[AMDGPU] Add UniformBinFrag to SALU fminimum/fmaximum patterns. NFCI. (#142169)
SALU patterns should have UniformBinFrag because they can only handle
uniform inputs. VALU patterns do not need DivergentBinFrag because they
work for both uniform and divergent inputs; instead we can use
AddedComplexity to ensure that SALU patterns are preferred.
diff --git a/llvm/lib/Target/AMDGPU/SOPInstructions.td b/llvm/lib/Target/AMDGPU/SOPInstructions.td
index 40b3dfb..e0a3675 100644
--- a/llvm/lib/Target/AMDGPU/SOPInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SOPInstructions.td
@@ -922,11 +922,11 @@
// On GFX12 MIN/MAX instructions do not read MODE register.
let SubtargetPredicate = isGFX12Plus, mayRaiseFPException = 1, isCommutable = 1,
- isReMaterializable = 1, SchedRW = [WriteSFPU], AddedComplexity = 17 in {
- def S_MINIMUM_F32 : SOP2_F32_Inst<"s_minimum_f32", fminimum>;
- def S_MAXIMUM_F32 : SOP2_F32_Inst<"s_maximum_f32", fmaximum>;
- def S_MINIMUM_F16 : SOP2_F16_Inst<"s_minimum_f16", fminimum>;
- def S_MAXIMUM_F16 : SOP2_F16_Inst<"s_maximum_f16", fmaximum>;
+ isReMaterializable = 1, SchedRW = [WriteSFPU], AddedComplexity = 25 in {
+ def S_MINIMUM_F32 : SOP2_F32_Inst<"s_minimum_f32", UniformBinFrag<fminimum>>;
+ def S_MAXIMUM_F32 : SOP2_F32_Inst<"s_maximum_f32", UniformBinFrag<fmaximum>>;
+ def S_MINIMUM_F16 : SOP2_F16_Inst<"s_minimum_f16", UniformBinFrag<fminimum>>;
+ def S_MAXIMUM_F16 : SOP2_F16_Inst<"s_maximum_f16", UniformBinFrag<fmaximum>>;
}
//===----------------------------------------------------------------------===//
diff --git a/llvm/lib/Target/AMDGPU/VOP3Instructions.td b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
index 0252c4f..594b37b 100644
--- a/llvm/lib/Target/AMDGPU/VOP3Instructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3Instructions.td
@@ -168,10 +168,10 @@
} // End SchedRW = [WriteIntMul]
let SubtargetPredicate = isGFX12Plus, ReadsModeReg = 0, AddedComplexity = 1 in {
-defm V_MINIMUM_F32 : VOP3Inst <"v_minimum_f32", VOP3_Profile<VOP_F32_F32_F32>, DivergentBinFrag<fminimum>>;
-defm V_MAXIMUM_F32 : VOP3Inst <"v_maximum_f32", VOP3_Profile<VOP_F32_F32_F32>, DivergentBinFrag<fmaximum>>;
-defm V_MINIMUM_F16 : VOP3Inst_t16 <"v_minimum_f16", VOP_F16_F16_F16, DivergentBinFrag<fminimum>>;
-defm V_MAXIMUM_F16 : VOP3Inst_t16 <"v_maximum_f16", VOP_F16_F16_F16, DivergentBinFrag<fmaximum>>;
+defm V_MINIMUM_F32 : VOP3Inst <"v_minimum_f32", VOP3_Profile<VOP_F32_F32_F32>, fminimum>;
+defm V_MAXIMUM_F32 : VOP3Inst <"v_maximum_f32", VOP3_Profile<VOP_F32_F32_F32>, fmaximum>;
+defm V_MINIMUM_F16 : VOP3Inst_t16 <"v_minimum_f16", VOP_F16_F16_F16, fminimum>;
+defm V_MAXIMUM_F16 : VOP3Inst_t16 <"v_maximum_f16", VOP_F16_F16_F16, fmaximum>;
let SchedRW = [WriteDoubleAdd] in {
defm V_MINIMUM_F64 : VOP3Inst <"v_minimum_f64", VOP3_Profile<VOP_F64_F64_F64>, fminimum>;
