[PATCH] D73069: AMDGPU: Look through casted selects to constant fold bin ops
Stanislav Mekhanoshin via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 20 17:22:26 PST 2020
rampitec accepted this revision.
rampitec added a comment.
This revision is now accepted and ready to land.
LGTM
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp:534
+// Find a select instruction, which may have been casted. This is mostly to deal
+// with cases where i16 selects weer promoted here to i32.
+static SelectInst *findSelectThroughCast(Value *V, CastInst *&Cast) {
----------------
typo: weer
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D73069/new/
https://reviews.llvm.org/D73069
More information about the llvm-commits
mailing list