[PATCH] D144759: [AMDGPU] Implement idempotent atomic lowering

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:13448
+  // Avoid replacing of an atomicrmw with a release semantics.
+  if (isReleaseOrStronger(AI->getOrdering()))
+    return nullptr;
----------------
Didn't use Order saved above


================
Comment at: llvm/test/CodeGen/AMDGPU/idemponent-atomics.ll:3
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX940 %s
+
+define i32 @global_agent_monotonic_idempotent_or(ptr addrspace(1) %in) {
----------------
Should include an IR run line 


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D144759/new/

https://reviews.llvm.org/D144759