mirror of
https://github.com/JayDDee/cpuminer-opt.git
synced 2025-09-17 23:44:27 +00:00
v3.9.5
This commit is contained in:
Jay D Dee
1102
algo/scrypt/neoscrypt.c
Normal file
1102
algo/scrypt/neoscrypt.c
Normal file
File diff suppressed because it is too large
Load Diff
511
algo/scrypt/pluck.c
Normal file
511
algo/scrypt/pluck.c
Normal file
@@ -0,0 +1,511 @@
|
||||
/*
|
||||
* Copyright 2009 Colin Percival, 2011 ArtForz, 2011-2014 pooler, 2015 Jordan Earls
|
||||
* 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.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``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.
|
||||
*/
|
||||
|
||||
#include "cpuminer-config.h"
|
||||
#include "algo-gate-api.h"
|
||||
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#define BLOCK_HEADER_SIZE 80
|
||||
|
||||
// windows
|
||||
#ifndef htobe32
|
||||
#define htobe32(x) ((uint32_t)htonl((uint32_t)(x)))
|
||||
#endif
|
||||
|
||||
#ifdef _MSC_VER
|
||||
#define ROTL(a, b) _rotl(a,b)
|
||||
#define ROTR(a, b) _rotr(a,b)
|
||||
#else
|
||||
#define ROTL(a, b) (((a) << b) | ((a) >> (32 - b)))
|
||||
#define ROTR(a, b) ((a >> b) | (a << (32 - b)))
|
||||
#endif
|
||||
|
||||
#if defined(_MSC_VER) && defined(_M_X64)
|
||||
#define _VECTOR __vectorcall
|
||||
#include <intrin.h>
|
||||
//#include <emmintrin.h> //SSE2
|
||||
//#include <pmmintrin.h> //SSE3
|
||||
//#include <tmmintrin.h> //SSSE3
|
||||
//#include <smmintrin.h> //SSE4.1
|
||||
//#include <nmmintrin.h> //SSE4.2
|
||||
//#include <ammintrin.h> //SSE4A
|
||||
//#include <wmmintrin.h> //AES
|
||||
//#include <immintrin.h> //AVX
|
||||
#define OPT_COMPATIBLE
|
||||
#elif defined(__GNUC__) && defined(__x86_64__)
|
||||
#include <x86intrin.h>
|
||||
#define _VECTOR
|
||||
#endif
|
||||
|
||||
static __thread char *scratchbuf;
|
||||
|
||||
#ifdef OPT_COMPATIBLE
|
||||
static void _VECTOR xor_salsa8(__m128i B[4], const __m128i Bx[4], int i)
|
||||
{
|
||||
__m128i X0, X1, X2, X3;
|
||||
|
||||
if (i <= 128) {
|
||||
// a xor 0 = a
|
||||
X0 = B[0] = Bx[0];
|
||||
X1 = B[1] = Bx[1];
|
||||
X2 = B[2] = Bx[2];
|
||||
X3 = B[3] = Bx[3];
|
||||
} else {
|
||||
X0 = B[0] = _mm_xor_si128(B[0], Bx[0]);
|
||||
X1 = B[1] = _mm_xor_si128(B[1], Bx[1]);
|
||||
X2 = B[2] = _mm_xor_si128(B[2], Bx[2]);
|
||||
X3 = B[3] = _mm_xor_si128(B[3], Bx[3]);
|
||||
}
|
||||
|
||||
for (i = 0; i < 4; i++) {
|
||||
/* Operate on columns. */
|
||||
X1.m128i_u32[0] ^= ROTL(X0.m128i_u32[0] + X3.m128i_u32[0], 7);
|
||||
X2.m128i_u32[1] ^= ROTL(X1.m128i_u32[1] + X0.m128i_u32[1], 7);
|
||||
X3.m128i_u32[2] ^= ROTL(X2.m128i_u32[2] + X1.m128i_u32[2], 7);
|
||||
X0.m128i_u32[3] ^= ROTL(X3.m128i_u32[3] + X2.m128i_u32[3], 7);
|
||||
|
||||
X2.m128i_u32[0] ^= ROTL(X1.m128i_u32[0] + X0.m128i_u32[0], 9);
|
||||
X3.m128i_u32[1] ^= ROTL(X2.m128i_u32[1] + X1.m128i_u32[1], 9);
|
||||
X0.m128i_u32[2] ^= ROTL(X3.m128i_u32[2] + X2.m128i_u32[2], 9);
|
||||
X1.m128i_u32[3] ^= ROTL(X0.m128i_u32[3] + X3.m128i_u32[3], 9);
|
||||
|
||||
X3.m128i_u32[0] ^= ROTL(X2.m128i_u32[0] + X1.m128i_u32[0], 13);
|
||||
X0.m128i_u32[1] ^= ROTL(X3.m128i_u32[1] + X2.m128i_u32[1], 13);
|
||||
X1.m128i_u32[2] ^= ROTL(X0.m128i_u32[2] + X3.m128i_u32[2], 13);
|
||||
X2.m128i_u32[3] ^= ROTL(X1.m128i_u32[3] + X0.m128i_u32[3], 13);
|
||||
|
||||
X0.m128i_u32[0] ^= ROTL(X3.m128i_u32[0] + X2.m128i_u32[0], 18);
|
||||
X1.m128i_u32[1] ^= ROTL(X0.m128i_u32[1] + X3.m128i_u32[1], 18);
|
||||
X2.m128i_u32[2] ^= ROTL(X1.m128i_u32[2] + X0.m128i_u32[2], 18);
|
||||
X3.m128i_u32[3] ^= ROTL(X2.m128i_u32[3] + X1.m128i_u32[3], 18);
|
||||
|
||||
/* Operate on rows. */
|
||||
X0.m128i_u32[1] ^= ROTL(X0.m128i_u32[0] + X0.m128i_u32[3], 7); X1.m128i_u32[2] ^= ROTL(X1.m128i_u32[1] + X1.m128i_u32[0], 7);
|
||||
X2.m128i_u32[3] ^= ROTL(X2.m128i_u32[2] + X2.m128i_u32[1], 7); X3.m128i_u32[0] ^= ROTL(X3.m128i_u32[3] + X3.m128i_u32[2], 7);
|
||||
X0.m128i_u32[2] ^= ROTL(X0.m128i_u32[1] + X0.m128i_u32[0], 9); X1.m128i_u32[3] ^= ROTL(X1.m128i_u32[2] + X1.m128i_u32[1], 9);
|
||||
X2.m128i_u32[0] ^= ROTL(X2.m128i_u32[3] + X2.m128i_u32[2], 9); X3.m128i_u32[1] ^= ROTL(X3.m128i_u32[0] + X3.m128i_u32[3], 9);
|
||||
|
||||
X0.m128i_u32[3] ^= ROTL(X0.m128i_u32[2] + X0.m128i_u32[1], 13); X1.m128i_u32[0] ^= ROTL(X1.m128i_u32[3] + X1.m128i_u32[2], 13);
|
||||
X2.m128i_u32[1] ^= ROTL(X2.m128i_u32[0] + X2.m128i_u32[3], 13); X3.m128i_u32[2] ^= ROTL(X3.m128i_u32[1] + X3.m128i_u32[0], 13);
|
||||
X0.m128i_u32[0] ^= ROTL(X0.m128i_u32[3] + X0.m128i_u32[2], 18); X1.m128i_u32[1] ^= ROTL(X1.m128i_u32[0] + X1.m128i_u32[3], 18);
|
||||
X2.m128i_u32[2] ^= ROTL(X2.m128i_u32[1] + X2.m128i_u32[0], 18); X3.m128i_u32[3] ^= ROTL(X3.m128i_u32[2] + X3.m128i_u32[1], 18);
