) ^ q[22] ^ q[15]);
|
||||
}
|
||||
|
||||
__global__
|
||||
@@ -323,8 +320,8 @@ void quark_bmw512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint64_t *
|
||||
{
|
||||
uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[8 * hashPosition];
|
||||
uint32_t hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[hashPosition * 8];
|
||||
|
||||
// Init
|
||||
uint2 h[16] = {
|
||||
@@ -349,10 +346,11 @@ void quark_bmw512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint64_t *
|
||||
// Nachricht kopieren (Achtung, die Nachricht hat 64 Byte,
|
||||
// BMW arbeitet mit 128 Byte!!!
|
||||
uint2 message[16];
|
||||
#pragma unroll 8
|
||||
#pragma unroll
|
||||
for(int i=0;i<8;i++)
|
||||
message[i] = vectorize(inpHash[i]);
|
||||
#pragma unroll 6
|
||||
|
||||
#pragma unroll 6
|
||||
for(int i=9;i<15;i++)
|
||||
message[i] = make_uint2(0,0);
|
||||
|
||||
@@ -365,7 +363,7 @@ void quark_bmw512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint64_t *
|
||||
Compression512_64_first(message, h);
|
||||
|
||||
// Final
|
||||
#pragma unroll 16
|
||||
#pragma unroll
|
||||
for(int i=0;i<16;i++)
|
||||
{
|
||||
message[i].y = 0xaaaaaaaa;
|
||||
@@ -374,9 +372,9 @@ void quark_bmw512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint64_t *
|
||||
Compression512(h, message);
|
||||
|
||||
// fertig
|
||||
uint64_t *outpHash = &g_hash[8 * hashPosition];
|
||||
uint64_t *outpHash = &g_hash[hashPosition * 8];
|
||||
|
||||
#pragma unroll 8
|
||||
#pragma unroll
|
||||
for(int i=0;i<8;i++)
|
||||
outpHash[i] = devectorize(message[i+8]);
|
||||
}
|
||||
@@ -430,7 +428,7 @@ void quark_bmw512_gpu_hash_80(uint32_t threads, uint32_t startNounce, uint64_t *
|
||||
Compression512(h, message);
|
||||
|
||||
// fertig
|
||||
uint64_t *outpHash = &g_hash[8 * thread];
|
||||
uint64_t *outpHash = &g_hash[thread * 8];
|
||||
|
||||
#pragma unroll 8
|
||||
for(int i=0;i<8;i++)
|
||||
|
||||
@@ -151,8 +151,8 @@ void quark_bmw512_gpu_hash_64_30(uint32_t threads, uint32_t startNounce, uint64_
|
||||
{
|
||||
uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[8 * hashPosition];
|
||||
uint32_t hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[hashPosition * 8];
|
||||
|
||||
// Init
|
||||
uint64_t h[16];
|
||||
@@ -205,7 +205,7 @@ void quark_bmw512_gpu_hash_64_30(uint32_t threads, uint32_t startNounce, uint64_
|
||||
|
||||
Compression512_30(h, message);
|
||||
|
||||
uint64_t *outpHash = &g_hash[8 * hashPosition];
|
||||
uint64_t *outpHash = &g_hash[hashPosition * 8];
|
||||
|
||||
#pragma unroll 8
|
||||
for(int i=0;i<8;i++)
|
||||
|
||||
+229
-186
@@ -1,245 +1,287 @@
|
||||
#include "cuda_helper.h"
|
||||
|
||||
__constant__ unsigned char c_E8_bitslice_roundconstant[42][32] = {
|
||||
{ 0x72, 0xd5, 0xde, 0xa2, 0xdf, 0x15, 0xf8, 0x67, 0x7b, 0x84, 0x15, 0xa, 0xb7, 0x23, 0x15, 0x57, 0x81, 0xab, 0xd6, 0x90, 0x4d, 0x5a, 0x87, 0xf6, 0x4e, 0x9f, 0x4f, 0xc5, 0xc3, 0xd1, 0x2b, 0x40 },
|
||||
{ 0xea, 0x98, 0x3a, 0xe0, 0x5c, 0x45, 0xfa, 0x9c, 0x3, 0xc5, 0xd2, 0x99, 0x66, 0xb2, 0x99, 0x9a, 0x66, 0x2, 0x96, 0xb4, 0xf2, 0xbb, 0x53, 0x8a, 0xb5, 0x56, 0x14, 0x1a, 0x88, 0xdb, 0xa2, 0x31 },
|
||||
{ 0x3, 0xa3, 0x5a, 0x5c, 0x9a, 0x19, 0xe, 0xdb, 0x40, 0x3f, 0xb2, 0xa, 0x87, 0xc1, 0x44, 0x10, 0x1c, 0x5, 0x19, 0x80, 0x84, 0x9e, 0x95, 0x1d, 0x6f, 0x33, 0xeb, 0xad, 0x5e, 0xe7, 0xcd, 0xdc },
|
||||
{ 0x10, 0xba, 0x13, 0x92, 0x2, 0xbf, 0x6b, 0x41, 0xdc, 0x78, 0x65, 0x15, 0xf7, 0xbb, 0x27, 0xd0, 0xa, 0x2c, 0x81, 0x39, 0x37, 0xaa, 0x78, 0x50, 0x3f, 0x1a, 0xbf, 0xd2, 0x41, 0x0, 0x91, 0xd3 },
|
||||
{ 0x42, 0x2d, 0x5a, 0xd, 0xf6, 0xcc, 0x7e, 0x90, 0xdd, 0x62, 0x9f, 0x9c, 0x92, 0xc0, 0x97, 0xce, 0x18, 0x5c, 0xa7, 0xb, 0xc7, 0x2b, 0x44, 0xac, 0xd1, 0xdf, 0x65, 0xd6, 0x63, 0xc6, 0xfc, 0x23 },
|
||||
{ 0x97, 0x6e, 0x6c, 0x3, 0x9e, 0xe0, 0xb8, 0x1a, 0x21, 0x5, 0x45, 0x7e, 0x44, 0x6c, 0xec, 0xa8, 0xee, 0xf1, 0x3, 0xbb, 0x5d, 0x8e, 0x61, 0xfa, 0xfd, 0x96, 0x97, 0xb2, 0x94, 0x83, 0x81, 0x97 },
|
||||
{ 0x4a, 0x8e, 0x85, 0x37, 0xdb, 0x3, 0x30, 0x2f, 0x2a, 0x67, 0x8d, 0x2d, 0xfb, 0x9f, 0x6a, 0x95, 0x8a, 0xfe, 0x73, 0x81, 0xf8, 0xb8, 0x69, 0x6c, 0x8a, 0xc7, 0x72, 0x46, 0xc0, 0x7f, 0x42, 0x14 },
|
||||
{ 0xc5, 0xf4, 0x15, 0x8f, 0xbd, 0xc7, 0x5e, 0xc4, 0x75, 0x44, 0x6f, 0xa7, 0x8f, 0x11, 0xbb, 0x80, 0x52, 0xde, 0x75, 0xb7, 0xae, 0xe4, 0x88, 0xbc, 0x82, 0xb8, 0x0, 0x1e, 0x98, 0xa6, 0xa3, 0xf4 },
|
||||
{ 0x8e, 0xf4, 0x8f, 0x33, 0xa9, 0xa3, 0x63, 0x15, 0xaa, 0x5f, 0x56, 0x24, 0xd5, 0xb7, 0xf9, 0x89, 0xb6, 0xf1, 0xed, 0x20, 0x7c, 0x5a, 0xe0, 0xfd, 0x36, 0xca, 0xe9, 0x5a, 0x6, 0x42, 0x2c, 0x36 },
|
||||
{ 0xce, 0x29, 0x35, 0x43, 0x4e, 0xfe, 0x98, 0x3d, 0x53, 0x3a, 0xf9, 0x74, 0x73, 0x9a, 0x4b, 0xa7, 0xd0, 0xf5, 0x1f, 0x59, 0x6f, 0x4e, 0x81, 0x86, 0xe, 0x9d, 0xad, 0x81, 0xaf, 0xd8, 0x5a, 0x9f },
|
||||
{ 0xa7, 0x5, 0x6, 0x67, 0xee, 0x34, 0x62, 0x6a, 0x8b, 0xb, 0x28, 0xbe, 0x6e, 0xb9, 0x17, 0x27, 0x47, 0x74, 0x7, 0x26, 0xc6, 0x80, 0x10, 0x3f, 0xe0, 0xa0, 0x7e, 0x6f, 0xc6, 0x7e, 0x48, 0x7b },
|
||||
{ 0xd, 0x55, 0xa, 0xa5, 0x4a, 0xf8, 0xa4, 0xc0, 0x91, 0xe3, 0xe7, 0x9f, 0x97, 0x8e, 0xf1, 0x9e, 0x86, 0x76, 0x72, 0x81, 0x50, 0x60, 0x8d, 0xd4, 0x7e, 0x9e, 0x5a, 0x41, 0xf3, 0xe5, 0xb0, 0x62 },
|
||||
{ 0xfc, 0x9f, 0x1f, 0xec, 0x40, 0x54, 0x20, 0x7a, 0xe3, 0xe4, 0x1a, 0x0, 0xce, 0xf4, 0xc9, 0x84, 0x4f, 0xd7, 0x94, 0xf5, 0x9d, 0xfa, 0x95, 0xd8, 0x55, 0x2e, 0x7e, 0x11, 0x24, 0xc3, 0x54, 0xa5 },
|
||||
{ 0x5b, 0xdf, 0x72, 0x28, 0xbd, 0xfe, 0x6e, 0x28, 0x78, 0xf5, 0x7f, 0xe2, 0xf, 0xa5, 0xc4, 0xb2, 0x5, 0x89, 0x7c, 0xef, 0xee, 0x49, 0xd3, 0x2e, 0x44, 0x7e, 0x93, 0x85, 0xeb, 0x28, 0x59, 0x7f },
|
||||
{ 0x70, 0x5f, 0x69, 0x37, 0xb3, 0x24, 0x31, 0x4a, 0x5e, 0x86, 0x28, 0xf1, 0x1d, 0xd6, 0xe4, 0x65, 0xc7, 0x1b, 0x77, 0x4, 0x51, 0xb9, 0x20, 0xe7, 0x74, 0xfe, 0x43, 0xe8, 0x23, 0xd4, 0x87, 0x8a },
|
||||
{ 0x7d, 0x29, 0xe8, 0xa3, 0x92, 0x76, 0x94, 0xf2, 0xdd, 0xcb, 0x7a, 0x9, 0x9b, 0x30, 0xd9, 0xc1, 0x1d, 0x1b, 0x30, 0xfb, 0x5b, 0xdc, 0x1b, 0xe0, 0xda, 0x24, 0x49, 0x4f, 0xf2, 0x9c, 0x82, 0xbf },
|
||||
{ 0xa4, 0xe7, 0xba, 0x31, 0xb4, 0x70, 0xbf, 0xff, 0xd, 0x32, 0x44, 0x5, 0xde, 0xf8, 0xbc, 0x48, 0x3b, 0xae, 0xfc, 0x32, 0x53, 0xbb, 0xd3, 0x39, 0x45, 0x9f, 0xc3, 0xc1, 0xe0, 0x29, 0x8b, 0xa0 },
|
||||
{ 0xe5, 0xc9, 0x5, 0xfd, 0xf7, 0xae, 0x9, 0xf, 0x94, 0x70, 0x34, 0x12, 0x42, 0x90, 0xf1, 0x34, 0xa2, 0x71, 0xb7, 0x1, 0xe3, 0x44, 0xed, 0x95, 0xe9, 0x3b, 0x8e, 0x36, 0x4f, 0x2f, 0x98, 0x4a },
|
||||
{ 0x88, 0x40, 0x1d, 0x63, 0xa0, 0x6c, 0xf6, 0x15, 0x47, 0xc1, 0x44, 0x4b, 0x87, 0x52, 0xaf, 0xff, 0x7e, 0xbb, 0x4a, 0xf1, 0xe2, 0xa, 0xc6, 0x30, 0x46, 0x70, 0xb6, 0xc5, 0xcc, 0x6e, 0x8c, 0xe6 },
|
||||
{ 0xa4, 0xd5, 0xa4, 0x56, 0xbd, 0x4f, 0xca, 0x0, 0xda, 0x9d, 0x84, 0x4b, 0xc8, 0x3e, 0x18, 0xae, 0x73, 0x57, 0xce, 0x45, 0x30, 0x64, 0xd1, 0xad, 0xe8, 0xa6, 0xce, 0x68, 0x14, 0x5c, 0x25, 0x67 },
|
||||
{ 0xa3, 0xda, 0x8c, 0xf2, 0xcb, 0xe, 0xe1, 0x16, 0x33, 0xe9, 0x6, 0x58, 0x9a, 0x94, 0x99, 0x9a, 0x1f, 0x60, 0xb2, 0x20, 0xc2, 0x6f, 0x84, 0x7b, 0xd1, 0xce, 0xac, 0x7f, 0xa0, 0xd1, 0x85, 0x18 },
|
||||
{ 0x32, 0x59, 0x5b, 0xa1, 0x8d, 0xdd, 0x19, 0xd3, 0x50, 0x9a, 0x1c, 0xc0, 0xaa, 0xa5, 0xb4, 0x46, 0x9f, 0x3d, 0x63, 0x67, 0xe4, 0x4, 0x6b, 0xba, 0xf6, 0xca, 0x19, 0xab, 0xb, 0x56, 0xee, 0x7e },
|
||||
{ 0x1f, 0xb1, 0x79, 0xea, 0xa9, 0x28, 0x21, 0x74, 0xe9, 0xbd, 0xf7, 0x35, 0x3b, 0x36, 0x51, 0xee, 0x1d, 0x57, 0xac, 0x5a, 0x75, 0x50, 0xd3, 0x76, 0x3a, 0x46, 0xc2, 0xfe, 0xa3, 0x7d, 0x70, 0x1 },
|
||||
{ 0xf7, 0x35, 0xc1, 0xaf, 0x98, 0xa4, 0xd8, 0x42, 0x78, 0xed, 0xec, 0x20, 0x9e, 0x6b, 0x67, 0x79, 0x41, 0x83, 0x63, 0x15, 0xea, 0x3a, 0xdb, 0xa8, 0xfa, 0xc3, 0x3b, 0x4d, 0x32, 0x83, 0x2c, 0x83 },
|
||||
{ 0xa7, 0x40, 0x3b, 0x1f, 0x1c, 0x27, 0x47, 0xf3, 0x59, 0x40, 0xf0, 0x34, 0xb7, 0x2d, 0x76, 0x9a, 0xe7, 0x3e, 0x4e, 0x6c, 0xd2, 0x21, 0x4f, 0xfd, 0xb8, 0xfd, 0x8d, 0x39, 0xdc, 0x57, 0x59, 0xef },
|
||||
{ 0x8d, 0x9b, 0xc, 0x49, 0x2b, 0x49, 0xeb, 0xda, 0x5b, 0xa2, 0xd7, 0x49, 0x68, 0xf3, 0x70, 0xd, 0x7d, 0x3b, 0xae, 0xd0, 0x7a, 0x8d, 0x55, 0x84, 0xf5, 0xa5, 0xe9, 0xf0, 0xe4, 0xf8, 0x8e, 0x65 },
|
||||
{ 0xa0, 0xb8, 0xa2, 0xf4, 0x36, 0x10, 0x3b, 0x53, 0xc, 0xa8, 0x7, 0x9e, 0x75, 0x3e, 0xec, 0x5a, 0x91, 0x68, 0x94, 0x92, 0x56, 0xe8, 0x88, 0x4f, 0x5b, 0xb0, 0x5c, 0x55, 0xf8, 0xba, 0xbc, 0x4c },
|
||||
{ 0xe3, 0xbb, 0x3b, 0x99, 0xf3, 0x87, 0x94, 0x7b, 0x75, 0xda, 0xf4, 0xd6, 0x72, 0x6b, 0x1c, 0x5d, 0x64, 0xae, 0xac, 0x28, 0xdc, 0x34, 0xb3, 0x6d, 0x6c, 0x34, 0xa5, 0x50, 0xb8, 0x28, 0xdb, 0x71 },
|
||||
{ 0xf8, 0x61, 0xe2, 0xf2, 0x10, 0x8d, 0x51, 0x2a, 0xe3, 0xdb, 0x64, 0x33, 0x59, 0xdd, 0x75, 0xfc, 0x1c, 0xac, 0xbc, 0xf1, 0x43, 0xce, 0x3f, 0xa2, 0x67, 0xbb, 0xd1, 0x3c, 0x2, 0xe8, 0x43, 0xb0 },
|
||||
{ 0x33, 0xa, 0x5b, 0xca, 0x88, 0x29, 0xa1, 0x75, 0x7f, 0x34, 0x19, 0x4d, 0xb4, 0x16, 0x53, 0x5c, 0x92, 0x3b, 0x94, 0xc3, 0xe, 0x79, 0x4d, 0x1e, 0x79, 0x74, 0x75, 0xd7, 0xb6, 0xee, 0xaf, 0x3f },
|
||||
{ 0xea, 0xa8, 0xd4, 0xf7, 0xbe, 0x1a, 0x39, 0x21, 0x5c, 0xf4, 0x7e, 0x9, 0x4c, 0x23, 0x27, 0x51, 0x26, 0xa3, 0x24, 0x53, 0xba, 0x32, 0x3c, 0xd2, 0x44, 0xa3, 0x17, 0x4a, 0x6d, 0xa6, 0xd5, 0xad },
|
||||
{ 0xb5, 0x1d, 0x3e, 0xa6, 0xaf, 0xf2, 0xc9, 0x8, 0x83, 0x59, 0x3d, 0x98, 0x91, 0x6b, 0x3c, 0x56, 0x4c, 0xf8, 0x7c, 0xa1, 0x72, 0x86, 0x60, 0x4d, 0x46, 0xe2, 0x3e, 0xcc, 0x8, 0x6e, 0xc7, 0xf6 },
|
||||
{ 0x2f, 0x98, 0x33, 0xb3, 0xb1, 0xbc, 0x76, 0x5e, 0x2b, 0xd6, 0x66, 0xa5, 0xef, 0xc4, 0xe6, 0x2a, 0x6, 0xf4, 0xb6, 0xe8, 0xbe, 0xc1, 0xd4, 0x36, 0x74, 0xee, 0x82, 0x15, 0xbc, 0xef, 0x21, 0x63 },
|
||||
{ 0xfd, 0xc1, 0x4e, 0xd, 0xf4, 0x53, 0xc9, 0x69, 0xa7, 0x7d, 0x5a, 0xc4, 0x6, 0x58, 0x58, 0x26, 0x7e, 0xc1, 0x14, 0x16, 0x6, 0xe0, 0xfa, 0x16, 0x7e, 0x90, 0xaf, 0x3d, 0x28, 0x63, 0x9d, 0x3f },
|
||||
{ 0xd2, 0xc9, 0xf2, 0xe3, 0x0, 0x9b, 0xd2, 0xc, 0x5f, 0xaa, 0xce, 0x30, 0xb7, 0xd4, 0xc, 0x30, 0x74, 0x2a, 0x51, 0x16, 0xf2, 0xe0, 0x32, 0x98, 0xd, 0xeb, 0x30, 0xd8, 0xe3, 0xce, 0xf8, 0x9a },
|
||||
{ 0x4b, 0xc5, 0x9e, 0x7b, 0xb5, 0xf1, 0x79, 0x92, 0xff, 0x51, 0xe6, 0x6e, 0x4, 0x86, 0x68, 0xd3, 0x9b, 0x23, 0x4d, 0x57, 0xe6, 0x96, 0x67, 0x31, 0xcc, 0xe6, 0xa6, 0xf3, 0x17, 0xa, 0x75, 0x5 },
|
||||
{ 0xb1, 0x76, 0x81, 0xd9, 0x13, 0x32, 0x6c, 0xce, 0x3c, 0x17, 0x52, 0x84, 0xf8, 0x5, 0xa2, 0x62, 0xf4, 0x2b, 0xcb, 0xb3, 0x78, 0x47, 0x15, 0x47, 0xff, 0x46, 0x54, 0x82, 0x23, 0x93, 0x6a, 0x48 },
|
||||
{ 0x38, 0xdf, 0x58, 0x7, 0x4e, 0x5e, 0x65, 0x65, 0xf2, 0xfc, 0x7c, 0x89, 0xfc, 0x86, 0x50, 0x8e, 0x31, 0x70, 0x2e, 0x44, 0xd0, 0xb, 0xca, 0x86, 0xf0, 0x40, 0x9, 0xa2, 0x30, 0x78, 0x47, 0x4e },
|
||||
{ 0x65, 0xa0, 0xee, 0x39, 0xd1, 0xf7, 0x38, 0x83, 0xf7, 0x5e, 0xe9, 0x37, 0xe4, 0x2c, 0x3a, 0xbd, 0x21, 0x97, 0xb2, 0x26, 0x1, 0x13, 0xf8, 0x6f, 0xa3, 0x44, 0xed, 0xd1, 0xef, 0x9f, 0xde, 0xe7 },
|
||||
{ 0x8b, 0xa0, 0xdf, 0x15, 0x76, 0x25, 0x92, 0xd9, 0x3c, 0x85, 0xf7, 0xf6, 0x12, 0xdc, 0x42, 0xbe, 0xd8, 0xa7, 0xec, 0x7c, 0xab, 0x27, 0xb0, 0x7e, 0x53, 0x8d, 0x7d, 0xda, 0xaa, 0x3e, 0xa8, 0xde },
|
||||
{ 0xaa, 0x25, 0xce, 0x93, 0xbd, 0x2, 0x69, 0xd8, 0x5a, 0xf6, 0x43, 0xfd, 0x1a, 0x73, 0x8, 0xf9, 0xc0, 0x5f, 0xef, 0xda, 0x17, 0x4a, 0x19, 0xa5, 0x97, 0x4d, 0x66, 0x33, 0x4c, 0xfd, 0x21, 0x6a },
|
||||
{ 0x35, 0xb4, 0x98, 0x31, 0xdb, 0x41, 0x15, 0x70, 0xea, 0x1e, 0xf, 0xbb, 0xed, 0xcd, 0x54, 0x9b, 0x9a, 0xd0, 0x63, 0xa1, 0x51, 0x97, 0x40, 0x72, 0xf6, 0x75, 0x9d, 0xbf, 0x91, 0x47, 0x6f, 0xe2 } };
|
||||
// #include <stdio.h> // printf
|
||||
// #include <unistd.h> // sleep
|
||||
|
||||
#define SWAP4(x,y)\
|
||||
y = (x & 0xf0f0f0f0UL); \
|
||||
x = (x ^ y); \
|
||||
y = (y >> 4); \
|
||||
x = (x << 4); \
|
||||
x= x | y;
|
||||
/* 1344 bytes */
|
||||
__constant__ static __align__(16) uint32_t c_E8_bslice32[42][8] = {
|
||||
// Round 0 (Function0)
|
||||
{ 0xa2ded572, 0x90d6ab81, 0x67f815df, 0xf6875a4d, 0x0a15847b, 0xc54f9f4e, 0x571523b7, 0x402bd1c3 },
|
||||
{ 0xe03a98ea, 0xb4960266, 0x9cfa455c, 0x8a53bbf2, 0x99d2c503, 0x1a1456b5, 0x9a99b266, 0x31a2db88 }, // 1
|
||||
{ 0x5c5aa303, 0x8019051c, 0xdb0e199a, 0x1d959e84, 0x0ab23f40, 0xadeb336f, 0x1044c187, 0xdccde75e }, // 2
|
||||
{ 0x9213ba10, 0x39812c0a, 0x416bbf02, 0x5078aa37, 0x156578dc, 0xd2bf1a3f, 0xd027bbf7, 0xd3910041 }, // 3
|
||||
{ 0x0d5a2d42, 0x0ba75c18, 0x907eccf6, 0xac442bc7, 0x9c9f62dd, 0xd665dfd1, 0xce97c092, 0x23fcc663 }, // 4
|
||||
{ 0x036c6e97, 0xbb03f1ee, 0x1ab8e09e, 0xfa618e5d, 0x7e450521, 0xb29796fd, 0xa8ec6c44, 0x97818394 }, // 5
|
||||
{ 0x37858e4a, 0x8173fe8a, 0x2f3003db, 0x6c69b8f8, 0x2d8d672a, 0x4672c78a, 0x956a9ffb, 0x14427fc0 }, // 6
|
||||
// Round 7 (Function0)
|
||||
{ 0x8f15f4c5, 0xb775de52, 0xc45ec7bd, 0xbc88e4ae, 0xa76f4475, 0x1e00b882, 0x80bb118f, 0xf4a3a698 },
|
||||
{ 0x338ff48e, 0x20edf1b6, 0x1563a3a9, 0xfde05a7c, 0x24565faa, 0x5ae9ca36, 0x89f9b7d5, 0x362c4206 },
|
||||
{ 0x433529ce, 0x591ff5d0, 0x3d98fe4e, 0x86814e6f, 0x74f93a53, 0x81ad9d0e, 0xa74b9a73, 0x9f5ad8af },
|
||||
{ 0x670605a7, 0x26077447, 0x6a6234ee, 0x3f1080c6, 0xbe280b8b, 0x6f7ea0e0, 0x2717b96e, 0x7b487ec6 },
|
||||
{ 0xa50a550d, 0x81727686, 0xc0a4f84a, 0xd48d6050, 0x9fe7e391, 0x415a9e7e, 0x9ef18e97, 0x62b0e5f3 },
|
||||
{ 0xec1f9ffc, 0xf594d74f, 0x7a205440, 0xd895fa9d, 0x001ae4e3, 0x117e2e55, 0x84c9f4ce, 0xa554c324 },
|
||||
{ 0x2872df5b, 0xef7c8905, 0x286efebd, 0x2ed349ee, 0xe27ff578, 0x85937e44, 0xb2c4a50f, 0x7f5928eb },
|
||||
// Round 14 (Function0)
|
||||
{ 0x37695f70, 0x04771bc7, 0x4a3124b3, 0xe720b951, 0xf128865e, 0xe843fe74, 0x65e4d61d, 0x8a87d423 },
|
||||
{ 0xa3e8297d, 0xfb301b1d, 0xf2947692, 0xe01bdc5b, 0x097acbdd, 0x4f4924da, 0xc1d9309b, 0xbf829cf2 },
|
||||
{ 0x31bae7a4, 0x32fcae3b, 0xffbf70b4, 0x39d3bb53, 0x0544320d, 0xc1c39f45, 0x48bcf8de, 0xa08b29e0 },
|
||||
{ 0xfd05c9e5, 0x01b771a2, 0x0f09aef7, 0x95ed44e3, 0x12347094, 0x368e3be9, 0x34f19042, 0x4a982f4f },
|
||||
{ 0x631d4088, 0xf14abb7e, 0x15f66ca0, 0x30c60ae2, 0x4b44c147, 0xc5b67046, 0xffaf5287, 0xe68c6ecc },
|
||||
{ 0x56a4d5a4, 0x45ce5773, 0x00ca4fbd, 0xadd16430, 0x4b849dda, 0x68cea6e8, 0xae183ec8, 0x67255c14 },
|
||||
{ 0xf28cdaa3, 0x20b2601f, 0x16e10ecb, 0x7b846fc2, 0x5806e933, 0x7facced1, 0x9a99949a, 0x1885d1a0 },
|
||||
// Round 21 (Function0)
|
||||
{ 0xa15b5932, 0x67633d9f, 0xd319dd8d, 0xba6b04e4, 0xc01c9a50, 0xab19caf6, 0x46b4a5aa, 0x7eee560b },
|
||||
{ 0xea79b11f, 0x5aac571d, 0x742128a9, 0x76d35075, 0x35f7bde9, 0xfec2463a, 0xee51363b, 0x01707da3 },
|
||||
{ 0xafc135f7, 0x15638341, 0x42d8a498, 0xa8db3aea, 0x20eced78, 0x4d3bc3fa, 0x79676b9e, 0x832c8332 },
|
||||
{ 0x1f3b40a7, 0x6c4e3ee7, 0xf347271c, 0xfd4f21d2, 0x34f04059, 0x398dfdb8, 0x9a762db7, 0xef5957dc },
|
||||
{ 0x490c9b8d, 0xd0ae3b7d, 0xdaeb492b, 0x84558d7a, 0x49d7a25b, 0xf0e9a5f5, 0x0d70f368, 0x658ef8e4 },
|
||||
{ 0xf4a2b8a0, 0x92946891, 0x533b1036, 0x4f88e856, 0x9e07a80c, 0x555cb05b, 0x5aec3e75, 0x4cbcbaf8 },
|
||||
{ 0x993bbbe3, 0x28acae64, 0x7b9487f3, 0x6db334dc, 0xd6f4da75, 0x50a5346c, 0x5d1c6b72, 0x71db28b8 },
|
||||
// Round 28 (Function0)
|
||||
{ 0xf2e261f8, 0xf1bcac1c, 0x2a518d10, 0xa23fce43, 0x3364dbe3, 0x3cd1bb67, 0xfc75dd59, 0xb043e802 },
|
||||
{ 0xca5b0a33, 0xc3943b92, 0x75a12988, 0x1e4d790e, 0x4d19347f, 0xd7757479, 0x5c5316b4, 0x3fafeeb6 },
|
||||
{ 0xf7d4a8ea, 0x5324a326, 0x21391abe, 0xd23c32ba, 0x097ef45c, 0x4a17a344, 0x5127234c, 0xadd5a66d },
|
||||
{ 0xa63e1db5, 0xa17cf84c, 0x08c9f2af, 0x4d608672, 0x983d5983, 0xcc3ee246, 0x563c6b91, 0xf6c76e08 },
|
||||
{ 0xb333982f, 0xe8b6f406, 0x5e76bcb1, 0x36d4c1be, 0xa566d62b, 0x1582ee74, 0x2ae6c4ef, 0x6321efbc },
|
||||
{ 0x0d4ec1fd, 0x1614c17e, 0x69c953f4, 0x16fae006, 0xc45a7da7, 0x3daf907e, 0x26585806, 0x3f9d6328 },
|
||||
{ 0xe3f2c9d2, 0x16512a74, 0x0cd29b00, 0x9832e0f2, 0x30ceaa5f, 0xd830eb0d, 0x300cd4b7, 0x9af8cee3 },
|
||||
// Round 35 (Function0)
|
||||
{ 0x7b9ec54b, 0x574d239b, 0x9279f1b5, 0x316796e6, 0x6ee651ff, 0xf3a6e6cc, 0xd3688604, 0x05750a17 },
|
||||
{ 0xd98176b1, 0xb3cb2bf4, 0xce6c3213, 0x47154778, 0x8452173c, 0x825446ff, 0x62a205f8, 0x486a9323 },
|
||||
{ 0x0758df38, 0x442e7031, 0x65655e4e, 0x86ca0bd0, 0x897cfcf2, 0xa20940f0, 0x8e5086fc, 0x4e477830 },
|
||||
{ 0x39eea065, 0x26b29721, 0x8338f7d1, 0x6ff81301, 0x37e95ef7, 0xd1ed44a3, 0xbd3a2ce4, 0xe7de9fef },
|
||||
{ 0x15dfa08b, 0x7ceca7d8, 0xd9922576, 0x7eb027ab, 0xf6f7853c, 0xda7d8d53, 0xbe42dc12, 0xdea83eaa },
|
||||
{ 0x93ce25aa, 0xdaef5fc0, 0xd86902bd, 0xa5194a17, 0xfd43f65a, 0x33664d97, 0xf908731a, 0x6a21fd4c },
|
||||
{ 0x3198b435, 0xa163d09a, 0x701541db, 0x72409751, 0xbb0f1eea, 0xbf9d75f6, 0x9b54cded, 0xe26f4791 }
|
||||
// 42 rounds...
