[PATCH] D157388: [AMDGPU] Support FMin/FMax in AMDGPUAtomicOptimizer.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp:320
     break;
+  case Intrinsic::amdgcn_global_atomic_fmax:
+    Op = AtomicRMWInst::FMax;
----------------
I don't want to implicitly convert the intrinsics here. We should move towards getting rid of the intrinsics and autoupgrading them


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUAtomicOptimizer.cpp:405
+  case AtomicRMWInst::FMax:
+    return B.CreateSelect(B.CreateFCmp(FCmpInst::FCMP_UGT, LHS, RHS), LHS, RHS);
+  case AtomicRMWInst::FMin:
----------------
This is incorrect, you should create minnum/maxnum


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D157388/new/

https://reviews.llvm.org/D157388