[PATCH] D153023: AMDGPU: Correctly lower llvm.log.f32 and llvm.log10.f32

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added a comment.

ping



================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp:2516
+
+  SDValue Scale32 = DAG.getConstantFP(0x1.0p+32, SL, VT);
+  SDValue One = DAG.getConstantFP(1.0, SL, VT);
----------------
TODO: Use ldexp instead 


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153023/new/

https://reviews.llvm.org/D153023