|
||||
};
|
||||
|
||||
#define SWAP2(x,y)\
|
||||
y = (x & 0xccccccccUL); \
|
||||
x = (x ^ y); \
|
||||
y = (y >> 2); \
|
||||
x = (x << 2); \
|
||||
x= x | y;
|
||||
|
||||
#define SWAP1(x,y)\
|
||||
y = (x & 0xaaaaaaaaUL); \
|
||||
x = (x ^ y); \
|
||||
y = (y >> 1); \
|
||||
x = x + x; \
|
||||
x= x | y;
|
||||
/*swapping bits 16i||16i+1||......||16i+7 with bits 16i+8||16i+9||......||16i+15 of 32-bit x*/
|
||||
//#define SWAP8(x) (x) = ((((x) & 0x00ff00ffUL) << 8) | (((x) & 0xff00ff00UL) >> 8));
|
||||
#define SWAP8(x) (x) = __byte_perm(x, x, 0x2301);
|
||||
/*swapping bits 32i||32i+1||......||32i+15 with bits 32i+16||32i+17||......||32i+31 of 32-bit x*/
|
||||
//#define SWAP16(x) (x) = ((((x) & 0x0000ffffUL) << 16) | (((x) & 0xffff0000UL) >> 16));
|
||||
#define SWAP16(x) (x) = __byte_perm(x, x, 0x1032);
|
||||
|
||||
/*The MDS transform*/
|
||||
#define L(m0,m1,m2,m3,m4,m5,m6,m7) \
|
||||
(m4) ^= (m1); \
|
||||
(m5) ^= (m2); \
|
||||
(m6) ^= (m0) ^ (m3); \
|
||||
(m7) ^= (m0); \
|
||||
(m0) ^= (m5); \
|
||||
(m1) ^= (m6); \
|
||||
(m2) ^= (m4) ^ (m7); \
|
||||
(m3) ^= (m4);
|
||||
/*swapping bits 16i||16i+1||......||16i+7 with bits 16i+8||16i+9||......||16i+15 of 32-bit x*/
|
||||
//#define SWAP8(x) (x) = ((((x) & 0x00ff00ffUL) << 8) | (((x) & 0xff00ff00UL) >> 8));
|
||||
#define SWAP8(x) (x) = __byte_perm(x, x, 0x2301);
|
||||
|
||||
/*The Sbox*/
|
||||
#define Sbox(m0,m1,m2,m3,cc) \
|
||||
/*
|
||||
__device__ __forceinline__
|
||||
static void SWAP4(uint32_t &x) {
|
||||
uint32_t y = x & 0xF0F0F0F0;
|
||||
x = (x ^ y) << 4;
|
||||
x |= y >> 4;
|
||||
}
|
||||
__device__ __forceinline__
|
||||
static void SWAP2(uint32_t &x) {
|
||||
uint32_t y = (x & 0xCCCCCCCC);
|
||||
x = (x ^ y) << 2;
|
||||
x |= y >> 2;
|
||||
}
|
||||
__device__ __forceinline__
|
||||
static void SWAP1(uint32_t &x) {
|
||||
uint32_t y = (x & 0xAAAAAAAA);
|
||||
x = (x ^ y) << 1;
|
||||
x |= y >> 1;
|
||||
}
|
||||
*/
|
||||
|
||||
__device__ __forceinline__
|
||||
static void SWAP4x4(uint32_t *x) {
|
||||
#pragma nounroll
|
||||
// y is used as tmp register too
|
||||
for (uint32_t y=0; y<4; y++, ++x) {
|
||||
asm("and.b32 %1, %0, 0xF0F0F0F0;"
|
||||
"xor.b32 %0, %0, %1;"
|
||||
"shr.b32 %1, %1, 4;"
|
||||
"vshl.u32.u32.u32.clamp.add %0, %0, 4, %1;\n\t"
|
||||
: "+r"(*x) : "r"(y));
|
||||
}
|
||||
}
|
||||
|
||||
__device__ __forceinline__
|
||||
static void SWAP2x4(uint32_t *x) {
|
||||
#pragma nounroll
|
||||
// y is used as tmp register too
|
||||
for (uint32_t y=0; y<4; y++, ++x) {
|
||||
asm("and.b32 %1, %0, 0xCCCCCCCC;"
|
||||
"xor.b32 %0, %0, %1;"
|
||||
"shr.b32 %1, %1, 2;"
|
||||
"vshl.u32.u32.u32.clamp.add %0, %0, 2, %1;\n\t"
|
||||
: "+r"(*x) : "r"(y));
|
||||
}
|
||||
}
|
||||
|
||||
__device__ __forceinline__
|
||||
static void SWAP1x4(uint32_t *x) {
|
||||
#pragma nounroll
|
||||
// y is used as tmp register too
|
||||
for (uint32_t y=0; y<4; y++, ++x) {
|
||||
asm("and.b32 %1, %0, 0xAAAAAAAA;"
|
||||
"xor.b32 %0, %0, %1;"
|
||||
"shr.b32 %1, %1, 1;"
|
||||
"vshl.u32.u32.u32.clamp.add %0, %0, 1, %1;\n\t"
|
||||
: "+r"(*x) : "r"(y));
|
||||
}
|
||||
}
|
||||
|
||||
/* The MDS transform */
|
||||
#define L(m0,m1,m2,m3,m4,m5,m6,m7) \
|
||||
m4 ^= m1; \
|
||||
m5 ^= m2; \
|
||||
m6 ^= m0 ^ m3; \
|
||||
m7 ^= m0; \
|
||||
m0 ^= m5; \
|
||||
m1 ^= m6; \
|
||||
m2 ^= m4 ^ m7; \
|
||||
m3 ^= m4;
|
||||
|
||||
/* The Sbox */
|
||||
#define Sbox(m0, m1, m2, m3, cc) \
|
||||
m3 = ~(m3); \
|
||||
m0 ^= ((~(m2)) & (cc)); \
|
||||
temp0 = (cc) ^ ((m0) & (m1));\
|
||||
m0 ^= ((m2) & (m3)); \
|
||||
m3 ^= ((~(m1)) & (m2)); \
|
||||
m1 ^= ((m0) & (m2)); \
|
||||
m2 ^= ((m0) & (~(m3))); \
|
||||
m0 ^= ((m1) | (m3)); \
|
||||
m3 ^= ((m1) & (m2)); \
|
||||
m1 ^= (temp0 & (m0)); \
|
||||
m0 ^= (~(m2)) & cc; \
|
||||
temp0 = cc ^ (m0 & m1); \
|
||||
m0 ^= m2 & m3; \
|
||||
m3 ^= (~(m1)) & m2; \
|
||||
m1 ^= m0 & m2; \
|
||||
m2 ^= m0 & (~(m3)); \
|
||||
m0 ^= m1 | m3; \
|
||||
m3 ^= m1 & m2; \
|
||||
m1 ^= temp0 & m0; \
|
||||
m2 ^= temp0;
|
||||
|
||||
static __device__ __forceinline__ void Sbox_and_MDS_layer(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void Sbox_and_MDS_layer(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
uint32_t temp0;
|
||||
uint32_t cc0, cc1;
|
||||
//Sbox and MDS layer
|
||||
#pragma unroll 4
|
||||
for (int i = 0; i < 4; i++) {
|
||||
cc0 = ((uint32_t*)c_E8_bitslice_roundconstant[roundnumber])[i];
|
||||
cc1 = ((uint32_t*)c_E8_bitslice_roundconstant[roundnumber])[i + 4];
|
||||
Sbox(x[0][i], x[2][i], x[4][i], x[6][i], cc0);
|
||||
Sbox(x[1][i], x[3][i], x[5][i], x[7][i], cc1);
|
||||
uint2* cc = (uint2*) &c_E8_bslice32[rnd];
|
||||
|
||||
// Sbox and MDS layer
|
||||
#pragma unroll
|
||||
for (int i = 0; i < 4; i++, ++cc) {
|
||||
uint32_t temp0;
|
||||
Sbox(x[0][i], x[2][i], x[4][i], x[6][i], cc->x);
|
||||
Sbox(x[1][i], x[3][i], x[5][i], x[7][i], cc->y);
|
||||
L(x[0][i], x[2][i], x[4][i], x[6][i], x[1][i], x[3][i], x[5][i], x[7][i]);
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ void RoundFunction0(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void RoundFunction0(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
Sbox_and_MDS_layer(x, roundnumber);
|
||||
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j = j + 2)
|
||||
{
|
||||
uint32_t y;
|
||||
SWAP1(x[j][0], y);
|
||||
SWAP1(x[j][1], y);
|
||||
SWAP1(x[j][2], y);
|
||||
SWAP1(x[j][3], y);
|
||||
Sbox_and_MDS_layer(x, rnd + 0); // 0, 7, 14 .. 35
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j += 2) { // 1, 3, 5, 7 (Even)
|
||||
SWAP1x4(x[j]);
|
||||
// SWAP1(x[j][0]); SWAP1(x[j][1]); SWAP1(x[j][2]); SWAP1(x[j][3]);
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ void RoundFunction1(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void RoundFunction1(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
Sbox_and_MDS_layer(x, roundnumber);
|
||||
Sbox_and_MDS_layer(x, rnd + 1);
|
||||
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j = j + 2)
|
||||
{
|
||||
uint32_t y;
|
||||
SWAP2(x[j][0], y);
|
||||
SWAP2(x[j][1], y);
|
||||
SWAP2(x[j][2], y);
|
||||
SWAP2(x[j][3], y);
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j += 2) {
|
||||
SWAP2x4(x[j]);
|
||||
// SWAP2(x[j][0]); SWAP2(x[j][1]); SWAP2(x[j][2]); SWAP2(x[j][3]);
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ void RoundFunction2(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void RoundFunction2(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
Sbox_and_MDS_layer(x, roundnumber);
|
||||
Sbox_and_MDS_layer(x, rnd + 2);
|
||||
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j = j + 2)
|
||||
{
|
||||
uint32_t y;
|
||||
SWAP4(x[j][0], y);
|
||||
SWAP4(x[j][1], y);
|
||||
SWAP4(x[j][2], y);
|
||||
SWAP4(x[j][3], y);
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j += 2) {
|
||||
SWAP4x4(x[j]);
|
||||
// SWAP4(x[j][0]); SWAP4(x[j][1]); SWAP4(x[j][2]); SWAP4(x[j][3]);
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ void RoundFunction3(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void RoundFunction3(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
Sbox_and_MDS_layer(x, roundnumber);
|
||||
Sbox_and_MDS_layer(x, rnd + 3);
|
||||
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j = j + 2)
|
||||
{
|
||||
#pragma unroll 4
|
||||
for (int i = 0; i < 4; i++) SWAP8(x[j][i]);
|
||||
//uint32_t* xj = x[j];
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j += 2) {
|
||||
SWAP8(x[j][0]);
|
||||
SWAP8(x[j][1]);
|
||||
SWAP8(x[j][2]);
|
||||
SWAP8(x[j][3]);
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ void RoundFunction4(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void RoundFunction4(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
Sbox_and_MDS_layer(x, roundnumber);
|
||||
Sbox_and_MDS_layer(x, rnd + 4);
|
||||
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j = j + 2)
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j += 2)
|
||||
{
|
||||
#pragma unroll 4
|
||||
for (int i = 0; i < 4; i++) SWAP16(x[j][i]);
|
||||
//uint32_t* xj = x[j];
|
||||
#pragma unroll
|
||||
for (int i = 0; i < 4; i++)
|
||||
SWAP16(x[j][i]);
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ void RoundFunction5(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void RoundFunction5(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
uint32_t temp0;
|
||||
Sbox_and_MDS_layer(x, rnd + 5);
|
||||
|
||||
Sbox_and_MDS_layer(x, roundnumber);
|
||||
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j = j + 2)
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j += 2)
|
||||
{
|
||||
#pragma unroll 2
|
||||
for (int i = 0; i < 4; i = i + 2) {
|
||||
temp0 = x[j][i]; x[j][i] = x[j][i + 1]; x[j][i + 1] = temp0;
|
||||
}
|
||||
xchg(x[j][0], x[j][1]);
|
||||
xchg(x[j][2], x[j][3]);
|
||||
}
|
||||
}
|
||||
|
||||
static __device__ __forceinline__ void RoundFunction6(uint32_t x[8][4], uint32_t roundnumber)
|
||||
__device__ __forceinline__
|
||||
static void RoundFunction6(uint32_t x[8][4], const int rnd)
|
||||
{
|
||||
uint32_t temp0;
|
||||
Sbox_and_MDS_layer(x, rnd + 6);
|
||||
|
||||
Sbox_and_MDS_layer(x, roundnumber);
|
||||
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j = j + 2)
|
||||
#pragma unroll 4
|
||||
for (int j = 1; j < 8; j += 2)
|
||||
{
|
||||
#pragma unroll 2
|
||||
for (int i = 0; i < 2; i++) {
|
||||
temp0 = x[j][i]; x[j][i] = x[j][i + 2]; x[j][i + 2] = temp0;
|
||||
}
|
||||
xchg(x[j][0], x[j][2]);
|
||||
xchg(x[j][1], x[j][3]);
|
||||
}
|
||||
}
|
||||
|
||||
/*The bijective function E8, in bitslice form */
|
||||
static __device__ __forceinline__ void E8(uint32_t x[8][4])
|
||||
/* The bijective function E8, in bitslice form */
|
||||
__device__
|
||||
static void E8(uint32_t x[8][4])
|
||||
{
|
||||
/*perform 6 rounds*/
|
||||
//#pragma unroll 6
|
||||
for (int i = 0; i < 42; i += 7)
|
||||
/* perform 6 loops of 7 rounds */
|
||||
for (int r = 0; r < 42; r += 7)
|
||||
{
|
||||
RoundFunction0(x, i);
|
||||
RoundFunction1(x, i + 1);
|
||||
RoundFunction2(x, i + 2);
|
||||
RoundFunction3(x, i + 3);
|
||||
RoundFunction4(x, i + 4);
|
||||
RoundFunction5(x, i + 5);
|
||||
RoundFunction6(x, i + 6);
|
||||
RoundFunction0(x, r);
|
||||
RoundFunction1(x, r);
|
||||
RoundFunction2(x, r);
|
||||
RoundFunction3(x, r);
|
||||
RoundFunction4(x, r);
|
||||
RoundFunction5(x, r);
|
||||
RoundFunction6(x, r);
|
||||
}
|
||||
}
|
||||
|
||||
// Die Hash-Funktion
|
||||
__global__ __launch_bounds__(256, 4)
|
||||
void quark_jh512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint32_t *const __restrict__ g_hash, const uint32_t *const __restrict__ g_nonceVector)
|
||||
void quark_jh512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint32_t* g_hash, const uint32_t *const __restrict__ g_nonceVector)
|
||||
{
|
||||
const uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
{
|
||||
const uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
const uint32_t hashPosition = nounce - startNounce;
|
||||
uint32_t *const Hash = &g_hash[hashPosition * 16U];
|
||||
uint32_t x[8][4] = {
|
||||
uint32_t hashPosition = nounce - startNounce;
|
||||
uint32_t *Hash = &g_hash[hashPosition * 16U];
|
||||
uint32_t x[8][4] = { /* init */
|
||||
{ 0x964bd16f, 0x17aa003e, 0x052e6a63, 0x43d5157a },
|
||||
{ 0x8d5e228a, 0x0bef970c, 0x591234e9, 0x61c3b3f2 },
|
||||
{ 0xc1a01d89, 0x1e806f53, 0x6b05a92a, 0x806d2bea },
|
||||
@@ -250,21 +292,22 @@ void quark_jh512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint32_t *c
|
||||
{ 0xdffcc2e3, 0xfb1785e6, 0x78465a54, 0x4bdd8ccc }
|
||||
};
|
||||
|
||||
#pragma unroll 16
|
||||
#pragma unroll
|
||||
for (int i = 0; i < 16; i++)
|
||||
x[i >> 2][i & 3] ^= Hash[i];
|
||||
x[i/4][i & 3] ^= Hash[i];
|
||||
|
||||
E8(x);
|
||||
|
||||
#pragma unroll 16
|
||||
for (int i = 0; i < 16; i++)
|
||||
x[(16 + i) >> 2][(16 + i) & 3] ^= Hash[i];
|
||||
#pragma unroll
|
||||
for (uint8_t i = 0; i < 16; i++)
|
||||
x[(i+16)/4][(i+16) & 3] ^= Hash[i];
|
||||
|
||||
x[0 >> 2][0 & 3] ^= 0x80;
|
||||
x[15 >> 2][15 & 3] ^= 0x00020000;
|
||||
x[0][0] ^= 0x80U;
|
||||
x[3][3] ^= 0x00020000U;
|
||||
E8(x);
|
||||
x[(16 + 0) >> 2][(16 + 0) & 3] ^= 0x80;
|
||||
x[(16 + 15) >> 2][(16 + 15) & 3] ^= 0x00020000;
|
||||
|
||||
x[4][0] ^= 0x80U;
|
||||
x[7][3] ^= 0x00020000U;
|
||||
|
||||
Hash[0] = x[4][0];
|
||||
Hash[1] = x[4][1];
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
#include <stdio.h>
|
||||
#include <stdio.h>
|
||||
#include <memory.h>
|
||||
#include <sys/types.h> // off_t
|
||||
|
||||
#include "cuda_helper.h"
|
||||
|
||||
@@ -119,12 +120,8 @@ void quark_blake512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint32_t
|
||||
uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
|
||||
#if USE_SHUFFLE
|
||||
const int warpID = threadIdx.x & 0x0F; // 16 warps
|
||||
const int warpBlockID = (thread + 15)>>4; // aufrunden auf volle Warp-Blöcke
|
||||
const int maxHashPosition = thread<<3;
|
||||
#endif
|
||||
const uint32_t warpBlockID = (thread + 15)>>4; // aufrunden auf volle Warp-Blöcke
|
||||
|
||||
#if USE_SHUFFLE
|
||||
if (warpBlockID < ( (threads+15)>>4 ))
|
||||
#else
|
||||
if (thread < threads)
|
||||
@@ -132,7 +129,7 @@ void quark_blake512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint32_t
|
||||
{
|
||||
uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
off_t hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[hashPosition<<3]; // hashPosition * 8
|
||||
|
||||
// 128 Bytes
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
#include <stdio.h>
|
||||
#include <memory.h>
|
||||
#include <sys/types.h> // off_t
|
||||
|
||||
#include "cuda_helper.h"
|
||||
|
||||
@@ -28,19 +29,19 @@ void quark_groestl512_gpu_hash_64_quad(uint32_t threads, uint32_t startNounce, u
|
||||
uint32_t state[8];
|
||||
|
||||
uint32_t nounce = g_nonceVector ? g_nonceVector[thread] : (startNounce + thread);
|
||||
int hashPosition = nounce - startNounce;
|
||||
uint32_t *inpHash = &g_hash[hashPosition << 4];
|
||||
off_t hashPosition = nounce - startNounce;
|
||||
uint32_t *pHash = &g_hash[hashPosition << 4];
|
||||
|
||||
const uint16_t thr = threadIdx.x % THF;
|
||||
const uint32_t thr = threadIdx.x % THF;
|
||||
|
||||
#pragma unroll
|
||||
for(int k=0;k<4;k++) message[k] = inpHash[(k * THF) + thr];
|
||||
for(int k=0;k<4;k++) message[k] = pHash[thr + (k * THF)];
|
||||
|
||||
#pragma unroll
|
||||
for(int k=4;k<8;k++) message[k] = 0;
|
||||
|
||||
if (thr == 0) message[4] = 0x80;
|
||||
if (thr == 3) message[7] = 0x01000000;
|
||||
if (thr == 0) message[4] = 0x80U;
|
||||
if (thr == 3) message[7] = 0x01000000U;
|
||||
|
||||
uint32_t msgBitsliced[8];
|
||||
to_bitslice_quad(message, msgBitsliced);
|
||||
@@ -48,15 +49,13 @@ void quark_groestl512_gpu_hash_64_quad(uint32_t threads, uint32_t startNounce, u
|
||||
groestl512_progressMessage_quad(state, msgBitsliced);
|
||||
|
||||
// Nur der erste von jeweils 4 Threads bekommt das Ergebns-Hash
|
||||
uint32_t *outpHash = inpHash;
|
||||
uint32_t hash[16];
|
||||
from_bitslice_quad(state, hash);
|
||||
|
||||
|
||||
// uint4 = 4x4 uint32_t = 16 bytes
|
||||
if (thr == 0) {
|
||||
uint4 *phash = (uint4*) hash;
|
||||
uint4 *outpt = (uint4*) outpHash; /* var kept for hash align */
|
||||
uint4 *outpt = (uint4*) pHash;
|
||||
outpt[0] = phash[0];
|
||||
outpt[1] = phash[1];
|
||||
outpt[2] = phash[2];
|
||||
@@ -85,7 +84,7 @@ __global__ void __launch_bounds__(TPB, THF)
|
||||
|
||||
uint32_t nounce = g_nonceVector ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
off_t hashPosition = nounce - startNounce;
|
||||
uint32_t * inpHash = &g_hash[hashPosition<<4];
|
||||
const uint16_t thr = threadIdx.x % THF;
|
||||
|
||||
|
||||
@@ -230,8 +230,8 @@ void quark_groestl512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint32
|
||||
|
||||
uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
uint32_t *inpHash = &g_hash[16 * hashPosition];
|
||||
off_t hashPosition = nounce - startNounce;
|
||||
uint32_t *inpHash = &g_hash[hashPosition * 16];
|
||||
|
||||
#pragma unroll 16
|
||||
for(int k=0; k<16; k++)
|
||||
@@ -266,7 +266,7 @@ void quark_groestl512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint32
|
||||
for(int u=0;u<32;u++) state[u] ^= message[u];
|
||||
|
||||
// Erzeugten Hash rausschreiben
|
||||
uint32_t *outpHash = &g_hash[16 * hashPosition];
|
||||
uint32_t *outpHash = &g_hash[hashPosition * 16];
|
||||
|
||||
#pragma unroll 16
|
||||
for(int k=0;k<16;k++) outpHash[k] = state[k+16];
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
#include <stdio.h>
|
||||
#include <memory.h>
|
||||
#include <sys/types.h> // off_t
|
||||
|
||||
#include "cuda_helper.h"
|
||||
|
||||
@@ -101,8 +102,8 @@ void quark_keccak512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint64_
|
||||
{
|
||||
uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[8 * hashPosition];
|
||||
off_t hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[hashPosition * 8];
|
||||
uint2 keccak_gpu_state[25];
|
||||
|
||||
for (int i = 0; i<8; i++) {
|
||||
@@ -200,8 +201,8 @@ void quark_keccak512_gpu_hash_64_v30(uint32_t threads, uint32_t startNounce, uin
|
||||
{
|
||||
uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
uint32_t *inpHash = (uint32_t*)&g_hash[8 * hashPosition];
|
||||
off_t hashPosition = nounce - startNounce;
|
||||
uint32_t *inpHash = (uint32_t*)&g_hash[hashPosition * 8];
|
||||
|
||||
uint32_t message[18];
|
||||
#pragma unroll 16
|
||||
@@ -224,7 +225,7 @@ void quark_keccak512_gpu_hash_64_v30(uint32_t threads, uint32_t startNounce, uin
|
||||
U64TO32_LE((&hash[i/4]), keccak_gpu_state[i / 8]);
|
||||
}
|
||||
|
||||
uint32_t *outpHash = (uint32_t*)&g_hash[8 * hashPosition];
|
||||
uint32_t *outpHash = (uint32_t*)&g_hash[hashPosition * 8];
|
||||
#pragma unroll 16
|
||||
for(int i=0; i<16; i++)
|
||||
outpHash[i] = hash[i];
|
||||
|
||||
+16
-6
@@ -418,13 +418,19 @@ void quark_skein512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint64_t
|
||||
h7 = vectorize(0xAE18A40B660FCC33ull);
|
||||
|
||||
uint2 p[8];
|
||||
// 1. Runde -> etype = 480, ptr = 64, bcount = 0, data = msg
|
||||
// 1st Round -> etype = 480, ptr = 64, bcount = 0, data = msg
|
||||
#pragma unroll 8
|
||||
for (int i = 0; i < 8; i++)
|
||||
p[i] = vectorize(inpHash[i]);
|
||||
|
||||
t0 = vectorize(64); // ptr
|
||||
t1 = vectorize(480ull << 55); // etype
|
||||
// t1 = vectorize(480ull << 55); // etype
|
||||
t1 = vectorize(0xf000000000000000ULL);
|
||||
|
||||
//#if CUDA_VERSION >= 7000
|
||||
// doesnt really affect x11 perfs.
|
||||
__threadfence();
|
||||
//#endif
|
||||
TFBIG_KINIT_UI2(h0, h1, h2, h3, h4, h5, h6, h7, h8, t0, t1, t2);
|
||||
TFBIG_4e_UI2(0);
|
||||
TFBIG_4o_UI2(1);
|
||||
@@ -458,10 +464,12 @@ void quark_skein512_gpu_hash_64(uint32_t threads, uint32_t startNounce, uint64_t
|
||||
// 2. Runde -> etype = 510, ptr = 8, bcount = 0, data = 0
|
||||
#pragma unroll 8
|
||||
for(int i=0; i<8; i++)
|
||||
p[i] = vectorize(0ull);
|
||||
p[i] = vectorize(0);
|
||||
|
||||
t0 = vectorize(8); // ptr
|
||||
t1 = vectorize(510ull << 55); // etype
|
||||
//t1 = vectorize(510ull << 55); // etype
|
||||
t1 = vectorize(0xff00000000000000ULL);
|
||||
|
||||
TFBIG_KINIT_UI2(h0, h1, h2, h3, h4, h5, h6, h7, h8, t0, t1, t2);
|
||||
TFBIG_4e_UI2(0);
|
||||
TFBIG_4o_UI2(1);
|
||||
@@ -504,7 +512,7 @@ void quark_skein512_gpu_hash_64_sm3(uint32_t threads, uint32_t startNounce, uint
|
||||
|
||||
uint32_t nounce = (g_nonceVector != NULL) ? g_nonceVector[thread] : (startNounce + thread);
|
||||
|
||||
int hashPosition = nounce - startNounce;
|
||||
uint32_t hashPosition = nounce - startNounce;
|
||||
uint64_t *inpHash = &g_hash[hashPosition * 8];
|
||||
|
||||
// Init
|
||||
@@ -523,7 +531,9 @@ void quark_skein512_gpu_hash_64_sm3(uint32_t threads, uint32_t startNounce, uint
|
||||
p[i] = inpHash[i];
|
||||
|
||||
t0 = 64; // ptr
|
||||
t1 = 480ull << 55; // etype
|
||||
// t1 = 480ull << 55; // etype
|
||||
t1 = 0xf000000000000000ULL;
|
||||
|
||||
TFBIG_KINIT(h0, h1, h2, h3, h4, h5, h6, h7, h8, t0, t1, t2);
|
||||
TFBIG_4e(0);
|
||||
TFBIG_4o(1);
|
||||
|
||||
+13
-16
@@ -19,8 +19,6 @@ static uint32_t *d_hash[MAX_GPUS];
|
||||
extern void qubit_luffa512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void qubit_luffa512_cpu_setBlock_80(void *pdata);
|
||||
extern void qubit_luffa512_cpu_hash_80(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_hash, int order);
|
||||
extern void qubit_luffa512_cpufinal_setBlock_80(void *pdata, const void *ptarget);
|
||||
extern uint32_t qubit_luffa512_cpu_finalhash_80(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_cubehash512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_cubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
@@ -30,13 +28,13 @@ extern void x11_echo512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t start
|
||||
|
||||
extern "C" void deephash(void *state, const void *input)
|
||||
{
|
||||
// luffa1-cubehash2-shavite3-simd4-echo5
|
||||
uint8_t _ALIGN(64) hash[64];
|
||||
|
||||
// luffa-80 cubehash-64 echo-64
|
||||
sph_luffa512_context ctx_luffa;
|
||||
sph_cubehash512_context ctx_cubehash;
|
||||
sph_echo512_context ctx_echo;
|
||||
|
||||
uint8_t hash[64];
|
||||
|
||||
sph_luffa512_init(&ctx_luffa);
|
||||
sph_luffa512 (&ctx_luffa, input, 80);
|
||||
sph_luffa512_close(&ctx_luffa, (void*) hash);
|
||||
@@ -54,14 +52,13 @@ extern "C" void deephash(void *state, const void *input)
|
||||
|
||||
static bool init[MAX_GPUS] = { 0 };
|
||||
|
||||
extern "C" int scanhash_deep(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done)
|
||||
extern "C" int scanhash_deep(int thr_id, uint32_t *pdata, const uint32_t *ptarget,
|
||||
uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
uint32_t _ALIGN(64) endiandata[20];
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
uint32_t endiandata[20];
|
||||
uint32_t throughput = device_intensity(thr_id, __func__, 1U << 19); // 256*256*8
|
||||
throughput = min(throughput, (max_nonce - first_nonce));
|
||||
throughput = min(throughput, (max_nonce - first_nonce));
|
||||
|
||||
if (opt_benchmark)
|
||||
((uint32_t*)ptarget)[7] = 0x0000f;
|
||||
@@ -69,7 +66,8 @@ extern "C" int scanhash_deep(int thr_id, uint32_t *pdata,
|
||||
if (!init[thr_id])
|
||||
{
|
||||
cudaSetDevice(device_map[thr_id]);
|
||||
cudaMalloc(&d_hash[thr_id], 16 * sizeof(uint32_t) * throughput);
|
||||
|
||||
CUDA_SAFE_CALL(cudaMalloc(&d_hash[thr_id], throughput * 64));
|
||||
|
||||
qubit_luffa512_cpu_init(thr_id, throughput);
|
||||
x11_cubehash512_cpu_init(thr_id, throughput);
|
||||
@@ -80,10 +78,10 @@ extern "C" int scanhash_deep(int thr_id, uint32_t *pdata,
|
||||
init[thr_id] = true;
|
||||
}
|
||||
|
||||
for (int k=0; k < 20; k++)
|
||||
for (int k=0; k < 19; k++)
|
||||
be32enc(&endiandata[k], pdata[k]);
|
||||
|
||||
qubit_luffa512_cpufinal_setBlock_80((void*)endiandata,ptarget);
|
||||
qubit_luffa512_cpu_setBlock_80((void*)endiandata);
|
||||
cuda_check_cpu_setTarget(ptarget);
|
||||
|
||||
do {
|
||||
@@ -96,12 +94,11 @@ extern "C" int scanhash_deep(int thr_id, uint32_t *pdata,
|
||||
uint32_t foundNonce = cuda_check_hash(thr_id, throughput, pdata[19], d_hash[thr_id]);
|
||||
if (foundNonce != UINT32_MAX)
|
||||
{
|
||||
const uint32_t Htarg = ptarget[7];
|
||||
uint32_t vhash64[8];
|
||||
uint32_t _ALIGN(64) vhash64[8];
|
||||
be32enc(&endiandata[19], foundNonce);
|
||||
deephash(vhash64, endiandata);
|
||||
|
||||
if (vhash64[7] <= Htarg && fulltest(vhash64, ptarget)) {
|
||||
if (vhash64[7] <= ptarget[7] && fulltest(vhash64, ptarget)) {
|
||||
int res = 1;
|
||||
uint32_t secNonce = cuda_check_hash_suppl(thr_id, throughput, pdata[19], d_hash[thr_id], 1);
|
||||
*hashes_done = pdata[19] - first_nonce + throughput;
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
/*
|
||||
* qubit algorithm
|
||||
*
|
||||
* luffa 80 algo (Introduced by Doomcoin)
|
||||
*/
|
||||
extern "C" {
|
||||
#include "sph/sph_luffa.h"
|
||||
@@ -15,15 +14,12 @@ static uint32_t *d_hash[MAX_GPUS];
|
||||
extern void qubit_luffa512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void qubit_luffa512_cpu_setBlock_80(void *pdata);
|
||||
extern void qubit_luffa512_cpu_hash_80(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_hash, int order);
|
||||
extern void qubit_luffa512_cpufinal_setBlock_80(void *pdata, const void *ptarget);
|
||||
extern uint32_t qubit_luffa512_cpu_finalhash_80(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_hash, int order);
|
||||
|
||||
extern void doomhash(void *state, const void *input)
|
||||
extern "C" void luffa_hash(void *state, const void *input)
|
||||
{
|
||||
// luffa512
|
||||
sph_luffa512_context ctx_luffa;
|
||||
uint8_t _ALIGN(64) hash[64];
|
||||
|
||||
uint8_t hash[64];
|
||||
sph_luffa512_context ctx_luffa;
|
||||
|
||||
sph_luffa512_init(&ctx_luffa);
|
||||
sph_luffa512 (&ctx_luffa, input, 80);
|
||||
@@ -34,12 +30,11 @@ extern void doomhash(void *state, const void *input)
|
||||
|
||||
static bool init[MAX_GPUS] = { 0 };
|
||||
|
||||
extern "C" int scanhash_doom(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce,
|
||||
unsigned long *hashes_done)
|
||||
extern "C" int scanhash_luffa(int thr_id, uint32_t *pdata, const uint32_t *ptarget,
|
||||
uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
uint32_t _ALIGN(64) endiandata[20];
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
uint32_t endiandata[20];
|
||||
uint32_t throughput = device_intensity(thr_id, __func__, 1U << 22); // 256*256*8*8
|
||||
throughput = min(throughput, max_nonce - first_nonce);
|
||||
|
||||
@@ -50,31 +45,35 @@ extern "C" int scanhash_doom(int thr_id, uint32_t *pdata,
|
||||
{
|
||||
cudaSetDevice(device_map[thr_id]);
|
||||
|
||||
CUDA_SAFE_CALL(cudaMalloc(&d_hash[thr_id], 16 * sizeof(uint32_t) * throughput));
|
||||
CUDA_SAFE_CALL(cudaMalloc(&d_hash[thr_id], throughput * 64));
|
||||
|
||||
qubit_luffa512_cpu_init(thr_id, (int) throughput);
|
||||
qubit_luffa512_cpu_init(thr_id, throughput);
|
||||
cuda_check_cpu_init(thr_id, throughput);
|
||||
|
||||
init[thr_id] = true;
|
||||
}
|
||||
|
||||
for (int k=0; k < 20; k++)
|
||||
for (int k=0; k < 19; k++)
|
||||
be32enc(&endiandata[k], pdata[k]);
|
||||
|
||||
qubit_luffa512_cpufinal_setBlock_80((void*)endiandata,ptarget);
|
||||
qubit_luffa512_cpu_setBlock_80((void*)endiandata);
|
||||
cuda_check_cpu_setTarget(ptarget);
|
||||
|
||||
do {
|
||||
int order = 0;
|
||||
*hashes_done = pdata[19] - first_nonce + throughput;
|
||||
|
||||
uint32_t foundNonce = qubit_luffa512_cpu_finalhash_80(thr_id, (int) throughput, pdata[19], d_hash[thr_id], order++);
|
||||
qubit_luffa512_cpu_hash_80(thr_id, (int) throughput, pdata[19], d_hash[thr_id], order++);
|
||||
|
||||
uint32_t foundNonce = cuda_check_hash(thr_id, throughput, pdata[19], d_hash[thr_id]);
|
||||
if (foundNonce != UINT32_MAX)
|
||||
{
|
||||
const uint32_t Htarg = ptarget[7];
|
||||
uint32_t vhash64[8];
|
||||
uint32_t _ALIGN(64) vhash64[8];
|
||||
be32enc(&endiandata[19], foundNonce);
|
||||
doomhash(vhash64, endiandata);
|
||||
luffa_hash(vhash64, endiandata);
|
||||
|
||||
if (vhash64[7] <= Htarg && fulltest(vhash64, ptarget)) {
|
||||
*hashes_done = min(max_nonce - first_nonce, (uint64_t) pdata[19] - first_nonce + throughput);
|
||||
if (vhash64[7] <= ptarget[7] && fulltest(vhash64, ptarget)) {
|
||||
//*hashes_done = min(max_nonce - first_nonce, (uint64_t) pdata[19] - first_nonce + throughput);
|
||||
pdata[19] = foundNonce;
|
||||
return 1;
|
||||
} else {
|
||||
@@ -82,7 +81,7 @@ extern "C" int scanhash_doom(int thr_id, uint32_t *pdata,
|
||||
}
|
||||
}
|
||||
|
||||
if ((uint64_t) pdata[19] + throughput > max_nonce) {
|
||||
if ((uint64_t) throughput + pdata[19] > max_nonce) {
|
||||
// pdata[19] = max_nonce;
|
||||
break;
|
||||
}
|
||||
+292
-293
@@ -1,49 +1,18 @@
|
||||
/*
|
||||
* luffa_for_32.c
|
||||
* Version 2.0 (Sep 15th 2009)
|
||||
*
|
||||
* Copyright (C) 2008-2009 Hitachi, Ltd. All rights reserved.