|
||||
}
|
||||
|
||||
B[0] = _mm_add_epi32(B[0], X0);
|
||||
B[1] = _mm_add_epi32(B[1], X1);
|
||||
B[2] = _mm_add_epi32(B[2], X2);
|
||||
B[3] = _mm_add_epi32(B[3], X3);
|
||||
}
|
||||
|
||||
#else
|
||||
|
||||
static inline void xor_salsa8(uint32_t B[16], const uint32_t Bx[16], int i)
|
||||
{
|
||||
uint32_t x00,x01,x02,x03,x04,x05,x06,x07,x08,x09,x10,x11,x12,x13,x14,x15;
|
||||
|
||||
if (i <= 128) {
|
||||
// a xor 0 = a
|
||||
x00 = B[ 0] = Bx[ 0]; x01 = B[ 1] = Bx[ 1]; x02 = B[ 2] = Bx[ 2]; x03 = B[ 3] = Bx[ 3];
|
||||
x04 = B[ 4] = Bx[ 4]; x05 = B[ 5] = Bx[ 5]; x06 = B[ 6] = Bx[ 6]; x07 = B[ 7] = Bx[ 7];
|
||||
x08 = B[ 8] = Bx[ 8]; x09 = B[ 9] = Bx[ 9]; x10 = B[10] = Bx[10]; x11 = B[11] = Bx[11];
|
||||
x12 = B[12] = Bx[12]; x13 = B[13] = Bx[13]; x14 = B[14] = Bx[14]; x15 = B[15] = Bx[15];
|
||||
} else {
|
||||
x00 = (B[ 0] ^= Bx[ 0]);
|
||||
x01 = (B[ 1] ^= Bx[ 1]);
|
||||
x02 = (B[ 2] ^= Bx[ 2]);
|
||||
x03 = (B[ 3] ^= Bx[ 3]);
|
||||
x04 = (B[ 4] ^= Bx[ 4]);
|
||||
x05 = (B[ 5] ^= Bx[ 5]);
|
||||
x06 = (B[ 6] ^= Bx[ 6]);
|
||||
x07 = (B[ 7] ^= Bx[ 7]);
|
||||
x08 = (B[ 8] ^= Bx[ 8]);
|
||||
x09 = (B[ 9] ^= Bx[ 9]);
|
||||
x10 = (B[10] ^= Bx[10]);
|
||||
x11 = (B[11] ^= Bx[11]);
|
||||
x12 = (B[12] ^= Bx[12]);
|
||||
x13 = (B[13] ^= Bx[13]);
|
||||
x14 = (B[14] ^= Bx[14]);
|
||||
x15 = (B[15] ^= Bx[15]);
|
||||
}
|
||||
|
||||
for (i = 0; i < 8; i += 2) {
|
||||
/* Operate on columns. */
|
||||
x04 ^= ROTL(x00 + x12, 7); x09 ^= ROTL(x05 + x01, 7);
|
||||
x14 ^= ROTL(x10 + x06, 7); x03 ^= ROTL(x15 + x11, 7);
|
||||
|
||||
x08 ^= ROTL(x04 + x00, 9); x13 ^= ROTL(x09 + x05, 9);
|
||||
x02 ^= ROTL(x14 + x10, 9); x07 ^= ROTL(x03 + x15, 9);
|
||||
|
||||
x12 ^= ROTL(x08 + x04, 13); x01 ^= ROTL(x13 + x09, 13);
|
||||
x06 ^= ROTL(x02 + x14, 13); x11 ^= ROTL(x07 + x03, 13);
|
||||
|
||||
x00 ^= ROTL(x12 + x08, 18); x05 ^= ROTL(x01 + x13, 18);
|
||||
x10 ^= ROTL(x06 + x02, 18); x15 ^= ROTL(x11 + x07, 18);
|
||||
|
||||
/* Operate on rows. */
|
||||
x01 ^= ROTL(x00 + x03, 7); x06 ^= ROTL(x05 + x04, 7);
|
||||
x11 ^= ROTL(x10 + x09, 7); x12 ^= ROTL(x15 + x14, 7);
|
||||
|
||||
x02 ^= ROTL(x01 + x00, 9); x07 ^= ROTL(x06 + x05, 9);
|
||||
x08 ^= ROTL(x11 + x10, 9); x13 ^= ROTL(x12 + x15, 9);
|
||||
|
||||
x03 ^= ROTL(x02 + x01, 13); x04 ^= ROTL(x07 + x06, 13);
|
||||
x09 ^= ROTL(x08 + x11, 13); x14 ^= ROTL(x13 + x12, 13);
|
||||
|
||||
x00 ^= ROTL(x03 + x02, 18); x05 ^= ROTL(x04 + x07, 18);
|
||||
x10 ^= ROTL(x09 + x08, 18); x15 ^= ROTL(x14 + x13, 18);
|
||||
}
|
||||
B[ 0] += x00;
|
||||
B[ 1] += x01;
|
||||
B[ 2] += x02;
|
||||
B[ 3] += x03;
|
||||
B[ 4] += x04;
|
||||
B[ 5] += x05;
|
||||
B[ 6] += x06;
|
||||
B[ 7] += x07;
|
||||
B[ 8] += x08;
|
||||
B[ 9] += x09;
|
||||
B[10] += x10;
|
||||
B[11] += x11;
|
||||
B[12] += x12;
|
||||
B[13] += x13;
|
||||
B[14] += x14;
|
||||
B[15] += x15;
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
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
|
||||
};
|
||||
|
||||
/* 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 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])
|
||||
|
||||
|
||||
static void sha256_transform_volatile(uint32_t *state, uint32_t *block)
|
||||
{
|
||||
uint32_t* W=block; //note: block needs to be a mutable 64 int32_t
|
||||
uint32_t S[8];
|
||||
uint32_t t0, t1;
|
||||
int i;
|
||||
|
||||
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];
|
||||
}
|
||||
|
||||
// standard sha256 hash
|
||||
#if 1
|
||||
static void sha256_hash(unsigned char *hash, const unsigned char *data, int len)
|
||||
{
|
||||
uint32_t _ALIGN(64) S[16];
|
||||
uint32_t _ALIGN(64) T[64];
|
||||
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);
|
||||
sha256_transform_volatile(S, T);
|
||||
}
|
||||
for (i = 0; i < 8; i++)
|
||||
be32enc((uint32_t *)hash + i, S[i]);
|
||||
}
|
||||
#else
|
||||
#include <openssl/sha.h>
|
||||
static void sha256_hash(unsigned char *hash, const unsigned char *data, int len)
|
||||
{
|
||||
SHA256_CTX ctx;
|
||||
SHA256_Init(&ctx);
|
||||
SHA256_Update(&ctx, data, len);
|
||||
SHA256_Final(hash, &ctx);
|
||||
}
|
||||
#endif
|
||||
|
||||
// hash exactly 64 bytes (ie, sha256 block size)
|
||||
static void sha256_hash512(uint32_t *hash, const uint32_t *data)
|
||||
{
|
||||
uint32_t _ALIGN(64) S[16];
|
||||
uint32_t _ALIGN(64) T[64];
|
||||
uchar _ALIGN(64) E[64*4] = { 0 };
|
||||
int i;
|
||||
|
||||
sha256_init(S);
|
||||
|
||||
for (i = 0; i < 16; i++)
|
||||
T[i] = be32dec(&data[i]);
|
||||
sha256_transform_volatile(S, T);
|
||||
|
||||
E[3] = 0x80;
|
||||
E[61] = 0x02; // T[15] = 8 * 64 => 0x200;
|
||||
sha256_transform_volatile(S, (uint32_t*)E);
