GOSTSec
/
ccminer-gostd-lite
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
GOSTCoin CUDA miner project, compatible with most nvidia cards, containing only gostd algo
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
877 Commits
1 Branch
55 Tags
65 MiB
Tree: cbede12c47
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'cbede12c47'
${ noResults }
ccminer-gostd-lite/equi/blake2/blake2-round.h

86 lines
2.5 KiB
Raw Normal View History Unescape

Interface nicehash djeZo equihash solver (squashed) Todo: - send block height via stratum protocol (encoded in jobid?) - remove equi/blake2 cpu algorithm to use common one the extranonce imcompatibility is related to the solver nonce data, offsets may be reversed in nheqminer, to check... The solver was adapted for SM 3.0+ support (no perf changes) Note: The solver was not improved on purpose, to be able compare the two miners performances (nheqminer 0.5c the last open sourced, and ccminer) Signed-off-by: Tanguy Pruvot <tanguy.pruvot@gmail.com> stratum: code cleanup, move equi fns in equi folder
8 years ago
#define _mm_roti_epi64(x, c) \
(-(c) == 32) ? _mm_shuffle_epi32((x), _MM_SHUFFLE(2,3,0,1)) \
: (-(c) == 24) ? _mm_shuffle_epi8((x), r24) \
: (-(c) == 16) ? _mm_shuffle_epi8((x), r16) \
: (-(c) == 63) ? _mm_xor_si128(_mm_srli_epi64((x), -(c)), _mm_add_epi64((x), (x))) \
: _mm_xor_si128(_mm_srli_epi64((x), -(c)), _mm_slli_epi64((x), 64-(-(c))))
#define G1(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h) \
row1l = _mm_add_epi64(row1l, row2l); \
row1h = _mm_add_epi64(row1h, row2h); \
\
row4l = _mm_xor_si128(row4l, row1l); \
row4h = _mm_xor_si128(row4h, row1h); \
\
row4l = _mm_roti_epi64(row4l, -32); \
row4h = _mm_roti_epi64(row4h, -32); \
\
row3l = _mm_add_epi64(row3l, row4l); \
row3h = _mm_add_epi64(row3h, row4h); \
\
row2l = _mm_xor_si128(row2l, row3l); \
row2h = _mm_xor_si128(row2h, row3h); \
\
row2l = _mm_roti_epi64(row2l, -24); \
row2h = _mm_roti_epi64(row2h, -24); \
#define G2(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h) \
row1l = _mm_add_epi64(row1l, row2l); \
row1h = _mm_add_epi64(row1h, row2h); \
\
row4l = _mm_xor_si128(row4l, row1l); \
row4h = _mm_xor_si128(row4h, row1h); \
\
row4l = _mm_roti_epi64(row4l, -16); \
row4h = _mm_roti_epi64(row4h, -16); \
\
row3l = _mm_add_epi64(row3l, row4l); \
row3h = _mm_add_epi64(row3h, row4h); \
\
row2l = _mm_xor_si128(row2l, row3l); \
row2h = _mm_xor_si128(row2h, row3h); \
\
row2l = _mm_roti_epi64(row2l, -63); \
row2h = _mm_roti_epi64(row2h, -63); \
#define DIAGONALIZE(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h) \
t0 = _mm_alignr_epi8(row2h, row2l, 8); \
t1 = _mm_alignr_epi8(row2l, row2h, 8); \
row2l = t0; \
row2h = t1; \
\
t0 = row3l; \
row3l = row3h; \
row3h = t0; \
\
t0 = _mm_alignr_epi8(row4h, row4l, 8); \
t1 = _mm_alignr_epi8(row4l, row4h, 8); \
row4l = t1; \
row4h = t0;
#define UNDIAGONALIZE(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h) \
t0 = _mm_alignr_epi8(row2l, row2h, 8); \
t1 = _mm_alignr_epi8(row2h, row2l, 8); \
row2l = t0; \
row2h = t1; \
\
t0 = row3l; \
row3l = row3h; \
row3h = t0; \
\
t0 = _mm_alignr_epi8(row4l, row4h, 8); \
t1 = _mm_alignr_epi8(row4h, row4l, 8); \
row4l = t1; \
row4h = t0;
#define BLAKE2_ROUND(row1l,row1h,row2l,row2h,row3l,row3h,row4l,row4h) \
G1(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h); \
G2(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h); \
\
DIAGONALIZE(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h); \
\
G1(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h); \
G2(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h); \
\
UNDIAGONALIZE(row1l,row2l,row3l,row4l,row1h,row2h,row3h,row4h);