DragonX/xmrig-hac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity
2,640 Commits 2 Branches 1 Tag
5f8b767dbe7cefb2590804cbeea024b002884057
Commit Graph

525 Commits

Author SHA1 Message Date
cohcho
6f29a548e0 RxVM: fix compilation error 2020-10-07 09:27:25 +00:00
SChernykh
6a25fa75c7 RandomX: allocate 2 MB pages for generated code, if possible 
+0.2% boost on Ryzen 7 3700X
 2020-10-07 10:35:10 +02:00
xmrig
e99806f109 Merge pull request #1870 from cohcho/fix_miner_state_machine 
Miner: fix state machine
 2020-10-07 12:25:17 +07:00
cohcho
e6e4519d96 RxVm: fix randomx_create_vm call 
randomx_create_vm requires either cache or dataset, but not both
 2020-10-06 19:45:43 +00:00
cohcho
6627c1472e Nonce: refactor static init 2020-10-06 13:34:19 +00:00
xmrig
3f85d142d9 Merge pull request #1864 from cohcho/soft_aes_optimization2 
soft_aes: fix previous optimization
 2020-10-05 12:20:41 +07:00
cohcho
a5f4548b27 soft_aes: fix previous optimization 
Previously removed unrolled variant is faster on some CPUs
Some CPUs are faster with added unrolled variant
The best variant depends on number of threads on some CPUs
 2020-10-04 14:47:58 +00:00
SChernykh
d5dd4ce89f RandomX: removed rx/loki 
Loki forks to PoS on October 9th.
 2020-10-02 17:02:52 +02:00
XMRig
92835b608f Renamed WITH_SSE to WITH_SSE4_1 and make it work on all platforms. 2020-10-01 11:00:08 +07:00
SChernykh
d498274ca9 RandomX: optimized soft AES code 
Unrolled loop was 5-10% slower depending on CPU.
 2020-09-29 21:22:11 +02:00
xmrig
c0c0e61f5e Merge pull request #1858 from SChernykh/dev 
RandomX: removed duplicate constants in Blake2b
 2020-09-27 16:51:03 +07:00
SChernykh
fbb8e955aa RandomX: removed duplicate constatns in Blake2b 2020-09-27 11:50:08 +02:00
xmrig
a860d88378 Merge pull request #1857 from SChernykh/dev 
RandomX: isolate SSE4.1 code to fix crashes on old CPUs
 2020-09-27 16:47:56 +07:00
SChernykh
36592c2fe0 RandomX: isolate SSE4.1 code to fix crashes on old CPUs 2020-09-27 11:46:32 +02:00
cohcho
37a47652b9 soft_aes: fix previous optimization 
the best order of hash/fill/prefetch depends on hw/soft AES
only hw AES is faster after previous optimization
 2020-09-25 15:26:19 +00:00
SChernykh
c4a083aa8c Fix for ARM compilation 2020-09-23 11:44:08 +02:00
SChernykh
b8d604bec4 RandomX improved performance of GCC compiled binaries 
JIT compilator was slower compared to MSVC compiled binary. Up to +0.1% speedup on rx/wow in Linux.
 2020-09-22 13:48:11 +02:00
SChernykh
60faba76e8 RandomX: AES improvements 
- A bit faster hardware AES code when compiled with MSVC
- More reliable software AES benchmark
 2020-09-21 17:51:08 +02:00
SChernykh
1e38eb3f4f RandomX refactoring, moved more stuff to compile time 
Small x86 JIT compiler speedup.
 2020-09-18 20:51:25 +02:00
SChernykh
3ef7c9b5e6 RandomX: returned old soft AES impl and auto-select between the two 2020-09-15 20:48:27 +02:00
cohcho
3068b7adbe reserve at most 1 bit for wrapping detection 2020-09-13 18:42:16 +00:00
SChernykh
f126fa112e RandomX: added performance profiler (for developers) 
Also optimized Blake2b SSE4.1 code size to avoid code cache pollution.
 2020-09-12 23:07:52 +02:00
xmrig
09bffdfb47 Merge pull request #1827 from cohcho/nonce_iteration_without_tests 
nonce iteration optimization
 2020-09-10 19:33:23 +07:00
SChernykh
9a53285c5f RandomX: added SSE4.1-optimized Blake2b 
+0.15% on `rx/0`