|
||||
*
|
||||
* Hitachi, Ltd. is the owner of this software and hereby grant
|
||||
* the U.S. Government and any interested party the right to use
|
||||
* this software for the purposes of the SHA-3 evaluation process,
|
||||
* notwithstanding that this software is copyrighted.
|
||||
*
|
||||
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
|
||||
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
|
||||
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
|
||||
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
|
||||
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
|
||||
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
|
||||
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
|
||||
/*******************************************************************************
|
||||
* luffa512 for 80-bytes input (with midstate precalc by klausT)
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
#include <stdint.h>
|
||||
#include <memory.h>
|
||||
|
||||
#include "cuda_helper.h"
|
||||
|
||||
typedef unsigned char BitSequence;
|
||||
static __constant__ uint64_t c_PaddedMessage80[16]; // padded message (80 bytes + padding)
|
||||
static __constant__ uint32_t statebufferpre[8];
|
||||
static __constant__ uint32_t statechainvpre[40];
|
||||
|
||||
__constant__ uint64_t c_PaddedMessage80[16]; // padded message (80 bytes + padding)
|
||||
__constant__ uint32_t c_Target[8];
|
||||
|
||||
static uint32_t *h_resNounce[MAX_GPUS];
|
||||
static uint32_t *d_resNounce[MAX_GPUS];
|
||||
|
||||
#define NBN 1 /* max results, could be 2, see blake32.cu */
|
||||
#if NBN > 1
|
||||
static uint32_t extra_results[2] = { UINT32_MAX, UINT32_MAX };
|
||||
#endif
|
||||
|
||||
typedef struct {
|
||||
uint32_t buffer[8]; /* Buffer to be hashed */
|
||||
uint32_t chainv[40]; /* Chaining values */
|
||||
} hashState;
|
||||
|
||||
#define BYTES_SWAP32(x) cuda_swab32(x)
|
||||
|
||||
#define MULT2(a,j)\
|
||||
#define MULT2(a,j) {\
|
||||
tmp = a[7+(8*j)];\
|
||||
a[7+(8*j)] = a[6+(8*j)];\
|
||||
a[6+(8*j)] = a[5+(8*j)];\
|
||||
@@ -52,22 +21,25 @@ typedef struct {
|
||||
a[3+(8*j)] = a[2+(8*j)] ^ tmp;\
|
||||
a[2+(8*j)] = a[1+(8*j)];\
|
||||
a[1+(8*j)] = a[0+(8*j)] ^ tmp;\
|
||||
a[0+(8*j)] = tmp;
|
||||
a[0+(8*j)] = tmp;\
|
||||
}
|
||||
|
||||
#define TWEAK(a0,a1,a2,a3,j)\
|
||||
#define TWEAK(a0,a1,a2,a3,j) { \
|
||||
a0 = (a0<<(j))|(a0>>(32-j));\
|
||||
a1 = (a1<<(j))|(a1>>(32-j));\
|
||||
a2 = (a2<<(j))|(a2>>(32-j));\
|
||||
a3 = (a3<<(j))|(a3>>(32-j));
|
||||
a3 = (a3<<(j))|(a3>>(32-j));\
|
||||
}
|
||||
|
||||
#define STEP(c0,c1)\
|
||||
#define STEP(c0,c1) { \
|
||||
SUBCRUMB(chainv[0],chainv[1],chainv[2],chainv[3],tmp);\
|
||||
SUBCRUMB(chainv[5],chainv[6],chainv[7],chainv[4],tmp);\
|
||||
MIXWORD(chainv[0],chainv[4]);\
|
||||
MIXWORD(chainv[1],chainv[5]);\
|
||||
MIXWORD(chainv[2],chainv[6]);\
|
||||
MIXWORD(chainv[3],chainv[7]);\
|
||||
ADD_CONSTANT(chainv[0],chainv[4],c0,c1);
|
||||
ADD_CONSTANT(chainv[0],chainv[4],c0,c1);\
|
||||
}
|
||||
|
||||
#define SUBCRUMB(a0,a1,a2,a3,a4)\
|
||||
a4 = a0;\
|
||||
@@ -104,7 +76,7 @@ typedef struct {
|
||||
|
||||
/* initial values of chaining variables */
|
||||
__constant__ uint32_t c_IV[40];
|
||||
const uint32_t h2_IV[40] = {
|
||||
static const uint32_t h_IV[40] = {
|
||||
0x6d251e69,0x44b051e0,0x4eaa6fb4,0xdbf78465,
|
||||
0x6e292011,0x90152df4,0xee058139,0xdef610bb,
|
||||
0xc3b44b95,0xd9d2f256,0x70eee9a0,0xde099fa3,
|
||||
@@ -117,7 +89,7 @@ const uint32_t h2_IV[40] = {
|
||||
0xf5df3999,0x0fc688f1,0xb07224cc,0x03e86cea};
|
||||
|
||||
__constant__ uint32_t c_CNS[80];
|
||||
uint32_t h2_CNS[80] = {
|
||||
static const uint32_t h_CNS[80] = {
|
||||
0x303994a6,0xe0337818,0xc0e65299,0x441ba90d,
|
||||
0x6cc33a12,0x7f34d442,0xdc56983e,0x9389217f,
|
||||
0x1e00108f,0xe5a8bce6,0x7800423d,0x5274baf4,
|
||||
@@ -142,213 +114,305 @@ uint32_t h2_CNS[80] = {
|
||||
|
||||
/***************************************************/
|
||||
__device__ __forceinline__
|
||||
void rnd512(hashState *state)
|
||||
void rnd512(uint32_t *statebuffer, uint32_t *statechainv)
|
||||
{
|
||||
int i,j;
|
||||
uint32_t t[40];
|
||||
uint32_t chainv[8];
|
||||
uint32_t tmp;
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++) {
|
||||
t[i]=0;
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
t[i] ^= state->chainv[i+8*j];
|
||||
}
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++)
|
||||
t[i] ^= statechainv[i+8*j];
|
||||
}
|
||||
|
||||
MULT2(t, 0);
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[i+8*j] ^= t[i];
|
||||
}
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++)
|
||||
statechainv[i+8*j] ^= t[i];
|
||||
}
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
t[i+8*j] = state->chainv[i+8*j];
|
||||
}
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++)
|
||||
t[i+8*j] = statechainv[i+8*j];
|
||||
}
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
MULT2(state->chainv, j);
|
||||
#pragma unroll
|
||||
for(j=0; j<5; j++)
|
||||
MULT2(statechainv, j);
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++)
|
||||
statechainv[8*j+i] ^= t[8*((j+1)%5)+i];
|
||||
}
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[8*j+i] ^= t[8*((j+1)%5)+i];
|
||||
}
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++)
|
||||
t[i+8*j] = statechainv[i+8*j];
|
||||
}
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
t[i+8*j] = state->chainv[i+8*j];
|
||||
}
|
||||
#pragma unroll
|
||||
for(j=0; j<5; j++)
|
||||
MULT2(statechainv, j);
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++)
|
||||
statechainv[8*j+i] ^= t[8*((j+4)%5)+i];
|
||||
}
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
MULT2(state->chainv, j);
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++)
|
||||
statechainv[i+8*j] ^= statebuffer[i];
|
||||
MULT2(statebuffer, 0);
|
||||
}
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[8*j+i] ^= t[8*((j+4)%5)+i];
|
||||
}
|
||||
}
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
chainv[i] = statechainv[i];
|
||||
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[i+8*j] ^= state->buffer[i];
|
||||
}
|
||||
MULT2(state->buffer, 0);
|
||||
}
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
STEP(c_CNS[(2*i)], c_CNS[(2*i)+1]);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
chainv[i] = state->chainv[i];
|
||||
}
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
STEP(c_CNS[(2*i)],c_CNS[(2*i)+1]);
|
||||
}
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[i] = chainv[i];
|
||||
chainv[i] = state->chainv[i+8];
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++) {
|
||||
statechainv[i] = chainv[i];
|
||||
chainv[i] = statechainv[i+8];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4],chainv[5],chainv[6],chainv[7],1);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
STEP(c_CNS[(2*i)+16],c_CNS[(2*i)+16+1]);
|
||||
}
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
STEP(c_CNS[(2*i)+16], c_CNS[(2*i)+16+1]);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[i+8] = chainv[i];
|
||||
chainv[i] = state->chainv[i+16];
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++) {
|
||||
statechainv[i+8] = chainv[i];
|
||||
chainv[i] = statechainv[i+16];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4],chainv[5],chainv[6],chainv[7],2);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
STEP(c_CNS[(2*i)+32],c_CNS[(2*i)+32+1]);
|
||||
}
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[i+16] = chainv[i];
|
||||
chainv[i] = state->chainv[i+24];
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++) {
|
||||
statechainv[i+16] = chainv[i];
|
||||
chainv[i] = statechainv[i+24];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4],chainv[5],chainv[6],chainv[7],3);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
STEP(c_CNS[(2*i)+48],c_CNS[(2*i)+48+1]);
|
||||
}
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[i+24] = chainv[i];
|
||||
chainv[i] = state->chainv[i+32];
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++) {
|
||||
statechainv[i+24] = chainv[i];
|
||||
chainv[i] = statechainv[i+32];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4],chainv[5],chainv[6],chainv[7],4);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
STEP(c_CNS[(2*i)+64],c_CNS[(2*i)+64+1]);
|
||||
}
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
state->chainv[i+32] = chainv[i];
|
||||
}
|
||||
#pragma unroll 8
|
||||
for(i=0; i<8; i++)
|
||||
statechainv[i+32] = chainv[i];
|
||||
}
|
||||
|
||||
|
||||
__device__ __forceinline__
|
||||
void Update512(hashState *state, const BitSequence *data)
|
||||
static void rnd512_cpu(uint32_t *statebuffer, uint32_t *statechainv)
|
||||
{
|
||||
#pragma unroll 8
|
||||
for(int i=0;i<8;i++) state->buffer[i] = BYTES_SWAP32(((uint32_t*)data)[i]);
|
||||
rnd512(state);
|
||||
int i, j;
|
||||
uint32_t t[40];
|
||||
uint32_t chainv[8];
|
||||
uint32_t tmp;
|
||||
|
||||
#pragma unroll 8
|
||||
for(int i=0;i<8;i++) state->buffer[i] = BYTES_SWAP32(((uint32_t*)(data+32))[i]);
|
||||
rnd512(state);
|
||||
#pragma unroll 4
|
||||
for(int i=0;i<4;i++) state->buffer[i] = BYTES_SWAP32(((uint32_t*)(data+64))[i]);
|
||||
for (i = 0; i<8; i++) {
|
||||
t[i] = statechainv[i];
|
||||
for (j = 1; j<5; j++)
|
||||
t[i] ^= statechainv[i + 8 * j];
|
||||
}
|
||||
|
||||
MULT2(t, 0);
|
||||
|
||||
for (j = 0; j<5; j++) {
|
||||
for (i = 0; i<8; i++)
|
||||
statechainv[i + 8 * j] ^= t[i];
|
||||
}
|
||||
|
||||
for (j = 0; j<5; j++) {
|
||||
for (i = 0; i<8; i++)
|
||||
t[i + 8 * j] = statechainv[i + 8 * j];
|
||||
}
|
||||
|
||||
for (j = 0; j<5; j++)
|
||||
MULT2(statechainv, j);
|
||||
|
||||
for (j = 0; j<5; j++) {
|
||||
for (i = 0; i<8; i++)
|
||||
statechainv[8 * j + i] ^= t[8 * ((j + 1) % 5) + i];
|
||||
}
|
||||
|
||||
for (j = 0; j<5; j++) {
|
||||
for (i = 0; i<8; i++)
|
||||
t[i + 8 * j] = statechainv[i + 8 * j];
|
||||
}
|
||||
|
||||
for (j = 0; j<5; j++)
|
||||
MULT2(statechainv, j);
|
||||
|
||||
for (j = 0; j<5; j++) {
|
||||
for (i = 0; i<8; i++)
|
||||
statechainv[8 * j + i] ^= t[8 * ((j + 4) % 5) + i];
|
||||
}
|
||||
|
||||
for (j = 0; j<5; j++) {
|
||||
for (i = 0; i<8; i++)
|
||||
statechainv[i + 8 * j] ^= statebuffer[i];
|
||||
MULT2(statebuffer, 0);
|
||||
}
|
||||
|
||||
for (i = 0; i<8; i++)
|
||||
chainv[i] = statechainv[i];
|
||||
|
||||
for (i = 0; i<8; i++)
|
||||
STEP(h_CNS[(2 * i)], h_CNS[(2 * i) + 1]);
|
||||
|
||||
for (i = 0; i<8; i++) {
|
||||
statechainv[i] = chainv[i];
|
||||
chainv[i] = statechainv[i + 8];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4], chainv[5], chainv[6], chainv[7], 1);
|
||||
|
||||
for (i = 0; i<8; i++)
|
||||
STEP(h_CNS[(2 * i) + 16], h_CNS[(2 * i) + 16 + 1]);
|
||||
|
||||
for (i = 0; i<8; i++) {
|
||||
statechainv[i + 8] = chainv[i];
|
||||
chainv[i] = statechainv[i + 16];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4], chainv[5], chainv[6], chainv[7], 2);
|
||||
|
||||
for (i = 0; i<8; i++)
|
||||
STEP(h_CNS[(2 * i) + 32], h_CNS[(2 * i) + 32 + 1]);
|
||||
|
||||
for (i = 0; i<8; i++) {
|
||||
statechainv[i + 16] = chainv[i];
|
||||
chainv[i] = statechainv[i + 24];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4], chainv[5], chainv[6], chainv[7], 3);
|
||||
|
||||
for (i = 0; i<8; i++)
|
||||
STEP(h_CNS[(2 * i) + 48], h_CNS[(2 * i) + 48 + 1]);
|
||||
|
||||
for (i = 0; i<8; i++) {
|
||||
statechainv[i + 24] = chainv[i];
|
||||
chainv[i] = statechainv[i + 32];
|
||||
}
|
||||
|
||||
TWEAK(chainv[4], chainv[5], chainv[6], chainv[7], 4);
|
||||
|
||||
for (i = 0; i<8; i++)
|
||||
STEP(h_CNS[(2 * i) + 64], h_CNS[(2 * i) + 64 + 1]);
|
||||
|
||||
for (i = 0; i<8; i++)
|
||||
statechainv[i + 32] = chainv[i];
|
||||
}
|
||||
|
||||
/***************************************************/
|
||||
__device__ __forceinline__
|
||||
void Update512(uint32_t* statebuffer, uint32_t *statechainv, const uint32_t *const __restrict__ data)
|
||||
{
|
||||
#pragma unroll
|
||||
for (int i = 0; i<8; i++)
|
||||
statebuffer[i] = cuda_swab32((data[i]));
|
||||
rnd512(statebuffer, statechainv);
|
||||
|
||||
#pragma unroll
|
||||
for(int i=0; i<8; i++)
|
||||
statebuffer[i] = cuda_swab32((data[i+8]));
|
||||
rnd512(statebuffer, statechainv);
|
||||
|
||||
#pragma unroll
|
||||
for(int i=0; i<4; i++)
|
||||
statebuffer[i] = cuda_swab32((data[i+16]));
|
||||
}
|
||||
|
||||
|
||||
/***************************************************/
|
||||
__device__ __forceinline__
|
||||
void finalization512(hashState *state, uint32_t *b)
|
||||
void finalization512(uint32_t* statebuffer, uint32_t *statechainv, uint32_t *b)
|
||||
{
|
||||
int i,j;
|
||||
|
||||
state->buffer[4] = 0x80000000;
|
||||
#pragma unroll 3
|
||||
for(int i=5;i<8;i++) state->buffer[i] = 0;
|
||||
rnd512(state);
|
||||
statebuffer[4] = 0x80000000U;
|
||||
|
||||
#pragma unroll 3
|
||||
for(int i=5; i<8; i++)
|
||||
statebuffer[i] = 0;
|
||||
rnd512(statebuffer, statechainv);
|
||||
|
||||
/*---- blank round with m=0 ----*/
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) state->buffer[i] =0;
|
||||
rnd512(state);
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
statebuffer[i] =0;
|
||||
rnd512(statebuffer, statechainv);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++) {
|
||||
b[i] = 0;
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
b[i] ^= state->chainv[i+8*j];
|
||||
}
|
||||
b[i] = BYTES_SWAP32((b[i]));
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++)
|
||||
b[i] ^= statechainv[i+8*j];
|
||||
b[i] = cuda_swab32((b[i]));
|
||||
}
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) state->buffer[i]=0;
|
||||
rnd512(state);
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
statebuffer[i]=0;
|
||||
rnd512(statebuffer, statechainv);
|
||||
|
||||
#pragma unroll 8
|
||||
for(i=0;i<8;i++) {
|
||||
#pragma unroll
|
||||
for(i=0; i<8; i++)
|
||||
{
|
||||
b[8+i] = 0;
|
||||
#pragma unroll 5
|
||||
for(j=0;j<5;j++) {
|
||||
b[8+i] ^= state->chainv[i+8*j];
|
||||
}
|
||||
b[8+i] = BYTES_SWAP32((b[8+i]));
|
||||
#pragma unroll 5
|
||||
for(j=0; j<5; j++)
|
||||
b[8+i] ^= statechainv[i+8*j];
|
||||
b[8+i] = cuda_swab32((b[8+i]));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/***************************************************/
|
||||
// Die Hash-Funktion
|
||||
__global__
|
||||
void qubit_luffa512_gpu_hash_80(uint32_t threads, uint32_t startNounce, void *outputHash)
|
||||
void qubit_luffa512_gpu_hash_80(uint32_t threads, uint32_t startNounce, uint32_t *outputHash)
|
||||
{
|
||||
uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
@@ -359,118 +423,37 @@ void qubit_luffa512_gpu_hash_80(uint32_t threads, uint32_t startNounce, void *ou
|
||||
uint32_t buf32[32];
|
||||
} buff;
|
||||
|
||||
#pragma unroll 16
|
||||
for (int i=0; i < 16; ++i) buff.buf64[i] = c_PaddedMessage80[i];
|
||||
#pragma unroll 8
|
||||
for (int i=8; i < 16; i++)
|
||||
buff.buf64[i] = c_PaddedMessage80[i];
|
||||
|
||||
// die Nounce durch die thread-spezifische ersetzen
|
||||
buff.buf64[9] = REPLACE_HIDWORD(buff.buf64[9], cuda_swab32(nounce));
|
||||
|
||||
uint32_t statebuffer[8], statechainv[40];
|
||||
|
||||
hashState state;
|
||||
#pragma unroll 40
|
||||
for(int i=0;i<40;i++) state.chainv[i] = c_IV[i];
|
||||
#pragma unroll 8
|
||||
for(int i=0;i<8;i++) state.buffer[i] = 0;
|
||||
Update512(&state, (BitSequence*)buff.buf32);
|
||||
uint32_t *outHash = (uint32_t *)outputHash + 16 * thread;
|
||||
finalization512(&state, (uint32_t*)outHash);
|
||||
}
|
||||
}
|
||||
#pragma unroll
|
||||
for (int i = 0; i<4; i++)
|
||||
statebuffer[i] = cuda_swab32(buff.buf32[i + 16]);
|
||||
|
||||
__global__
|
||||
void qubit_luffa512_gpu_finalhash_80(uint32_t threads, uint32_t startNounce, void *outputHash, uint32_t *resNounce)
|
||||
{
|
||||
uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
{
|
||||
uint32_t nounce = startNounce + thread;
|
||||
union {
|
||||
uint64_t buf64[16];
|
||||
uint32_t buf32[32];
|
||||
} buff;
|
||||
uint32_t Hash[16];
|
||||
#pragma unroll 4
|
||||
for (int i = 4; i<8; i++)
|
||||
statebuffer[i] = statebufferpre[i];
|
||||
|
||||
#pragma unroll 16
|
||||
for (int i=0; i < 16; ++i) buff.buf64[i] = c_PaddedMessage80[i];
|
||||
#pragma unroll
|
||||
for (int i = 0; i<40; i++)
|
||||
statechainv[i] = statechainvpre[i];
|
||||
|
||||
// Tested nonce
|
||||
buff.buf64[9] = REPLACE_HIDWORD(buff.buf64[9], cuda_swab32(nounce));
|
||||
|
||||
hashState state;
|
||||
#pragma unroll 40
|
||||
for(int i=0;i<40;i++) state.chainv[i] = c_IV[i];
|
||||
|
||||
#pragma unroll 8
|
||||
for(int i=0;i<8;i++) state.buffer[i] = 0;
|
||||
|
||||
Update512(&state, (BitSequence*)buff.buf32);
|
||||
finalization512(&state, Hash);
|
||||
|
||||
/* dont ask me why not a simple if (Hash[i] > c_Target[i]) return;
|
||||
* we lose 20% in perfs without the position test */
|
||||
int position = -1;
|
||||
#pragma unroll 8
|
||||
for (int i = 7; i >= 0; i--) {
|
||||
if (Hash[i] > c_Target[i]) {
|
||||
if (position < i) {
|
||||
return;
|
||||
}
|
||||
}
|
||||
if (Hash[i] < c_Target[i]) {
|
||||
if (position < i) {
|
||||
position = i;
|
||||
//break; /* impact perfs, unroll ? */
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#if NBN == 1
|
||||
if (resNounce[0] > nounce) {
|
||||
resNounce[0] = nounce;
|
||||
}
|
||||
#else
|
||||
/* keep the smallest nounce, + extra one if found */
|
||||
if (resNounce[0] > nounce) {
|
||||
resNounce[1] = resNounce[0];
|
||||
resNounce[0] = nounce;
|
||||
} else {
|
||||
resNounce[1] = nounce;
|
||||
}
|
||||
#endif
|
||||
uint32_t *outHash = &outputHash[thread * 16];
|
||||
finalization512(statebuffer, statechainv, outHash);
|
||||
}
|
||||
}
|
||||
|
||||
__host__
|
||||
void qubit_luffa512_cpu_init(int thr_id, uint32_t threads)
|
||||
{
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_IV, h2_IV, sizeof(h2_IV), 0, cudaMemcpyHostToDevice));
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_CNS, h2_CNS, sizeof(h2_CNS), 0, cudaMemcpyHostToDevice));
|
||||
CUDA_SAFE_CALL(cudaMalloc(&d_resNounce[thr_id], NBN * sizeof(uint32_t)));
|
||||
CUDA_SAFE_CALL(cudaMallocHost(&h_resNounce[thr_id], NBN * sizeof(uint32_t)));
|
||||
}
|
||||
|
||||
__host__
|
||||
uint32_t qubit_luffa512_cpu_finalhash_80(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_outputHash,int order)
|
||||
{
|
||||
uint32_t result = UINT32_MAX;
|
||||
cudaMemset(d_resNounce[thr_id], 0xff, NBN * sizeof(uint32_t));
|
||||
const uint32_t threadsperblock = 256;
|
||||
|
||||
dim3 grid((threads + threadsperblock-1)/threadsperblock);
|
||||
dim3 block(threadsperblock);
|
||||
|
||||
size_t shared_size = 0;
|
||||
|
||||
qubit_luffa512_gpu_finalhash_80 <<<grid, block, shared_size>>> (threads, startNounce, d_outputHash, d_resNounce[thr_id]);
|
||||
cudaThreadSynchronize();
|
||||
if (cudaSuccess == cudaMemcpy(h_resNounce[thr_id], d_resNounce[thr_id], NBN * sizeof(uint32_t), cudaMemcpyDeviceToHost)) {
|
||||
//cudaThreadSynchronize();
|
||||
result = h_resNounce[thr_id][0];
|
||||
#if NBN > 1
|
||||
extra_results[0] = h_resNounce[thr_id][1];
|
||||
#endif
|
||||
}
|
||||
return result;
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_IV, h_IV, sizeof(h_IV), 0, cudaMemcpyHostToDevice));
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_CNS, h_CNS, sizeof(h_CNS), 0, cudaMemcpyHostToDevice));
|
||||
}
|
||||
|
||||
__host__
|
||||
@@ -485,6 +468,37 @@ void qubit_luffa512_cpu_hash_80(int thr_id, uint32_t threads, uint32_t startNoun
|
||||
qubit_luffa512_gpu_hash_80 <<<grid, block, shared_size>>> (threads, startNounce, d_outputHash);
|
||||
}
|
||||
|
||||
__host__
|
||||
void qubit_cpu_precalc(uint32_t* message)
|
||||
{
|
||||
uint32_t statebuffer[8];
|
||||
uint32_t statechainv[40] =
|
||||
{
|
||||
0x6d251e69, 0x44b051e0, 0x4eaa6fb4, 0xdbf78465,
|
||||
0x6e292011, 0x90152df4, 0xee058139, 0xdef610bb,
|
||||
0xc3b44b95, 0xd9d2f256, 0x70eee9a0, 0xde099fa3,
|
||||
0x5d9b0557, 0x8fc944b3, 0xcf1ccf0e, 0x746cd581,
|
||||
0xf7efc89d, 0x5dba5781, 0x04016ce5, 0xad659c05,
|
||||
0x0306194f, 0x666d1836, 0x24aa230a, 0x8b264ae7,
|
||||
0x858075d5, 0x36d79cce, 0xe571f7d7, 0x204b1f67,
|
||||
0x35870c6a, 0x57e9e923, 0x14bcb808, 0x7cde72ce,
|
||||
0x6c68e9be, 0x5ec41e22, 0xc825b7c7, 0xaffb4363,
|
||||
0xf5df3999, 0x0fc688f1, 0xb07224cc, 0x03e86cea
|
||||
};
|
||||
|
||||
for (int i = 0; i<8; i++)
|
||||
statebuffer[i] = cuda_swab32(message[i]);
|
||||
rnd512_cpu(statebuffer, statechainv);
|
||||
|
||||
for (int i = 0; i<8; i++)
|
||||
statebuffer[i] = cuda_swab32(message[i+8]);
|
||||
|
||||
rnd512_cpu(statebuffer, statechainv);
|
||||
|
||||
cudaMemcpyToSymbol(statebufferpre, statebuffer, sizeof(statebuffer), 0, cudaMemcpyHostToDevice);
|
||||
cudaMemcpyToSymbol(statechainvpre, statechainv, sizeof(statechainv), 0, cudaMemcpyHostToDevice);
|
||||
}
|
||||
|
||||
__host__
|
||||
void qubit_luffa512_cpu_setBlock_80(void *pdata)
|
||||
{
|
||||
@@ -497,21 +511,6 @@ void qubit_luffa512_cpu_setBlock_80(void *pdata)
|
||||
PaddedMessage[126] = 0x02;
|
||||
PaddedMessage[127] = 0x80;
|
||||
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol( c_PaddedMessage80, PaddedMessage, 16*sizeof(uint64_t), 0, cudaMemcpyHostToDevice));
|
||||
}
|
||||
|
||||
__host__
|
||||
void qubit_luffa512_cpufinal_setBlock_80(void *pdata, const void *ptarget)
|
||||
{
|
||||
unsigned char PaddedMessage[128];
|
||||
|
||||
memcpy(PaddedMessage, pdata, 80);
|
||||
memset(PaddedMessage+80, 0, 48);
|
||||
PaddedMessage[80] = 0x80;
|
||||
PaddedMessage[111] = 1;
|
||||
PaddedMessage[126] = 0x02;
|
||||
PaddedMessage[127] = 0x80;
|
||||
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_Target, ptarget, 8*sizeof(uint32_t), 0, cudaMemcpyHostToDevice));
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_PaddedMessage80, PaddedMessage, 16*sizeof(uint64_t), 0, cudaMemcpyHostToDevice));
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_PaddedMessage80, PaddedMessage, sizeof(PaddedMessage), 0, cudaMemcpyHostToDevice));
|
||||
qubit_cpu_precalc((uint32_t*) PaddedMessage);
|
||||
}
|
||||
+4
-4
@@ -60,8 +60,8 @@ IDI_ICON1 ICON "ccminer.ico"
|
||||
//
|
||||
|
||||
VS_VERSION_INFO VERSIONINFO
|
||||
FILEVERSION 1,6,0,0
|
||||
PRODUCTVERSION 1,6,0,0
|
||||
FILEVERSION 1,6,4,0
|
||||
PRODUCTVERSION 1,6,4,0
|
||||
FILEFLAGSMASK 0x3fL
|
||||
#ifdef _DEBUG
|
||||
FILEFLAGS 0x21L
|
||||
@@ -76,10 +76,10 @@ BEGIN
|
||||
BEGIN
|
||||
BLOCK "040904e4"
|
||||
BEGIN
|
||||
VALUE "FileVersion", "1.6"
|
||||
VALUE "FileVersion", "1.6.4"
|
||||
VALUE "LegalCopyright", "Copyright (C) 2015"
|
||||
VALUE "ProductName", "ccminer"
|
||||
VALUE "ProductVersion", "1.6"
|
||||
VALUE "ProductVersion", "1.6.4"
|
||||
END
|
||||
END
|
||||
BLOCK "VarFileInfo"
|
||||
|
||||
@@ -23,7 +23,6 @@ extern char *device_name[MAX_GPUS];
|
||||
extern bool opt_autotune;
|
||||
extern int opt_nfactor;
|
||||
extern char *jane_params;
|
||||
extern bool abort_flag;
|
||||
extern int parallel;
|
||||
|
||||
extern void get_currentalgo(char* buf, int sz);
|
||||
|
||||
+860
@@ -0,0 +1,860 @@
|
||||
// Copyright (c) 2009-2010 Satoshi Nakamoto
|
||||
// Copyright (c) 2009-2014 The Bitcoin Core developers
|
||||
// Distributed under the MIT software license, see the accompanying
|
||||
// file COPYING or http://www.opensource.org/licenses/mit-license.php.
