AVX2 optimized code for AstroBWT
Added "astrobwt-avx2" parameter in config.json, it's turned off ("false") by default.
4-5% speedup on CPUs with proper AVX2 support (AMD Ryzen starting with Zen2, Intel Core starting with Haswell).
There will be no speedup on the following CPUs:
- Intel Pentium/Celeron don't support AVX2
- AMD Zen/Zen+ have only half-speed AVX
GCC compiled version is faster without AVX2, MSVC compiled version is faster with AVX2
This commit is contained in:
SChernykh
parent
8698b73036
commit
e22f798085
14 changed files with 563 additions and 15 deletions
164
src/crypto/astrobwt/sha3_256_avx2.inc
Normal file
164
src/crypto/astrobwt/sha3_256_avx2.inc
Normal file
|
|
@ -0,0 +1,164 @@
|
|||
;# XMRig
|
||||
;# Copyright 2010 Jeff Garzik <jgarzik@pobox.com>
|
||||
;# Copyright 2012-2014 pooler <pooler@litecoinpool.org>
|
||||
;# Copyright 2014 Lucas Jones <https://github.com/lucasjones>
|
||||
;# Copyright 2014-2016 Wolf9466 <https://github.com/OhGodAPet>
|
||||
;# Copyright 2016 Jay D Dee <jayddee246@gmail.com>
|
||||
;# Copyright 2017-2019 XMR-Stak <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
|
||||
;# Copyright 2018 Lee Clagett <https://github.com/vtnerd>
|
||||
;# Copyright 2018-2019 tevador <tevador@gmail.com>
|
||||
;# Copyright 2000 Transmeta Corporation <https://github.com/intel/msr-tools>
|
||||
;# Copyright 2004-2008 H. Peter Anvin <https://github.com/intel/msr-tools>
|
||||
;# Copyright 2018-2020 SChernykh <https://github.com/SChernykh>
|
||||
;# Copyright 2016-2020 XMRig <https://github.com/xmrig>, <support@xmrig.com>
|
||||
;#
|
||||
;# This program is free software: you can redistribute it and/or modify
|
||||
;# it under the terms of the GNU General Public License as published by
|
||||
;# the Free Software Foundation, either version 3 of the License, or
|
||||
;# (at your option) any later version.
|
||||
;#
|
||||
;# This program is distributed in the hope that it will be useful,
|
||||
;# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
;# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
;# GNU General Public License for more details.
|
||||
;#
|
||||
;# You should have received a copy of the GNU General Public License
|
||||
;# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
;#
|
||||
|
||||
ALIGN 64
|
||||
SHA3_256_AVX2_ASM:
|
||||
vzeroupper
|
||||
|
||||
mov qword ptr [rsp+8],rbx
|
||||
mov qword ptr [rsp+16],rsi
|
||||
mov qword ptr [rsp+24],rdi
|
||||
push rbp
|
||||
push r12
|
||||
push r13
|
||||
push r14
|
||||
push r15
|
||||
|
||||
sub rsp, 80
|
||||
movdqu xmmword ptr [rsp+64], xmm6
|
||||
movdqu xmmword ptr [rsp+48], xmm7
|
||||
movdqu xmmword ptr [rsp+32], xmm8
|
||||
movdqu xmmword ptr [rsp+16], xmm9
|
||||
movdqu xmmword ptr [rsp+0], xmm10
|
||||
sub rsp, 80
|
||||
movdqu xmmword ptr [rsp+64], xmm11
|
||||
movdqu xmmword ptr [rsp+48], xmm12
|
||||
movdqu xmmword ptr [rsp+32], xmm13