|
||||
|
||||
for (i = 0; i < 8; i++)
|
||||
be32enc(&hash[i], S[i]);
|
||||
}
|
||||
|
||||
void pluck_hash(uint32_t *hash, const uint32_t *data, uchar *hashbuffer, const int N)
|
||||
{
|
||||
int size = N * 1024;
|
||||
sha256_hash(hashbuffer, (void*)data, BLOCK_HEADER_SIZE);
|
||||
memset(&hashbuffer[32], 0, 32);
|
||||
|
||||
for(int i = 64; i < size - 32; i += 32)
|
||||
{
|
||||
uint32_t _ALIGN(64) randseed[16];
|
||||
uint32_t _ALIGN(64) randbuffer[16];
|
||||
uint32_t _ALIGN(64) joint[16];
|
||||
//i-4 because we use integers for all references against this, and we don't want to go 3 bytes over the defined area
|
||||
//we could use size here, but then it's probable to use 0 as the value in most cases
|
||||
int randmax = i - 4;
|
||||
|
||||
//setup randbuffer to be an array of random indexes
|
||||
memcpy(randseed, &hashbuffer[i - 64], 64);
|
||||
|
||||
if(i > 128) memcpy(randbuffer, &hashbuffer[i - 128], 64);
|
||||
//else memset(randbuffer, 0, 64);
|
||||
|
||||
xor_salsa8((void*)randbuffer, (void*)randseed, i);
|
||||
memcpy(joint, &hashbuffer[i - 32], 32);
|
||||
|
||||
//use the last hash value as the seed
|
||||
for (int j = 32; j < 64; j += 4)
|
||||
{
|
||||
//every other time, change to next random index
|
||||
//randmax - 32 as otherwise we go beyond memory that's already been written to
|
||||
uint32_t rand = randbuffer[(j - 32) >> 2] % (randmax - 32);
|
||||
joint[j >> 2] = *((uint32_t *)&hashbuffer[rand]);
|
||||
}
|
||||
|
||||
sha256_hash512((uint32_t*) &hashbuffer[i], joint);
|
||||
|
||||
//setup randbuffer to be an array of random indexes
|
||||
//use last hash value and previous hash value(post-mixing)
|
||||
memcpy(randseed, &hashbuffer[i - 32], 64);
|
||||
|
||||
if(i > 128) memcpy(randbuffer, &hashbuffer[i - 128], 64);
|
||||
//else memset(randbuffer, 0, 64);
|
||||
|
||||
xor_salsa8((void*)randbuffer, (void*)randseed, i);
|
||||
|
||||
//use the last hash value as the seed
|
||||
for (int j = 0; j < 32; j += 2)
|
||||
{
|
||||
uint32_t rand = randbuffer[j >> 1] % randmax;
|
||||
*((uint32_t *)(hashbuffer + rand)) = *((uint32_t *)(hashbuffer + j + randmax));
|
||||
}
|
||||
}
|
||||
|
||||
memcpy(hash, hashbuffer, 32);
|
||||
}
|
||||
|
||||
int scanhash_pluck( struct work *work, uint32_t max_nonce,
|
||||
uint64_t *hashes_done, struct thr_info *mythr )
|
||||
{
|
||||
uint32_t *pdata = work->data;
|
||||
uint32_t *ptarget = work->target;
|
||||
uint32_t _ALIGN(64) endiandata[20];
|
||||
uint32_t _ALIGN(64) hash[8];
|
||||
const uint32_t first_nonce = pdata[19];
|
||||
int thr_id = mythr->id; // thr_id arg is deprecated
|
||||
volatile uint8_t *restart = &(work_restart[thr_id].restart);
|
||||
uint32_t n = first_nonce;
|
||||
|
||||
|
||||
if (opt_benchmark)
|
||||
((uint32_t*)ptarget)[7] = 0x0ffff;
|
||||
|
||||
for (int i=0; i < 19; i++)
|
||||
be32enc(&endiandata[i], pdata[i]);
|
||||
|
||||
const uint32_t Htarg = ptarget[7];
|
||||
do {
|
||||
//be32enc(&endiandata[19], n);
|
||||
endiandata[19] = n;
|
||||
pluck_hash(hash, endiandata, scratchbuf, opt_pluck_n);
|
||||
|
||||
if (hash[7] <= Htarg && fulltest(hash, ptarget))
|
||||
{
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
pdata[19] = htobe32(endiandata[19]);
|
||||
return 1;
|
||||
}
|
||||
n++;
|
||||
} while (n < max_nonce && !(*restart));
|
||||
|
||||
*hashes_done = n - first_nonce + 1;
|
||||
pdata[19] = n;
|
||||
return 0;
|
||||
}
|
||||
|
||||
int64_t pluck_get_max64 ()
|
||||
{
|
||||
return 0x1ffLL;
|
||||
}
|
||||
|
||||
bool pluck_miner_thread_init( int thr_id )
|
||||
{
|
||||
scratchbuf = malloc( 128 * 1024 );
|
||||
if ( scratchbuf )
|
||||
return true;
|
||||
applog( LOG_ERR, "Thread %u: Pluck buffer allocation failed", thr_id );
|
||||
return false;
|
||||
}
|
||||
|
||||
bool register_pluck_algo( algo_gate_t* gate )
|
||||
{
|
||||
algo_not_tested();
|
||||
gate->miner_thread_init = (void*)&pluck_miner_thread_init;
|
||||
gate->scanhash = (void*)&scanhash_pluck;
|
||||
gate->hash = (void*)&pluck_hash;
|
||||
gate->set_target = (void*)&scrypt_set_target;
|
||||
gate->get_max64 = (void*)&pluck_get_max64;
|
||||
return true;
|
||||
};
|
||||
|
||||
|
||||
795
algo/scrypt/scrypt.c
Normal file
795
algo/scrypt/scrypt.c
Normal file
@@ -0,0 +1,795 @@
|
||||
/*
|
||||
* Copyright 2009 Colin Percival, 2011 ArtForz, 2011-2014 pooler
|
||||
* 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.
|
||||
*
|
||||
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``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.
|
||||
*
|
||||
* This file was originally written by Colin Percival as part of the Tarsnap
|
||||
* online backup system.
