[llvm] [AMDGPU][GISel] Fold 'min(min(x,y),z)' and 'max(max(x,y),z)' into min3 and max3 (PR #200410)
Petar Avramovic via llvm-commits
llvm-commits at lists.llvm.org
Thu Jun 4 09:23:09 PDT 2026
================
@@ -481,6 +491,97 @@ bool AMDGPURegBankCombinerImpl::combineD16Load(MachineInstr &MI) const {
return false;
}
+void AMDGPURegBankCombinerImpl::applyMinMaxToMinMax3(
+ MachineInstr &MI, MinMaxToMinMax3MatchInfo &MatchInfo) const {
+ B.buildInstr(MatchInfo.Opc, {MI.getOperand(0)},
+ {MatchInfo.Val0, MatchInfo.Val1, MatchInfo.Val2}, MI.getFlags());
+ MI.eraseFromParent();
+ return;
+}
+
+bool AMDGPURegBankCombinerImpl::matchMinMaxToMinMax3(
+ MachineInstr &MI, MinMaxToMinMax3MatchInfo &MatchInfo) const {
+ Register Dst = MI.getOperand(0).getReg();
+ Register Src1 = MI.getOperand(1).getReg();
+ Register Src2 = MI.getOperand(2).getReg();
+ // If the register is SGPR, don't optimize it.
+ if (!(isVgprRegBank(Dst) && isVgprRegBank(Src1) && isVgprRegBank(Src2))) {
+ return false;
+ }
+
+ LLT Ty = MRI.getType(Dst);
+ unsigned Opc = MI.getOpcode();
+ bool IsFPOp = Opc == AMDGPU::G_FMAXNUM || Opc == AMDGPU::G_FMAXNUM_IEEE ||
+ Opc == AMDGPU::G_FMINNUM || Opc == AMDGPU::G_FMINNUM_IEEE;
+ bool IsSupportedTy = Ty == LLT::scalar(32) ||
+ (Ty == LLT::scalar(16) && STI.hasMin3Max3_16()) ||
+ (IsFPOp && Ty == LLT::fixed_vector(2, 32));
----------------
petar-avramovic wrote:
where is test for this?
https://github.com/llvm/llvm-project/pull/200410
More information about the llvm-commits
mailing list