|
||||
|
||||
#ifndef BITCOIN_SERIALIZE_H
|
||||
#define BITCOIN_SERIALIZE_H
|
||||
|
||||
//#include "compat/endian.h"
|
||||
|
||||
#include <algorithm>
|
||||
#include <assert.h>
|
||||
#include <ios>
|
||||
#include <limits>
|
||||
#include <map>
|
||||
#include <set>
|
||||
#include <stdint.h>
|
||||
#include <string>
|
||||
#include <string.h>
|
||||
#include <utility>
|
||||
#include <vector>
|
||||
|
||||
class CScript;
|
||||
|
||||
static const unsigned int MAX_SIZE = 0x02000000;
|
||||
|
||||
/**
|
||||
* Used to bypass the rule against non-const reference to temporary
|
||||
* where it makes sense with wrappers such as CFlatData or CTxDB
|
||||
*/
|
||||
template<typename T>
|
||||
inline T& REF(const T& val)
|
||||
{
|
||||
return const_cast<T&>(val);
|
||||
}
|
||||
|
||||
/**
|
||||
* Used to acquire a non-const pointer "this" to generate bodies
|
||||
* of const serialization operations from a template
|
||||
*/
|
||||
template<typename T>
|
||||
inline T* NCONST_PTR(const T* val)
|
||||
{
|
||||
return const_cast<T*>(val);
|
||||
}
|
||||
|
||||
/**
|
||||
* Get begin pointer of vector (non-const version).
|
||||
* @note These functions avoid the undefined case of indexing into an empty
|
||||
* vector, as well as that of indexing after the end of the vector.
|
||||
*/
|
||||
template <class T, class TAl>
|
||||
inline T* begin_ptr(std::vector<T,TAl>& v)
|
||||
{
|
||||
return v.empty() ? NULL : &v[0];
|
||||
}
|
||||
/** Get begin pointer of vector (const version) */
|
||||
template <class T, class TAl>
|
||||
inline const T* begin_ptr(const std::vector<T,TAl>& v)
|
||||
{
|
||||
return v.empty() ? NULL : &v[0];
|
||||
}
|
||||
/** Get end pointer of vector (non-const version) */
|
||||
template <class T, class TAl>
|
||||
inline T* end_ptr(std::vector<T,TAl>& v)
|
||||
{
|
||||
return v.empty() ? NULL : (&v[0] + v.size());
|
||||
}
|
||||
/** Get end pointer of vector (const version) */
|
||||
template <class T, class TAl>
|
||||
inline const T* end_ptr(const std::vector<T,TAl>& v)
|
||||
{
|
||||
return v.empty() ? NULL : (&v[0] + v.size());
|
||||
}
|
||||
|
||||
/*
|
||||
* Lowest-level serialization and conversion.
|
||||
* @note Sizes of these types are verified in the tests
|
||||
*/
|
||||
template<typename Stream> inline void ser_writedata8(Stream &s, uint8_t obj)
|
||||
{
|
||||
s.write((char*)&obj, 1);
|
||||
}
|
||||
template<typename Stream> inline void ser_writedata16(Stream &s, uint16_t obj)
|
||||
{
|
||||
obj = htole16(obj);
|
||||
s.write((char*)&obj, 2);
|
||||
}
|
||||
template<typename Stream> inline void ser_writedata32(Stream &s, uint32_t obj)
|
||||
{
|
||||
obj = htole32(obj);
|
||||
s.write((char*)&obj, 4);
|
||||
}
|
||||
template<typename Stream> inline void ser_writedata64(Stream &s, uint64_t obj)
|
||||
{
|
||||
obj = htole64(obj);
|
||||
s.write((char*)&obj, 8);
|
||||
}
|
||||
template<typename Stream> inline uint8_t ser_readdata8(Stream &s)
|
||||
{
|
||||
uint8_t obj;
|
||||
s.read((char*)&obj, 1);
|
||||
return obj;
|
||||
}
|
||||
template<typename Stream> inline uint16_t ser_readdata16(Stream &s)
|
||||
{
|
||||
uint16_t obj;
|
||||
s.read((char*)&obj, 2);
|
||||
return le16toh(obj);
|
||||
}
|
||||
template<typename Stream> inline uint32_t ser_readdata32(Stream &s)
|
||||
{
|
||||
uint32_t obj;
|
||||
s.read((char*)&obj, 4);
|
||||
return le32toh(obj);
|
||||
}
|
||||
template<typename Stream> inline uint64_t ser_readdata64(Stream &s)
|
||||
{
|
||||
uint64_t obj;
|
||||
s.read((char*)&obj, 8);
|
||||
return le64toh(obj);
|
||||
}
|
||||
inline uint64_t ser_double_to_uint64(double x)
|
||||
{
|
||||
union { double x; uint64_t y; } tmp;
|
||||
tmp.x = x;
|
||||
return tmp.y;
|
||||
}
|
||||
inline uint32_t ser_float_to_uint32(float x)
|
||||
{
|
||||
union { float x; uint32_t y; } tmp;
|
||||
tmp.x = x;
|
||||
return tmp.y;
|
||||
}
|
||||
inline double ser_uint64_to_double(uint64_t y)
|
||||
{
|
||||
union { double x; uint64_t y; } tmp;
|
||||
tmp.y = y;
|
||||
return tmp.x;
|
||||
}
|
||||
inline float ser_uint32_to_float(uint32_t y)
|
||||
{
|
||||
union { float x; uint32_t y; } tmp;
|
||||
tmp.y = y;
|
||||
return tmp.x;
|
||||
}
|
||||
|
||||
|
||||
/////////////////////////////////////////////////////////////////
|
||||
//
|
||||
// Templates for serializing to anything that looks like a stream,
|
||||
// i.e. anything that supports .read(char*, size_t) and .write(char*, size_t)
|
||||
//
|
||||
|
||||
enum
|
||||
{
|
||||
// primary actions
|
||||
SER_NETWORK = (1 << 0),
|
||||
SER_DISK = (1 << 1),
|
||||
SER_GETHASH = (1 << 2),
|
||||
};
|
||||
|
||||
#define READWRITE(obj) (::SerReadWrite(s, (obj), nType, nVersion, ser_action))
|
||||
|
||||
/**
|
||||
* Implement three methods for serializable objects. These are actually wrappers over
|
||||
* "SerializationOp" template, which implements the body of each class' serialization
|
||||
* code. Adding "ADD_SERIALIZE_METHODS" in the body of the class causes these wrappers to be
|
||||
* added as members.
|
||||
*/
|
||||
#define ADD_SERIALIZE_METHODS \
|
||||
size_t GetSerializeSize(int nType, int nVersion) const { \
|
||||
CSizeComputer s(nType, nVersion); \
|
||||
NCONST_PTR(this)->SerializationOp(s, CSerActionSerialize(), nType, nVersion);\
|
||||
return s.size(); \
|
||||
} \
|
||||
template<typename Stream> \
|
||||
void Serialize(Stream& s, int nType, int nVersion) const { \
|
||||
NCONST_PTR(this)->SerializationOp(s, CSerActionSerialize(), nType, nVersion);\
|
||||
} \
|
||||
template<typename Stream> \
|
||||
void Unserialize(Stream& s, int nType, int nVersion) { \
|
||||
SerializationOp(s, CSerActionUnserialize(), nType, nVersion); \
|
||||
}
|
||||
|
||||
/*
|
||||
* Basic Types
|
||||
*/
|
||||
inline unsigned int GetSerializeSize(char a, int, int=0) { return 1; }
|
||||
inline unsigned int GetSerializeSize(int8_t a, int, int=0) { return 1; }
|
||||
inline unsigned int GetSerializeSize(uint8_t a, int, int=0) { return 1; }
|
||||
inline unsigned int GetSerializeSize(int16_t a, int, int=0) { return 2; }
|
||||
inline unsigned int GetSerializeSize(uint16_t a, int, int=0) { return 2; }
|
||||
inline unsigned int GetSerializeSize(int32_t a, int, int=0) { return 4; }
|
||||
inline unsigned int GetSerializeSize(uint32_t a, int, int=0) { return 4; }
|
||||
inline unsigned int GetSerializeSize(int64_t a, int, int=0) { return 8; }
|
||||
inline unsigned int GetSerializeSize(uint64_t a, int, int=0) { return 8; }
|
||||
inline unsigned int GetSerializeSize(float a, int, int=0) { return 4; }
|
||||
inline unsigned int GetSerializeSize(double a, int, int=0) { return 8; }
|
||||
|
||||
template<typename Stream> inline void Serialize(Stream& s, char a, int, int=0) { ser_writedata8(s, a); } // TODO Get rid of bare char
|
||||
template<typename Stream> inline void Serialize(Stream& s, int8_t a, int, int=0) { ser_writedata8(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, uint8_t a, int, int=0) { ser_writedata8(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, int16_t a, int, int=0) { ser_writedata16(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, uint16_t a, int, int=0) { ser_writedata16(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, int32_t a, int, int=0) { ser_writedata32(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, uint32_t a, int, int=0) { ser_writedata32(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, int64_t a, int, int=0) { ser_writedata64(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, uint64_t a, int, int=0) { ser_writedata64(s, a); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, float a, int, int=0) { ser_writedata32(s, ser_float_to_uint32(a)); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, double a, int, int=0) { ser_writedata64(s, ser_double_to_uint64(a)); }
|
||||
|
||||
template<typename Stream> inline void Unserialize(Stream& s, char& a, int, int=0) { a = ser_readdata8(s); } // TODO Get rid of bare char
|
||||
template<typename Stream> inline void Unserialize(Stream& s, int8_t& a, int, int=0) { a = ser_readdata8(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, uint8_t& a, int, int=0) { a = ser_readdata8(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, int16_t& a, int, int=0) { a = ser_readdata16(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, uint16_t& a, int, int=0) { a = ser_readdata16(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, int32_t& a, int, int=0) { a = ser_readdata32(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, uint32_t& a, int, int=0) { a = ser_readdata32(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, int64_t& a, int, int=0) { a = ser_readdata64(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, uint64_t& a, int, int=0) { a = ser_readdata64(s); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, float& a, int, int=0) { a = ser_uint32_to_float(ser_readdata32(s)); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, double& a, int, int=0) { a = ser_uint64_to_double(ser_readdata64(s)); }
|
||||
|
||||
inline unsigned int GetSerializeSize(bool a, int, int=0) { return sizeof(char); }
|
||||
template<typename Stream> inline void Serialize(Stream& s, bool a, int, int=0) { char f=a; ser_writedata8(s, f); }
|
||||
template<typename Stream> inline void Unserialize(Stream& s, bool& a, int, int=0) { char f=ser_readdata8(s); a=f; }
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* Compact Size
|
||||
* size < 253 -- 1 byte
|
||||
* size <= USHRT_MAX -- 3 bytes (253 + 2 bytes)
|
||||
* size <= UINT_MAX -- 5 bytes (254 + 4 bytes)
|
||||
* size > UINT_MAX -- 9 bytes (255 + 8 bytes)
|
||||
*/
|
||||
inline unsigned int GetSizeOfCompactSize(uint64_t nSize)
|
||||
{
|
||||
if (nSize < 253) return sizeof(unsigned char);
|
||||
else if (nSize <= std::numeric_limits<unsigned short>::max()) return sizeof(unsigned char) + sizeof(unsigned short);
|
||||
else if (nSize <= std::numeric_limits<unsigned int>::max()) return sizeof(unsigned char) + sizeof(unsigned int);
|
||||
else return sizeof(unsigned char) + sizeof(uint64_t);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void WriteCompactSize(Stream& os, uint64_t nSize)
|
||||
{
|
||||
if (nSize < 253)
|
||||
{
|
||||
ser_writedata8(os, nSize);
|
||||
}
|
||||
else if (nSize <= std::numeric_limits<unsigned short>::max())
|
||||
{
|
||||
ser_writedata8(os, 253);
|
||||
ser_writedata16(os, nSize);
|
||||
}
|
||||
else if (nSize <= std::numeric_limits<unsigned int>::max())
|
||||
{
|
||||
ser_writedata8(os, 254);
|
||||
ser_writedata32(os, nSize);
|
||||
}
|
||||
else
|
||||
{
|
||||
ser_writedata8(os, 255);
|
||||
ser_writedata64(os, nSize);
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
uint64_t ReadCompactSize(Stream& is)
|
||||
{
|
||||
uint8_t chSize = ser_readdata8(is);
|
||||
uint64_t nSizeRet = 0;
|
||||
if (chSize < 253)
|
||||
{
|
||||
nSizeRet = chSize;
|
||||
}
|
||||
else if (chSize == 253)
|
||||
{
|
||||
nSizeRet = ser_readdata16(is);
|
||||
if (nSizeRet < 253)
|
||||
throw std::ios_base::failure("non-canonical ReadCompactSize()");
|
||||
}
|
||||
else if (chSize == 254)
|
||||
{
|
||||
nSizeRet = ser_readdata32(is);
|
||||
if (nSizeRet < 0x10000u)
|
||||
throw std::ios_base::failure("non-canonical ReadCompactSize()");
|
||||
}
|
||||
else
|
||||
{
|
||||
nSizeRet = ser_readdata64(is);
|
||||
if (nSizeRet < 0x100000000ULL)
|
||||
throw std::ios_base::failure("non-canonical ReadCompactSize()");
|
||||
}
|
||||
if (nSizeRet > (uint64_t)MAX_SIZE)
|
||||
throw std::ios_base::failure("ReadCompactSize(): size too large");
|
||||
return nSizeRet;
|
||||
}
|
||||
|
||||
/**
|
||||
* Variable-length integers: bytes are a MSB base-128 encoding of the number.
|
||||
* The high bit in each byte signifies whether another digit follows. To make
|
||||
* sure the encoding is one-to-one, one is subtracted from all but the last digit.
|
||||
* Thus, the byte sequence a[] with length len, where all but the last byte
|
||||
* has bit 128 set, encodes the number:
|
||||
*
|
||||
* (a[len-1] & 0x7F) + sum(i=1..len-1, 128^i*((a[len-i-1] & 0x7F)+1))
|
||||
*
|
||||
* Properties:
|
||||
* * Very small (0-127: 1 byte, 128-16511: 2 bytes, 16512-2113663: 3 bytes)
|
||||
* * Every integer has exactly one encoding
|
||||
* * Encoding does not depend on size of original integer type
|
||||
* * No redundancy: every (infinite) byte sequence corresponds to a list
|
||||
* of encoded integers.
|
||||
*
|
||||
* 0: [0x00] 256: [0x81 0x00]
|
||||
* 1: [0x01] 16383: [0xFE 0x7F]
|
||||
* 127: [0x7F] 16384: [0xFF 0x00]
|
||||
* 128: [0x80 0x00] 16511: [0x80 0xFF 0x7F]
|
||||
* 255: [0x80 0x7F] 65535: [0x82 0xFD 0x7F]
|
||||
* 2^32: [0x8E 0xFE 0xFE 0xFF 0x00]
|
||||
*/
|
||||
|
||||
template<typename I>
|
||||
inline unsigned int GetSizeOfVarInt(I n)
|
||||
{
|
||||
int nRet = 0;
|
||||
while(true) {
|
||||
nRet++;
|
||||
if (n <= 0x7F)
|
||||
break;
|
||||
n = (n >> 7) - 1;
|
||||
}
|
||||
return nRet;
|
||||
}
|
||||
|
||||
template<typename Stream, typename I>
|
||||
void WriteVarInt(Stream& os, I n)
|
||||
{
|
||||
unsigned char tmp[(sizeof(n)*8+6)/7];
|
||||
int len=0;
|
||||
while(true) {
|
||||
tmp[len] = (n & 0x7F) | (len ? 0x80 : 0x00);
|
||||
if (n <= 0x7F)
|
||||
break;
|
||||
n = (n >> 7) - 1;
|
||||
len++;
|
||||
}
|
||||
do {
|
||||
ser_writedata8(os, tmp[len]);
|
||||
} while(len--);
|
||||
}
|
||||
|
||||
template<typename Stream, typename I>
|
||||
I ReadVarInt(Stream& is)
|
||||
{
|
||||
I n = 0;
|
||||
while(true) {
|
||||
unsigned char chData = ser_readdata8(is);
|
||||
n = (n << 7) | (chData & 0x7F);
|
||||
if (chData & 0x80)
|
||||
n++;
|
||||
else
|
||||
return n;
|
||||
}
|
||||
}
|
||||
|
||||
#define FLATDATA(obj) REF(CFlatData((char*)&(obj), (char*)&(obj) + sizeof(obj)))
|
||||
#define VARINT(obj) REF(WrapVarInt(REF(obj)))
|
||||
#define LIMITED_STRING(obj,n) REF(LimitedString< n >(REF(obj)))
|
||||
|
||||
/**
|
||||
* Wrapper for serializing arrays and POD.
|
||||
*/
|
||||
class CFlatData
|
||||
{
|
||||
protected:
|
||||
char* pbegin;
|
||||
char* pend;
|
||||
public:
|
||||
CFlatData(void* pbeginIn, void* pendIn) : pbegin((char*)pbeginIn), pend((char*)pendIn) { }
|
||||
template <class T, class TAl>
|
||||
explicit CFlatData(std::vector<T,TAl> &v)
|
||||
{
|
||||
pbegin = (char*)begin_ptr(v);
|
||||
pend = (char*)end_ptr(v);
|
||||
}
|
||||
char* begin() { return pbegin; }
|
||||
const char* begin() const { return pbegin; }
|
||||
char* end() { return pend; }
|
||||
const char* end() const { return pend; }
|
||||
|
||||
unsigned int GetSerializeSize(int, int=0) const
|
||||
{
|
||||
return pend - pbegin;
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Serialize(Stream& s, int, int=0) const
|
||||
{
|
||||
s.write(pbegin, pend - pbegin);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Unserialize(Stream& s, int, int=0)
|
||||
{
|
||||
s.read(pbegin, pend - pbegin);
|
||||
}
|
||||
};
|
||||
|
||||
template<typename I>
|
||||
class CVarInt
|
||||
{
|
||||
protected:
|
||||
I &n;
|
||||
public:
|
||||
CVarInt(I& nIn) : n(nIn) { }
|
||||
|
||||
unsigned int GetSerializeSize(int, int) const {
|
||||
return GetSizeOfVarInt<I>(n);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Serialize(Stream &s, int, int) const {
|
||||
WriteVarInt<Stream,I>(s, n);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Unserialize(Stream& s, int, int) {
|
||||
n = ReadVarInt<Stream,I>(s);
|
||||
}
|
||||
};
|
||||
|
||||
template<size_t Limit>
|
||||
class LimitedString
|
||||
{
|
||||
protected:
|
||||
std::string& string;
|
||||
public:
|
||||
LimitedString(std::string& string) : string(string) {}
|
||||
|
||||
template<typename Stream>
|
||||
void Unserialize(Stream& s, int, int=0)
|
||||
{
|
||||
size_t size = ReadCompactSize(s);
|
||||
if (size > Limit) {
|
||||
throw std::ios_base::failure("String length limit exceeded");
|
||||
}
|
||||
string.resize(size);
|
||||
if (size != 0)
|
||||
s.read((char*)&string[0], size);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Serialize(Stream& s, int, int=0) const
|
||||
{
|
||||
WriteCompactSize(s, string.size());
|
||||
if (!string.empty())
|
||||
s.write((char*)&string[0], string.size());
|
||||
}
|
||||
|
||||
unsigned int GetSerializeSize(int, int=0) const
|
||||
{
|
||||
return GetSizeOfCompactSize(string.size()) + string.size();
|
||||
}
|
||||
};
|
||||
|
||||
template<typename I>
|
||||
CVarInt<I> WrapVarInt(I& n) { return CVarInt<I>(n); }
|
||||
|
||||
/**
|
||||
* Forward declarations
|
||||
*/
|
||||
|
||||
/**
|
||||
* string
|
||||
*/
|
||||
template<typename C> unsigned int GetSerializeSize(const std::basic_string<C>& str, int, int=0);
|
||||
template<typename Stream, typename C> void Serialize(Stream& os, const std::basic_string<C>& str, int, int=0);
|
||||
template<typename Stream, typename C> void Unserialize(Stream& is, std::basic_string<C>& str, int, int=0);
|
||||
|
||||
/**
|
||||
* vector
|
||||
* vectors of unsigned char are a special case and are intended to be serialized as a single opaque blob.
|
||||
*/
|
||||
template<typename T, typename A> unsigned int GetSerializeSize_impl(const std::vector<T, A>& v, int nType, int nVersion, const unsigned char&);
|
||||
template<typename T, typename A, typename V> unsigned int GetSerializeSize_impl(const std::vector<T, A>& v, int nType, int nVersion, const V&);
|
||||
template<typename T, typename A> inline unsigned int GetSerializeSize(const std::vector<T, A>& v, int nType, int nVersion);
|
||||
template<typename Stream, typename T, typename A> void Serialize_impl(Stream& os, const std::vector<T, A>& v, int nType, int nVersion, const unsigned char&);
|
||||
template<typename Stream, typename T, typename A, typename V> void Serialize_impl(Stream& os, const std::vector<T, A>& v, int nType, int nVersion, const V&);
|
||||
template<typename Stream, typename T, typename A> inline void Serialize(Stream& os, const std::vector<T, A>& v, int nType, int nVersion);
|
||||
template<typename Stream, typename T, typename A> void Unserialize_impl(Stream& is, std::vector<T, A>& v, int nType, int nVersion, const unsigned char&);
|
||||
template<typename Stream, typename T, typename A, typename V> void Unserialize_impl(Stream& is, std::vector<T, A>& v, int nType, int nVersion, const V&);
|
||||
template<typename Stream, typename T, typename A> inline void Unserialize(Stream& is, std::vector<T, A>& v, int nType, int nVersion);
|
||||
|
||||
/**
|
||||
* others derived from vector
|
||||
*/
|
||||
extern inline unsigned int GetSerializeSize(const CScript& v, int nType, int nVersion);
|
||||
template<typename Stream> void Serialize(Stream& os, const CScript& v, int nType, int nVersion);
|
||||
template<typename Stream> void Unserialize(Stream& is, CScript& v, int nType, int nVersion);
|
||||
|
||||
/**
|
||||
* pair
|
||||
*/
|
||||
template<typename K, typename T> unsigned int GetSerializeSize(const std::pair<K, T>& item, int nType, int nVersion);
|
||||
template<typename Stream, typename K, typename T> void Serialize(Stream& os, const std::pair<K, T>& item, int nType, int nVersion);
|
||||
template<typename Stream, typename K, typename T> void Unserialize(Stream& is, std::pair<K, T>& item, int nType, int nVersion);
|
||||
|
||||
/**
|
||||
* map
|
||||
*/
|
||||
template<typename K, typename T, typename Pred, typename A> unsigned int GetSerializeSize(const std::map<K, T, Pred, A>& m, int nType, int nVersion);
|
||||
template<typename Stream, typename K, typename T, typename Pred, typename A> void Serialize(Stream& os, const std::map<K, T, Pred, A>& m, int nType, int nVersion);
|
||||
template<typename Stream, typename K, typename T, typename Pred, typename A> void Unserialize(Stream& is, std::map<K, T, Pred, A>& m, int nType, int nVersion);
|
||||
|
||||
/**
|
||||
* set
|
||||
*/
|
||||
template<typename K, typename Pred, typename A> unsigned int GetSerializeSize(const std::set<K, Pred, A>& m, int nType, int nVersion);
|
||||
template<typename Stream, typename K, typename Pred, typename A> void Serialize(Stream& os, const std::set<K, Pred, A>& m, int nType, int nVersion);
|
||||
template<typename Stream, typename K, typename Pred, typename A> void Unserialize(Stream& is, std::set<K, Pred, A>& m, int nType, int nVersion);
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* If none of the specialized versions above matched, default to calling member function.
|
||||
* "int nType" is changed to "long nType" to keep from getting an ambiguous overload error.
|
||||
* The compiler will only cast int to long if none of the other templates matched.
|
||||
* Thanks to Boost serialization for this idea.
