eden-emu/eden
24
3
Fork 15
Code Issues 138 Pull requests 56 Projects 1 Releases Packages Wiki Activity Actions

[dynarmic] fix hardcoded AVX512 registers, use xmm0 instead of xmm16 to align with spec

Browse source 
Signed-off-by: lizzie <lizzie@eden-emu.dev>
This commit is contained in:
lizzie 2025-09-09 03:31:12 +00:00 • committed by crueter
parent 560b93a8de
commit b47cbefa11
2 changed files with 10 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

7
src/dynarmic/src/dynarmic/backend/x64/emit_x64_floating_point.cpp
View file

@ -92,13 +92,10 @@ void ForceDenormalsToZero(BlockOfCode& code, std::initializer_list<Xbyak::Xmm> t
FpFixup::Norm_Src,
FpFixup::Norm_Src,
FpFixup::Norm_Src);
const Xbyak::Xmm tmp = xmm16;
const Xbyak::Xmm tmp = xmm0;
FCODE(vmovap)(tmp, code.BConst<fsize>(xword, denormal_to_zero));
for (const Xbyak::Xmm& xmm : to_daz) {
for (const Xbyak::Xmm& xmm : to_daz)
FCODE(vfixupimms)(xmm, xmm, tmp, u8(0));
}
return;
}

16
src/dynarmic/src/dynarmic/backend/x64/emit_x64_vector.cpp
View file

@ -609,8 +609,8 @@ void EmitX64::EmitVectorArithmeticVShift16(EmitContext& ctx, IR::Inst* inst) {
const Xbyak::Xmm result = ctx.reg_alloc.UseScratchXmm(args[0]);
const Xbyak::Xmm left_shift = ctx.reg_alloc.UseScratchXmm(args[1]);
const Xbyak::Xmm right_shift = xmm16;
const Xbyak::Xmm tmp = xmm17;
const Xbyak::Xmm right_shift = ctx.reg_alloc.ScratchXmm();
const Xbyak::Xmm tmp = ctx.reg_alloc.ScratchXmm();
code.vmovdqa32(tmp, code.Const(xword, 0x00FF00FF00FF00FF, 0x00FF00FF00FF00FF));
code.vpxord(right_shift, right_shift, right_shift);
@ -674,8 +674,8 @@ void EmitX64::EmitVectorArithmeticVShift64(EmitContext& ctx, IR::Inst* inst) {
const Xbyak::Xmm result = ctx.reg_alloc.UseScratchXmm(args[0]);
const Xbyak::Xmm left_shift = ctx.reg_alloc.UseScratchXmm(args[1]);
const Xbyak::Xmm right_shift = xmm16;
const Xbyak::Xmm tmp = xmm17;
const Xbyak::Xmm right_shift = ctx.reg_alloc.ScratchXmm();
const Xbyak::Xmm tmp = ctx.reg_alloc.ScratchXmm();
code.vmovdqa32(tmp, code.Const(xword, 0x00000000000000FF, 0x00000000000000FF));
code.vpxorq(right_shift, right_shift, right_shift);
@ -1955,8 +1955,8 @@ void EmitX64::EmitVectorLogicalVShift16(EmitContext& ctx, IR::Inst* inst) {
const Xbyak::Xmm result = ctx.reg_alloc.UseScratchXmm(args[0]);
const Xbyak::Xmm left_shift = ctx.reg_alloc.UseScratchXmm(args[1]);
const Xbyak::Xmm right_shift = xmm16;
const Xbyak::Xmm tmp = xmm17;
const Xbyak::Xmm right_shift = ctx.reg_alloc.ScratchXmm();
const Xbyak::Xmm tmp = ctx.reg_alloc.ScratchXmm();
code.vmovdqa32(tmp, code.Const(xword, 0x00FF00FF00FF00FF, 0x00FF00FF00FF00FF));
code.vpxord(right_shift, right_shift, right_shift);
@ -2737,7 +2737,7 @@ void EmitX64::EmitVectorPairedAddSignedWiden32(EmitContext& ctx, IR::Inst* inst)
const Xbyak::Xmm a = ctx.reg_alloc.UseScratchXmm(args[0]);
if (code.HasHostFeature(HostFeature::AVX512_Ortho)) {
const Xbyak::Xmm c = xmm16;
const Xbyak::Xmm c = ctx.reg_alloc.ScratchXmm();
code.vpsraq(c, a, 32);
code.vpsllq(a, a, 32);
code.vpsraq(a, a, 32);
@ -5461,7 +5461,7 @@ void EmitX64::EmitVectorTableLookup128(EmitContext& ctx, IR::Inst* inst) {
if (code.HasHostFeature(HostFeature::AVX512_Ortho | HostFeature::AVX512BW)) {
const Xbyak::Xmm indicies = ctx.reg_alloc.UseXmm(args[2]);
const Xbyak::Xmm result = ctx.reg_alloc.UseScratchXmm(args[0]);
const Xbyak::Xmm masked = xmm16;
const Xbyak::Xmm masked = ctx.reg_alloc.ScratchXmm();
code.vpandd(masked, indicies, code.Const(xword_b, 0xF0F0F0F0F0F0F0F0, 0xF0F0F0F0F0F0F0F0));