+0.3% on `rx/wow`
 2020-09-10 14:28:40 +02:00
cohcho
b183af0953 fix nonce mask 2020-09-09 19:39:52 +00:00
cohcho
5cf1494401 nonce iteration optimization 
efficient and correct nonce iteration without duplicates
 2020-09-09 10:03:37 +00:00
SChernykh
f26d4274fc RandomX: added parameter for scratchpad prefetch mode 
`scratchpad_prefetch_mode` can have 4 values:
0: off
1: use `prefetcht0` instruction (default, same as previous XMRig versions)
2: use `prefetchnta` instruction (faster on Coffee Lake and a few other CPUs)
3: use `mov` instruction
 2020-09-04 16:16:07 +02:00
XMRig
e254283089 Fix compile warnings. 2020-08-24 10:04:46 +07:00
XMRig
42576e91dc Fix compile warning. 2020-08-23 14:22:08 +07:00
XMRig
3baf926bb7 Fix compile warning 2020-08-17 06:08:14 +07:00
XMRig
e5e5b48216 Fixed compile warning and updated build.uv.sh. 2020-08-16 16:03:27 +07:00
SChernykh
07d9abc90e RandomX JIT: optimized address mask calculation 2020-08-12 16:45:16 +02:00
XMRig
d3ddb76962 Fixed RandomX cache initialization if 1GB pages fails to allocate on a first NUMA node. 2020-08-01 12:30:02 +07:00
SChernykh
3d78f30171 Try to allocate scratchpad from dataset's 1 GB huge pages, if normal huge pages are not available 2020-07-31 13:37:22 +02:00
SChernykh
5aae95eddc Force 2 MB pages size in allocateLargePagesMemory() on Linux 2020-07-31 09:55:49 +02:00
XMRig
b2b54cbe82 Cleanup 2020-07-22 21:27:40 +07:00
SChernykh
51370682f3 Fixed RandomX initialization for VS debug builds 2020-07-21 10:10:07 +02:00
XMRig
3526c1335d Added command line options --cache-qos (--randomx-cache-qos) and --argon2-impl (--cpu-argon2-impl). 2020-07-20 09:17:59 +07:00
XMRig
da244e7acf Fixed build without MSR support. 2020-07-16 05:15:35 +07:00
SChernykh
e8dbb8ca9f Removed cache QoS warning at exit on unsupported CPUs 2020-07-13 20:43:49 +02:00
SChernykh
a3f4d91ad7 Cache QoS: fix for seting MSR 2020-07-13 20:30:44 +02:00
SChernykh
5af50b854c RandomX: added cache QoS support 
False by default. If set to true, all non-mining CPU cores will not have access to L3 cache.
 2020-07-13 17:23:18 +02:00
Jim Huang
3343e373e8 Adopt new SSE2NEON and reduce ARM-specific changes 
This patch updated SSE2NEON [1], which contains more functions
provided by Intel intrinsics, only implemented with NEON-based
counterparts to produce the exact semantics of the intrinsics.
Consequently, ARM-specific changes against CryptoNight_arm can
be reduced as well.

[1] https://github.com/DLTcollab/sse2neon/
 2020-07-11 01:55:11 +08:00
SChernykh
08d71d5144 RandomX: tweaked Ryzen code 
Very small speedup
 2020-07-05 16:06:59 +02:00
SChernykh
038629c093 Print error message when MSR mod fails 
Make sure user knows that hashrate is worse than it could be.
 2020-06-26 19:54:06 +02:00
SChernykh
683ca745a8 KawPow: optimized CPU share verification 
- 2 times faster CPU share verification (11 -> 5 ms)
- 1.5 times faster light cache initialization
 2020-06-26 12:31:26 +02:00
SChernykh
3292679e66 KawPow: fixed crash on old CPUs 
- Use `popcnt` instruction only when it's supported
 2020-06-10 21:49:43 +02:00
XMRig
a4032b9f4f Merge branch 'dev' into evo 2020-06-07 21:25:31 +07:00
SChernykh
63dd56831e Fixed GCC 10.1 issues 
- Fixed uninitialized `state->x` warning
- Fixed broken code with `-O3` or `-Ofast`
 2020-06-07 16:23:17 +02:00
XMRig
6fde2cc703 Merge branch 'dev' into evo 2020-06-07 20:15:12 +07:00