[PATCH] D153025: AMDGPU: Correctly lower llvm.exp.f32

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:3425
+    auto Overflow =
+        B.buildFCmp(CmpInst::FCMP_OGT, LLT::scalar(1), X, OverflowCheckConst);
+    auto Inf = B.buildFConstant(Ty, APFloat::getInf(APFloat::IEEEsingle()));
----------------
This produces worse code than the DAG because we don't have the compare commuting combine. We can get closer matching and better output by pre-commuting this


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153025/new/

https://reviews.llvm.org/D153025