|
||||
*/
|
||||
|
||||
#include "algo-gate-api.h"
|
||||
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#include <inttypes.h>
|
||||
|
||||
static const uint32_t keypad[12] = {
|
||||
0x80000000, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x00000280
|
||||
};
|
||||
static const uint32_t innerpad[11] = {
|
||||
0x80000000, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x000004a0
|
||||
};
|
||||
static const uint32_t outerpad[8] = {
|
||||
0x80000000, 0, 0, 0, 0, 0, 0, 0x00000300
|
||||
};
|
||||
static const uint32_t finalblk[16] = {
|
||||
0x00000001, 0x80000000, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x00000620
|
||||
};
|
||||
|
||||
static __thread char *scratchbuf;
|
||||
int scratchbuf_size = 0;
|
||||
|
||||
static inline void HMAC_SHA256_80_init(const uint32_t *key,
|
||||
uint32_t *tstate, uint32_t *ostate)
|
||||
{
|
||||
uint32_t ihash[8];
|
||||
uint32_t pad[16];
|
||||
int i;
|
||||
|
||||
/* tstate is assumed to contain the midstate of key */
|
||||
memcpy(pad, key + 16, 16);
|
||||
memcpy(pad + 4, keypad, 48);
|
||||
sha256_transform(tstate, pad, 0);
|
||||
memcpy(ihash, tstate, 32);
|
||||
|
||||
sha256_init(ostate);
|
||||
for (i = 0; i < 8; i++)
|
||||
pad[i] = ihash[i] ^ 0x5c5c5c5c;
|
||||
for (; i < 16; i++)
|
||||
pad[i] = 0x5c5c5c5c;
|
||||
sha256_transform(ostate, pad, 0);
|
||||
|
||||
sha256_init(tstate);
|
||||
for (i = 0; i < 8; i++)
|
||||
pad[i] = ihash[i] ^ 0x36363636;
|
||||
for (; i < 16; i++)
|
||||
pad[i] = 0x36363636;
|
||||
sha256_transform(tstate, pad, 0);
|
||||
}
|
||||
|
||||
static inline void PBKDF2_SHA256_80_128(const uint32_t *tstate,
|
||||
const uint32_t *ostate, const uint32_t *salt, uint32_t *output)
|
||||
{
|
||||
uint32_t istate[8], ostate2[8];
|
||||
uint32_t ibuf[16], obuf[16];
|
||||
int i, j;
|
||||
|
||||
memcpy(istate, tstate, 32);
|
||||
sha256_transform(istate, salt, 0);
|
||||
|
||||
memcpy(ibuf, salt + 16, 16);
|
||||
memcpy(ibuf + 5, innerpad, 44);
|
||||
memcpy(obuf + 8, outerpad, 32);
|
||||
|
||||
for (i = 0; i < 4; i++) {
|
||||
memcpy(obuf, istate, 32);
|
||||
ibuf[4] = i + 1;
|
||||
sha256_transform(obuf, ibuf, 0);
|
||||
|
||||
memcpy(ostate2, ostate, 32);
|
||||
sha256_transform(ostate2, obuf, 0);
|
||||
for (j = 0; j < 8; j++)
|
||||
output[8 * i + j] = swab32(ostate2[j]);
|
||||
}
|
||||
}
|
||||
|
||||
static inline void PBKDF2_SHA256_128_32(uint32_t *tstate, uint32_t *ostate,
|
||||
const uint32_t *salt, uint32_t *output)
|
||||
{
|
||||
uint32_t buf[16];
|
||||
int i;
|
||||
|
||||
sha256_transform(tstate, salt, 1);
|
||||
sha256_transform(tstate, salt + 16, 1);
|
||||
sha256_transform(tstate, finalblk, 0);
|
||||
memcpy(buf, tstate, 32);
|
||||
memcpy(buf + 8, outerpad, 32);
|
||||
|
||||
sha256_transform(ostate, buf, 0);
|
||||
for (i = 0; i < 8; i++)
|
||||
output[i] = swab32(ostate[i]);
|
||||
}
|
||||
|
||||
|
||||
#ifdef HAVE_SHA256_4WAY
|
||||
|
||||
static const uint32_t keypad_4way[4 * 12] = {
|
||||
0x80000000, 0x80000000, 0x80000000, 0x80000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000280, 0x00000280, 0x00000280, 0x00000280
|
||||
};
|
||||
static const uint32_t innerpad_4way[4 * 11] = {
|
||||
0x80000000, 0x80000000, 0x80000000, 0x80000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x000004a0, 0x000004a0, 0x000004a0, 0x000004a0
|
||||
};
|
||||
static const uint32_t outerpad_4way[4 * 8] = {
|
||||
0x80000000, 0x80000000, 0x80000000, 0x80000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000300, 0x00000300, 0x00000300, 0x00000300
|
||||
};
|
||||
static const uint32_t _ALIGN(16) finalblk_4way[4 * 16] = {
|
||||
0x00000001, 0x00000001, 0x00000001, 0x00000001,
|
||||
0x80000000, 0x80000000, 0x80000000, 0x80000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000620, 0x00000620, 0x00000620, 0x00000620
|
||||
};
|
||||
|
||||
static inline void HMAC_SHA256_80_init_4way(const uint32_t *key,
|
||||
uint32_t *tstate, uint32_t *ostate)
|
||||
{
|
||||
uint32_t _ALIGN(16) ihash[4 * 8];
|
||||
uint32_t _ALIGN(16) pad[4 * 16];
|
||||
int i;
|
||||
|
||||
/* tstate is assumed to contain the midstate of key */
|
||||
memcpy(pad, key + 4 * 16, 4 * 16);
|
||||
memcpy(pad + 4 * 4, keypad_4way, 4 * 48);
|
||||
sha256_transform_4way(tstate, pad, 0);
|
||||
memcpy(ihash, tstate, 4 * 32);
|
||||
|
||||
sha256_init_4way(ostate);
|
||||
for (i = 0; i < 4 * 8; i++)
|
||||
pad[i] = ihash[i] ^ 0x5c5c5c5c;
|
||||
for (; i < 4 * 16; i++)
|
||||
pad[i] = 0x5c5c5c5c;
|
||||
sha256_transform_4way(ostate, pad, 0);
|
||||
|
||||
sha256_init_4way(tstate);
|
||||
for (i = 0; i < 4 * 8; i++)
|
||||
pad[i] = ihash[i] ^ 0x36363636;
|
||||
for (; i < 4 * 16; i++)
|
||||
pad[i] = 0x36363636;
|
||||
sha256_transform_4way(tstate, pad, 0);
|
||||
}
|
||||
|
||||
static inline void PBKDF2_SHA256_80_128_4way(const uint32_t *tstate,
|
||||
const uint32_t *ostate, const uint32_t *salt, uint32_t *output)
|
||||
{
|
||||
uint32_t _ALIGN(16) istate[4 * 8];
|
||||
