rt/snapraid
1
0
Fork 0
mirror of https://github.com/amadvance/snapraid.git synced 2026-10-26 10:51:54 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

Optimize AVX512 gen1 parity with the vpternlogq instruction

Browse source
This commit is contained in:
Andrea Mazzoleni 2026-05-26 23:39:59 +02:00
parent d773f21c1e
commit d67cdd8b9d
1 changed files with 13 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

15
raid/x86.c
View file

@ -208,9 +208,20 @@ void raid_gen1_avx512bw(int nd, size_t size, void **vv)
for (i = 0; i < size; i += 64) {
asm volatile ("vmovdqa64 %0,%%zmm0" : : "m" (v[l][i]));
for (d = l - 1; d >= 0; --d) {
asm volatile ("vpxorq %0,%%zmm0,%%zmm0" : : "m" (v[d][i]));
for (d = l - 1; d >= 1; d -= 2) {
asm volatile (
"vmovdqa64 %0,%%zmm1\n\t"
"vpternlogq $0x96,%1,%%zmm1,%%zmm0"
:
: "m" (v[d][i]), "m" (v[d-1][i])
);
}
if (d == 0) {
asm volatile ("vpxorq %0, %%zmm0,%%zmm0" : : "m" (v[0][i]));
}
asm volatile ("vmovntdq %%zmm0,%0" : "=m" (p[i]));
}