[PATCH] D128205: [AMDGPU] gfx11 Select on Buffer Atomic FAdd Rtn type

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUGlobalISelUtils.cpp:76
+    return Subtarget.hasAtomicFaddRtnInsts();
+  } else if (Ty == LLT::fixed_vector(2, 16) || Ty == LLT::scalar(64)) {
+    return Subtarget.hasGFX90AInsts();
----------------
No else after return.


================
Comment at: llvm/lib/Target/AMDGPU/SIISelLowering.cpp:12636
     if ((AS == AMDGPUAS::GLOBAL_ADDRESS || AS == AMDGPUAS::FLAT_ADDRESS) &&
-         Subtarget->hasAtomicFaddInsts()) {
+        Subtarget->hasAtomicFaddNoRtnInsts()) {
       if (Subtarget->hasGFX940Insts())
----------------
Is this change intentional? What is the effect of it?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128205/new/

https://reviews.llvm.org/D128205