SChernykh
ff82ca57f2
RandomX: rewrote dataset read code
...
Unified code for AMD and Intel
1% faster on Intel
0.15% faster on AMD Ryzen
2021-05-20 12:45:42 +02:00
SChernykh
d443dd86f1
RandomX: added BMI2 version for scratchpad prefetch
...
Saves 1 instruction and 1 byte in the main loop.
2021-05-19 17:52:16 +02:00
SChernykh
3477f9fbc1
RandomX: optimized IMUL_RCP instruction
...
+0.4% on AMD Zen2
+0.3% on AMD Zen3
+0.1% on Intel SandyBridge
+0.3% on rx/wow on Intel SandyBridge
2021-04-19 17:43:58 +02:00
SChernykh
78922a0772
RandomX JIT x86: remove unnecessary instructions
...
Adopted from https://github.com/tevador/RandomX/pull/201
2021-01-23 22:28:50 +01:00
SChernykh
5efd00abec
Another dataset AVX2 init speedup (+3.8% faster on Zen3)
2020-12-19 19:46:31 +01:00
SChernykh
515a85e66c
Dataset initialization with AVX2 (WIP)
2020-12-18 14:53:54 +01:00
SChernykh
9f1753cc4f
Optimized CFROUND
2020-01-22 20:11:00 +01:00
SChernykh
f80177cbd3
Optimizations for AMD Bulldozer
...
- Added support for XOP instructions
- Enabled Ryzen code for Bulldozer because it's faster there too
2020-01-15 13:04:26 +01:00
SChernykh
3a2941b719
Fix for 1st-gen Ryzen crashes
2019-12-27 12:40:38 +02:00
SChernykh
7459677fd5
Add vzeroupper for processors with AVX
...
To avoid false dependencies on upper 128 bits of YMM registers.
2019-12-18 09:12:25 +01:00
SChernykh
763691fa4b
More optimizations for Ryzen
2019-12-09 20:29:05 +01:00
SChernykh
d0df824599
Optimized dataset read for Ryzen CPUs
...
Removed register dependency in dataset read, +0.8% speedup on average.
2019-12-08 16:14:02 +01:00
SChernykh
2322e3bcf7
RandomX: optimized loading from scratchpad
...
Prefetches scratchpad data as soon as possible to calculate data address for the next load.
Up to ~1.4% speedup on Ryzen 7 3700X @ 4.1 GHz, RAM 3200 MHz 14-14-14-28 with optimized sub-timings:
Variant|Before H/S|After H/S
-------|----------|---------
rx/0|8663|8777
rx/wow|9867|10009
rx/loki|8652|8731
2019-09-11 19:10:01 +02:00
SChernykh
6eb9d0963b
Integrated RandomX, added RandomXL (Loki)
2019-07-01 20:11:51 +02:00