|
||||
*/
|
||||
template<typename T>
|
||||
inline unsigned int GetSerializeSize(const T& a, long nType, int nVersion)
|
||||
{
|
||||
return a.GetSerializeSize((int)nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename T>
|
||||
inline void Serialize(Stream& os, const T& a, long nType, int nVersion)
|
||||
{
|
||||
a.Serialize(os, (int)nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename T>
|
||||
inline void Unserialize(Stream& is, T& a, long nType, int nVersion)
|
||||
{
|
||||
a.Unserialize(is, (int)nType, nVersion);
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* string
|
||||
*/
|
||||
template<typename C>
|
||||
unsigned int GetSerializeSize(const std::basic_string<C>& str, int, int)
|
||||
{
|
||||
return GetSizeOfCompactSize(str.size()) + str.size() * sizeof(str[0]);
|
||||
}
|
||||
|
||||
template<typename Stream, typename C>
|
||||
void Serialize(Stream& os, const std::basic_string<C>& str, int, int)
|
||||
{
|
||||
WriteCompactSize(os, str.size());
|
||||
if (!str.empty())
|
||||
os.write((char*)&str[0], str.size() * sizeof(str[0]));
|
||||
}
|
||||
|
||||
template<typename Stream, typename C>
|
||||
void Unserialize(Stream& is, std::basic_string<C>& str, int, int)
|
||||
{
|
||||
unsigned int nSize = ReadCompactSize(is);
|
||||
str.resize(nSize);
|
||||
if (nSize != 0)
|
||||
is.read((char*)&str[0], nSize * sizeof(str[0]));
|
||||
}
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* vector
|
||||
*/
|
||||
template<typename T, typename A>
|
||||
unsigned int GetSerializeSize_impl(const std::vector<T, A>& v, int nType, int nVersion, const unsigned char&)
|
||||
{
|
||||
return (GetSizeOfCompactSize(v.size()) + v.size() * sizeof(T));
|
||||
}
|
||||
|
||||
template<typename T, typename A, typename V>
|
||||
unsigned int GetSerializeSize_impl(const std::vector<T, A>& v, int nType, int nVersion, const V&)
|
||||
{
|
||||
unsigned int nSize = GetSizeOfCompactSize(v.size());
|
||||
for (typename std::vector<T, A>::const_iterator vi = v.begin(); vi != v.end(); ++vi)
|
||||
nSize += GetSerializeSize((*vi), nType, nVersion);
|
||||
return nSize;
|
||||
}
|
||||
|
||||
template<typename T, typename A>
|
||||
inline unsigned int GetSerializeSize(const std::vector<T, A>& v, int nType, int nVersion)
|
||||
{
|
||||
return GetSerializeSize_impl(v, nType, nVersion, T());
|
||||
}
|
||||
|
||||
|
||||
template<typename Stream, typename T, typename A>
|
||||
void Serialize_impl(Stream& os, const std::vector<T, A>& v, int nType, int nVersion, const unsigned char&)
|
||||
{
|
||||
WriteCompactSize(os, v.size());
|
||||
if (!v.empty())
|
||||
os.write((char*)&v[0], v.size() * sizeof(T));
|
||||
}
|
||||
|
||||
template<typename Stream, typename T, typename A, typename V>
|
||||
void Serialize_impl(Stream& os, const std::vector<T, A>& v, int nType, int nVersion, const V&)
|
||||
{
|
||||
WriteCompactSize(os, v.size());
|
||||
for (typename std::vector<T, A>::const_iterator vi = v.begin(); vi != v.end(); ++vi)
|
||||
::Serialize(os, (*vi), nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename T, typename A>
|
||||
inline void Serialize(Stream& os, const std::vector<T, A>& v, int nType, int nVersion)
|
||||
{
|
||||
Serialize_impl(os, v, nType, nVersion, T());
|
||||
}
|
||||
|
||||
|
||||
template<typename Stream, typename T, typename A>
|
||||
void Unserialize_impl(Stream& is, std::vector<T, A>& v, int nType, int nVersion, const unsigned char&)
|
||||
{
|
||||
// Limit size per read so bogus size value won't cause out of memory
|
||||
v.clear();
|
||||
unsigned int nSize = ReadCompactSize(is);
|
||||
unsigned int i = 0;
|
||||
while (i < nSize)
|
||||
{
|
||||
unsigned int blk = std::min(nSize - i, (unsigned int)(1 + 4999999 / sizeof(T)));
|
||||
v.resize(i + blk);
|
||||
is.read((char*)&v[i], blk * sizeof(T));
|
||||
i += blk;
|
||||
}
|
||||
}
|
||||
|
||||
template<typename Stream, typename T, typename A, typename V>
|
||||
void Unserialize_impl(Stream& is, std::vector<T, A>& v, int nType, int nVersion, const V&)
|
||||
{
|
||||
v.clear();
|
||||
unsigned int nSize = ReadCompactSize(is);
|
||||
unsigned int i = 0;
|
||||
unsigned int nMid = 0;
|
||||
while (nMid < nSize)
|
||||
{
|
||||
nMid += 5000000 / sizeof(T);
|
||||
if (nMid > nSize)
|
||||
nMid = nSize;
|
||||
v.resize(nMid);
|
||||
for (; i < nMid; i++)
|
||||
Unserialize(is, v[i], nType, nVersion);
|
||||
}
|
||||
}
|
||||
|
||||
template<typename Stream, typename T, typename A>
|
||||
inline void Unserialize(Stream& is, std::vector<T, A>& v, int nType, int nVersion)
|
||||
{
|
||||
Unserialize_impl(is, v, nType, nVersion, T());
|
||||
}
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* others derived from vector
|
||||
*/
|
||||
inline unsigned int GetSerializeSize(const CScript& v, int nType, int nVersion)
|
||||
{
|
||||
return GetSerializeSize((const std::vector<unsigned char>&)v, nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Serialize(Stream& os, const CScript& v, int nType, int nVersion)
|
||||
{
|
||||
Serialize(os, (const std::vector<unsigned char>&)v, nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream>
|
||||
void Unserialize(Stream& is, CScript& v, int nType, int nVersion)
|
||||
{
|
||||
Unserialize(is, (std::vector<unsigned char>&)v, nType, nVersion);
|
||||
}
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* pair
|
||||
*/
|
||||
template<typename K, typename T>
|
||||
unsigned int GetSerializeSize(const std::pair<K, T>& item, int nType, int nVersion)
|
||||
{
|
||||
return GetSerializeSize(item.first, nType, nVersion) + GetSerializeSize(item.second, nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename K, typename T>
|
||||
void Serialize(Stream& os, const std::pair<K, T>& item, int nType, int nVersion)
|
||||
{
|
||||
Serialize(os, item.first, nType, nVersion);
|
||||
Serialize(os, item.second, nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename K, typename T>
|
||||
void Unserialize(Stream& is, std::pair<K, T>& item, int nType, int nVersion)
|
||||
{
|
||||
Unserialize(is, item.first, nType, nVersion);
|
||||
Unserialize(is, item.second, nType, nVersion);
|
||||
}
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* map
|
||||
*/
|
||||
template<typename K, typename T, typename Pred, typename A>
|
||||
unsigned int GetSerializeSize(const std::map<K, T, Pred, A>& m, int nType, int nVersion)
|
||||
{
|
||||
unsigned int nSize = GetSizeOfCompactSize(m.size());
|
||||
for (typename std::map<K, T, Pred, A>::const_iterator mi = m.begin(); mi != m.end(); ++mi)
|
||||
nSize += GetSerializeSize((*mi), nType, nVersion);
|
||||
return nSize;
|
||||
}
|
||||
|
||||
template<typename Stream, typename K, typename T, typename Pred, typename A>
|
||||
void Serialize(Stream& os, const std::map<K, T, Pred, A>& m, int nType, int nVersion)
|
||||
{
|
||||
WriteCompactSize(os, m.size());
|
||||
for (typename std::map<K, T, Pred, A>::const_iterator mi = m.begin(); mi != m.end(); ++mi)
|
||||
Serialize(os, (*mi), nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename K, typename T, typename Pred, typename A>
|
||||
void Unserialize(Stream& is, std::map<K, T, Pred, A>& m, int nType, int nVersion)
|
||||
{
|
||||
m.clear();
|
||||
unsigned int nSize = ReadCompactSize(is);
|
||||
typename std::map<K, T, Pred, A>::iterator mi = m.begin();
|
||||
for (unsigned int i = 0; i < nSize; i++)
|
||||
{
|
||||
std::pair<K, T> item;
|
||||
Unserialize(is, item, nType, nVersion);
|
||||
mi = m.insert(mi, item);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* set
|
||||
*/
|
||||
template<typename K, typename Pred, typename A>
|
||||
unsigned int GetSerializeSize(const std::set<K, Pred, A>& m, int nType, int nVersion)
|
||||
{
|
||||
unsigned int nSize = GetSizeOfCompactSize(m.size());
|
||||
for (typename std::set<K, Pred, A>::const_iterator it = m.begin(); it != m.end(); ++it)
|
||||
nSize += GetSerializeSize((*it), nType, nVersion);
|
||||
return nSize;
|
||||
}
|
||||
|
||||
template<typename Stream, typename K, typename Pred, typename A>
|
||||
void Serialize(Stream& os, const std::set<K, Pred, A>& m, int nType, int nVersion)
|
||||
{
|
||||
WriteCompactSize(os, m.size());
|
||||
for (typename std::set<K, Pred, A>::const_iterator it = m.begin(); it != m.end(); ++it)
|
||||
Serialize(os, (*it), nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename K, typename Pred, typename A>
|
||||
void Unserialize(Stream& is, std::set<K, Pred, A>& m, int nType, int nVersion)
|
||||
{
|
||||
m.clear();
|
||||
unsigned int nSize = ReadCompactSize(is);
|
||||
typename std::set<K, Pred, A>::iterator it = m.begin();
|
||||
for (unsigned int i = 0; i < nSize; i++)
|
||||
{
|
||||
K key;
|
||||
Unserialize(is, key, nType, nVersion);
|
||||
it = m.insert(it, key);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
/**
|
||||
* Support for ADD_SERIALIZE_METHODS and READWRITE macro
|
||||
*/
|
||||
struct CSerActionSerialize
|
||||
{
|
||||
bool ForRead() const { return false; }
|
||||
};
|
||||
struct CSerActionUnserialize
|
||||
{
|
||||
bool ForRead() const { return true; }
|
||||
};
|
||||
|
||||
template<typename Stream, typename T>
|
||||
inline void SerReadWrite(Stream& s, const T& obj, int nType, int nVersion, CSerActionSerialize ser_action)
|
||||
{
|
||||
::Serialize(s, obj, nType, nVersion);
|
||||
}
|
||||
|
||||
template<typename Stream, typename T>
|
||||
inline void SerReadWrite(Stream& s, T& obj, int nType, int nVersion, CSerActionUnserialize ser_action)
|
||||
{
|
||||
::Unserialize(s, obj, nType, nVersion);
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
class CSizeComputer
|
||||
{
|
||||
protected:
|
||||
size_t nSize;
|
||||
|
||||
public:
|
||||
int nType;
|
||||
int nVersion;
|
||||
|
||||
CSizeComputer(int nTypeIn, int nVersionIn) : nSize(0), nType(nTypeIn), nVersion(nVersionIn) {}
|
||||
|
||||
CSizeComputer& write(const char *psz, size_t nSize)
|
||||
{
|
||||
this->nSize += nSize;
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<typename T>
|
||||
CSizeComputer& operator<<(const T& obj)
|
||||
{
|
||||
::Serialize(*this, obj, nType, nVersion);
|
||||
return (*this);
|
||||
}
|
||||
|
||||
size_t size() const {
|
||||
return nSize;
|
||||
}
|
||||
};
|
||||
|
||||
#endif // BITCOIN_SERIALIZE_H
|
||||
@@ -0,0 +1,206 @@
|
||||
/* bitcoin algo (by klaus) */
|
||||
|
||||
#include "miner.h"
|
||||
#include "cuda_helper.h"
|
||||
|
||||
static __thread uint32_t *h_nounce;
|
||||
|
||||
extern cudaStream_t gpustream[MAX_GPUS];
|
||||
|
||||
extern void bitcoin_cpu_init(int thr_id);
|
||||
extern void bitcoin_cpu_hash(int thr_id, uint32_t threads, uint32_t startNounce, const uint32_t *const ms, uint32_t merkle, uint32_t time, uint32_t compacttarget, uint32_t *const h_nounce);
|
||||
extern void bitcoin_midstate(const uint32_t *data, uint32_t *midstate);
|
||||
|
||||
uint32_t rrot(uint32_t x, unsigned int n)
|
||||
{
|
||||
return (x >> n) | (x << (32 - n));
|
||||
}
|
||||
|
||||
// CPU HASH
|
||||
void bitcoin_hash(uint32_t *output, const uint32_t *data, uint32_t nonce, const uint32_t *midstate)
|
||||
{
|
||||
uint32_t w[64];
|
||||
uint32_t s0, s1, t1, t2, maj, ch, a, b, c, d, e, f, g, h;
|
||||
int i;
|
||||
|
||||
const uint32_t k[64] = {
|
||||
0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
|
||||
0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
|
||||
0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
|
||||
0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
|
||||
0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
|
||||
0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
|
||||
0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
|
||||
0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
|
||||
};
|
||||
const uint32_t hc[8] = {
|
||||
0x6a09e667U, 0xbb67ae85U, 0x3c6ef372U, 0xa54ff53aU,
|
||||
0x510e527fU, 0x9b05688cU, 0x1f83d9abU, 0x5be0cd19U
|
||||
};
|
||||
|
||||
for (i = 0; i <= 15; i++)
|
||||
{
|
||||
w[i] = data[i + 16];
|
||||
}
|
||||
w[3] = nonce;
|
||||
for (i = 16; i <= 63; i++)
|
||||
{
|
||||
s0 = rrot(w[i - 15], 7) ^ rrot(w[i - 15], 18) ^ (w[i - 15] >> 3);
|
||||
s1 = rrot(w[i - 2], 17) ^ rrot(w[i - 2], 19) ^ (w[i - 2] >> 10);
|
||||
w[i] = w[i - 16] + s0 + w[i - 7] + s1;
|
||||
}
|
||||
a = midstate[0];
|
||||
b = midstate[1];
|
||||
c = midstate[2];
|
||||
d = midstate[3];
|
||||
e = midstate[4];
|
||||
f = midstate[5];
|
||||
g = midstate[6];
|
||||
h = midstate[7];
|
||||
for (i = 0; i <= 63; i++)
|
||||
{
|
||||
s0 = rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22);
|
||||
maj = (a & b) ^ (a & c) ^ (b & c);
|
||||
t2 = s0 + maj;
|
||||
s1 = rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25);
|
||||
ch = (e & f) ^ ((~e) & g);
|
||||
t1 = h + s1 + ch + k[i] + w[i];
|
||||
h = g;
|
||||
g = f;
|
||||
f = e;
|
||||
e = d + t1;
|
||||
d = c;
|
||||
c = b;
|
||||
b = a;
|
||||
a = t1 + t2;
|
||||
}
|
||||
w[0] = a + midstate[0];
|
||||
w[1] = b + midstate[1];
|
||||
w[2] = c + midstate[2];
|
||||
w[3] = d + midstate[3];
|
||||
w[4] = e + midstate[4];
|
||||
w[5] = f + midstate[5];
|
||||
w[6] = g + midstate[6];
|
||||
w[7] = h + midstate[7];
|
||||
w[8] = 0x80000000U;
|
||||
for (i = 9; i <= 14; i++)
|
||||
w[i] = 0U;
|
||||
w[15] = 0x100U;
|
||||
for (i = 16; i <= 63; i++)
|
||||
{
|
||||
s0 = rrot(w[i - 15], 7) ^ rrot(w[i - 15], 18) ^ (w[i - 15] >> 3);
|
||||
s1 = rrot(w[i - 2], 17) ^ rrot(w[i - 2], 19) ^ (w[i - 2] >> 10);
|
||||
w[i] = w[i - 16] + s0 + w[i - 7] + s1;
|
||||
}
|
||||
a = hc[0];
|
||||
b = hc[1];
|
||||
c = hc[2];
|
||||
d = hc[3];
|
||||
e = hc[4];
|
||||
f = hc[5];
|
||||
g = hc[6];
|
||||
h = hc[7];
|
||||
for (i = 0; i <= 63; i++)
|
||||
{
|
||||
s0 = rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22);
|
||||
maj = (a & b) ^ (a & c) ^ (b & c);
|
||||
t2 = s0 + maj;
|
||||
s1 = rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25);
|
||||
ch = (e & f) ^ ((~e) & g);
|
||||
t1 = h + s1 + ch + k[i] + w[i];
|
||||
h = g;
|
||||
g = f;
|
||||
f = e;
|
||||
e = d + t1;
|
||||
d = c;
|
||||
c = b;
|
||||
b = a;
|
||||
a = t1 + t2;
|
||||
}
|
||||
be32enc(&output[0], a + hc[0]);
|
||||
be32enc(&output[1], b + hc[1]);
|
||||
be32enc(&output[2], c + hc[2]);
|
||||
be32enc(&output[3], d + hc[3]);
|
||||
be32enc(&output[4], e + hc[4]);
|
||||
be32enc(&output[5], f + hc[5]);
|
||||
be32enc(&output[6], g + hc[6]);
|
||||
be32enc(&output[7], h + hc[7]);
|
||||
}
|
||||
|
||||
static bool init[MAX_GPUS] = { 0 };
|
||||
|
||||
int scanhash_bitcoin(int thr_id, uint32_t *pdata, uint32_t *ptarget,
|
||||
uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
uint32_t throughput = device_intensity(thr_id, __func__, 1U << 25);
|
||||
throughput = min(throughput, (max_nonce - first_nonce));
|
||||
|
||||
if (opt_benchmark)
|
||||
ptarget[7] = 0x0005;
|
||||
|
||||
if (!init[thr_id])
|
||||
{
|
||||
CUDA_SAFE_CALL(cudaSetDevice(device_map[thr_id]));
|
||||
//cudaSetDeviceFlags(cudaDeviceScheduleBlockingSync);
|
||||
//cudaDeviceSetCacheConfig(cudaFuncCachePreferL1);
|
||||
|
||||
CUDA_SAFE_CALL(cudaStreamCreate(&gpustream[thr_id]));
|
||||
bitcoin_cpu_init(thr_id);
|
||||
CUDA_SAFE_CALL(cudaMallocHost(&h_nounce, 2 * sizeof(uint32_t)));
|
||||
init[thr_id] = true;
|
||||
}
|
||||
|
||||
uint32_t ms[8];
|
||||
bitcoin_midstate(pdata, ms);
|
||||
|
||||
do
|
||||
{
|
||||
bitcoin_cpu_hash(thr_id, throughput, pdata[19], ms, pdata[16], pdata[17], pdata[18], h_nounce);
|
||||
if (abort_flag) {
|
||||
cudaStreamDestroy(gpustream[thr_id]);
|
||||
pthread_exit(NULL);
|
||||
return -1;
|
||||
}
|
||||
if (h_nounce[0] != UINT32_MAX)
|
||||
{
|
||||
uint32_t _ALIGN(64) vhash64[8];
|
||||
bitcoin_hash(vhash64, pdata, h_nounce[0], ms);
|
||||
if (vhash64[7] == 0 && fulltest(vhash64, ptarget))
|
||||
{
|
||||
int res = 1;
|
||||
// check if there was some other ones...
|
||||
*hashes_done = pdata[19] - first_nonce + throughput;
|
||||
if (h_nounce[1] != UINT32_MAX)
|
||||
{
|
||||
bitcoin_hash(vhash64, pdata, h_nounce[1], ms);
|
||||
if (vhash64[7] == 0 && fulltest(vhash64, ptarget))
|
||||
{
|
||||
pdata[21] = h_nounce[1];
|
||||
res++;
|
||||
if (opt_benchmark)
|
||||
applog(LOG_INFO, "GPU #%d Found second nounce %08x", device_map[thr_id], h_nounce[1]);
|
||||
}
|
||||
else if (vhash64[7] > 0)
|
||||
applog(LOG_WARNING, "GPU #%d: result for %08x does not validate on CPU!", device_map[thr_id], h_nounce[1]);
|
||||
}
|
||||
pdata[19] = h_nounce[0];
|
||||
if (opt_benchmark)
|
||||
applog(LOG_INFO, "GPU #%d Found nounce %08x", device_map[thr_id], h_nounce[0]);
|
||||
|
||||
cudaStreamSynchronize(NULL);
|
||||
return res;
|
||||
}
|
||||
else if (vhash64[7] > 0)
|
||||
applog(LOG_WARNING, "GPU #%d: result for %08x does not validate on CPU!", device_map[thr_id], h_nounce[0]);
|
||||
}
|
||||
|
||||
pdata[19] += throughput; CUDA_SAFE_CALL(cudaGetLastError());
|
||||
|
||||
} while (!work_restart[thr_id].restart && (max_nonce > (uint64_t)(pdata[19]) + throughput));
|
||||
|
||||
cudaStreamSynchronize(NULL);
|
||||
|
||||
*hashes_done = pdata[19] - first_nonce;
|
||||
return 0;
|
||||
}
|
||||
@@ -0,0 +1,89 @@
|
||||
/* creditscoin SHA256 djm34 implementation - 2015 */
|
||||
|
||||
extern "C" {
|
||||
#include "sph/sph_types.h"
|
||||
#include "sph/sph_sha2.h"
|
||||
}
|
||||
|
||||
#include "miner.h"
|
||||
#include "cuda_helper.h"
|
||||
|
||||
static uint32_t *d_hash[MAX_GPUS] ;
|
||||
|
||||
extern void bitcredit_setBlockTarget(uint32_t * data,const uint32_t * midstate, const void *ptarget);
|
||||
extern void bitcredit_cpu_init(uint32_t thr_id, int threads, uint32_t* hash);
|
||||
|
||||
extern uint32_t bitcredit_cpu_hash(uint32_t thr_id, int threads, uint32_t startNounce, int order);
|
||||
|
||||
// CPU HASH
|
||||
void creditshash(void *state, const void *input)
|
||||
{
|
||||
uint32_t hash[8], hash2[8];
|
||||
sph_sha256_context sha1,sha2;
|
||||
|
||||
sph_sha256_init(&sha1);
|
||||
sph_sha256(&sha1, input, 168);
|
||||
sph_sha256_close(&sha1, hash);
|
||||
|
||||
sph_sha256_init(&sha2);
|
||||
sph_sha256(&sha2, hash, 32);
|
||||
sph_sha256_close(&sha2, hash2);
|
||||
|
||||
memcpy(state, hash2, 32);
|
||||
}
|
||||
|
||||
static bool init[MAX_GPUS] = { 0 };
|
||||
|
||||
extern "C" int scanhash_credits(int thr_id, uint32_t *pdata, const uint32_t *ptarget,
|
||||
const uint32_t *midstate, uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
uint32_t endiandata[42];
|
||||
const uint32_t first_nonce = pdata[35];
|
||||
|
||||
uint32_t throughput = device_intensity(thr_id, __func__, 1U << 25); // 256*256*64*8
|
||||
throughput = min(throughput, (max_nonce - first_nonce));
|
||||
|
||||
if (opt_benchmark)
|
||||
((uint32_t*)ptarget)[7] = 0x0000ff;
|
||||
|
||||
if (!init[thr_id])
|
||||
{
|
||||
cudaSetDevice(device_map[thr_id]);
|
||||
cudaSetDeviceFlags(cudaDeviceScheduleBlockingSync);
|
||||
cudaDeviceSetCacheConfig(cudaFuncCachePreferL1);
|
||||
|
||||
bitcredit_cpu_init(thr_id, throughput, d_hash[thr_id]);
|
||||
|
||||
CUDA_SAFE_CALL(cudaMalloc(&d_hash[thr_id], throughput * 32));
|
||||
|
||||
init[thr_id] = true;
|
||||
}
|
||||
|
||||
for (int k = 0; k < 42; k++)
|
||||
be32enc(&endiandata[k], ((uint32_t*)pdata)[k]);
|
||||
|
||||
bitcredit_setBlockTarget(pdata,midstate,ptarget);
|
||||
|
||||
// uint64_t nloop = max_nonce/throughput + 1;
|
||||
|
||||
do {
|
||||
int order = 0;
|
||||
uint32_t foundNonce = bitcredit_cpu_hash(thr_id, throughput, pdata[35], order++);
|
||||
if (foundNonce != UINT32_MAX)
|
||||
{
|
||||
pdata[35] = foundNonce;
|
||||
*hashes_done = foundNonce - first_nonce + 1;
|
||||
return 1;
|
||||
}
|
||||
if ((uint64_t)pdata[35] + throughput > UINT32_MAX) {
|
||||
pdata[35]= UINT32_MAX;
|
||||
*hashes_done = pdata[35] - first_nonce + 1; return 0;
|
||||
} else {
|
||||
pdata[35] += throughput;
|
||||
}
|
||||
|
||||
} while (pdata[19] < max_nonce && !work_restart[thr_id].restart);
|
||||
|
||||
*hashes_done = pdata[35] - first_nonce + 1;
|
||||
return 0;
|
||||
}
|
||||
@@ -0,0 +1,679 @@
|
||||
// Original version written by Schleicher (KlausT @github)
|
||||
// Redistribution and use in source and binary forms, with or without modification, are permitted
|
||||
|
||||
//#ifdef __cplusplus
|
||||
//#include <cstdint>
|
||||
//#else
|
||||
#include <stdint.h>
|
||||
//#endif
|
||||
#include "miner.h"
|
||||
#include "cuda_helper.h"
|
||||
|
||||
void bitcoin_cpu_init(int thr_id);
|
||||
void bitcoin_cpu_hash(int thr_id, uint32_t threads, uint32_t startNounce, const uint32_t *const ms, uint32_t merkle, uint32_t time, uint32_t compacttarget, uint32_t *const h_nounce);
|
||||
void bitcoin_midstate(const uint32_t *data, uint32_t *midstate);
|
||||
|
||||
cudaStream_t gpustream[MAX_GPUS] = { 0 };
|
||||
|
||||
__constant__ uint32_t pTarget[8];
|
||||
static uint32_t *d_result[MAX_GPUS];
|
||||
|
||||
#define TPB 512
|
||||
#define NONCES_PER_THREAD 32
|
||||
|
||||
#define rrot(x, n) ((x >> n) | (x << (32 - n)))
|
||||
|
||||
__global__ __launch_bounds__(TPB, 2)
|
||||
void bitcoin_gpu_hash(const uint32_t threads, const uint32_t startNounce, uint32_t *const result, const uint32_t t1c, const uint32_t t2c,
|
||||
const uint32_t w16, const uint32_t w16rot, const uint32_t w17, const uint32_t w17rot, const uint32_t b2, const uint32_t c2, const uint32_t d2, const uint32_t f2, const uint32_t g2, const uint32_t h2,
|
||||
const uint32_t ms0, const uint32_t ms1, const uint32_t ms2, const uint32_t ms3, const uint32_t ms4, const uint32_t ms5, const uint32_t ms6, const uint32_t ms7, const uint32_t compacttarget)
|
||||
{
|
||||
uint32_t threadindex = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (threadindex < threads)
|
||||
{
|
||||
uint32_t t1, a, b, c, d, e, f, g, h;
|
||||
uint32_t w[64];
|
||||
const uint32_t numberofthreads = blockDim.x*gridDim.x;
|
||||
const uint32_t maxnonce = startNounce + threadindex + numberofthreads*NONCES_PER_THREAD - 1;
|
||||
const uint32_t threadindex = blockIdx.x*blockDim.x + threadIdx.x;
|
||||
|
||||
|
||||
#pragma unroll
|
||||
for (uint32_t nonce = startNounce + threadindex; nonce <= maxnonce; nonce += numberofthreads)
|
||||
{
|
||||
w[18] = (rrot(nonce, 7) ^ rrot(nonce, 18) ^ (nonce >> 3)) + w16rot;
|
||||
w[19] = nonce + w17rot;
|
||||
w[20] = 0x80000000U + (rrot(w[18], 17) ^ rrot(w[18], 19) ^ (w[18] >> 10));
|
||||
w[21] = (rrot(w[19], 17) ^ rrot(w[19], 19) ^ (w[19] >> 10));
|
||||
w[22] = 0x280U + (rrot(w[20], 17) ^ rrot(w[20], 19) ^ (w[20] >> 10));
|
||||
w[23] = w16 + (rrot(w[21], 17) ^ rrot(w[21], 19) ^ (w[21] >> 10));
|
||||
w[24] = w17 + (rrot(w[22], 17) ^ rrot(w[22], 19) ^ (w[22] >> 10));
|
||||
w[25] = w[18] + (rrot(w[23], 17) ^ rrot(w[23], 19) ^ (w[23] >> 10));
|
||||
w[26] = w[19] + (rrot(w[24], 17) ^ rrot(w[24], 19) ^ (w[24] >> 10));
|
||||
w[27] = w[20] + (rrot(w[25], 17) ^ rrot(w[25], 19) ^ (w[25] >> 10));
|
||||
w[28] = w[21] + (rrot(w[26], 17) ^ rrot(w[26], 19) ^ (w[26] >> 10));
|
||||
w[29] = w[22] + (rrot(w[27], 17) ^ rrot(w[27], 19) ^ (w[27] >> 10));
|
||||
w[30] = w[23] + 0xa00055U + (rrot(w[28], 17) ^ rrot(w[28], 19) ^ (w[28] >> 10));
|
||||
w[31] = 0x280U + w[24] + (rrot(w16, 7) ^ rrot(w16, 18) ^ (w16 >> 3)) + (rrot(w[29], 17) ^ rrot(w[29], 19) ^ (w[29] >> 10));
|
||||
w[32] = w16 + w[25] + (rrot(w17, 7) ^ rrot(w17, 18) ^ (w17 >> 3)) + (rrot(w[30], 17) ^ rrot(w[30], 19) ^ (w[30] >> 10));
|
||||
w[33] = w17 + w[26] + (rrot(w[18], 7) ^ rrot(w[18], 18) ^ (w[18] >> 3)) + (rrot(w[31], 17) ^ rrot(w[31], 19) ^ (w[31] >> 10));
|
||||
#pragma unroll
|
||||
for (int i = 34; i < 62; i++)
|
||||
w[i] = w[i-16] + w[i-7] + (rrot(w[i-15], 7) ^ rrot(w[i-15], 18) ^ (w[i-15] >> 3)) + (rrot(w[i-2], 17) ^ rrot(w[i-2], 19) ^ (w[i-2] >> 10));
|
||||
|
||||
t1 = t1c + (uint32_t)nonce;
|
||||
a = ms0 + t1;
|
||||
e = t1 + t2c;
|
||||
//
|
||||
t1 = d2 + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c2 ^ (a & (b2 ^ c2))) + 0xb956c25bU;
|
||||
h = h2 + t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g2 & f2) | (e & (g2 | f2)));
|
||||
//
|
||||
t1 = c2 + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b2 ^ (h & (a ^ b2))) + 0x59f111f1U;
|
||||
g = g2 + t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f2 & e) | (d & (f2 | e)));
|
||||
//
|
||||
t1 = b2 + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x923f82a4U;
|
||||
f = f2 + t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0xab1c5ed5U;
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0xd807aa98U;
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x12835b01U;
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x243185beU;
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x550c7dc3U;
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x72be5d74U;
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x80deb1feU;
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x9bdc06a7U;
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0xc19bf3f4U;
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0xe49b69c1U + w16;
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0xefbe4786U + w17;
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x0fc19dc6U + w[18];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x240ca1ccU + w[19];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x2de92c6fU + w[20];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x4a7484aaU + w[21];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x5cb0a9dcU + w[22];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x76f988daU + w[23];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x983e5152U + w[24];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0xa831c66dU + w[25];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0xb00327c8U + w[26];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0xbf597fc7U + w[27];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0xc6e00bf3U + w[28];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0xd5a79147U + w[29];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x06ca6351U + w[30];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x14292967U + w[31];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x27b70a85U + w[32];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x2e1b2138U + w[33];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x4d2c6dfcU + w[34];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x53380d13U + w[35];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x650a7354U + w[36];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x766a0abbU + w[37];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x81c2c92eU + w[38];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x92722c85U + w[39];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0xa2bfe8a1U + w[40];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0xa81a664bU + w[41];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0xc24b8b70U + w[42];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0xc76c51a3U + w[43];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0xd192e819U + w[44];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0xd6990624U + w[45];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0xf40e3585U + w[46];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x106aa070U + w[47];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x19a4c116U + w[48];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x1e376c08U + w[49];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x2748774cU + w[50];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x34b0bcb5U + w[51];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x391c0cb3U + w[52];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x4ed8aa4aU + w[53];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x5b9cca4fU + w[54];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x682e6ff3U + w[55];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x748f82eeU + w[56];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x78a5636fU + w[57];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x84c87814U + w[58];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x8cc70208U + w[59];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x90befffaU + w[60];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0xa4506cebU + w[61];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0xbef9a3f7U + w[46] + w[55] + (rrot(w[47], 7) ^ rrot(w[47], 18) ^ (w[47] >> 3)) + (rrot(w[60], 17) ^ rrot(w[60], 19) ^ (w[60] >> 10));
