[PATCH] D156301: [AMDGPU] Support FAdd/FSub global atomics in AMDGPUAtomicOptimizer.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp:78
   Value *buildReduction(IRBuilder<> &B, AtomicRMWInst::BinOp Op, Value *V,
-                        Value *const Identity) const;
+                        Value *const Identity,
+                        bool isAtomicFloatingPointTy) const;
----------------
foad wrote:
> No need to pass in isAtomicFloatingPointTy to all these functions. It is just V->getType()->isFloatingPointTy().
This is wrong in the case of FP typed xchg, which the pass just happens to not handle


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156301/new/

https://reviews.llvm.org/D156301