[PATCH] D124678: [AMDGPU] Allow for MFMA Inst Clustering

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp:926
+        if (Node.second != MFMAOpa->NodeNum)
+          continue; // only add the combined succs to the current cluster
+
----------------
Nit: please use full capitalized punctuated English sentences for all your comments: https://llvm.org/docs/CodingStandards.html#commenting


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp:943
+        DAGInstrs->MF.getInfo<SIMachineFunctionInfo>();
+    // The purpose of clustering is to aid with multive wave scheduling
+    // If our occupancy doesn't support multi waves, bypass clustering
----------------
Typo "multive".


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D124678/new/

https://reviews.llvm.org/D124678