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0xc67178f2U + w[47] + w[56] + (rrot(w[48], 7) ^ rrot(w[48], 18) ^ (w[48] >> 3)) + (rrot(w[61], 17) ^ rrot(w[61], 19) ^ (w[61] >> 10));
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
w[0] = a + ms0; w[1] = b + ms1; w[2] = c + ms2; w[3] = d + ms3;
|
||||
w[4] = e + ms4; w[5] = f + ms5; w[6] = g + ms6; w[7] = h + ms7;
|
||||
// hash the hash ***************************************************************
|
||||
w[16] = w[0] + (rrot(w[1], 7) ^ rrot(w[1], 18) ^ (w[1] >> 3));
|
||||
w[17] = w[1] + (rrot(w[2], 7) ^ rrot(w[2], 18) ^ (w[2] >> 3)) + (rrot(0x100, 17) ^ rrot(0x100, 19) ^ (0x100 >> 10));
|
||||
w[18] = w[2] + (rrot(w[3], 7) ^ rrot(w[3], 18) ^ (w[3] >> 3)) + (rrot(w[16], 17) ^ rrot(w[16], 19) ^ (w[16] >> 10));
|
||||
w[19] = w[3] + (rrot(w[4], 7) ^ rrot(w[4], 18) ^ (w[4] >> 3)) + (rrot(w[17], 17) ^ rrot(w[17], 19) ^ (w[17] >> 10));
|
||||
w[20] = w[4] + (rrot(w[5], 7) ^ rrot(w[5], 18) ^ (w[5] >> 3)) + (rrot(w[18], 17) ^ rrot(w[18], 19) ^ (w[18] >> 10));
|
||||
w[21] = w[5] + (rrot(w[6], 7) ^ rrot(w[6], 18) ^ (w[6] >> 3)) + (rrot(w[19], 17) ^ rrot(w[19], 19) ^ (w[19] >> 10));
|
||||
w[22] = w[6] + 0x100 + (rrot(w[7], 7) ^ rrot(w[7], 18) ^ (w[7] >> 3)) + (rrot(w[20], 17) ^ rrot(w[20], 19) ^ (w[20] >> 10));
|
||||
w[23] = w[7] + w[16] + 0x11002000U + (rrot(w[21], 17) ^ rrot(w[21], 19) ^ (w[21] >> 10));
|
||||
w[24] = 0x80000000U + w[17] + (rrot(w[22], 17) ^ rrot(w[22], 19) ^ (w[22] >> 10));
|
||||
w[25] = w[18] + (rrot(w[23], 17) ^ rrot(w[23], 19) ^ (w[23] >> 10));
|
||||
w[26] = w[19] + (rrot(w[24], 17) ^ rrot(w[24], 19) ^ (w[24] >> 10));
|
||||
w[27] = w[20] + (rrot(w[25], 17) ^ rrot(w[25], 19) ^ (w[25] >> 10));
|
||||
w[28] = w[21] + (rrot(w[26], 17) ^ rrot(w[26], 19) ^ (w[26] >> 10));
|
||||
w[29] = w[22] + (rrot(w[27], 17) ^ rrot(w[27], 19) ^ (w[27] >> 10));
|
||||
w[30] = w[23] + (rrot(0x100, 7) ^ rrot(0x100, 18) ^ (0x100 >> 3)) + (rrot(w[28], 17) ^ rrot(w[28], 19) ^ (w[28] >> 10));
|
||||
w[31] = 0x100 + w[24] + (rrot(w[16], 7) ^ rrot(w[16], 18) ^ (w[16] >> 3)) + (rrot(w[29], 17) ^ rrot(w[29], 19) ^ (w[29] >> 10));
|
||||
#pragma unroll
|
||||
for (int i = 32; i < 59; i++)
|
||||
w[i] = w[i - 16] + w[i - 7] + (rrot(w[i - 15], 7) ^ rrot(w[i - 15], 18) ^ (w[i - 15] >> 3)) + (rrot(w[i - 2], 17) ^ rrot(w[i - 2], 19) ^ (w[i - 2] >> 10));
|
||||
|
||||
d = 0x98c7e2a2U + w[0];
|
||||
h = 0xfc08884dU + w[0];
|
||||
//
|
||||
t1 = (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (0x9b05688cU ^ (d & 0xca0b3af3)) + 0x90bb1e3cU + w[1];
|
||||
c = 0x3c6ef372U + t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + (0x2A01A605 | (h & 0xfb6feee7));
|
||||
//
|
||||
t1 = (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (0x510e527fU ^ (c & (d ^ 0x510e527fU))) + 0x50C6645BU + w[2];
|
||||
b = 0xbb67ae85U + t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((0x6a09e667U & h) | (g & (0x6a09e667U | h)));
|
||||
//
|
||||
t1 = (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x3AC42E24U + w[3];
|
||||
a = 0x6a09e667U + t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x3956c25bU + w[4];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x59f111f1U + w[5];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x923f82a4U + w[6];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0xab1c5ed5U + w[7];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x5807aa98U;
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x12835b01U;
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x243185beU;
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x550c7dc3U;
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x72be5d74U;
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x80deb1feU;
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x9bdc06a7U;
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0xc19bf274U;
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0xe49b69c1U + w[16];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0xefbe4786U + w[17];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x0fc19dc6U + w[18];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x240ca1ccU + w[19];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x2de92c6fU + w[20];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x4a7484aaU + w[21];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x5cb0a9dcU + w[22];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x76f988daU + w[23];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x983e5152U + w[24];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0xa831c66dU + w[25];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0xb00327c8U + w[26];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0xbf597fc7U + w[27];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0xc6e00bf3U + w[28];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0xd5a79147U + w[29];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x06ca6351U + w[30];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x14292967U + w[31];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x27b70a85U + w[32];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x2e1b2138U + w[33];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x4d2c6dfcU + w[34];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x53380d13U + w[35];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x650a7354U + w[36];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x766a0abbU + w[37];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x81c2c92eU + w[38];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x92722c85U + w[39];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0xa2bfe8a1U + w[40];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0xa81a664bU + w[41];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0xc24b8b70U + w[42];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0xc76c51a3U + w[43];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0xd192e819U + w[44];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0xd6990624U + w[45];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0xf40e3585U + w[46];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x106aa070U + w[47];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x19a4c116U + w[48];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
t1 = g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x1e376c08U + w[49];
|
||||
c += t1;
|
||||
g = t1 + (rrot(h, 2) ^ rrot(h, 13) ^ rrot(h, 22)) + ((b & a) | (h & (b | a)));
|
||||
//
|
||||
t1 = f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x2748774cU + w[50];
|
||||
b += t1;
|
||||
f = t1 + (rrot(g, 2) ^ rrot(g, 13) ^ rrot(g, 22)) + ((a & h) | (g & (a | h)));
|
||||
//
|
||||
t1 = e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x34b0bcb5U + w[51];
|
||||
a += t1;
|
||||
e = t1 + (rrot(f, 2) ^ rrot(f, 13) ^ rrot(f, 22)) + ((h & g) | (f & (h | g)));
|
||||
//
|
||||
t1 = d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x391c0cb3U + w[52];
|
||||
h += t1;
|
||||
d = t1 + (rrot(e, 2) ^ rrot(e, 13) ^ rrot(e, 22)) + ((g & f) | (e & (g | f)));
|
||||
//
|
||||
t1 = c + (rrot(h, 6) ^ rrot(h, 11) ^ rrot(h, 25)) + (b ^ (h & (a ^ b))) + 0x4ed8aa4aU + w[53];
|
||||
g += t1;
|
||||
c = t1 + (rrot(d, 2) ^ rrot(d, 13) ^ rrot(d, 22)) + ((f & e) | (d & (f | e)));
|
||||
//
|
||||
t1 = b + (rrot(g, 6) ^ rrot(g, 11) ^ rrot(g, 25)) + (a ^ (g & (h ^ a))) + 0x5b9cca4fU + w[54];
|
||||
f += t1;
|
||||
b = t1 + (rrot(c, 2) ^ rrot(c, 13) ^ rrot(c, 22)) + ((e & d) | (c & (e | d)));
|
||||
//
|
||||
t1 = a + (rrot(f, 6) ^ rrot(f, 11) ^ rrot(f, 25)) + (h ^ (f & (g ^ h))) + 0x682e6ff3U + w[55];
|
||||
e += t1;
|
||||
a = t1 + (rrot(b, 2) ^ rrot(b, 13) ^ rrot(b, 22)) + ((d & c) | (b & (d | c)));
|
||||
//
|
||||
t1 = h + (rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25)) + (g ^ (e & (f ^ g))) + 0x748f82eeU + w[56];
|
||||
d += t1;
|
||||
h = t1 + (rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22)) + ((c & b) | (a & (c | b)));
|
||||
//
|
||||
c += g + (rrot(d, 6) ^ rrot(d, 11) ^ rrot(d, 25)) + (f ^ (d & (e ^ f))) + 0x78a5636fU + w[57];
|
||||
//
|
||||
b += f + (rrot(c, 6) ^ rrot(c, 11) ^ rrot(c, 25)) + (e ^ (c & (d ^ e))) + 0x84c87814U + w[58];
|
||||
//
|
||||
a += e + (rrot(b, 6) ^ rrot(b, 11) ^ rrot(b, 25)) + (d ^ (b & (c ^ d))) + 0x8cc70208U + w[43] + w[52] + (rrot(w[44], 7) ^ rrot(w[44], 18) ^ (w[44] >> 3)) + (rrot(w[57], 17) ^ rrot(w[57], 19) ^ (w[57] >> 10));
|
||||
//
|
||||
h += d + (rrot(a, 6) ^ rrot(a, 11) ^ rrot(a, 25)) + (c ^ (a & (b ^ c))) + 0x90befffaU + w[44] + w[53] + (rrot(w[45], 7) ^ rrot(w[45], 18) ^ (w[45] >> 3)) + (rrot(w[58], 17) ^ rrot(w[58], 19) ^ (w[58] >> 10));
|
||||
//
|
||||
if (h == 0xa41f32e7)
|
||||
{
|
||||
uint32_t tmp = atomicCAS(result, 0xffffffff, nonce);
|
||||
if (tmp != 0xffffffff)
|
||||
result[1] = nonce;
|
||||
}
|
||||
} // nonce loop
|
||||
} // if thread<threads
|
||||
}
|
||||
|
||||
__host__
|
||||
void bitcoin_midstate(const uint32_t *data, uint32_t *midstate)
|
||||
{
|
||||
int i;
|
||||
uint32_t s0, s1, t1, t2, maj, ch, a, b, c, d, e, f, g, h;
|
||||
uint32_t w[64];
|
||||
|
||||
const uint32_t k[64] = {
|
||||
0x428a2f98U, 0x71374491U, 0xb5c0fbcfU, 0xe9b5dba5U, 0x3956c25bU, 0x59f111f1U, 0x923f82a4U, 0xab1c5ed5U,
|
||||
0xd807aa98U, 0x12835b01U, 0x243185beU, 0x550c7dc3U, 0x72be5d74U, 0x80deb1feU, 0x9bdc06a7U, 0xc19bf174U,
|
||||
0xe49b69c1U, 0xefbe4786U, 0x0fc19dc6U, 0x240ca1ccU, 0x2de92c6fU, 0x4a7484aaU, 0x5cb0a9dcU, 0x76f988daU,
|
||||
0x983e5152U, 0xa831c66dU, 0xb00327c8U, 0xbf597fc7U, 0xc6e00bf3U, 0xd5a79147U, 0x06ca6351U, 0x14292967U,
|
||||
0x27b70a85U, 0x2e1b2138U, 0x4d2c6dfcU, 0x53380d13U, 0x650a7354U, 0x766a0abbU, 0x81c2c92eU, 0x92722c85U,
|
||||
0xa2bfe8a1U, 0xa81a664bU, 0xc24b8b70U, 0xc76c51a3U, 0xd192e819U, 0xd6990624U, 0xf40e3585U, 0x106aa070U,
|
||||
0x19a4c116U, 0x1e376c08U, 0x2748774cU, 0x34b0bcb5U, 0x391c0cb3U, 0x4ed8aa4aU, 0x5b9cca4fU, 0x682e6ff3U,
|
||||
0x748f82eeU, 0x78a5636fU, 0x84c87814U, 0x8cc70208U, 0x90befffaU, 0xa4506cebU, 0xbef9a3f7U, 0xc67178f2U
|
||||
};
|
||||
const uint32_t hc[8] = {
|
||||
0x6a09e667U, 0xbb67ae85U, 0x3c6ef372U, 0xa54ff53aU,
|
||||
0x510e527fU, 0x9b05688cU, 0x1f83d9abU, 0x5be0cd19U
|
||||
};
|
||||
|
||||
for (i = 0; i <= 15; i++)
|
||||
{
|
||||
w[i] = data[i];
|
||||
}
|
||||
for (i = 16; i <= 63; i++)
|
||||
{
|
||||
s0 = rrot(w[i - 15], 7) ^ rrot(w[i - 15], 18) ^ (w[i - 15] >> 3);
|
||||
s1 = rrot(w[i - 2], 17) ^ rrot(w[i - 2], 19) ^ (w[i - 2] >> 10);
|
||||
w[i] = w[i - 16] + s0 + w[i - 7] + s1;
|
||||
}
|
||||
a = hc[0];
|
||||
b = hc[1];
|
||||
c = hc[2];
|
||||
d = hc[3];
|
||||
e = hc[4];
|
||||
f = hc[5];
|
||||
g = hc[6];
|
||||
h = hc[7];
|
||||
for (i = 0; i <= 63; i++)
|
||||
{
|
||||
s0 = rrot(a, 2) ^ rrot(a, 13) ^ rrot(a, 22);
|
||||
maj = (a & b) ^ (a & c) ^ (b & c);
|
||||
t2 = s0 + maj;
|
||||
s1 = rrot(e, 6) ^ rrot(e, 11) ^ rrot(e, 25);
|
||||
ch = (e & f) ^ ((~e) & g);
|
||||
t1 = h + s1 + ch + k[i] + w[i];
|
||||
h = g;
|
||||
g = f;
|
||||
f = e;
|
||||
e = d + t1;
|
||||
d = c;
|
||||
c = b;
|
||||
b = a;
|
||||
a = t1 + t2;
|
||||
}
|
||||
midstate[0] = a + hc[0];
|
||||
midstate[1] = b + hc[1];
|
||||
midstate[2] = c + hc[2];
|
||||
midstate[3] = d + hc[3];
|
||||
midstate[4] = e + hc[4];
|
||||
midstate[5] = f + hc[5];
|
||||
midstate[6] = g + hc[6];
|
||||
midstate[7] = h + hc[7];
|
||||
}
|
||||
|
||||
__host__
|
||||
void bitcoin_cpu_hash(int thr_id, uint32_t threads, uint32_t startNounce, const uint32_t *const ms, uint32_t merkle, uint32_t time, uint32_t compacttarget, uint32_t *const h_nounce)
|
||||
{
|
||||
uint32_t b2, c2, d2, f2, g2, h2, t1, w16, w17, t1c, t2c, w16rot, w17rot;
|
||||
|
||||
cudaMemsetAsync(d_result[thr_id], 0xff, 2 * sizeof(uint32_t), gpustream[thr_id]);
|
||||
|
||||
t1 = ms[7] + (rrot(ms[4], 6) ^ rrot(ms[4], 11) ^ rrot(ms[4], 25)) + (ms[6] ^ (ms[4] & (ms[5] ^ ms[6]))) + 0x428a2f98U + merkle;
|
||||
d2 = ms[3] + t1;
|
||||
h2 = t1 + (rrot(ms[0], 2) ^ rrot(ms[0], 13) ^ rrot(ms[0], 22)) + ((ms[2] & ms[1]) | (ms[0] & (ms[2] | ms[1])));
|
||||
//
|
||||
t1 = ms[6] + (rrot(d2, 6) ^ rrot(d2, 11) ^ rrot(d2, 25)) + (ms[5] ^ (d2 & (ms[4] ^ ms[5]))) + 0x71374491U + time;
|
||||
c2 = ms[2] + t1;
|
||||
g2 = t1 + (rrot(h2, 2) ^ rrot(h2, 13) ^ rrot(h2, 22)) + ((ms[1] & ms[0]) | (h2 & (ms[1] | ms[0])));
|
||||
//
|
||||
t1 = ms[5] + (rrot(c2, 6) ^ rrot(c2, 11) ^ rrot(c2, 25)) + (ms[4] ^ (c2 & (d2 ^ ms[4]))) + 0xb5c0fbcfU + compacttarget;
|
||||
b2 = ms[1] + t1;
|
||||
f2 = t1 + (rrot(g2, 2) ^ rrot(g2, 13) ^ rrot(g2, 22)) + ((ms[0] & h2) | (g2 & (ms[0] | h2)));
|
||||
|
||||
w16 = merkle + (rrot(time, 7) ^ rrot(time, 18) ^ (time >> 3));
|
||||
w16rot = (rrot(w16, 17) ^ rrot(w16, 19) ^ (w16 >> 10)) + compacttarget;
|
||||
w17 = time + (rrot(compacttarget, 7) ^ rrot(compacttarget, 18) ^ (compacttarget >> 3)) + 0x01100000U;
|
||||
w17rot = (rrot(w17, 17) ^ rrot(w17, 19) ^ (w17 >> 10)) + 0x11002000U;
|
||||
t2c = (rrot(f2, 2) ^ rrot(f2, 13) ^ rrot(f2, 22)) + ((h2 & g2) | (f2 & (h2 | g2)));
|
||||
t1c = ms[4] + (rrot(b2, 6) ^ rrot(b2, 11) ^ rrot(b2, 25)) + (d2 ^ (b2 & (c2 ^ d2))) + 0xe9b5dba5U;
|
||||
|
||||
dim3 grid((threads + TPB*NONCES_PER_THREAD - 1) / TPB / NONCES_PER_THREAD);
|
||||
dim3 block(TPB);
|
||||
bitcoin_gpu_hash << <grid, block, 0, gpustream[thr_id]>>> (threads, startNounce, d_result[thr_id], t1c, t2c, w16, w16rot, w17, w17rot, b2, c2, d2, f2, g2, h2, ms[0], ms[1], ms[2], ms[3], ms[4], ms[5], ms[6], ms[7], compacttarget);
|
||||
CUDA_SAFE_CALL(cudaMemcpyAsync(h_nounce, d_result[thr_id], 2 * sizeof(uint32_t), cudaMemcpyDeviceToHost, gpustream[thr_id])); cudaStreamSynchronize(gpustream[thr_id]);
|
||||
}
|
||||
|
||||
__host__
|
||||
void bitcoin_cpu_init(int thr_id)
|
||||
{
|
||||
CUDA_SAFE_CALL(cudaMalloc(&d_result[thr_id], 4 * sizeof(uint32_t)));
|
||||
}
|
||||
@@ -0,0 +1,262 @@
|
||||
/* CreditsCoin [CRD] djm34 implementation - 2015 */
|
||||
|
||||
/*
|
||||
#include <cuda.h>
|
||||
#include "cuda_runtime.h"
|
||||
#include "device_launch_parameters.h"
|
||||
|
||||
#include <stdint.h>
|
||||
#include <memory.h>
|
||||
*/
|
||||
|
||||
#include <stdio.h>
|
||||
#include <memory.h>
|
||||
|
||||
#include "cuda_vector.h"
|
||||
|
||||
// extern cudaError_t MyStreamSynchronize(cudaStream_t stream, int situation, int thr_id);
|
||||
|
||||
// __device__ uint4 * S;
|
||||
__device__ uint8 *TheHash;
|
||||
uint32_t *d_BitNonce[MAX_GPUS];
|
||||
__constant__ uint32_t pTarget[8];
|
||||
__constant__ uint8 midstate;
|
||||
__constant__ uint32_t c_data[48];
|
||||
__constant__ uint16 shapad;
|
||||
|
||||
///////////////////////////////////////////////////////////////////////////////////
|
||||
/////////////////////////////// sha256 Transform function /////////////////////////
|
||||
|
||||
static __constant__ uint8 pad4 = {
|
||||
0x80000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000100
|
||||
};
|
||||
|
||||
static __constant__ uint8 H256 = {
|
||||
0x6A09E667, 0xBB67AE85, 0x3C6EF372,
|
||||
0xA54FF53A, 0x510E527F, 0x9B05688C,
|
||||
0x1F83D9AB, 0x5BE0CD19
|
||||
};
|
||||
|
||||
static __constant__ uint32_t Ksha[64] = {
|
||||
0x428A2F98, 0x71374491, 0xB5C0FBCF, 0xE9B5DBA5,
|
||||
0x3956C25B, 0x59F111F1, 0x923F82A4, 0xAB1C5ED5,
|
||||
0xD807AA98, 0x12835B01, 0x243185BE, 0x550C7DC3,
|
||||
0x72BE5D74, 0x80DEB1FE, 0x9BDC06A7, 0xC19BF174,
|
||||
0xE49B69C1, 0xEFBE4786, 0x0FC19DC6, 0x240CA1CC,
|
||||
0x2DE92C6F, 0x4A7484AA, 0x5CB0A9DC, 0x76F988DA,
|
||||
0x983E5152, 0xA831C66D, 0xB00327C8, 0xBF597FC7,
|
||||
0xC6E00BF3, 0xD5A79147, 0x06CA6351, 0x14292967,
|
||||
0x27B70A85, 0x2E1B2138, 0x4D2C6DFC, 0x53380D13,
|
||||
0x650A7354, 0x766A0ABB, 0x81C2C92E, 0x92722C85,
|
||||
0xA2BFE8A1, 0xA81A664B, 0xC24B8B70, 0xC76C51A3,
|
||||
0xD192E819, 0xD6990624, 0xF40E3585, 0x106AA070,
|
||||
0x19A4C116, 0x1E376C08, 0x2748774C, 0x34B0BCB5,
|
||||
0x391C0CB3, 0x4ED8AA4A, 0x5B9CCA4F, 0x682E6FF3,
|
||||
0x748F82EE, 0x78A5636F, 0x84C87814, 0x8CC70208,
|
||||
0x90BEFFFA, 0xA4506CEB, 0xBEF9A3F7, 0xC67178F2
|
||||
};
|
||||
|
||||
static __device__ __forceinline__
|
||||
uint32_t bsg2_0(const uint32_t x)
|
||||
{
|
||||
uint32_t r1 = ROTR32(x, 2);
|
||||
uint32_t r2 = ROTR32(x, 13);
|
||||
uint32_t r3 = ROTR32(x, 22);
|
||||
return xor3b(r1, r2, r3);
|
||||
}
|
||||
|
||||
static __device__ __forceinline__
|
||||
uint32_t bsg2_1(const uint32_t x)
|
||||
{
|
||||
uint32_t r1 = ROTR32(x, 6);
|
||||
uint32_t r2 = ROTR32(x, 11);
|
||||
uint32_t r3 = ROTR32(x, 25);
|
||||
return xor3b(r1, r2, r3);
|
||||
}
|
||||
|
||||
static __device__ __forceinline__
|
||||
uint32_t ssg2_0(const uint32_t x)
|
||||
{
|
||||
uint32_t r1 = ROTR32(x, 7);
|
||||
uint32_t r2 = ROTR32(x, 18);
|
||||
uint32_t r3 = shr_t32(x, 3);
|
||||
return xor3b(r1, r2, r3);
|
||||
}
|
||||
|
||||
static __device__ __forceinline__
|
||||
uint32_t ssg2_1(const uint32_t x)
|
||||
{
|
||||
uint32_t r1 = ROTR32(x, 17);
|
||||
uint32_t r2 = ROTR32(x, 19);
|
||||
uint32_t r3 = shr_t32(x, 10);
|
||||
return xor3b(r1, r2, r3);
|
||||
}
|
||||
|
||||
static __device__ __forceinline__
|
||||
void sha2_step1(const uint32_t a, const uint32_t b, const uint32_t c, uint32_t &d, const uint32_t e,
|
||||
const uint32_t f, const uint32_t g, uint32_t &h, const uint32_t in, const uint32_t Kshared)
|
||||
{
|
||||
uint32_t t1, t2;
|
||||
uint32_t vxandx = xandx(e, f, g);
|
||||
uint32_t bsg21 = bsg2_1(e);
|
||||
uint32_t bsg20 = bsg2_0(a);
|
||||
uint32_t andorv = andor32(a, b, c);
|
||||
|
||||
t1 = h + bsg21 + vxandx + Kshared + in;
|
||||
t2 = bsg20 + andorv;
|
||||
d = d + t1;
|
||||
h = t1 + t2;
|
||||
}
|
||||
|
||||
static __device__ __forceinline__
|
||||
void sha2_step2(const uint32_t a, const uint32_t b, const uint32_t c, uint32_t &d, const uint32_t e,
|
||||
const uint32_t f, const uint32_t g, uint32_t &h, uint32_t* in, const uint32_t pc, const uint32_t Kshared)
|
||||
{
|
||||
uint32_t t1, t2;
|
||||
|
||||
int pcidx1 = (pc - 2) & 0xF;
|
||||
int pcidx2 = (pc - 7) & 0xF;
|
||||
int pcidx3 = (pc - 15) & 0xF;
|
||||
uint32_t inx0 = in[pc];
|
||||
uint32_t inx1 = in[pcidx1];
|
||||
uint32_t inx2 = in[pcidx2];
|
||||
uint32_t inx3 = in[pcidx3];
|
||||
|
||||
uint32_t ssg21 = ssg2_1(inx1);
|
||||
uint32_t ssg20 = ssg2_0(inx3);
|
||||
uint32_t vxandx = xandx(e, f, g);
|
||||
uint32_t bsg21 = bsg2_1(e);
|
||||
uint32_t bsg20 = bsg2_0(a);
|
||||
uint32_t andorv = andor32(a, b, c);
|
||||
|
||||
in[pc] = ssg21 + inx2 + ssg20 + inx0;
|
||||
|
||||
t1 = h + bsg21 + vxandx + Kshared + in[pc];
|
||||
t2 = bsg20 + andorv;
|
||||
d = d + t1;
|
||||
h = t1 + t2;
|
||||
}
|
||||
|
||||
static __device__ __forceinline__
|
||||
uint8 sha256_Transform2(uint16 in[1], const uint8 &r) // also known as sha2_round_body
|
||||
{
|
||||
uint8 tmp = r;
|
||||
#define a tmp.s0
|
||||
#define b tmp.s1
|
||||
#define c tmp.s2
|
||||
#define d tmp.s3
|
||||
#define e tmp.s4
|
||||
#define f tmp.s5
|
||||
#define g tmp.s6
|
||||
#define h tmp.s7
|
||||
|
||||
sha2_step1(a, b, c, d, e, f, g, h, in[0].s0, Ksha[0]);
|
||||
sha2_step1(h, a, b, c, d, e, f, g, in[0].s1, Ksha[1]);
|
||||
sha2_step1(g, h, a, b, c, d, e, f, in[0].s2, Ksha[2]);
|
||||
sha2_step1(f, g, h, a, b, c, d, e, in[0].s3, Ksha[3]);
|
||||
sha2_step1(e, f, g, h, a, b, c, d, in[0].s4, Ksha[4]);
|
||||
sha2_step1(d, e, f, g, h, a, b, c, in[0].s5, Ksha[5]);
|
||||
sha2_step1(c, d, e, f, g, h, a, b, in[0].s6, Ksha[6]);
|
||||
sha2_step1(b, c, d, e, f, g, h, a, in[0].s7, Ksha[7]);
|
||||
sha2_step1(a, b, c, d, e, f, g, h, in[0].s8, Ksha[8]);
|
||||
sha2_step1(h, a, b, c, d, e, f, g, in[0].s9, Ksha[9]);
|
||||
sha2_step1(g, h, a, b, c, d, e, f, in[0].sa, Ksha[10]);
|
||||
sha2_step1(f, g, h, a, b, c, d, e, in[0].sb, Ksha[11]);
|
||||
sha2_step1(e, f, g, h, a, b, c, d, in[0].sc, Ksha[12]);
|
||||
sha2_step1(d, e, f, g, h, a, b, c, in[0].sd, Ksha[13]);
|
||||
sha2_step1(c, d, e, f, g, h, a, b, in[0].se, Ksha[14]);
|
||||
sha2_step1(b, c, d, e, f, g, h, a, in[0].sf, Ksha[15]);
|
||||
|
||||
#pragma unroll
|
||||
for (int i = 0; i<3; i++) {
|
||||
|
||||
sha2_step2(a, b, c, d, e, f, g, h, (uint32_t*)in, 0, Ksha[16 + 16 * i]);
|
||||
sha2_step2(h, a, b, c, d, e, f, g, (uint32_t*)in, 1, Ksha[17 + 16 * i]);
|
||||
sha2_step2(g, h, a, b, c, d, e, f, (uint32_t*)in, 2, Ksha[18 + 16 * i]);
|
||||
sha2_step2(f, g, h, a, b, c, d, e, (uint32_t*)in, 3, Ksha[19 + 16 * i]);
|
||||
sha2_step2(e, f, g, h, a, b, c, d, (uint32_t*)in, 4, Ksha[20 + 16 * i]);
|
||||
sha2_step2(d, e, f, g, h, a, b, c, (uint32_t*)in, 5, Ksha[21 + 16 * i]);
|
||||
sha2_step2(c, d, e, f, g, h, a, b, (uint32_t*)in, 6, Ksha[22 + 16 * i]);
|
||||
sha2_step2(b, c, d, e, f, g, h, a, (uint32_t*)in, 7, Ksha[23 + 16 * i]);
|
||||
sha2_step2(a, b, c, d, e, f, g, h, (uint32_t*)in, 8, Ksha[24 + 16 * i]);
|
||||
sha2_step2(h, a, b, c, d, e, f, g, (uint32_t*)in, 9, Ksha[25 + 16 * i]);
|
||||
sha2_step2(g, h, a, b, c, d, e, f, (uint32_t*)in, 10, Ksha[26 + 16 * i]);
|
||||
sha2_step2(f, g, h, a, b, c, d, e, (uint32_t*)in, 11, Ksha[27 + 16 * i]);
|
||||
sha2_step2(e, f, g, h, a, b, c, d, (uint32_t*)in, 12, Ksha[28 + 16 * i]);
|
||||
sha2_step2(d, e, f, g, h, a, b, c, (uint32_t*)in, 13, Ksha[29 + 16 * i]);
|
||||
sha2_step2(c, d, e, f, g, h, a, b, (uint32_t*)in, 14, Ksha[30 + 16 * i]);
|
||||
sha2_step2(b, c, d, e, f, g, h, a, (uint32_t*)in, 15, Ksha[31 + 16 * i]);
|
||||
}
|
||||
|
||||
#undef a
|
||||
#undef b
|
||||
#undef c
|
||||
#undef d
|
||||
#undef e
|
||||
#undef f
|
||||
return (r + tmp);
|
||||
}
|
||||
|
||||
|
||||
__global__ __launch_bounds__(256, 3)
|
||||
void bitcredit_gpu_hash(int threads, uint32_t startNonce,uint32_t* NonceVector)
|
||||
{
|
||||
uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
uint32_t nonce = startNonce + thread;
|
||||
|
||||
uint16 data[1];
|
||||
uint8 state,state2;
|
||||
|
||||
data[0] = ((uint16*)c_data)[2];
|
||||
data[0].s3 = nonce;
|
||||
state = sha256_Transform2(data, midstate);
|
||||
|
||||
data[0].lo=state;
|
||||
data[0].hi=pad4;
|
||||
state2 = sha256_Transform2(data, H256);
|
||||
|
||||
if (MAKE_ULONGLONG(cuda_swab32(state2.s6), cuda_swab32(state2.s7)) <= ((uint64_t*)pTarget)[3])
|
||||
NonceVector[0] = nonce;
|
||||
}
|
||||
|
||||
__host__
|
||||
void bitcredit_cpu_init(uint32_t thr_id, int threads, uint32_t *hash)
|
||||
{
|
||||
cudaMemcpyToSymbol(TheHash, &hash, sizeof(hash), 0, cudaMemcpyHostToDevice);
|
||||
cudaMalloc(&d_BitNonce[thr_id], sizeof(uint32_t));
|
||||
}
|
||||
|
||||
__host__
|
||||
void bitcredit_setBlockTarget(uint32_t* pdata, const uint32_t* zmidstate,const void *target)
|
||||
{
|
||||
unsigned char PaddedMessage[192]; //bring balance to the force
|
||||
|
||||
memcpy(PaddedMessage, pdata, 168);
|
||||
memset(PaddedMessage+168, 0, 24);
|
||||
((uint32_t*)PaddedMessage)[42] = 0x80000000;
|
||||
((uint32_t*)PaddedMessage)[47] = 0x00000540;
|
||||
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(midstate, zmidstate, 32, 0, cudaMemcpyHostToDevice));
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(pTarget, target, 32, 0, cudaMemcpyHostToDevice));
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_data, PaddedMessage, 48 * sizeof(uint32_t), 0, cudaMemcpyHostToDevice));
|
||||
}
|
||||
|
||||
__host__
|
||||
uint32_t bitcredit_cpu_hash(uint32_t thr_id, int threads, uint32_t startNounce, int order)
|
||||
{
|
||||
uint32_t result[MAX_GPUS];
|
||||
const int threadsperblock = 256;
|
||||
|
||||
memset(result, 0xff, sizeof(result));
|
||||
cudaMemset(d_BitNonce[thr_id], 0xff, sizeof(uint32_t));
|
||||
|
||||
dim3 grid((threads + threadsperblock - 1) / threadsperblock);
|
||||
dim3 block(threadsperblock);
|
||||
|
||||
bitcredit_gpu_hash << <grid, block >> >(threads, startNounce, d_BitNonce[thr_id]);
|
||||
|
||||
cudaMemcpy(&result[thr_id], d_BitNonce[thr_id], sizeof(uint32_t), cudaMemcpyDeviceToHost);
|
||||
|
||||
return result[thr_id];
|
||||
}
|
||||
@@ -355,6 +355,7 @@ extern "C" int scanhash_skeincoin(int thr_id, uint32_t *pdata, const uint32_t *p
|
||||
const int swap = 1;
|
||||
|
||||
bool sm5 = (device_sm[device_map[thr_id]] >= 500);
|
||||
bool checkSecnonce = (have_stratum || have_longpoll) && !sm5;
|
||||
|
||||
uint32_t throughput = device_intensity(thr_id, __func__, 1U << 20);
|
||||
throughput = min(throughput, (max_nonce - first_nonce));
|
||||
@@ -416,7 +417,7 @@ extern "C" int scanhash_skeincoin(int thr_id, uint32_t *pdata, const uint32_t *p
|
||||
if (vhash64[7] <= ptarget[7] && fulltest(vhash64, ptarget)) {
|
||||
int res = 1;
|
||||
uint8_t num = res;
|
||||
if (!sm5) {
|
||||
if (checkSecnonce) {
|
||||
secNonce = cuda_check_hash_suppl(thr_id, throughput, pdata[19], d_hash[thr_id], num);
|
||||
}
|
||||
while (secNonce != 0 && res < 2) /* todo: up to 6 */
|
||||
@@ -429,7 +430,10 @@ extern "C" int scanhash_skeincoin(int thr_id, uint32_t *pdata, const uint32_t *p
|
||||
res++;
|
||||
}
|
||||
num++;
|
||||
secNonce = cuda_check_hash_suppl(thr_id, throughput, pdata[19], d_hash[thr_id], num);
|
||||
//if (checkSecnonce)
|
||||
// secNonce = cuda_check_hash_suppl(thr_id, throughput, pdata[19], d_hash[thr_id], num);
|
||||
//else
|
||||
break; // only one secNonce...
|
||||
}
|
||||
if (res > 1 && opt_debug)
|
||||
applog(LOG_BLUE, "GPU #%d: %d/%d valid nonces !!!", device_map[thr_id], res, (int)num);
|
||||
@@ -441,7 +445,8 @@ extern "C" int scanhash_skeincoin(int thr_id, uint32_t *pdata, const uint32_t *p
|
||||
}
|
||||
}
|
||||
|
||||
if ((uint64_t) pdata[19] + throughput > max_nonce) {
|
||||
if ((uint64_t) throughput + pdata[19] > max_nonce) {
|
||||
//applog(LOG_DEBUG, "done... max=%u", max_nonce);
|
||||
*hashes_done = pdata[19] - first_nonce;
|
||||
pdata[19] = max_nonce;
|
||||
break;
|
||||
|
||||
+1
-1
@@ -101,7 +101,7 @@ int scanhash_skein2(int thr_id, uint32_t *pdata, const uint32_t *ptarget,
|
||||
}
|
||||
}
|
||||
|
||||
if ((uint64_t) pdata[19] + throughput > max_nonce) {
|
||||
if ((uint64_t) throughput + pdata[19] > max_nonce) {
|
||||
*hashes_done = pdata[19] - first_nonce;
|
||||
pdata[19] = max_nonce;
|
||||
break;
|
||||
|
||||
+664
-601
File diff suppressed because it is too large.