uint32_t _ALIGN(16) ostate2[4 * 8];
|
||||
uint32_t _ALIGN(16) ibuf[4 * 16];
|
||||
uint32_t _ALIGN(16) obuf[4 * 16];
|
||||
int i, j;
|
||||
|
||||
memcpy(istate, tstate, 4 * 32);
|
||||
sha256_transform_4way(istate, salt, 0);
|
||||
|
||||
memcpy(ibuf, salt + 4 * 16, 4 * 16);
|
||||
memcpy(ibuf + 4 * 5, innerpad_4way, 4 * 44);
|
||||
memcpy(obuf + 4 * 8, outerpad_4way, 4 * 32);
|
||||
|
||||
for (i = 0; i < 4; i++) {
|
||||
memcpy(obuf, istate, 4 * 32);
|
||||
ibuf[4 * 4 + 0] = i + 1;
|
||||
ibuf[4 * 4 + 1] = i + 1;
|
||||
ibuf[4 * 4 + 2] = i + 1;
|
||||
ibuf[4 * 4 + 3] = i + 1;
|
||||
sha256_transform_4way(obuf, ibuf, 0);
|
||||
|
||||
memcpy(ostate2, ostate, 4 * 32);
|
||||
sha256_transform_4way(ostate2, obuf, 0);
|
||||
for (j = 0; j < 4 * 8; j++)
|
||||
output[4 * 8 * i + j] = swab32(ostate2[j]);
|
||||
}
|
||||
}
|
||||
|
||||
static inline void PBKDF2_SHA256_128_32_4way(uint32_t *tstate,
|
||||
uint32_t *ostate, const uint32_t *salt, uint32_t *output)
|
||||
{
|
||||
uint32_t _ALIGN(16) buf[4 * 16];
|
||||
int i;
|
||||
|
||||
sha256_transform_4way(tstate, salt, 1);
|
||||
sha256_transform_4way(tstate, salt + 4 * 16, 1);
|
||||
sha256_transform_4way(tstate, finalblk_4way, 0);
|
||||
memcpy(buf, tstate, 4 * 32);
|
||||
memcpy(buf + 4 * 8, outerpad_4way, 4 * 32);
|
||||
|
||||
sha256_transform_4way(ostate, buf, 0);
|
||||
for (i = 0; i < 4 * 8; i++)
|
||||
output[i] = swab32(ostate[i]);
|
||||
}
|
||||
|
||||
#endif /* HAVE_SHA256_4WAY */
|
||||
|
||||
|
||||
#ifdef HAVE_SHA256_8WAY
|
||||
|
||||
static const uint32_t _ALIGN(32) finalblk_8way[8 * 16] = {
|
||||
0x00000001, 0x00000001, 0x00000001, 0x00000001, 0x00000001, 0x00000001, 0x00000001, 0x00000001,
|
||||
0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
|
||||
0x00000620, 0x00000620, 0x00000620, 0x00000620, 0x00000620, 0x00000620, 0x00000620, 0x00000620
|
||||
};
|
||||
|
||||
static inline void HMAC_SHA256_80_init_8way(const uint32_t *key,
|
||||
uint32_t *tstate, uint32_t *ostate)
|
||||
{
|
||||
uint32_t _ALIGN(32) ihash[8 * 8];
|
||||
uint32_t _ALIGN(32) pad[8 * 16];
|
||||
int i;
|
||||
|
||||
/* tstate is assumed to contain the midstate of key */
|
||||
memcpy(pad, key + 8 * 16, 8 * 16);
|
||||
for (i = 0; i < 8; i++)
|
||||
pad[8 * 4 + i] = 0x80000000;
|
||||
memset(pad + 8 * 5, 0x00, 8 * 40);
|
||||
for (i = 0; i < 8; i++)
|
||||
pad[8 * 15 + i] = 0x00000280;
|
||||
sha256_transform_8way(tstate, pad, 0);
|
||||
memcpy(ihash, tstate, 8 * 32);
|
||||
|
||||
sha256_init_8way(ostate);
|
||||
for (i = 0; i < 8 * 8; i++)
|
||||
pad[i] = ihash[i] ^ 0x5c5c5c5c;
|
||||
for (; i < 8 * 16; i++)
|
||||
pad[i] = 0x5c5c5c5c;
|
||||
sha256_transform_8way(ostate, pad, 0);
|
||||
|
||||
sha256_init_8way(tstate);
|
||||
for (i = 0; i < 8 * 8; i++)
|
||||
pad[i] = ihash[i] ^ 0x36363636;
|
||||
for (; i < 8 * 16; i++)
|
||||
pad[i] = 0x36363636;
|
||||
sha256_transform_8way(tstate, pad, 0);
|
||||
}
|
||||
|
||||
static inline void PBKDF2_SHA256_80_128_8way(const uint32_t *tstate,
|
||||
const uint32_t *ostate, const uint32_t *salt, uint32_t *output)
|
||||
{
|
||||
uint32_t _ALIGN(32) istate[8 * 8];
|
||||
uint32_t _ALIGN(32) ostate2[8 * 8];
|
||||
uint32_t _ALIGN(32) ibuf[8 * 16];
|
||||
uint32_t _ALIGN(32) obuf[8 * 16];
|
||||
int i, j;
|
||||
|
||||
memcpy(istate, tstate, 8 * 32);
|
||||
sha256_transform_8way(istate, salt, 0);
|
||||
|
||||
memcpy(ibuf, salt + 8 * 16, 8 * 16);
|
||||
for (i = 0; i < 8; i++)
|
||||
ibuf[8 * 5 + i] = 0x80000000;
|
||||
memset(ibuf + 8 * 6, 0x00, 8 * 36);
|
||||
for (i = 0; i < 8; i++)
|
||||
ibuf[8 * 15 + i] = 0x000004a0;
|
||||
|
||||
for (i = 0; i < 8; i++)
|
||||
obuf[8 * 8 + i] = 0x80000000;
|
||||
memset(obuf + 8 * 9, 0x00, 8 * 24);
|
||||
for (i = 0; i < 8; i++)
|
||||
obuf[8 * 15 + i] = 0x00000300;
|
||||
|
||||
for (i = 0; i < 4; i++) {
|
||||
memcpy(obuf, istate, 8 * 32);
|
||||
ibuf[8 * 4 + 0] = i + 1;
|
||||
ibuf[8 * 4 + 1] = i + 1;
|
||||
ibuf[8 * 4 + 2] = i + 1;
|
||||
ibuf[8 * 4 + 3] = i + 1;
|
||||
ibuf[8 * 4 + 4] = i + 1;
|
||||
ibuf[8 * 4 + 5] = i + 1;
|
||||
ibuf[8 * 4 + 6] = i + 1;
|
||||
ibuf[8 * 4 + 7] = i + 1;
|
||||
sha256_transform_8way(obuf, ibuf, 0);
|
||||
|
||||
memcpy(ostate2, ostate, 8 * 32);
|
||||
sha256_transform_8way(ostate2, obuf, 0);
|
||||
for (j = 0; j < 8 * 8; j++)
|
||||
output[8 * 8 * i + j] = swab32(ostate2[j]);
|
||||
}
|
||||
}
|
||||
|
||||
static inline void PBKDF2_SHA256_128_32_8way(uint32_t *tstate,
|
||||
uint32_t *ostate, const uint32_t *salt, uint32_t *output)
|
||||
{
|
||||
uint32_t _ALIGN(32) buf[8 * 16];
|
||||
int i;
|
||||
|
||||
sha256_transform_8way(tstate, salt, 1);
|
||||
sha256_transform_8way(tstate, salt + 8 * 16, 1);
|
||||
sha256_transform_8way(tstate, finalblk_8way, 0);
|
||||
|
||||
memcpy(buf, tstate, 8 * 32);
|
||||
for (i = 0; i < 8; i++)
|
||||
buf[8 * 8 + i] = 0x80000000;
|
||||
memset(buf + 8 * 9, 0x00, 8 * 24);
|
||||
for (i = 0; i < 8; i++)
|
||||
buf[8 * 15 + i] = 0x00000300;
|
||||
sha256_transform_8way(ostate, buf, 0);
