Tanguy Pruvot
|
e7ae27137e
|
x11/qubit: remove some extra MyStreamSynchronize
only one per loop is required to prevent 100% cpu usage
|
10 years ago |
|
Tanguy Pruvot
|
4f43abb402
|
bmw512: indent and restore SM 3.0 compat
could be also the source of the problem seen with CUDA 7
restored the code before sp/klaus changes for SM 3.0 devices...
|
10 years ago |
|
Tanguy Pruvot
|
e6112e878d
|
cleanup: use unsigned throughput parameters
Yes, its a big commit, was waiting 1.6 to do that...
Sorry for your possible merge issues ;)
|
10 years ago |
|
Tanguy Pruvot
|
cafd4477d7
|
Handle a maximum of 16 gpus (vs 8 before)
Some cards have 2 gpus on board...
|
10 years ago |
|
Tanguy Pruvot
|
b521acb480
|
groestl: use sp bitslice enhancement, prepare SM 2.x variant
todo: simd512 SM 2.x variant (shfl op), and groestl/myriad functions
|
10 years ago |
|
Tanguy Pruvot
|
90efbdcece
|
simd cleanup
|
10 years ago |
|
Tanguy Pruvot
|
ec5a48f420
|
x11: small simd512 gpu_expand improvement
|
10 years ago |
|
Tanguy Pruvot
|
d0316220dd
|
simd512: restore full maxwell power (typo)
|
10 years ago |
|
Tanguy Pruvot
|
c88750332c
|
simd512: restore SM3/3.5 perfs
Simple change which affect all algos based on SIMD512
fresh, qubit, s3, x11 to x17...
|
10 years ago |
|
sp-hash
|
7d88e5cca1
|
Faster Simd
On maxwell compress1 and compress2 can be run in one run instead of two.(750TI + 20KHASH)
|
10 years ago |
|
Tanguy Pruvot
|
73f22b237a
|
Prepare trap of hardware/mem failures
|
10 years ago |
|
Tanguy Pruvot
|
93f4409dde
|
simd: then reindent the code
no changes, only error checks (cuda safe call)
|
10 years ago |
|
Tanguy Pruvot
|
b465fe6825
|
optimize x11 simd512 (+100KH/s)
change picked from tsiv repo
|
10 years ago |
|
Tanguy Pruvot
|
b4e690b486
|
sources: swith to UTF-8
|
11 years ago |
|
Tanguy Pruvot
|
194fda87c1
|
x11: restore simd host2dev memcpytosymbol to reduce used cmem
Remove define attempts for SM 2.1 devices, fermi is not compatible
|
11 years ago |
|
Tanguy Pruvot
|
d9ea5f72ce
|
Remove duplicated defines present in cuda_helper.h
also add cudaDeviceReset() on Ctrl+C for nvprof
|
11 years ago |
|
Tanguy Pruvot
|
6984a001d6
|
Win32 build fix after linux work (configure)
|
11 years ago |
|
Tanguy Pruvot
|
cf7351d138
|
x10 funcs cleanup, we dont need host constant tables
|
11 years ago |
|
Tanguy Pruvot
|
9d3d09103b
|
Try to restore compat with 2.1 devices (GTX 460)
|
11 years ago |
|
Christian Buchner
|
be5ba30131
|
massive speed upgrade for the SIMD hash. AMD, be afraid.
|
11 years ago |
|
Christian Buchner
|
44d38e3a9a
|
Simplification of the SIMD hash code (remove unnecessary lookup tables), increase X11 throughput value somewhat
|
11 years ago |
|
Christian Buchner
|
af07302b4b
|
v1.0 - Yo, I heard y'all like X11
|
11 years ago |
