The-Homebrew-Cloud/dolphin
2
0
Fork 0
mirror of https://github.com/dolphin-emu/dolphin.git synced 2025-01-08 15:20:45 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #13211 from Sintendo/blendvpd

Browse Source 
Jit_FloatingPoint: fselx - Prefer BLENDVPD over VBLENDVPD
This commit is contained in:
JMC47 2024-12-22 18:35:11 -05:00 committed by GitHub
commit c528a70e64
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
Source/Core/Core/PowerPC/Jit64/Jit_FloatingPoint.cpp
View File

@ -644,6 +644,20 @@ void Jit64::fselx(UGeckoInstruction inst)
if (cpu_info.bAVX) if (cpu_info.bAVX)
{ {
// Prefer BLENDVPD over VBLENDVPD if the latter doesn't save any
// instructions.
//
// VBLENDVPD allows separate source and destination registers, which can
// eliminate a MOVAPD/MOVSD. However, on Intel since Skylake, VBLENDVPD
// takes additional uops to execute compared to BLENDVPD (according to
// https://uops.info). On AMD and older Intel microarchitectures there is no
// difference.
if (d == c)
{
BLENDVPD(Rd, Rb);
return;
}
X64Reg src1 = XMM1; X64Reg src1 = XMM1;
if (Rc.IsSimpleReg()) if (Rc.IsSimpleReg())
{ {
@ -654,7 +668,7 @@ void Jit64::fselx(UGeckoInstruction inst)
MOVAPD(XMM1, Rc); MOVAPD(XMM1, Rc);
} }
if (d == c || packed) if (packed)
{ {
VBLENDVPD(Rd, src1, Rb, XMM0); VBLENDVPD(Rd, src1, Rb, XMM0);
return; return;