[PATCH] D20304: AMDGPU: Run pointer optimization passes

[Tom Stellard via llvm-commits]

tstellarAMD accepted this revision.
tstellarAMD added a comment.
This revision is now accepted and ready to land.

LGTM.


================
Comment at: lib/Target/AMDGPU/AMDGPUTargetMachine.cpp:235-236
@@ +234,4 @@
+  // SeparateConstOffsetFromGEP and SLSR creates common expressions which GVN or
+  // EarlyCSE can reuse. GVN generates significantly better code than EarlyCSE
+  // for some of our benchmarks.
+  addEarlyCSEOrGVNPass();
----------------
I would drop this last sentence about bencmarks until we've done our own analysis or instead mentions that it improves some benchmarks with NVPTX.


http://reviews.llvm.org/D20304