|
||||
|
||||
for (i = 0; i < 8 * 8; i++)
|
||||
output[i] = swab32(ostate[i]);
|
||||
}
|
||||
|
||||
#endif /* HAVE_SHA256_8WAY */
|
||||
|
||||
|
||||
#if defined(USE_ASM) && defined(__x86_64__)
|
||||
|
||||
#define SCRYPT_MAX_WAYS 12
|
||||
#define HAVE_SCRYPT_3WAY 1
|
||||
int scrypt_best_throughput();
|
||||
void scrypt_core(uint32_t *X, uint32_t *V, int N);
|
||||
void scrypt_core_3way(uint32_t *X, uint32_t *V, int N);
|
||||
#if defined(USE_AVX2)
|
||||
#undef SCRYPT_MAX_WAYS
|
||||
#define SCRYPT_MAX_WAYS 24
|
||||
#define HAVE_SCRYPT_6WAY 1
|
||||
void scrypt_core_6way(uint32_t *X, uint32_t *V, int N);
|
||||
#endif
|
||||
|
||||
#elif defined(USE_ASM) && defined(__i386__)
|
||||
|
||||
#define SCRYPT_MAX_WAYS 4
|
||||
#define scrypt_best_throughput() 1
|
||||
void scrypt_core(uint32_t *X, uint32_t *V, int N);
|
||||
|
||||
#elif defined(USE_ASM) && defined(__arm__) && defined(__APCS_32__)
|
||||
|
||||
void scrypt_core(uint32_t *X, uint32_t *V, int N);
|
||||
#if defined(__ARM_NEON__)
|
||||
#undef HAVE_SHA256_4WAY
|
||||
#define SCRYPT_MAX_WAYS 3
|
||||
#define HAVE_SCRYPT_3WAY 1
|
||||
#define scrypt_best_throughput() 3
|
||||
void scrypt_core_3way(uint32_t *X, uint32_t *V, int N);
|
||||
#endif
|
||||
|
||||
#else
|
||||
|
||||
static inline void xor_salsa8(uint32_t B[16], const uint32_t Bx[16])
|
||||
{
|
||||
uint32_t x00,x01,x02,x03,x04,x05,x06,x07,x08,x09,x10,x11,x12,x13,x14,x15;
|
||||
int i;
|
||||
|
||||
x00 = (B[ 0] ^= Bx[ 0]);
|
||||
x01 = (B[ 1] ^= Bx[ 1]);
|
||||
x02 = (B[ 2] ^= Bx[ 2]);
|
||||
x03 = (B[ 3] ^= Bx[ 3]);
|
||||
x04 = (B[ 4] ^= Bx[ 4]);
|
||||
x05 = (B[ 5] ^= Bx[ 5]);
|
||||
x06 = (B[ 6] ^= Bx[ 6]);
|
||||
x07 = (B[ 7] ^= Bx[ 7]);
|
||||
x08 = (B[ 8] ^= Bx[ 8]);
|
||||
x09 = (B[ 9] ^= Bx[ 9]);
|
||||
x10 = (B[10] ^= Bx[10]);
|
||||
x11 = (B[11] ^= Bx[11]);
|
||||
x12 = (B[12] ^= Bx[12]);
|
||||
x13 = (B[13] ^= Bx[13]);
|
||||
x14 = (B[14] ^= Bx[14]);
|
||||
x15 = (B[15] ^= Bx[15]);
|
||||
for (i = 0; i < 8; i += 2) {
|
||||
#define R(a, b) (((a) << (b)) | ((a) >> (32 - (b))))
|
||||
/* Operate on columns. */
|
||||
x04 ^= R(x00+x12, 7); x09 ^= R(x05+x01, 7);
|
||||
x14 ^= R(x10+x06, 7); x03 ^= R(x15+x11, 7);
|
||||
|
||||
x08 ^= R(x04+x00, 9); x13 ^= R(x09+x05, 9);
|
||||
x02 ^= R(x14+x10, 9); x07 ^= R(x03+x15, 9);
|
||||
|
||||
x12 ^= R(x08+x04,13); x01 ^= R(x13+x09,13);
|
||||
x06 ^= R(x02+x14,13); x11 ^= R(x07+x03,13);
|
||||
|
||||
x00 ^= R(x12+x08,18); x05 ^= R(x01+x13,18);
|
||||
x10 ^= R(x06+x02,18); x15 ^= R(x11+x07,18);
|
||||
|
||||
/* Operate on rows. */
|
||||
x01 ^= R(x00+x03, 7); x06 ^= R(x05+x04, 7);
|
||||
x11 ^= R(x10+x09, 7); x12 ^= R(x15+x14, 7);
|
||||
|
||||
x02 ^= R(x01+x00, 9); x07 ^= R(x06+x05, 9);
|
||||
x08 ^= R(x11+x10, 9); x13 ^= R(x12+x15, 9);
|
||||
|
||||
x03 ^= R(x02+x01,13); x04 ^= R(x07+x06,13);
|
||||
x09 ^= R(x08+x11,13); x14 ^= R(x13+x12,13);
|
||||
|
||||
x00 ^= R(x03+x02,18); x05 ^= R(x04+x07,18);
|
||||
x10 ^= R(x09+x08,18); x15 ^= R(x14+x13,18);
|
||||
#undef R
|
||||
}
|
||||
B[ 0] += x00;
|
||||
B[ 1] += x01;
|
||||
B[ 2] += x02;
|
||||
B[ 3] += x03;
|
||||
B[ 4] += x04;
|
||||
B[ 5] += x05;
|
||||
B[ 6] += x06;
|
||||
B[ 7] += x07;
|
||||
B[ 8] += x08;
|
||||
B[ 9] += x09;
|
||||
B[10] += x10;
|
||||
B[11] += x11;
|
||||
B[12] += x12;
|
||||
B[13] += x13;
|
||||
B[14] += x14;
|
||||
B[15] += x15;
|
||||
}
|
||||
|
||||
static inline void scrypt_core(uint32_t *X, uint32_t *V, int N)
|
||||
{
|
||||
int i;
|
||||
|
||||
for (i = 0; i < N; i++) {
|
||||
memcpy(&V[i * 32], X, 128);
|
||||
xor_salsa8(&X[0], &X[16]);
|
||||
xor_salsa8(&X[16], &X[0]);
|
||||
}
|
||||
for (i = 0; i < N; i++) {
|
||||
uint32_t j = 32 * (X[16] & (N - 1));
|
||||
for (uint8_t k = 0; k < 32; k++)
|
||||
X[k] ^= V[j + k];
|
||||
xor_salsa8(&X[0], &X[16]);
|
||||
xor_salsa8(&X[16], &X[0]);
|
||||
}
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
#ifndef SCRYPT_MAX_WAYS
|
||||
#define SCRYPT_MAX_WAYS 1
|
||||
#define scrypt_best_throughput() 1
|
||||
#endif
|
||||
|
||||
unsigned char *scrypt_buffer_alloc(int N)
|
||||
{
|
||||
return (uchar*) malloc((size_t)N * SCRYPT_MAX_WAYS * 128 + 63);
|
||||
}
|
||||
|
||||
static void scrypt_1024_1_1_256(const uint32_t *input, uint32_t *output,
|
||||
uint32_t *midstate, unsigned char *scratchpad, int N)
|
||||
{
|
||||
uint32_t tstate[8], ostate[8];
|
||||
uint32_t X[32];
|
||||
uint32_t *V;
|
||||
|
||||
V = (uint32_t *)(((uintptr_t)(scratchpad) + 63) & ~ (uintptr_t)(63));
|
||||
|
||||
memcpy(tstate, midstate, 32);
|
||||
HMAC_SHA256_80_init(input, tstate, ostate);
|
||||
PBKDF2_SHA256_80_128(tstate, ostate, input, X);
|
||||
|
||||
scrypt_core(X, V, N);
|
||||
|
||||
PBKDF2_SHA256_128_32(tstate, ostate, X, output);
|
||||
}
|
||||
|
||||
#ifdef HAVE_SHA256_4WAY
|
||||
static void scrypt_1024_1_1_256_4way(const uint32_t *input,
|
||||
uint32_t *output, uint32_t *midstate, unsigned char *scratchpad, int N)
|
||||
{
|
||||
uint32_t _ALIGN(128) tstate[4 * 8];