Load diff
+630
@@ -0,0 +1,630 @@
|
||||
/*
|
||||
* Copyright 2011 ArtForz
|
||||
* Copyright 2011-2013 pooler
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or modify it
|
||||
* under the terms of the GNU General Public License as published by the Free
|
||||
* Software Foundation; either version 2 of the License, or (at your option)
|
||||
* any later version. See COPYING for more details.
|
||||
*/
|
||||
|
||||
#include "cpuminer-config.h"
|
||||
#include "miner.h"
|
||||
|
||||
#include <string.h>
|
||||
#include <inttypes.h>
|
||||
|
||||
#if defined(__arm__) && defined(__APCS_32__)
|
||||
#define EXTERN_SHA256
|
||||
#endif
|
||||
|
||||
static const uint32_t sha256_h[8] = {
|
||||
0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a,
|
||||
0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19
|
||||
};
|
||||
|
||||
static const uint32_t sha256_k[64] = {
|
||||
0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5,
|
||||
0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
|
||||
0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
|
||||
0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
|
||||
0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc,
|
||||
0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
|
||||
0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7,
|
||||
0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
|
||||
0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
|
||||
0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
|
||||
0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3,
|
||||
0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
|
||||
0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5,
|
||||
0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
|
||||
0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
|
||||
0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
|
||||
};
|
||||
|
||||
void sha256_init(uint32_t *state)
|
||||
{
|
||||
memcpy(state, sha256_h, 32);
|
||||
}
|
||||
|
||||
/* Elementary functions used by SHA256 */
|
||||
#define Ch(x, y, z) ((x & (y ^ z)) ^ z)
|
||||
#define Maj(x, y, z) ((x & (y | z)) | (y & z))
|
||||
#define ROTR(x, n) ((x >> n) | (x << (32 - n)))
|
||||
#define S0(x) (ROTR(x, 2) ^ ROTR(x, 13) ^ ROTR(x, 22))
|
||||
#define S1(x) (ROTR(x, 6) ^ ROTR(x, 11) ^ ROTR(x, 25))
|
||||
#define s0(x) (ROTR(x, 7) ^ ROTR(x, 18) ^ (x >> 3))
|
||||
#define s1(x) (ROTR(x, 17) ^ ROTR(x, 19) ^ (x >> 10))
|
||||
|
||||
/* SHA256 round function */
|
||||
#define RND(a, b, c, d, e, f, g, h, k) \
|
||||
do { \
|
||||
t0 = h + S1(e) + Ch(e, f, g) + k; \
|
||||
t1 = S0(a) + Maj(a, b, c); \
|
||||
d += t0; \
|
||||
h = t0 + t1; \
|
||||
} while (0)
|
||||
|
||||
/* Adjusted round function for rotating state */
|
||||
#define RNDr(S, W, i) \
|
||||
RND(S[(64 - i) % 8], S[(65 - i) % 8], \
|
||||
S[(66 - i) % 8], S[(67 - i) % 8], \
|
||||
S[(68 - i) % 8], S[(69 - i) % 8], \
|
||||
S[(70 - i) % 8], S[(71 - i) % 8], \
|
||||
W[i] + sha256_k[i])
|
||||
|
||||
#ifndef EXTERN_SHA256
|
||||
|
||||
/*
|
||||
* SHA256 block compression function. The 256-bit state is transformed via
|
||||
* the 512-bit input block to produce a new state.
|
||||
*/
|
||||
void sha256_transform(uint32_t *state, const uint32_t *block, int swap)
|
||||
{
|
||||
uint32_t W[64];
|
||||
uint32_t S[8];
|
||||
uint32_t t0, t1;
|
||||
int i;
|
||||
|
||||
/* 1. Prepare message schedule W. */
|
||||
if (swap) {
|
||||
for (i = 0; i < 16; i++)
|
||||
W[i] = swab32(block[i]);
|
||||
} else
|
||||
memcpy(W, block, 64);
|
||||
for (i = 16; i < 64; i += 2) {
|
||||
W[i] = s1(W[i - 2]) + W[i - 7] + s0(W[i - 15]) + W[i - 16];
|
||||
W[i+1] = s1(W[i - 1]) + W[i - 6] + s0(W[i - 14]) + W[i - 15];
|
||||
}
|
||||
|
||||
/* 2. Initialize working variables. */
|
||||
memcpy(S, state, 32);
|
||||
|
||||
/* 3. Mix. */
|
||||
RNDr(S, W, 0);
|
||||
RNDr(S, W, 1);
|
||||
RNDr(S, W, 2);
|
||||
RNDr(S, W, 3);
|
||||
RNDr(S, W, 4);
|
||||
RNDr(S, W, 5);
|
||||
RNDr(S, W, 6);
|
||||
RNDr(S, W, 7);
|
||||
RNDr(S, W, 8);
|
||||
RNDr(S, W, 9);
|
||||
RNDr(S, W, 10);
|
||||
RNDr(S, W, 11);
|
||||
RNDr(S, W, 12);
|
||||
RNDr(S, W, 13);
|
||||
RNDr(S, W, 14);
|
||||
RNDr(S, W, 15);
|
||||
RNDr(S, W, 16);
|
||||
RNDr(S, W, 17);
|
||||
RNDr(S, W, 18);
|
||||
RNDr(S, W, 19);
|
||||
RNDr(S, W, 20);
|
||||
RNDr(S, W, 21);
|
||||
RNDr(S, W, 22);
|
||||
RNDr(S, W, 23);
|
||||
RNDr(S, W, 24);
|
||||
RNDr(S, W, 25);
|
||||
RNDr(S, W, 26);
|
||||
RNDr(S, W, 27);
|
||||
RNDr(S, W, 28);
|
||||
RNDr(S, W, 29);
|
||||
RNDr(S, W, 30);
|
||||
RNDr(S, W, 31);
|
||||
RNDr(S, W, 32);
|
||||
RNDr(S, W, 33);
|
||||
RNDr(S, W, 34);
|
||||
RNDr(S, W, 35);
|
||||
RNDr(S, W, 36);
|
||||
RNDr(S, W, 37);
|
||||
RNDr(S, W, 38);
|
||||
RNDr(S, W, 39);
|
||||
RNDr(S, W, 40);
|
||||
RNDr(S, W, 41);
|
||||
RNDr(S, W, 42);
|
||||
RNDr(S, W, 43);
|
||||
RNDr(S, W, 44);
|
||||
RNDr(S, W, 45);
|
||||
RNDr(S, W, 46);
|
||||
RNDr(S, W, 47);
|
||||
RNDr(S, W, 48);
|
||||
RNDr(S, W, 49);
|
||||
RNDr(S, W, 50);
|
||||
RNDr(S, W, 51);
|
||||
RNDr(S, W, 52);
|
||||
RNDr(S, W, 53);
|
||||
RNDr(S, W, 54);
|
||||
RNDr(S, W, 55);
|
||||
RNDr(S, W, 56);
|
||||
RNDr(S, W, 57);
|
||||
RNDr(S, W, 58);
|
||||
RNDr(S, W, 59);
|
||||
RNDr(S, W, 60);
|
||||
RNDr(S, W, 61);
|
||||
RNDr(S, W, 62);
|
||||
RNDr(S, W, 63);
|
||||
|
||||
/* 4. Mix local working variables into global state */
|
||||
for (i = 0; i < 8; i++)
|
||||
state[i] += S[i];
|
||||
}
|
||||
|
||||
#endif /* EXTERN_SHA256 */
|
||||
|
||||
|
||||
static const uint32_t sha256d_hash1[16] = {
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x80000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000100
|
||||
};
|
||||
|
||||
static void sha256d_80_swap(uint32_t *hash, const uint32_t *data)
|
||||
{
|
||||
uint32_t S[16];
|
||||
int i;
|
||||
|
||||
sha256_init(S);
|
||||
sha256_transform(S, data, 0);
|
||||
sha256_transform(S, data + 16, 0);
|
||||
memcpy(S + 8, sha256d_hash1 + 8, 32);
|
||||
sha256_init(hash);
|
||||
sha256_transform(hash, S, 0);
|
||||
for (i = 0; i < 8; i++)
|
||||
hash[i] = swab32(hash[i]);
|
||||
}
|
||||
|
||||
void sha256d(unsigned char *hash, const unsigned char *data, int len)
|
||||
{
|
||||
uint32_t S[16], T[16];
|
||||
int i, r;
|
||||
|
||||
sha256_init(S);
|
||||
for (r = len; r > -9; r -= 64) {
|
||||
if (r < 64)
|
||||
memset(T, 0, 64);
|
||||
memcpy(T, data + len - r, r > 64 ? 64 : (r < 0 ? 0 : r));
|
||||
if (r >= 0 && r < 64)
|
||||
((unsigned char *)T)[r] = 0x80;
|
||||
for (i = 0; i < 16; i++)
|
||||
T[i] = be32dec(T + i);
|
||||
if (r < 56)
|
||||
T[15] = 8 * len;
|
||||
sha256_transform(S, T, 0);
|
||||
}
|
||||
memcpy(S + 8, sha256d_hash1 + 8, 32);
|
||||
sha256_init(T);
|
||||
sha256_transform(T, S, 0);
|
||||
for (i = 0; i < 8; i++)
|
||||
be32enc((uint32_t *)hash + i, T[i]);
|
||||
}
|
||||
|
||||
static inline void sha256d_preextend(uint32_t *W)
|
||||
{
|
||||
W[16] = s1(W[14]) + W[ 9] + s0(W[ 1]) + W[ 0];
|
||||
W[17] = s1(W[15]) + W[10] + s0(W[ 2]) + W[ 1];
|
||||
W[18] = s1(W[16]) + W[11] + W[ 2];
|
||||
W[19] = s1(W[17]) + W[12] + s0(W[ 4]);
|
||||
W[20] = W[13] + s0(W[ 5]) + W[ 4];
|
||||
W[21] = W[14] + s0(W[ 6]) + W[ 5];
|
||||
W[22] = W[15] + s0(W[ 7]) + W[ 6];
|
||||
W[23] = W[16] + s0(W[ 8]) + W[ 7];
|
||||
W[24] = W[17] + s0(W[ 9]) + W[ 8];
|
||||
W[25] = s0(W[10]) + W[ 9];
|
||||
W[26] = s0(W[11]) + W[10];
|
||||
W[27] = s0(W[12]) + W[11];
|
||||
W[28] = s0(W[13]) + W[12];
|
||||
W[29] = s0(W[14]) + W[13];
|
||||
W[30] = s0(W[15]) + W[14];
|
||||
W[31] = s0(W[16]) + W[15];
|
||||
}
|
||||
|
||||
static inline void sha256d_prehash(uint32_t *S, const uint32_t *W)
|
||||
{
|
||||
uint32_t t0, t1;
|
||||
RNDr(S, W, 0);
|
||||
RNDr(S, W, 1);
|
||||
RNDr(S, W, 2);
|
||||
}
|
||||
|
||||
#ifdef EXTERN_SHA256
|
||||
|
||||
void sha256d_ms(uint32_t *hash, uint32_t *W,
|
||||
const uint32_t *midstate, const uint32_t *prehash);
|
||||
|
||||
#else
|
||||
|
||||
static inline void sha256d_ms(uint32_t *hash, uint32_t *W,
|
||||
const uint32_t *midstate, const uint32_t *prehash)
|
||||
{
|
||||
uint32_t S[64];
|
||||
uint32_t t0, t1;
|
||||
int i;
|
||||
|
||||
S[18] = W[18];
|
||||
S[19] = W[19];
|
||||
S[20] = W[20];
|
||||
S[22] = W[22];
|
||||
S[23] = W[23];
|
||||
S[24] = W[24];
|
||||
S[30] = W[30];
|
||||
S[31] = W[31];
|
||||
|
||||
W[18] += s0(W[3]);
|
||||
W[19] += W[3];
|
||||
W[20] += s1(W[18]);
|
||||
W[21] = s1(W[19]);
|
||||
W[22] += s1(W[20]);
|
||||
W[23] += s1(W[21]);
|
||||
W[24] += s1(W[22]);
|
||||
W[25] = s1(W[23]) + W[18];
|
||||
W[26] = s1(W[24]) + W[19];
|
||||
W[27] = s1(W[25]) + W[20];
|
||||
W[28] = s1(W[26]) + W[21];
|
||||
W[29] = s1(W[27]) + W[22];
|
||||
W[30] += s1(W[28]) + W[23];
|
||||
W[31] += s1(W[29]) + W[24];
|
||||
for (i = 32; i < 64; i += 2) {
|
||||
W[i] = s1(W[i - 2]) + W[i - 7] + s0(W[i - 15]) + W[i - 16];
|
||||
W[i+1] = s1(W[i - 1]) + W[i - 6] + s0(W[i - 14]) + W[i - 15];
|
||||
}
|
||||
|
||||
memcpy(S, prehash, 32);
|
||||
|
||||
RNDr(S, W, 3);
|
||||
RNDr(S, W, 4);
|
||||
RNDr(S, W, 5);
|
||||
RNDr(S, W, 6);
|
||||
RNDr(S, W, 7);
|
||||
RNDr(S, W, 8);
|
||||
RNDr(S, W, 9);
|
||||
RNDr(S, W, 10);
|
||||
RNDr(S, W, 11);
|
||||
RNDr(S, W, 12);
|
||||
RNDr(S, W, 13);
|
||||
RNDr(S, W, 14);
|
||||
RNDr(S, W, 15);
|
||||
RNDr(S, W, 16);
|
||||
RNDr(S, W, 17);
|
||||
RNDr(S, W, 18);
|
||||
RNDr(S, W, 19);
|
||||
RNDr(S, W, 20);
|
||||
RNDr(S, W, 21);
|
||||
RNDr(S, W, 22);
|
||||
RNDr(S, W, 23);
|
||||
RNDr(S, W, 24);
|
||||
RNDr(S, W, 25);
|
||||
RNDr(S, W, 26);
|
||||
RNDr(S, W, 27);
|
||||
RNDr(S, W, 28);
|
||||
RNDr(S, W, 29);
|
||||
RNDr(S, W, 30);
|
||||
RNDr(S, W, 31);
|
||||
RNDr(S, W, 32);
|
||||
RNDr(S, W, 33);
|
||||
RNDr(S, W, 34);
|
||||
RNDr(S, W, 35);
|
||||
RNDr(S, W, 36);
|
||||
RNDr(S, W, 37);
|
||||
RNDr(S, W, 38);
|
||||
RNDr(S, W, 39);
|
||||
RNDr(S, W, 40);
|
||||
RNDr(S, W, 41);
|
||||
RNDr(S, W, 42);
|
||||
RNDr(S, W, 43);
|
||||
RNDr(S, W, 44);
|
||||
RNDr(S, W, 45);
|
||||
RNDr(S, W, 46);
|
||||
RNDr(S, W, 47);
|
||||
RNDr(S, W, 48);
|
||||
RNDr(S, W, 49);
|
||||
RNDr(S, W, 50);
|
||||
RNDr(S, W, 51);
|
||||
RNDr(S, W, 52);
|
||||
RNDr(S, W, 53);
|
||||
RNDr(S, W, 54);
|
||||
RNDr(S, W, 55);
|
||||
RNDr(S, W, 56);
|
||||
RNDr(S, W, 57);
|
||||
RNDr(S, W, 58);
|
||||
RNDr(S, W, 59);
|
||||
RNDr(S, W, 60);
|
||||
RNDr(S, W, 61);
|
||||
RNDr(S, W, 62);
|
||||
RNDr(S, W, 63);
|
||||
|
||||
for (i = 0; i < 8; i++)
|
||||
S[i] += midstate[i];
|
||||
|
||||
W[18] = S[18];
|
||||
W[19] = S[19];
|
||||
W[20] = S[20];
|
||||
W[22] = S[22];
|
||||
W[23] = S[23];
|
||||
W[24] = S[24];
|
||||
W[30] = S[30];
|
||||
W[31] = S[31];
|
||||
|
||||
memcpy(S + 8, sha256d_hash1 + 8, 32);
|
||||
S[16] = s1(sha256d_hash1[14]) + sha256d_hash1[ 9] + s0(S[ 1]) + S[ 0];
|
||||
S[17] = s1(sha256d_hash1[15]) + sha256d_hash1[10] + s0(S[ 2]) + S[ 1];
|
||||
S[18] = s1(S[16]) + sha256d_hash1[11] + s0(S[ 3]) + S[ 2];
|
||||
S[19] = s1(S[17]) + sha256d_hash1[12] + s0(S[ 4]) + S[ 3];
|
||||
S[20] = s1(S[18]) + sha256d_hash1[13] + s0(S[ 5]) + S[ 4];
|
||||
S[21] = s1(S[19]) + sha256d_hash1[14] + s0(S[ 6]) + S[ 5];
|
||||
S[22] = s1(S[20]) + sha256d_hash1[15] + s0(S[ 7]) + S[ 6];
|
||||
S[23] = s1(S[21]) + S[16] + s0(sha256d_hash1[ 8]) + S[ 7];
|
||||
S[24] = s1(S[22]) + S[17] + s0(sha256d_hash1[ 9]) + sha256d_hash1[ 8];
|
||||
S[25] = s1(S[23]) + S[18] + s0(sha256d_hash1[10]) + sha256d_hash1[ 9];
|
||||
S[26] = s1(S[24]) + S[19] + s0(sha256d_hash1[11]) + sha256d_hash1[10];
|
||||
S[27] = s1(S[25]) + S[20] + s0(sha256d_hash1[12]) + sha256d_hash1[11];
|
||||
S[28] = s1(S[26]) + S[21] + s0(sha256d_hash1[13]) + sha256d_hash1[12];
|
||||
S[29] = s1(S[27]) + S[22] + s0(sha256d_hash1[14]) + sha256d_hash1[13];
|
||||
S[30] = s1(S[28]) + S[23] + s0(sha256d_hash1[15]) + sha256d_hash1[14];
|
||||
S[31] = s1(S[29]) + S[24] + s0(S[16]) + sha256d_hash1[15];
|
||||
for (i = 32; i < 60; i += 2) {
|
||||
S[i] = s1(S[i - 2]) + S[i - 7] + s0(S[i - 15]) + S[i - 16];
|
||||
S[i+1] = s1(S[i - 1]) + S[i - 6] + s0(S[i - 14]) + S[i - 15];
|
||||
}
|
||||
S[60] = s1(S[58]) + S[53] + s0(S[45]) + S[44];
|
||||
|
||||
sha256_init(hash);
|
||||
|
||||
RNDr(hash, S, 0);
|
||||
RNDr(hash, S, 1);
|
||||
RNDr(hash, S, 2);
|
||||
RNDr(hash, S, 3);
|
||||
RNDr(hash, S, 4);
|
||||
RNDr(hash, S, 5);
|
||||
RNDr(hash, S, 6);
|
||||
RNDr(hash, S, 7);
|
||||
RNDr(hash, S, 8);
|
||||
RNDr(hash, S, 9);
|
||||
RNDr(hash, S, 10);
|
||||
RNDr(hash, S, 11);
|
||||
RNDr(hash, S, 12);
|
||||
RNDr(hash, S, 13);
|
||||
RNDr(hash, S, 14);
|
||||
RNDr(hash, S, 15);
|
||||
RNDr(hash, S, 16);
|
||||
RNDr(hash, S, 17);
|
||||
RNDr(hash, S, 18);
|
||||
RNDr(hash, S, 19);
|
||||
RNDr(hash, S, 20);
|
||||
RNDr(hash, S, 21);
|
||||
RNDr(hash, S, 22);
|
||||
RNDr(hash, S, 23);
|
||||
RNDr(hash, S, 24);
|
||||
RNDr(hash, S, 25);
|
||||
RNDr(hash, S, 26);
|
||||
RNDr(hash, S, 27);
|
||||
RNDr(hash, S, 28);
|
||||
RNDr(hash, S, 29);
|
||||
RNDr(hash, S, 30);
|
||||
RNDr(hash, S, 31);
|
||||
RNDr(hash, S, 32);
|
||||
RNDr(hash, S, 33);
|
||||
RNDr(hash, S, 34);
|
||||
RNDr(hash, S, 35);
|
||||
RNDr(hash, S, 36);
|
||||
RNDr(hash, S, 37);
|
||||
RNDr(hash, S, 38);
|
||||
RNDr(hash, S, 39);
|
||||
RNDr(hash, S, 40);
|
||||
RNDr(hash, S, 41);
|
||||
RNDr(hash, S, 42);
|
||||
RNDr(hash, S, 43);
|
||||
RNDr(hash, S, 44);
|
||||
RNDr(hash, S, 45);
|
||||
RNDr(hash, S, 46);
|
||||
RNDr(hash, S, 47);
|
||||
RNDr(hash, S, 48);
|
||||
RNDr(hash, S, 49);
|
||||
RNDr(hash, S, 50);
|
||||
RNDr(hash, S, 51);
|
||||
RNDr(hash, S, 52);
|
||||
RNDr(hash, S, 53);
|
||||
RNDr(hash, S, 54);
|
||||
RNDr(hash, S, 55);
|
||||
RNDr(hash, S, 56);
|
||||
|
||||
hash[2] += hash[6] + S1(hash[3]) + Ch(hash[3], hash[4], hash[5])
|
||||
+ S[57] + sha256_k[57];
|
||||
hash[1] += hash[5] + S1(hash[2]) + Ch(hash[2], hash[3], hash[4])
|
||||
+ S[58] + sha256_k[58];
|
||||
hash[0] += hash[4] + S1(hash[1]) + Ch(hash[1], hash[2], hash[3])
|
||||
+ S[59] + sha256_k[59];
|
||||
hash[7] += hash[3] + S1(hash[0]) + Ch(hash[0], hash[1], hash[2])
|
||||
+ S[60] + sha256_k[60]
|
||||
+ sha256_h[7];
|
||||
}
|
||||
|
||||
#endif /* EXTERN_SHA256 */
|
||||
|
||||
#if HAVE_SHA256_4WAY
|
||||
|
||||
void sha256d_ms_4way(uint32_t *hash, uint32_t *data,
|
||||
const uint32_t *midstate, const uint32_t *prehash);
|
||||
|
||||
static inline int scanhash_sha256d_4way(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
uint32_t data[4 * 64] __attribute__((aligned(128)));
|
||||
uint32_t hash[4 * 8] __attribute__((aligned(32)));
|
||||
uint32_t midstate[4 * 8] __attribute__((aligned(32)));
|
||||
uint32_t prehash[4 * 8] __attribute__((aligned(32)));
|
||||
uint32_t n = pdata[19] - 1;
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
const uint32_t Htarg = ptarget[7];
|
||||
int i, j;
|
||||
|
||||
memcpy(data, pdata + 16, 64);
|
||||
sha256d_preextend(data);
|
||||
for (i = 31; i >= 0; i--)
|
||||
for (j = 0; j < 4; j++)
|
||||
data[i * 4 + j] = data[i];
|
||||
|
||||
sha256_init(midstate);
|
||||
sha256_transform(midstate, pdata, 0);
|
||||
memcpy(prehash, midstate, 32);
|
||||
sha256d_prehash(prehash, pdata + 16);
|
||||
for (i = 7; i >= 0; i--) {
|
||||
for (j = 0; j < 4; j++) {
|
||||
midstate[i * 4 + j] = midstate[i];
|
||||
prehash[i * 4 + j] = prehash[i];
|
||||
}
|
||||
}
|
||||
|
||||
do {
|
||||
for (i = 0; i < 4; i++)
|
||||
data[4 * 3 + i] = ++n;
|
||||
|
||||
sha256d_ms_4way(hash, data, midstate, prehash);
|
||||
|
||||
for (i = 0; i < 4; i++) {
|
||||
if (swab32(hash[4 * 7 + i]) <= Htarg) {
|
||||
pdata[19] = data[4 * 3 + i];
|
||||
sha256d_80_swap(hash, pdata);
|
||||
if (fulltest(hash, ptarget)) {
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
} while (n < max_nonce && !work_restart[thr_id].restart);
|
||||
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
pdata[19] = n;
|
||||
return 0;
|
||||
}
|
||||
|
||||
#endif /* HAVE_SHA256_4WAY */
|
||||
|
||||
#if HAVE_SHA256_8WAY
|
||||
|
||||
void sha256d_ms_8way(uint32_t *hash, uint32_t *data,
|
||||
const uint32_t *midstate, const uint32_t *prehash);
|
||||
|
||||
static inline int scanhash_sha256d_8way(int thr_id, uint32_t *pdata,
|
||||
const uint32_t *ptarget, uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
uint32_t data[8 * 64] __attribute__((aligned(128)));
|
||||
uint32_t hash[8 * 8] __attribute__((aligned(32)));
|
||||
uint32_t midstate[8 * 8] __attribute__((aligned(32)));
|
||||
uint32_t prehash[8 * 8] __attribute__((aligned(32)));
|
||||
uint32_t n = pdata[19] - 1;
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
const uint32_t Htarg = ptarget[7];
|
||||
int i, j;
|
||||
|
||||
memcpy(data, pdata + 16, 64);
|
||||
sha256d_preextend(data);
|
||||
for (i = 31; i >= 0; i--)
|
||||
for (j = 0; j < 8; j++)
|
||||
data[i * 8 + j] = data[i];
|
||||
|
||||
sha256_init(midstate);
|
||||
sha256_transform(midstate, pdata, 0);
|
||||
memcpy(prehash, midstate, 32);
|
||||
sha256d_prehash(prehash, pdata + 16);
|
||||
for (i = 7; i >= 0; i--) {
|
||||
for (j = 0; j < 8; j++) {
|
||||
midstate[i * 8 + j] = midstate[i];
|
||||
prehash[i * 8 + j] = prehash[i];
|
||||
}
|
||||
}
|
||||
|
||||
do {
|
||||
for (i = 0; i < 8; i++)
|
||||
data[8 * 3 + i] = ++n;
|
||||
|
||||
sha256d_ms_8way(hash, data, midstate, prehash);
|
||||
|
||||
for (i = 0; i < 8; i++) {
|
||||
if (swab32(hash[8 * 7 + i]) <= Htarg) {
|
||||
pdata[19] = data[8 * 3 + i];
|
||||
sha256d_80_swap(hash, pdata);
|
||||
if (fulltest(hash, ptarget)) {
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
}
|
||||
} while (n < max_nonce && !work_restart[thr_id].restart);
|
||||
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
pdata[19] = n;
|
||||
return 0;
|
||||
}
|
||||
|
||||
#endif /* HAVE_SHA256_8WAY */
|
||||
|
||||
int scanhash_sha256d(int thr_id, uint32_t *pdata, const uint32_t *ptarget,
|
||||
uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
uint32_t data[64] /* __attribute__((aligned(128))) */;
|
||||
uint32_t hash[8] /* __attribute__((aligned(32))) */;
|
||||
uint32_t midstate[8] /* __attribute__((aligned(32))) */;
|
||||
uint32_t prehash[8] /* __attribute__((aligned(32))) */;
|
||||
uint32_t n = pdata[19] - 1;
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
const uint32_t Htarg = ptarget[7];
|
||||
|
||||
#if HAVE_SHA256_8WAY
|
||||
if (sha256_use_8way())
|
||||
return scanhash_sha256d_8way(thr_id, pdata, ptarget,
|
||||
max_nonce, hashes_done);
|
||||
#endif
|
||||
#if HAVE_SHA256_4WAY
|
||||
if (sha256_use_4way())
|
||||
return scanhash_sha256d_4way(thr_id, pdata, ptarget,
|
||||
max_nonce, hashes_done);
|
||||
#endif
|
||||
|
||||
memcpy(data, pdata + 16, 64);
|
||||
sha256d_preextend(data);
|
||||
|
||||
sha256_init(midstate);
|
||||
sha256_transform(midstate, pdata, 0);
|
||||
memcpy(prehash, midstate, 32);
|
||||
sha256d_prehash(prehash, pdata + 16);
|
||||
|
||||
do {
|
||||
data[3] = ++n;
|
||||
sha256d_ms(hash, data, midstate, prehash);
|
||||
if (swab32(hash[7]) <= Htarg) {
|
||||
pdata[19] = data[3];
|
||||
sha256d_80_swap(hash, pdata);
|
||||
if (fulltest(hash, ptarget)) {
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
} while (n < max_nonce && !work_restart[thr_id].restart);
|
||||
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
pdata[19] = n;
|
||||
return 0;
|
||||
}
|
||||
@@ -41,6 +41,8 @@ void stats_remember_speed(int thr_id, uint32_t hashcount, double hashrate, uint8
|
||||
data.thr_id = (uint8_t) thr_id;
|
||||
data.tm_stat = (uint32_t) time(NULL);
|
||||
data.height = height;
|
||||
data.npool = (uint8_t) cur_pooln;
|
||||
data.pool_type = pools[cur_pooln].type;
|
||||
data.hashcount = hashcount;
|
||||
data.hashfound = found;
|
||||
data.hashrate = hashrate;
|
||||
|
||||
@@ -36,6 +36,9 @@
|
||||
#include "miner.h"
|
||||
#include "elist.h"
|
||||
|
||||
extern pthread_mutex_t stratum_sock_lock;
|
||||
extern pthread_mutex_t stratum_work_lock;
|
||||
|
||||
bool opt_tracegpu = false;
|
||||
|
||||
struct data_buffer {
|
||||
@@ -385,9 +388,12 @@ static int sockopt_keepalive_cb(void *userdata, curl_socket_t fd,
|
||||
}
|
||||
#endif
|
||||
|
||||
json_t *json_rpc_call(CURL *curl, const char *url,
|
||||
/* For getwork (longpoll or wallet) - not stratum pools!
