[PATCH] D75187: [AMDGPU][ConstantFolding] Fold llvm.amdgcn.cube* intrinsics

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Analysis/ConstantFolding.cpp:2310
 
+static float ConstantFoldAMDGCNCubeIntrinsic(Intrinsic::ID IntrinsicID, float S0, float S1, float S2) {
+  float ID, MA, SC, TC;
----------------
Using host FP operations is generally frowned on, and this should use APFloat


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D75187/new/

https://reviews.llvm.org/D75187