[PATCH] D74345: AMDGPU: Don't report 2-byte alignment as fast

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/chain-hi-to-lo.ll:210
+; GCN-NEXT:    buffer_store_short v4, off, s[0:3], s9 offset:6
+; GCN-NEXT:    global_load_ushort v2, v[2:3], off offset:4
+; GCN-NEXT:    s_waitcnt vmcnt(0)
----------------
It does not seem to be better to have 3 global_load_ushort then global_load_ushort + global_load_dword.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D74345/new/

https://reviews.llvm.org/D74345