|
||||
uint32_t _ALIGN(128) ostate[4 * 8];
|
||||
uint32_t _ALIGN(128) W[4 * 32];
|
||||
uint32_t _ALIGN(128) X[4 * 32];
|
||||
uint32_t *V;
|
||||
int i, k;
|
||||
|
||||
V = (uint32_t *)(((uintptr_t)(scratchpad) + 63) & ~ (uintptr_t)(63));
|
||||
|
||||
for (i = 0; i < 20; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
W[4 * i + k] = input[k * 20 + i];
|
||||
for (i = 0; i < 8; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
tstate[4 * i + k] = midstate[i];
|
||||
HMAC_SHA256_80_init_4way(W, tstate, ostate);
|
||||
PBKDF2_SHA256_80_128_4way(tstate, ostate, W, W);
|
||||
for (i = 0; i < 32; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
X[k * 32 + i] = W[4 * i + k];
|
||||
scrypt_core(X + 0 * 32, V, N);
|
||||
scrypt_core(X + 1 * 32, V, N);
|
||||
scrypt_core(X + 2 * 32, V, N);
|
||||
scrypt_core(X + 3 * 32, V, N);
|
||||
for (i = 0; i < 32; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
W[4 * i + k] = X[k * 32 + i];
|
||||
PBKDF2_SHA256_128_32_4way(tstate, ostate, W, W);
|
||||
for (i = 0; i < 8; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
output[k * 8 + i] = W[4 * i + k];
|
||||
}
|
||||
#endif /* HAVE_SHA256_4WAY */
|
||||
|
||||
#ifdef HAVE_SCRYPT_3WAY
|
||||
|
||||
static void scrypt_1024_1_1_256_3way(const uint32_t *input,
|
||||
uint32_t *output, uint32_t *midstate, unsigned char *scratchpad, int N)
|
||||
{
|
||||
uint32_t _ALIGN(64) tstate[3 * 8], ostate[3 * 8];
|
||||
uint32_t _ALIGN(64) X[3 * 32];
|
||||
uint32_t *V;
|
||||
|
||||
V = (uint32_t *)(((uintptr_t)(scratchpad) + 63) & ~ (uintptr_t)(63));
|
||||
|
||||
memcpy(tstate + 0, midstate, 32);
|
||||
memcpy(tstate + 8, midstate, 32);
|
||||
memcpy(tstate + 16, midstate, 32);
|
||||
HMAC_SHA256_80_init(input + 0, tstate + 0, ostate + 0);
|
||||
HMAC_SHA256_80_init(input + 20, tstate + 8, ostate + 8);
|
||||
HMAC_SHA256_80_init(input + 40, tstate + 16, ostate + 16);
|
||||
PBKDF2_SHA256_80_128(tstate + 0, ostate + 0, input + 0, X + 0);
|
||||
PBKDF2_SHA256_80_128(tstate + 8, ostate + 8, input + 20, X + 32);
|
||||
PBKDF2_SHA256_80_128(tstate + 16, ostate + 16, input + 40, X + 64);
|
||||
|
||||
scrypt_core_3way(X, V, N);
|
||||
|
||||
PBKDF2_SHA256_128_32(tstate + 0, ostate + 0, X + 0, output + 0);
|
||||
PBKDF2_SHA256_128_32(tstate + 8, ostate + 8, X + 32, output + 8);
|
||||
PBKDF2_SHA256_128_32(tstate + 16, ostate + 16, X + 64, output + 16);
|
||||
}
|
||||
|
||||
#ifdef HAVE_SHA256_4WAY
|
||||
static void scrypt_1024_1_1_256_12way(const uint32_t *input,
|
||||
uint32_t *output, uint32_t *midstate, unsigned char *scratchpad, int N)
|
||||
{
|
||||
uint32_t _ALIGN(128) tstate[12 * 8];
|
||||
uint32_t _ALIGN(128) ostate[12 * 8];
|
||||
uint32_t _ALIGN(128) W[12 * 32];
|
||||
uint32_t _ALIGN(128) X[12 * 32];
|
||||
uint32_t *V;
|
||||
int i, j, k;
|
||||
|
||||
V = (uint32_t *)(((uintptr_t)(scratchpad) + 63) & ~ (uintptr_t)(63));
|
||||
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 20; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
W[128 * j + 4 * i + k] = input[80 * j + k * 20 + i];
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 8; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
tstate[32 * j + 4 * i + k] = midstate[i];
|
||||
HMAC_SHA256_80_init_4way(W + 0, tstate + 0, ostate + 0);
|
||||
HMAC_SHA256_80_init_4way(W + 128, tstate + 32, ostate + 32);
|
||||
HMAC_SHA256_80_init_4way(W + 256, tstate + 64, ostate + 64);
|
||||
PBKDF2_SHA256_80_128_4way(tstate + 0, ostate + 0, W + 0, W + 0);
|
||||
PBKDF2_SHA256_80_128_4way(tstate + 32, ostate + 32, W + 128, W + 128);
|
||||
PBKDF2_SHA256_80_128_4way(tstate + 64, ostate + 64, W + 256, W + 256);
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 32; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
X[128 * j + k * 32 + i] = W[128 * j + 4 * i + k];
|
||||
scrypt_core_3way(X + 0 * 96, V, N);
|
||||
scrypt_core_3way(X + 1 * 96, V, N);
|
||||
scrypt_core_3way(X + 2 * 96, V, N);
|
||||
scrypt_core_3way(X + 3 * 96, V, N);
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 32; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
W[128 * j + 4 * i + k] = X[128 * j + k * 32 + i];
|
||||
PBKDF2_SHA256_128_32_4way(tstate + 0, ostate + 0, W + 0, W + 0);
|
||||
PBKDF2_SHA256_128_32_4way(tstate + 32, ostate + 32, W + 128, W + 128);
|
||||
PBKDF2_SHA256_128_32_4way(tstate + 64, ostate + 64, W + 256, W + 256);
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 8; i++)
|
||||
for (k = 0; k < 4; k++)
|
||||
output[32 * j + k * 8 + i] = W[128 * j + 4 * i + k];
|
||||
}
|
||||
#endif /* HAVE_SHA256_4WAY */
|
||||
|
||||
#endif /* HAVE_SCRYPT_3WAY */
|
||||
|
||||
#ifdef HAVE_SCRYPT_6WAY
|
||||
static void scrypt_1024_1_1_256_24way(const uint32_t *input,
|
||||
uint32_t *output, uint32_t *midstate, unsigned char *scratchpad, int N)
|
||||
{
|
||||
uint32_t _ALIGN(128) tstate[24 * 8];
|
||||
uint32_t _ALIGN(128) ostate[24 * 8];
|
||||
uint32_t _ALIGN(128) W[24 * 32];
|
||||
uint32_t _ALIGN(128) X[24 * 32];