|
||||
movdqu xmmword ptr [rsp+16], xmm14
|
||||
movdqu xmmword ptr [rsp+0], xmm15
|
||||
|
||||
sub rsp,320
|
||||
lea rbp,[rsp+64]
|
||||
and rbp,-32
|
||||
vpxor xmm0,xmm0,xmm0
|
||||
xor edi,edi
|
||||
mov dword ptr [rbp],50462976
|
||||
mov r12,rdx
|
||||
mov dword ptr [rbp+4],169150212
|
||||
mov r14,rdx
|
||||
mov dword ptr [rbp+8],218436623
|
||||
shr r14,3
|
||||
and r12d,7
|
||||
mov dword ptr [rbp+12],135009046
|
||||
mov r13,r8
|
||||
mov byte ptr [rbp+16],9
|
||||
mov rsi,rcx
|
||||
mov ebx,edi
|
||||
vmovdqa ymmword ptr [rbp+32],ymm0
|
||||
vmovdqa ymmword ptr [rbp+64],ymm0
|
||||
vmovdqa ymmword ptr [rbp+96],ymm0
|
||||
vmovdqa ymmword ptr [rbp+128],ymm0
|
||||
vmovdqa ymmword ptr [rbp+160],ymm0
|
||||
vmovdqa ymmword ptr [rbp+192],ymm0
|
||||
vmovdqa ymmword ptr [rbp+224],ymm0
|
||||
test r14,r14
|
||||
je sha3_main_loop_end
|
||||
|
||||
sha3_main_loop:
|
||||
movzx eax,byte ptr [rbp+rbx]
|
||||
lea rcx,[rbp+32]
|
||||
lea rcx,[rcx+rax*8]
|
||||
mov rax,qword ptr [rsi]
|
||||
xor qword ptr [rcx],rax
|
||||
lea r15,[rbx+1]
|
||||
cmp rbx,16
|
||||
jne skip_keccak
|
||||
|
||||
lea rcx,[rbp+32]
|
||||
call KeccakF1600_AVX2_ASM
|
||||
|
||||
skip_keccak:
|
||||
cmp rbx,16
|
||||
mov rax,rdi
|
||||
cmovne rax,r15
|
||||
add rsi,8
|
||||
mov rbx,rax
|
||||
sub r14,1
|
||||
jne sha3_main_loop
|
||||
|
||||
sha3_main_loop_end:
|
||||
mov rdx,rdi
|
||||
test r12,r12
|
||||
je sha3_tail_loop_end
|
||||
mov r8,rdi
|
||||
|
||||
sha3_tail_loop:
|
||||
movzx eax,byte ptr [rdx+rsi]
|
||||
inc rdx
|
||||
shlx rcx,rax,r8
|
||||
or rdi,rcx
|
||||
add r8,8
|
||||
cmp rdx,r12
|
||||
jb sha3_tail_loop
|
||||
|
||||
sha3_tail_loop_end:
|
||||
movzx eax,byte ptr [rbp+rbx]
|
||||
lea rdx,[rbp+32]
|
||||
lea rdx,[rdx+rax*8]
|
||||
mov ecx,6
|
||||
lea rax,[r12*8]
|
||||
shlx rcx,rcx,rax
|
||||
xor rcx,qword ptr [rdx]
|
||||
mov eax,1
|
||||
shl rax,63
|
||||
xor rcx,rdi
|
||||
mov qword ptr [rdx],rcx
|
||||
xor qword ptr [rbp+104],rax
|
||||
|
||||
lea rcx,[rbp+32]
|
||||
call KeccakF1600_AVX2_ASM
|
||||
|
||||
vmovups ymm0,ymmword ptr [rbp+32]
|
||||
vmovups ymmword ptr [r13],ymm0
|
||||
vzeroupper
|
||||
|
||||
add rsp,320
|
||||
|
||||
movdqu xmm15, xmmword ptr [rsp]
|
||||
movdqu xmm14, xmmword ptr [rsp+16]
|
||||
movdqu xmm13, xmmword ptr [rsp+32]
|
||||
movdqu xmm12, xmmword ptr [rsp+48]
|
||||
movdqu xmm11, xmmword ptr [rsp+64]
|
||||
add rsp, 80
|
||||
movdqu xmm10, xmmword ptr [rsp]
|
||||
movdqu xmm9, xmmword ptr [rsp+16]
|
||||
movdqu xmm8, xmmword ptr [rsp+32]
|
||||
movdqu xmm7, xmmword ptr [rsp+48]
|
||||
movdqu xmm6, xmmword ptr [rsp+64]
|
||||
add rsp, 80
|
||||
|
||||
pop r15
|
||||
pop r14
|
||||
pop r13
|
||||
pop r12
|
||||
pop rbp
|
||||
mov rbx,qword ptr [rsp+8]
|
||||
mov rsi,qword ptr [rsp+16]
|
||||
mov rdi,qword ptr [rsp+24]
|
||||
|
||||
ret
|
||||
Loading…
Add table
Add a link
Reference in a new issue