[llvm] [AMDGPU] Correctly restore FP mode in FDIV32 lowering (PR #66346)
Pierre van Houtryve via llvm-commits
llvm-commits at lists.llvm.org
Thu Sep 14 06:53:22 PDT 2023
================
@@ -4723,10 +4722,23 @@ bool AMDGPULegalizerInfo::legalizeFDIV32(MachineInstr &MI,
.setMIFlags(Flags);
auto NegDivScale0 = B.buildFNeg(S32, DenominatorScaled, Flags);
+ const bool PreservesDenormals = Mode.FP32Denormals == DenormalMode::getIEEE();
+ const bool HasDynamicDenormals =
+ (Mode.FP32Denormals.Input == DenormalMode::Dynamic) ||
+ (Mode.FP32Denormals.Output == DenormalMode::Dynamic);
+
// FIXME: Doesn't correctly model the FP mode switch, and the FP operations
----------------
Pierre-vh wrote:
Ah I thought it was unrelated, i'll remove it.
https://github.com/llvm/llvm-project/pull/66346
More information about the llvm-commits
mailing list