Emulation/ppsspp
1
0
Fork 0
mirror of https://github.com/hrydgard/ppsspp.git synced 2025-04-02 11:01:50 -04:00
Code Issues Projects Releases Packages Wiki Activity

Fix simd vmmul transpose optimizations.

Browse source 
Yep, gotta discard the S matrix when we're done with it.
This commit is contained in:
Bovine 2015-01-03 16:58:03 -07:00
parent 0fdebdc1ca
commit 54c7a12306
1 changed files with 5 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
Core/MIPS/x86/CompVFPU.cpp
View file

@ -2726,6 +2726,11 @@ void Jit::Comp_Vmmul(MIPSOpcode op) {
#endif
MOVAPS(fpr.VS(dcol), XMM1);
}
if (transposeS){
for (int i = 0; i < n; i++){
fpr.DiscardVS(scols[i]);
}
}
#ifndef _M_X64
fpr.ReleaseSpillLocks();