Jeff Garzik
|
0b67740707
|
Pass max-nonce as arg to each sha256 algo.
Should be an equivalent transformation, with no behavior changes.
|
2011-01-29 00:56:24 -05:00 |
|
Jeff Garzik
|
8504cf4803
|
sha256_4way minor optimizations
http://www.bitcoin.org/smf/index.php?topic=820.msg40022#msg40022
Credit: BeeCee1
|
2011-01-29 00:36:32 -05:00 |
|
Jeff Garzik
|
0ee24c00ce
|
sha256_4way: work around gcc 4.5.x bug by always inlining ROTR and SHR
|
2010-12-18 16:29:07 -05:00 |
|
Jeff Garzik
|
8ca6ffa8a9
|
sha256_4way: do not include unnecessary headers, when !4way
Reported by lfm
|
2010-12-06 00:59:59 -05:00 |
|
Jeff Garzik
|
339ddf4d75
|
Move sha256_generic into its own .o build output. Const-ify midstate param.
|
2010-11-27 04:31:32 -05:00 |
|
Jeff Garzik
|
6288d943ab
|
sha256_4way: patch proper nonce into data block
|
2010-11-27 03:50:12 -05:00 |
|
Jeff Garzik
|
86eb37d631
|
Improve and modularize compile-time CPU detection.
Ideally, we should move this to autoconf.
|
2010-11-27 00:46:59 -05:00 |
|
Jeff Garzik
|
500759cea1
|
s/__SSE__/__SSE2__/
|
2010-11-27 00:12:28 -05:00 |
|
Jeff Garzik
|
eed9b3c7df
|
sha256_4way: perform 16m hashes, not 64k, per invocation
|
2010-11-26 23:15:38 -05:00 |
|
Jeff Garzik
|
35ea649d97
|
Improve hash performance statistics.
|
2010-11-26 23:12:24 -05:00 |
|
Jeff Garzik
|
c639149977
|
Add tcatm's 4way SSE2 sha256 implementation.
|
2010-11-26 19:04:48 -05:00 |
|