Tanguy Pruvot d43dc9a021 use blake512 sp kernels on SM 5+ (80+64) ...

import and keep my code for older archs, like skein 64

reduce the gap between our versions...

+150kH x11   GTX 960 / +30kH  750Ti
+900kH quark GTX 960 / +230kH 750Ti

2015-10-24 13:43:22 +02:00

..

cuda_bmw512_30.cu

bmw512: save a few KBs, ifdef 80-bytes kernel

2015-10-24 07:30:57 +02:00

cuda_bmw512.cu

bmw512: save a few KBs, ifdef 80-bytes kernel

2015-10-24 07:30:57 +02:00

cuda_jh512.cu

jh512: rewrite and optimize with asm swap

2015-06-16 08:20:48 +02:00

cuda_quark_blake512_sp.cuh

use blake512 sp kernels on SM 5+ (80+64)

2015-10-24 13:43:22 +02:00

cuda_quark_blake512.cu

use blake512 sp kernels on SM 5+ (80+64)

2015-10-24 13:43:22 +02:00

cuda_quark_compactionTest.cu

algos: add functions to free allocated resources

2015-09-25 07:51:57 +02:00

cuda_quark_groestl512_sm20.cu

algos: free allocated mem for algo switch

2015-10-08 21:35:30 +02:00

cuda_quark_groestl512.cu

algos: free allocated mem for algo switch

2015-10-08 21:35:30 +02:00

cuda_quark_keccak512.cu

windows: fix missing off_t include

2015-06-08 16:58:12 +02:00

cuda_skein512_sp.cuh

skein: cleanup, strip uint2x4.h + update vstudio

2015-10-23 13:32:18 +02:00

cuda_skein512.cu

import sp skein512 unrolled 64-bytes kernel (+0,6% x11)

2015-10-23 09:43:20 +02:00

groestl_functions_quad.h

groestl: rename included cuda files

2015-04-06 23:46:34 +02:00

groestl_transf_quad.h

groestl: rename included cuda files

2015-04-06 23:46:34 +02:00

quarkcoin.cu

use blake512 sp kernels on SM 5+ (80+64)

2015-10-24 13:43:22 +02:00