|
||||
* DO NOT USE DIRECTLY
|
||||
*/
|
||||
static json_t *json_rpc_call(CURL *curl, const char *url,
|
||||
const char *userpass, const char *rpc_req,
|
||||
bool longpoll_scan, bool longpoll, int *curl_err)
|
||||
bool longpoll_scan, bool longpoll, bool keepalive, int *curl_err)
|
||||
{
|
||||
json_t *val, *err_val, *res_val;
|
||||
int rc;
|
||||
@@ -395,10 +401,10 @@ json_t *json_rpc_call(CURL *curl, const char *url,
|
||||
struct upload_buffer upload_data;
|
||||
json_error_t err;
|
||||
struct curl_slist *headers = NULL;
|
||||
char* httpdata;
|
||||
char *httpdata;
|
||||
char len_hdr[64], hashrate_hdr[64];
|
||||
char curl_err_str[CURL_ERROR_SIZE] = { 0 };
|
||||
long timeout = longpoll ? opt_timeout : 30;
|
||||
long timeout = longpoll ? opt_timeout*2 : opt_timeout;
|
||||
struct header_info hi = { 0 };
|
||||
bool lp_scanning = longpoll_scan && !have_longpoll;
|
||||
|
||||
@@ -435,7 +441,7 @@ json_t *json_rpc_call(CURL *curl, const char *url,
|
||||
curl_easy_setopt(curl, CURLOPT_HTTPAUTH, CURLAUTH_BASIC);
|
||||
}
|
||||
#if LIBCURL_VERSION_NUM >= 0x070f06
|
||||
if (longpoll)
|
||||
if (keepalive)
|
||||
curl_easy_setopt(curl, CURLOPT_SOCKOPTFUNCTION, sockopt_keepalive_cb);
|
||||
#endif
|
||||
curl_easy_setopt(curl, CURLOPT_POST, 1);
|
||||
@@ -486,7 +492,8 @@ json_t *json_rpc_call(CURL *curl, const char *url,
|
||||
}
|
||||
|
||||
if (!all_data.buf || !all_data.len) {
|
||||
applog(LOG_ERR, "Empty data received in json_rpc_call.");
|
||||
if (!have_longpoll) // seems normal on longpoll timeout
|
||||
applog(LOG_ERR, "Empty data received in json_rpc_call.");
|
||||
goto err_out;
|
||||
}
|
||||
|
||||
@@ -571,6 +578,31 @@ err_out:
|
||||
return NULL;
|
||||
}
|
||||
|
||||
/* getwork calls with pool pointer (wallet/longpoll pools) */
|
||||
json_t *json_rpc_call_pool(CURL *curl, struct pool_infos *pool, const char *req,
|
||||
bool longpoll_scan, bool longpoll, int *curl_err)
|
||||
{
|
||||
char userpass[256];
|
||||
// todo, malloc and store that in pool array
|
||||
snprintf(userpass, sizeof(userpass), "%s%c%s", pool->user,
|
||||
strlen(pool->pass)?':':'\0', pool->pass);
|
||||
|
||||
return json_rpc_call(curl, pool->url, userpass, req, longpoll_scan, false, false, curl_err);
|
||||
}
|
||||
|
||||
/* called only from longpoll thread, we have the lp_url */
|
||||
json_t *json_rpc_longpoll(CURL *curl, char *lp_url, struct pool_infos *pool, const char *req, int *curl_err)
|
||||
{
|
||||
char userpass[256];
|
||||
snprintf(userpass, sizeof(userpass), "%s%c%s", pool->user,
|
||||
strlen(pool->pass)?':':'\0', pool->pass);
|
||||
|
||||
// on pool rotate by time-limit, this keepalive can be a problem
|
||||
bool keepalive = pool->time_limit == 0 || pool->time_limit > opt_timeout*4;
|
||||
|
||||
return json_rpc_call(curl, lp_url, userpass, req, false, true, keepalive, curl_err);
|
||||
}
|
||||
|
||||
/**
|
||||
* Unlike malloc, calloc set the memory to zero
|
||||
*/
|
||||
@@ -774,9 +806,9 @@ bool stratum_send_line(struct stratum_ctx *sctx, char *s)
|
||||
if (opt_protocol)
|
||||
applog(LOG_DEBUG, "> %s", s);
|
||||
|
||||
pthread_mutex_lock(&sctx->sock_lock);
|
||||
pthread_mutex_lock(&stratum_sock_lock);
|
||||
ret = send_line(sctx->sock, s);
|
||||
pthread_mutex_unlock(&sctx->sock_lock);
|
||||
pthread_mutex_unlock(&stratum_sock_lock);
|
||||
|
||||
return ret;
|
||||
}
|
||||
@@ -797,6 +829,7 @@ static bool socket_full(curl_socket_t sock, int timeout)
|
||||
|
||||
bool stratum_socket_full(struct stratum_ctx *sctx, int timeout)
|
||||
{
|
||||
if (!sctx->sockbuf) return false;
|
||||
return strlen(sctx->sockbuf) || socket_full(sctx->sock, timeout);
|
||||
}
|
||||
|
||||
@@ -821,10 +854,13 @@ char *stratum_recv_line(struct stratum_ctx *sctx)
|
||||
ssize_t len, buflen;
|
||||
char *tok, *sret = NULL;
|
||||
|
||||
if (!sctx->sockbuf)
|
||||
return NULL;
|
||||
|
||||
if (!strstr(sctx->sockbuf, "\n")) {
|
||||
bool ret = true;
|
||||
time_t rstart = time(NULL);
|
||||
if (!socket_full(sctx->sock, 60)) {
|
||||
if (!socket_full(sctx->sock, opt_timeout)) {
|
||||
applog(LOG_ERR, "stratum_recv_line timed out");
|
||||
goto out;
|
||||
}
|
||||
@@ -845,7 +881,7 @@ char *stratum_recv_line(struct stratum_ctx *sctx)
|
||||
}
|
||||
} else
|
||||
stratum_buffer_append(sctx, s);
|
||||
} while (time(NULL) - rstart < 60 && !strstr(sctx->sockbuf, "\n"));
|
||||
} while (time(NULL) - rstart < opt_timeout && !strstr(sctx->sockbuf, "\n"));
|
||||
|
||||
if (!ret) {
|
||||
applog(LOG_ERR, "stratum_recv_line failed");
|
||||
@@ -888,13 +924,13 @@ bool stratum_connect(struct stratum_ctx *sctx, const char *url)
|
||||
CURL *curl;
|
||||
int rc;
|
||||
|
||||
pthread_mutex_lock(&sctx->sock_lock);
|
||||
pthread_mutex_lock(&stratum_sock_lock);
|
||||
if (sctx->curl)
|
||||
curl_easy_cleanup(sctx->curl);
|
||||
sctx->curl = curl_easy_init();
|
||||
if (!sctx->curl) {
|
||||
applog(LOG_ERR, "CURL initialization failed");
|
||||
pthread_mutex_unlock(&sctx->sock_lock);
|
||||
pthread_mutex_unlock(&stratum_sock_lock);
|
||||
return false;
|
||||
}
|
||||
curl = sctx->curl;
|
||||
@@ -903,21 +939,21 @@ bool stratum_connect(struct stratum_ctx *sctx, const char *url)
|
||||
sctx->sockbuf_size = RBUFSIZE;
|
||||
}
|
||||
sctx->sockbuf[0] = '\0';
|
||||
pthread_mutex_unlock(&sctx->sock_lock);
|
||||
pthread_mutex_unlock(&stratum_sock_lock);
|
||||
|
||||
if (url != sctx->url) {
|
||||
free(sctx->url);
|
||||
sctx->url = strdup(url);
|
||||
}
|
||||
free(sctx->curl_url);
|
||||
sctx->curl_url = (char*)malloc(strlen(url));
|
||||
sctx->curl_url = (char*)malloc(strlen(url)+1);
|
||||
sprintf(sctx->curl_url, "http%s", strstr(url, "://"));
|
||||
|
||||
if (opt_protocol)
|
||||
curl_easy_setopt(curl, CURLOPT_VERBOSE, 1);
|
||||
curl_easy_setopt(curl, CURLOPT_URL, sctx->curl_url);
|
||||
curl_easy_setopt(curl, CURLOPT_FRESH_CONNECT, 1);
|
||||
curl_easy_setopt(curl, CURLOPT_CONNECTTIMEOUT, 30);
|
||||
curl_easy_setopt(curl, CURLOPT_CONNECTTIMEOUT, opt_timeout);
|
||||
curl_easy_setopt(curl, CURLOPT_ERRORBUFFER, sctx->curl_err_str);
|
||||
curl_easy_setopt(curl, CURLOPT_NOSIGNAL, 1);
|
||||
curl_easy_setopt(curl, CURLOPT_TCP_NODELAY, 1);
|
||||
@@ -957,16 +993,41 @@ bool stratum_connect(struct stratum_ctx *sctx, const char *url)
|
||||
return true;
|
||||
}
|
||||
|
||||
void stratum_free_job(struct stratum_ctx *sctx)
|
||||
{
|
||||
pthread_mutex_lock(&stratum_work_lock);
|
||||
if (sctx->job.job_id) {
|
||||
free(sctx->job.job_id);
|
||||
}
|
||||
if (sctx->job.merkle_count) {
|
||||
for (int i = 0; i < sctx->job.merkle_count; i++) {
|
||||
free(sctx->job.merkle[i]);
|
||||
sctx->job.merkle[i] = NULL;
|
||||
}
|
||||
free(sctx->job.merkle);
|
||||
}
|
||||
free(sctx->job.coinbase);
|
||||
// note: xnonce2 is not allocated
|
||||
memset(&(sctx->job.job_id), 0, sizeof(struct stratum_job));
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
}
|
||||
|
||||
void stratum_disconnect(struct stratum_ctx *sctx)
|
||||
{
|
||||
pthread_mutex_lock(&sctx->sock_lock);
|
||||
pthread_mutex_lock(&stratum_sock_lock);
|
||||
if (sctx->curl) {
|
||||
sctx->disconnects++;
|
||||
pools[sctx->pooln].disconnects++;
|
||||
curl_easy_cleanup(sctx->curl);
|
||||
sctx->curl = NULL;
|
||||
sctx->sockbuf[0] = '\0';
|
||||
if (sctx->sockbuf)
|
||||
sctx->sockbuf[0] = '\0';
|
||||
// free(sctx->sockbuf);
|
||||
// sctx->sockbuf = NULL;
|
||||
}
|
||||
pthread_mutex_unlock(&sctx->sock_lock);
|
||||
if (sctx->job.job_id) {
|
||||
stratum_free_job(sctx);
|
||||
}
|
||||
pthread_mutex_unlock(&stratum_sock_lock);
|
||||
}
|
||||
|
||||
static const char *get_stratum_session_id(json_t *val)
|
||||
@@ -1012,19 +1073,19 @@ static bool stratum_parse_extranonce(struct stratum_ctx *sctx, json_t *params, i
|
||||
goto out;
|
||||
}
|
||||
|
||||
pthread_mutex_lock(&sctx->work_lock);
|
||||
pthread_mutex_lock(&stratum_work_lock);
|
||||
if (sctx->xnonce1)
|
||||
free(sctx->xnonce1);
|
||||
sctx->xnonce1_size = strlen(xnonce1) / 2;
|
||||
sctx->xnonce1 = (uchar*) calloc(1, sctx->xnonce1_size);
|
||||
if (unlikely(!sctx->xnonce1)) {
|
||||
applog(LOG_ERR, "Failed to alloc xnonce1");
|
||||
pthread_mutex_unlock(&sctx->work_lock);
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
goto out;
|
||||
}
|
||||
hex2bin(sctx->xnonce1, xnonce1, sctx->xnonce1_size);
|
||||
sctx->xnonce2_size = xn2_size;
|
||||
pthread_mutex_unlock(&sctx->work_lock);
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
|
||||
if (pndx == 0 && opt_debug) /* pool dynamic change */
|
||||
applog(LOG_DEBUG, "Stratum set nonce %s with extranonce2 size=%d",
|
||||
@@ -1103,12 +1164,12 @@ start:
|
||||
if (opt_debug && sid)
|
||||
applog(LOG_DEBUG, "Stratum session id: %s", sid);
|
||||
|
||||
pthread_mutex_lock(&sctx->work_lock);
|
||||
pthread_mutex_lock(&stratum_work_lock);
|
||||
if (sctx->session_id)
|
||||
free(sctx->session_id);
|
||||
sctx->session_id = sid ? strdup(sid) : NULL;
|
||||
sctx->next_diff = 1.0;
|
||||
pthread_mutex_unlock(&sctx->work_lock);
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
|
||||
out:
|
||||
free(s);
|
||||
@@ -1253,8 +1314,8 @@ static bool stratum_notify(struct stratum_ctx *sctx, json_t *params)
|
||||
bool clean, ret = false;
|
||||
int merkle_count, i;
|
||||
json_t *merkle_arr;
|
||||
uchar **merkle;
|
||||
uchar(*merkle_tree)[32] = NULL;
|
||||
uchar **merkle = NULL;
|
||||
// uchar(*merkle_tree)[32] = { 0 };
|
||||
int ntime;
|
||||
|
||||
job_id = json_string_value(json_array_get(params, 0));
|
||||
@@ -1287,7 +1348,8 @@ static bool stratum_notify(struct stratum_ctx *sctx, json_t *params)
|
||||
applog(LOG_DEBUG, "stratum time is at least %ds in the future", ntime);
|
||||
}
|
||||
|
||||
merkle = (uchar**) malloc(merkle_count * sizeof(char *));
|
||||
if (merkle_count)
|
||||
merkle = (uchar**) malloc(merkle_count * sizeof(char *));
|
||||
for (i = 0; i < merkle_count; i++) {
|
||||
const char *s = json_string_value(json_array_get(merkle_arr, i));
|
||||
if (!s || strlen(s) != 64) {
|
||||
@@ -1301,7 +1363,7 @@ static bool stratum_notify(struct stratum_ctx *sctx, json_t *params)
|
||||
hex2bin(merkle[i], s, 32);
|
||||
}
|
||||
|
||||
pthread_mutex_lock(&sctx->work_lock);
|
||||
pthread_mutex_lock(&stratum_work_lock);
|
||||
|
||||
coinb1_size = strlen(coinb1) / 2;
|
||||
coinb2_size = strlen(coinb2) / 2;
|
||||
@@ -1341,7 +1403,7 @@ static bool stratum_notify(struct stratum_ctx *sctx, json_t *params)
|
||||
|
||||
sctx->job.diff = sctx->next_diff;
|
||||
|
||||
pthread_mutex_unlock(&sctx->work_lock);
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
|
||||
ret = true;
|
||||
|
||||
@@ -1349,7 +1411,7 @@ out:
|
||||
return ret;
|
||||
}
|
||||
|
||||
extern time_t g_work_time;
|
||||
extern volatile time_t g_work_time;
|
||||
static bool stratum_set_difficulty(struct stratum_ctx *sctx, json_t *params)
|
||||
{
|
||||
double diff;
|
||||
@@ -1358,9 +1420,9 @@ static bool stratum_set_difficulty(struct stratum_ctx *sctx, json_t *params)
|
||||
if (diff <= 0.0)
|
||||
return false;
|
||||
|
||||
pthread_mutex_lock(&sctx->work_lock);
|
||||
pthread_mutex_lock(&stratum_work_lock);
|
||||
sctx->next_diff = diff;
|
||||
pthread_mutex_unlock(&sctx->work_lock);
|
||||
pthread_mutex_unlock(&stratum_work_lock);
|
||||
|
||||
/* store for api stats */
|
||||
if (diff != stratum_diff) {
|
||||
@@ -1708,9 +1770,9 @@ void do_gpu_tests(void)
|
||||
//memcpy(buf, zrtest, 80);
|
||||
//scanhash_zr5(0, (uint32_t*)buf, tgt, zrtest[19]+1, &done);
|
||||
|
||||
struct timeval tv;
|
||||
memset(buf, 0, sizeof buf);
|
||||
scanhash_scrypt_jane(0, (uint32_t*)buf, tgt, NULL, 1, &done, &tv, &tv);
|
||||
//struct timeval tv;
|
||||
//memset(buf, 0, sizeof buf);
|
||||
//scanhash_scrypt_jane(0, (uint32_t*)buf, tgt, NULL, 1, &done, &tv, &tv);
|
||||
|
||||
memset(buf, 0, sizeof buf);
|
||||
scanhash_x11(0, (uint32_t*)buf, tgt, 1, &done);
|
||||
@@ -1733,7 +1795,7 @@ void print_hash_tests(void)
|
||||
uchar *scratchbuf = NULL;
|
||||
char s[128] = {'\0'};
|
||||
uchar hash[128];
|
||||
uchar buf[128];
|
||||
uchar buf[168];
|
||||
|
||||
// work space for scratchpad based algos
|
||||
scratchbuf = (uchar*)calloc(128, 1024);
|
||||
@@ -1752,6 +1814,9 @@ void print_hash_tests(void)
|
||||
blake256hash(&hash[0], &buf[0], 14);
|
||||
printpfx("blake", hash);
|
||||
|
||||
creditshash(&hash[0], &buf[0]);
|
||||
printpfx("credits", hash);
|
||||
|
||||
deephash(&hash[0], &buf[0]);
|
||||
printpfx("deep", hash);
|
||||
|
||||
@@ -1773,7 +1838,7 @@ void print_hash_tests(void)
|
||||
keccak256_hash(&hash[0], &buf[0]);
|
||||
printpfx("keccak", hash);
|
||||
|
||||
doomhash(&hash[0], &buf[0]);
|
||||
luffa_hash(&hash[0], &buf[0]);
|
||||
printpfx("luffa", hash);
|
||||
|
||||
lyra2_hash(&hash[0], &buf[0]);
|
||||
|
||||
+672
-484
File diff suppressed because it is too large.
Load diff
+2
-2
@@ -43,7 +43,7 @@ extern void quark_jh512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void quark_jh512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_luffaCubehash512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_shavite512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_shavite512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
@@ -201,7 +201,7 @@ extern "C" int scanhash_x11(int thr_id, uint32_t *pdata,
|
||||
TRACE("jh512 :");
|
||||
quark_keccak512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
TRACE("keccak :");
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, d_hash[thr_id], order++);
|
||||
TRACE("luffa+c:");
|
||||
x11_shavite512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
TRACE("shavite:");
|
||||
|
||||
+2
-2
@@ -45,7 +45,7 @@ extern void quark_jh512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void quark_jh512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_luffaCubehash512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_shavite512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_shavite512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
@@ -200,7 +200,7 @@ extern "C" int scanhash_x13(int thr_id, uint32_t *pdata,
|
||||
quark_skein512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_jh512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_keccak512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, d_hash[thr_id], order++);
|
||||
x11_shavite512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_simd512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_echo512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
|
||||
+2
-2
@@ -49,7 +49,7 @@ extern void quark_jh512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void quark_jh512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_luffaCubehash512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_shavite512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_shavite512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
@@ -208,7 +208,7 @@ extern "C" int scanhash_x14(int thr_id, uint32_t *pdata,
|
||||
quark_skein512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_jh512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_keccak512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, d_hash[thr_id], order++);
|
||||
x11_shavite512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_simd512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_echo512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
|
||||
+2
-2
@@ -50,7 +50,7 @@ extern void quark_jh512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void quark_jh512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_luffaCubehash512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_shavite512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_shavite512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
@@ -219,7 +219,7 @@ extern "C" int scanhash_x15(int thr_id, uint32_t *pdata,
|
||||
quark_skein512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_jh512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_keccak512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, d_hash[thr_id], order++);
|
||||
x11_shavite512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_simd512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_echo512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
|
||||
+2
-2
@@ -53,7 +53,7 @@ extern void quark_jh512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void quark_jh512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_luffaCubehash512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
extern void x11_luffaCubehash512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t *d_hash, int order);
|
||||
|
||||
extern void x11_shavite512_cpu_init(int thr_id, uint32_t threads);
|
||||
extern void x11_shavite512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_nonceVector, uint32_t *d_hash, int order);
|
||||
@@ -243,7 +243,7 @@ extern "C" int scanhash_x17(int thr_id, uint32_t *pdata,
|
||||
quark_skein512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_jh512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
quark_keccak512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_luffaCubehash512_cpu_hash_64(thr_id, throughput, d_hash[thr_id], order++);
|
||||
x11_shavite512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_simd512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
x11_echo512_cpu_hash_64(thr_id, throughput, pdata[19], NULL, d_hash[thr_id], order++);
|
||||
|
||||
@@ -33,6 +33,9 @@ static uint32_t* d_groes[MAX_GPUS];
|
||||
static uint32_t* d_jh512[MAX_GPUS];
|
||||
static uint32_t* d_skein[MAX_GPUS];
|
||||
|
||||
static uint8_t* d_txs[MAX_GPUS];
|
||||
__constant__ uint16_t c_txlens[POK_MAX_TXS];
|
||||
|
||||
__constant__ uint8_t c_permut[24][4];
|
||||
static const uint8_t permut[24][4] = {
|
||||
{0, 1, 2, 3},
|
||||
@@ -112,8 +115,8 @@ extern "C" void zr5hash(void *output, const void *input)
|
||||
|
||||
extern "C" void zr5hash_pok(void *output, uint32_t *pdata)
|
||||
{
|
||||
const uint32_t version = pdata[0] & (~POK_DATA_MASK);
|
||||
uint32_t _ALIGN(64) hash[8];
|
||||
const uint32_t version = (pdata[0] & (~POK_DATA_MASK)) | (use_pok ? POK_BOOL_MASK : 0);
|
||||
|
||||
pdata[0] = version;
|
||||
zr5hash(hash, pdata);
|
||||
@@ -208,7 +211,7 @@ void zr5_move_data_to_hash(int thr_id, uint32_t threads, int rnd)
|
||||
|
||||
|
||||
__global__ __launch_bounds__(128, 8)
|
||||
void zr5_get_poks_gpu(uint32_t threads, uint32_t** const d_buffers, uint8_t* const d_permut, uint32_t *d_hash, uint16_t *d_poks)
|
||||
void zr5_get_poks_gpu(uint32_t threads, uint32_t** const d_buffers, uint8_t* const d_permut, uint16_t *d_poks)
|
||||
{
|
||||
const uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
@@ -223,14 +226,54 @@ void zr5_get_poks_gpu(uint32_t threads, uint32_t** const d_buffers, uint8_t* con
|
||||
}
|
||||
}
|
||||
|
||||
__global__ __launch_bounds__(128, 4)
|
||||
void zr5_get_poks_xor_gpu(uint32_t threads, uint32_t** const d_buffers, uint8_t* d_permut, uint16_t* d_poks, uint8_t* d_txs, uint8_t txs)
|
||||
{
|
||||
const uint32_t thread = (blockDim.x * blockIdx.x + threadIdx.x);
|
||||
if (thread < threads)
|
||||
{
|
||||
const uint8_t norder = d_permut[thread];
|
||||
const uint8_t algo = c_permut[norder][3];
|
||||
const uint8_t ntx = norder % txs; // generally 0 on testnet...
|
||||
const uint32_t offset = thread * 16U; // 64 / 4;
|
||||
uint32_t* hash = (uint32_t*) (d_buffers[algo] + offset);
|
||||
uint32_t randNdx = hash[1] % c_txlens[ntx];
|
||||
uint8_t* ptx = &d_txs[POK_MAX_TX_SZ*ntx] + randNdx;
|
||||
uint32_t x = 0x100UL * ptx[3] + ptx[2];
|
||||
|
||||
d_poks[thread] = x ^ (hash[2] >> 16);
|
||||
}
|
||||
}
|
||||
|
||||
__host__
|
||||
void zr5_get_poks(int thr_id, uint32_t threads, uint16_t* d_poks)
|
||||
void zr5_get_poks(int thr_id, uint32_t threads, uint16_t* d_poks, struct work* work)
|
||||
{
|
||||
const uint32_t threadsperblock = 128;
|
||||
dim3 grid((threads + threadsperblock - 1) / threadsperblock);
|
||||
dim3 block(threadsperblock);
|
||||
|
||||
zr5_get_poks_gpu <<<grid, block>>> (threads, d_buffers[thr_id], d_permut[thr_id], d_hash[thr_id], d_poks);
|
||||
uint8_t txs = (uint8_t) work->tx_count;
|
||||
|
||||
if (txs && use_pok)
|
||||
{
|
||||
uint32_t txlens[POK_MAX_TXS];
|
||||
uint8_t* txdata = (uint8_t*) calloc(POK_MAX_TXS, POK_MAX_TX_SZ);
|
||||
if (!txdata) {
|
||||
applog(LOG_ERR, "%s: error, memory alloc failure", __func__);
|
||||
return;
|
||||
}
|
||||
// create blocs to copy on device
|
||||
for (uint8_t tx=0; tx < txs; tx++) {
|
||||
txlens[tx] = (uint32_t) (work->txs[tx].len - 3U);
|
||||
memcpy(&txdata[POK_MAX_TX_SZ*tx], work->txs[tx].data, min(POK_MAX_TX_SZ, txlens[tx]+3U));
|
||||
}
|
||||
cudaMemcpy(d_txs[thr_id], txdata, txs * POK_MAX_TX_SZ, cudaMemcpyHostToDevice);
|
||||
CUDA_SAFE_CALL(cudaMemcpyToSymbol(c_txlens, txlens, txs * sizeof(uint32_t), 0, cudaMemcpyHostToDevice));
|
||||
zr5_get_poks_xor_gpu <<<grid, block>>> (threads, d_buffers[thr_id], d_permut[thr_id], d_poks, d_txs[thr_id], txs);
|
||||
free(txdata);
|
||||
} else {
|
||||
zr5_get_poks_gpu <<<grid, block>>> (threads, d_buffers[thr_id], d_permut[thr_id], d_poks);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -285,18 +328,21 @@ extern void quark_skein512_cpu_hash_64(int thr_id, uint32_t threads, uint32_t st
|
||||
|
||||
static bool init[MAX_GPUS] = { 0 };
|
||||
|
||||
extern "C" int scanhash_zr5(int thr_id, uint32_t *pdata, const uint32_t *ptarget,
|
||||
extern "C" int scanhash_zr5(int thr_id, struct work *work,
|
||||
uint32_t max_nonce, unsigned long *hashes_done)
|
||||
{
|
||||
uint32_t _ALIGN(64) tmpdata[20];
|
||||
const uint32_t version = pdata[0] & (~POK_DATA_MASK);
|
||||
uint32_t *pdata = work->data;
|
||||
uint32_t *ptarget = work->target;
|
||||
const uint32_t oldp0 = pdata[0];
|
||||
const uint32_t version = (oldp0 & (~POK_DATA_MASK)) | (use_pok ? POK_BOOL_MASK : 0);
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
uint32_t throughput = device_intensity(thr_id, __func__, 1U << 18);
|
||||
throughput = min(throughput, (1U << 20)-1024);
|
||||
throughput = min(throughput, max_nonce - first_nonce);
|
||||
|
||||
if (opt_benchmark)
|
||||
((uint32_t*)ptarget)[7] = 0x0000ff;
|
||||
ptarget[7] = 0x0000ff;
|
||||
|
||||
memcpy(tmpdata, pdata, 80);
|
||||
|
||||
@@ -319,6 +365,8 @@ extern "C" int scanhash_zr5(int thr_id, uint32_t *pdata, const uint32_t *ptarget
|
||||
cudaMalloc(&d_jh512[thr_id], 64 * throughput);
|
||||
cudaMalloc(&d_skein[thr_id], 64 * throughput);
|
||||
|
||||
cudaMalloc(&d_txs[thr_id], POK_MAX_TXS * POK_MAX_TX_SZ);
|
||||
|
||||
jackpot_keccak512_cpu_init(thr_id, throughput);
|
||||
|
||||
quark_blake512_cpu_init(thr_id, throughput);
|
||||
@@ -354,7 +402,7 @@ extern "C" int scanhash_zr5(int thr_id, uint32_t *pdata, const uint32_t *ptarget
|
||||
}
|
||||
|
||||
// store on device d_poks all hash[0] prefixes
|
||||
zr5_get_poks(thr_id, throughput, d_poks[thr_id]);
|
||||
zr5_get_poks(thr_id, throughput, d_poks[thr_id], work);
|
||||
|
||||
// Keccak512 with pok
|
||||
zr5_keccak512_cpu_hash_pok(thr_id, throughput, pdata[19], pdata, d_hash[thr_id], d_poks[thr_id]);
|
||||
@@ -374,7 +422,6 @@ extern "C" int scanhash_zr5(int thr_id, uint32_t *pdata, const uint32_t *ptarget
|
||||
if (foundNonce != UINT32_MAX)
|
||||
{
|
||||
uint32_t vhash64[8];
|
||||
uint32_t oldp0 = pdata[0];
|
||||
uint32_t oldp19 = pdata[19];
|
||||
uint32_t offset = foundNonce - pdata[19];
|
||||
uint32_t pok = 0;
|
||||
@@ -406,9 +453,6 @@ extern "C" int scanhash_zr5(int thr_id, uint32_t *pdata, const uint32_t *ptarget
|
||||
} else {
|
||||
applog(LOG_WARNING, "GPU #%d: result for %08x does not validate on CPU!", device_map[thr_id], foundNonce);
|
||||
|
||||
// reinit the card.. segfault so no
|
||||
// cuda_reset_device(thr_id, init);
|
||||
|
||||
pdata[19]++;
|
||||
pdata[0] = oldp0;
|
||||
}
|
||||
@@ -417,6 +461,8 @@ extern "C" int scanhash_zr5(int thr_id, uint32_t *pdata, const uint32_t *ptarget
|
||||
|
||||
} while (pdata[19] < max_nonce && !work_restart[thr_id].restart);
|
||||
|
||||
pdata[0] = oldp0;
|
||||
|
||||
*hashes_done = pdata[19] - first_nonce + 1;
|
||||
return 0;
|
||||
}
|
||||
Reference in new issue
Block a user