mirror of
https://github.com/GOSTSec/ccminer
synced 2025-01-10 23:08:02 +00:00
5bf1f98200
X11+ algos and quark are not compatible for the moment
but these ones are :
Benchmark results for Gigabyte GTX 460 (SM 2.1 / 1 GB):
blakecoin : 159090.5 kH/s, 1 MB, 1048576 thr.
blake : 70208.9 kH/s, 1 MB, 1048576 thr.
bmw : 122802.6 kH/s, 65 MB, 2097152 thr.
deep : 3533.6 kH/s, 33 MB, 524288 thr.
fugue256 : 43177.9 kH/s, 17 MB, 524288 thr.
heavy : 4118.2 kH/s, 147 MB, 524032 thr.
keccak : 18673.1 kH/s, 129 MB, 2097152 thr.
luffa : 28816.0 kH/s, 257 MB, 4194304 thr.
lyra2 : 213.7 kH/s, 570 MB, 65536 thr.
mjollnir : 3895.6 kH/s, 147 MB, 524032 thr.
nist5 : 1101.4 kH/s, 67 MB, 1048576 thr.
penta : 501.6 kH/s, 21 MB, 327680 thr.
skein : 5432.4 kH/s, 65 MB, 1048576 thr.
skein2 : 6788.9 kH/s, 33 MB, 524288 thr.
whirlpool : 688.5 kH/s, 33 MB, 524288 thr.
zr5 : 122.5 kH/s, 86 MB, 262144 thr.
113 lines
2.5 KiB
Plaintext
113 lines
2.5 KiB
Plaintext
/*
|
|
* Keccak 256
|
|
*
|
|
*/
|
|
|
|
extern "C"
|
|
{
|
|
#include "sph/sph_shavite.h"
|
|
#include "sph/sph_simd.h"
|
|
#include "sph/sph_keccak.h"
|
|
|
|
#include "miner.h"
|
|
}
|
|
|
|
#include "cuda_helper.h"
|
|
|
|
static uint32_t *d_hash[MAX_GPUS];
|
|
|
|
extern void keccak256_cpu_init(int thr_id, uint32_t threads);
|
|
extern void keccak256_cpu_free(int thr_id);
|
|
extern void keccak256_setBlock_80(void *pdata,const void *ptarget);
|
|
extern uint32_t keccak256_cpu_hash_80(int thr_id, uint32_t threads, uint32_t startNounce, uint32_t *d_hash, int order);
|
|
|
|
// CPU Hash
|
|
extern "C" void keccak256_hash(void *state, const void *input)
|
|
{
|
|
uint32_t _ALIGN(64) hash[16];
|
|
sph_keccak_context ctx_keccak;
|
|
|
|
sph_keccak256_init(&ctx_keccak);
|
|
sph_keccak256 (&ctx_keccak, input, 80);
|
|
sph_keccak256_close(&ctx_keccak, (void*) hash);
|
|
|
|
memcpy(state, hash, 32);
|
|
}
|
|
|
|
static bool init[MAX_GPUS] = { 0 };
|
|
|
|
extern "C" int scanhash_keccak256(int thr_id, struct work* work, uint32_t max_nonce, unsigned long *hashes_done)
|
|
{
|
|
uint32_t _ALIGN(64) endiandata[20];
|
|
uint32_t *pdata = work->data;
|
|
uint32_t *ptarget = work->target;
|
|
const uint32_t first_nonce = pdata[19];
|
|
uint32_t throughput = cuda_default_throughput(thr_id, 1U << 21); // 256*256*8*4
|
|
if (init[thr_id]) throughput = min(throughput, max_nonce - first_nonce);
|
|
|
|
if (opt_benchmark)
|
|
ptarget[7] = 0x00ff;
|
|
|
|
if (!init[thr_id]) {
|
|
cudaSetDevice(device_map[thr_id]);
|
|
|
|
CUDA_SAFE_CALL(cudaMalloc(&d_hash[thr_id], throughput * 64));
|
|
keccak256_cpu_init(thr_id, throughput);
|
|
|
|
init[thr_id] = true;
|
|
}
|
|
|
|
for (int k=0; k < 20; k++) {
|
|
be32enc(&endiandata[k], pdata[k]);
|
|
}
|
|
|
|
keccak256_setBlock_80((void*)endiandata, ptarget);
|
|
do {
|
|
int order = 0;
|
|
|
|
*hashes_done = pdata[19] - first_nonce + throughput;
|
|
|
|
uint32_t foundNonce = keccak256_cpu_hash_80(thr_id, throughput, pdata[19], d_hash[thr_id], order++);
|
|
if (foundNonce != UINT32_MAX)
|
|
{
|
|
uint32_t _ALIGN(64) vhash64[8];
|
|
be32enc(&endiandata[19], foundNonce);
|
|
keccak256_hash(vhash64, endiandata);
|
|
|
|
if (vhash64[7] <= ptarget[7] && fulltest(vhash64, ptarget)) {
|
|
work_set_target_ratio(work, vhash64);
|
|
pdata[19] = foundNonce;
|
|
return 1;
|
|
}
|
|
else {
|
|
gpulog(LOG_WARNING, thr_id, "result for nonce %08x does not validate on CPU!", foundNonce);
|
|
}
|
|
}
|
|
|
|
if ((uint64_t) pdata[19] + throughput > max_nonce) {
|
|
break;
|
|
}
|
|
|
|
pdata[19] += throughput;
|
|
|
|
} while (!work_restart[thr_id].restart);
|
|
|
|
return 0;
|
|
}
|
|
|
|
// cleanup
|
|
extern "C" void free_keccak256(int thr_id)
|
|
{
|
|
if (!init[thr_id])
|
|
return;
|
|
|
|
cudaThreadSynchronize();
|
|
|
|
cudaFree(d_hash[thr_id]);
|
|
|
|
keccak256_cpu_free(thr_id);
|
|
|
|
cudaDeviceSynchronize();
|
|
init[thr_id] = false;
|
|
}
|