mirror of
https://github.com/RPCS3/rpcs3
synced 2024-09-05 07:56:33 +00:00
SPU LLVM: Minor SUMB AVX-512 path optimization
- Tweak shuffle to allow LLVM to emit a cheap blend instruction instead of the expensive VPERMI2W instruction
This commit is contained in:
parent
6532d2b650
commit
813f7b50c1
|
@ -7709,7 +7709,7 @@ public:
|
|||
|
||||
const auto ax = vdbpsadbw(a, zeroes, 0);
|
||||
const auto bx = vdbpsadbw(b, zeroes, 0);
|
||||
set_vr(op.rt, shuffle2(ax, bx, 0, 8, 2, 10, 4, 12, 6, 14));
|
||||
set_vr(op.rt, shuffle2(ax, bx, 0, 9, 2, 11, 4, 13, 6, 15));
|
||||
return;
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in a new issue