[PATCH] D31993: [AMDGPU] Combine DS operations with offsets bigger than byte

[Valery Pykhtin via Phabricator via llvm-commits]

vpykhtin added a comment.

Looks good.



================
Comment at: lib/Target/AMDGPU/SILoadStoreOptimizer.cpp:78
+    unsigned Offset1;
+    unsigned BaseOff;
+    bool UseST64;
----------------
Why 3 offsets?


Repository:
  rL LLVM

https://reviews.llvm.org/D31993