869a042330
m7: update vstudio project
...
need a new mpir lib, so use the x15/17 branch if you dont have it
reset xml to DOS format, as VStudio always change it...
PS: use "git diff -w <hash>" to show the diff without spaces/crlf ;)
10 years ago
c9ce05a82b
m7: fine tune threads and max registers
...
TODO:
on 750 Ti, this version of ripemd seems very slow...
It could be made in 3ms and take actually 25ms
whirlpool can also be optimized, with last djm code...
10 years ago
fcd381cda2
m7: forgot to indent some cuda files
...
and remove unused variables...
10 years ago
871add21f1
m7: adapt cpu-miner for m7 stratum (working)
...
proper commit based on djm34's work
10 years ago
bf55536ba6
m7, add sources from djm34 repo (v6+)
...
fix most part of indentation and headers
but ive copied whirlpool and x17 stuff in a new m7 folder
10 years ago
10314d844f
whirlpool: remove dead code, win 2ms in final hash
10 years ago
52dade56b5
heavy: warnings and tabs (no changes)
10 years ago
ee2f6dece5
x17: update vstudio project
10 years ago
64e8cd3f98
add x17 algo, cleaned djm34 commit
...
todo: visual studio...
10 years ago
5d6a489b98
scrypt: fix implicit function declaration
10 years ago
2c24bc93d4
Makefile: luffa was using more than 80 regs (10 vs 14ms)
...
add easy switch for nvcc target arch
and move duplicated sha2 to sph folder
10 years ago
5cf024cc5d
whirl: add missing merkle for some pools
10 years ago
b3becb67dd
groestl: small optimisation (nist5 + 100kH on a 750Ti)
...
But, almost nothing on X15, no big changes...
10 years ago
0867fb15c6
output: add the --color parameter (-C)
...
disabled by default or if syslog option is set
Signed-off-by: Tanguy Pruvot <tanguy.pruvot@gmail.com>
10 years ago
d928317981
vs2013: hamsi need 72 registers, simd 64
10 years ago
09ecb490c6
vs2013: simplify project options
10 years ago
3f6ebc10cc
whirlpool: x64 asm is very slow (30ms win32 vs 90)
10 years ago
91da15aa75
windows: intercept Ctrl+C to use nvprof
10 years ago
b4e690b486
sources: swith to UTF-8
10 years ago
a586cee493
quark: dos2unix files to reduce problems later
10 years ago
82981f9736
update README
10 years ago
912ef1215d
small reg tunes, rename whirlcoin to whirl
10 years ago
7d430edc25
x15: optimize by 2ms (39ms to 37)
...
and clean whirlpool ifdefs, cost too much to keep both methods
10 years ago
0c27bd42a4
whirlcoin: update vstudio project
10 years ago
1fbcbbacc4
Add whirlcoin and optimize x11 luffa (maxrregcount)
10 years ago
4bc23048b5
x15: use djm34 code with asm xor64 + my rot64
...
some optimizations could be done later, after whirlcoin integration
10 years ago
194fda87c1
x11: restore simd host2dev memcpytosymbol to reduce used cmem
...
Remove define attempts for SM 2.1 devices, fermi is not compatible
10 years ago
bc2eb75758
Add fresh algo (based on djm34 code)
...
Cleaned up and adapted to my changes (cputest added)
Remove Makefile.in which should be in gitignore
(Plz refresh it with ./config.sh to compile on linux)
10 years ago
d9ea5f72ce
Remove duplicated defines present in cuda_helper.h
...
also add cudaDeviceReset() on Ctrl+C for nvprof
10 years ago
a3ea36a5f9
cudaDeviceReset on Ctrl+C for nvprof
10 years ago
e1aa028b9f
x15: optimize, adds some kH/s
10 years ago
a9a3ad8afc
cuda: check for errors on cuda mem alloc
10 years ago
6984a001d6
Win32 build fix after linux work (configure)
10 years ago
cf7351d138
x10 funcs cleanup, we dont need host constant tables
10 years ago
35c0eb5512
x15: optimize the algo
10 years ago
17e10400a4
Switch to shader model 5.0 for the GTX 750
10 years ago
81d7e0421d
x15 now works
10 years ago
8e32e5ea09
cputest: add other hashes to cpu tests
10 years ago
9d3d09103b
Try to restore compat with 2.1 devices (GTX 460)
10 years ago
2c8ccd0edc
refresh pregenerated linux make files
10 years ago
2c9e4127de
libs: only copy the 32 or 64bit in output folder
10 years ago
06763c20b1
Implement x14 (cuda + cpu functions)
...
Project was updated for VS2013 and CUDA SDK 6.5
add also a --cputest function to dump cpu hash results
TODO: x15 is not fully functional, but first loop seems ok
Signed-off-by: Tanguy Pruvot <tanguy.pruvot@gmail.com>
10 years ago
df840b7dfb
commit missing Makefile.am
10 years ago
6c346eef64
bump to revision V1.2
10 years ago
d99b91ea65
adding third party X13 and Diamond Groestl code contributions.
10 years ago
3b21069504
bump to revision V1.1 with Killer Groestl
10 years ago
ac40fac038
The ccminer console output looks a bit more like cudaMiner now. 64 bit Windows compilation should no longer take "forever" but only "annoyingly long"
10 years ago
be5ba30131
massive speed upgrade for the SIMD hash. AMD, be afraid.
10 years ago
44d38e3a9a
Simplification of the SIMD hash code (remove unnecessary lookup tables), increase X11 throughput value somewhat
10 years ago
baf6c9e4e3
fix syntax problem in Makefile.am
10 years ago
Tanguy Pruvot