|
||||
uint32_t *V;
|
||||
int i, j, k;
|
||||
|
||||
V = (uint32_t *)(((uintptr_t)(scratchpad) + 63) & ~ (uintptr_t)(63));
|
||||
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 20; i++)
|
||||
for (k = 0; k < 8; k++)
|
||||
W[8 * 32 * j + 8 * i + k] = input[8 * 20 * j + k * 20 + i];
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 8; i++)
|
||||
for (k = 0; k < 8; k++)
|
||||
tstate[8 * 8 * j + 8 * i + k] = midstate[i];
|
||||
HMAC_SHA256_80_init_8way(W + 0, tstate + 0, ostate + 0);
|
||||
HMAC_SHA256_80_init_8way(W + 256, tstate + 64, ostate + 64);
|
||||
HMAC_SHA256_80_init_8way(W + 512, tstate + 128, ostate + 128);
|
||||
PBKDF2_SHA256_80_128_8way(tstate + 0, ostate + 0, W + 0, W + 0);
|
||||
PBKDF2_SHA256_80_128_8way(tstate + 64, ostate + 64, W + 256, W + 256);
|
||||
PBKDF2_SHA256_80_128_8way(tstate + 128, ostate + 128, W + 512, W + 512);
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 32; i++)
|
||||
for (k = 0; k < 8; k++)
|
||||
X[8 * 32 * j + k * 32 + i] = W[8 * 32 * j + 8 * i + k];
|
||||
scrypt_core_6way(X + 0 * 32, V, N);
|
||||
scrypt_core_6way(X + 6 * 32, V, N);
|
||||
scrypt_core_6way(X + 12 * 32, V, N);
|
||||
scrypt_core_6way(X + 18 * 32, V, N);
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 32; i++)
|
||||
for (k = 0; k < 8; k++)
|
||||
W[8 * 32 * j + 8 * i + k] = X[8 * 32 * j + k * 32 + i];
|
||||
PBKDF2_SHA256_128_32_8way(tstate + 0, ostate + 0, W + 0, W + 0);
|
||||
PBKDF2_SHA256_128_32_8way(tstate + 64, ostate + 64, W + 256, W + 256);
|
||||
PBKDF2_SHA256_128_32_8way(tstate + 128, ostate + 128, W + 512, W + 512);
|
||||
for (j = 0; j < 3; j++)
|
||||
for (i = 0; i < 8; i++)
|
||||
for (k = 0; k < 8; k++)
|
||||
output[8 * 8 * j + k * 8 + i] = W[8 * 32 * j + 8 * i + k];
|
||||
}
|
||||
#endif /* HAVE_SCRYPT_6WAY */
|
||||
|
||||
extern int scanhash_scrypt( struct work *work, uint32_t max_nonce,
|
||||
uint64_t *hashes_done, struct thr_info *mythr )
|
||||
{
|
||||
uint32_t *pdata = work->data;
|
||||
uint32_t *ptarget = work->target;
|
||||
uint32_t data[SCRYPT_MAX_WAYS * 20], hash[SCRYPT_MAX_WAYS * 8];
|
||||
uint32_t midstate[8];
|
||||
uint32_t n = pdata[19] - 1;
|
||||
const uint32_t Htarg = ptarget[7];
|
||||
int thr_id = mythr->id; // thr_id arg is deprecated
|
||||
int throughput = scrypt_best_throughput();
|
||||
int i;
|
||||
|
||||
#ifdef HAVE_SHA256_4WAY
|
||||
if (sha256_use_4way())
|
||||
throughput *= 4;
|
||||
#endif
|
||||
|
||||
for (i = 0; i < throughput; i++)
|
||||
memcpy(data + i * 20, pdata, 80);
|
||||
|
||||
sha256_init(midstate);
|
||||
sha256_transform(midstate, data, 0);
|
||||
|
||||
do {
|
||||
|
||||
for (i = 0; i < throughput; i++)
|
||||
data[i * 20 + 19] = ++n;
|
||||
|
||||
#if defined(HAVE_SHA256_4WAY)
|
||||
if (throughput == 4)
|
||||
scrypt_1024_1_1_256_4way(data, hash, midstate,
|
||||
scratchbuf, scratchbuf_size );
|
||||
else
|
||||
#endif
|
||||
#if defined(HAVE_SCRYPT_3WAY) && defined(HAVE_SHA256_4WAY)
|
||||
if (throughput == 12)
|
||||
scrypt_1024_1_1_256_12way(data, hash, midstate,
|
||||
scratchbuf, scratchbuf_size );
|
||||
else
|
||||
#endif
|
||||
#if defined(HAVE_SCRYPT_6WAY)
|
||||
if (throughput == 24)
|
||||
scrypt_1024_1_1_256_24way(data, hash, midstate,
|
||||
scratchbuf, scratchbuf_size );
|
||||
else
|
||||
#endif
|
||||
#if defined(HAVE_SCRYPT_3WAY)
|
||||
if (throughput == 3)
|
||||
scrypt_1024_1_1_256_3way(data, hash, midstate,
|
||||
scratchbuf, scratchbuf_size );
|
||||
else
|
||||
#endif
|
||||
scrypt_1024_1_1_256(data, hash, midstate, scratchbuf,
|
||||
scratchbuf_size );
|
||||
|
||||
for (i = 0; i < throughput; i++) {
|
||||
if (unlikely(hash[i * 8 + 7] <= Htarg && fulltest(hash + i * 8, ptarget))) {
|
||||
*hashes_done = n - pdata[19] + 1;
|
||||
pdata[19] = data[i * 20 + 19];
|
||||
work_set_target_ratio( work, hash );
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
} while (likely(n < max_nonce && !work_restart[thr_id].restart));
|
||||
|
||||
*hashes_done = n - pdata[19] + 1;
|
||||
pdata[19] = n;
|
||||
return 0;
|
||||
}
|
||||
|
||||
int64_t scrypt_get_max64() { return 0xfff; }
|
||||
|
||||
bool scrypt_miner_thread_init( int thr_id )
|
||||
{
|
||||
scratchbuf = scrypt_buffer_alloc( scratchbuf_size );
|
||||
if ( scratchbuf )
|
||||
return true;
|
||||
applog( LOG_ERR, "Thread %u: Scrypt buffer allocation failed", thr_id );
|
||||
return false;
|
||||
}
|
||||
|
||||
bool register_scrypt_algo( algo_gate_t* gate )
|
||||
{
|
||||
gate->optimizations = SSE2_OPT | AVX2_OPT;
|
||||
gate->miner_thread_init =(void*)&scrypt_miner_thread_init;
|
||||
gate->scanhash = (void*)&scanhash_scrypt;
|
||||
// gate->hash = (void*)&scrypt_1024_1_1_256_24way;
|
||||
gate->set_target = (void*)&scrypt_set_target;
|
||||
gate->get_max64 = (void*)&scrypt_get_max64;
|
||||
|
||||
if ( !opt_scrypt_n )
|
||||
scratchbuf_size = 1024;
|
||||
else
|
||||
scratchbuf_size = opt_scrypt_n;
|
||||
return true;
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user