[PATCH] D27106: AMDGPU/SI: Enable MemorySSA for EarlyCSE

[Tom Stellard via llvm-commits]

tstellarAMD created this revision.
tstellarAMD added a reviewer: arsenm.
tstellarAMD added a subscriber: llvm-commits.
Herald added subscribers: tony-tye, yaxunl, nhaehnle, wdng, kzhuravl.

With MemorySSA this pass does a much better job of CSE'ing intrinsic
with pointer arguments.


https://reviews.llvm.org/D27106

Files:
  lib/Target/AMDGPU/AMDGPUTargetMachine.cpp


Index: lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -351,7 +351,7 @@
   if (getOptLevel() == CodeGenOpt::Aggressive)
     addPass(createGVNPass());
   else
-    addPass(createEarlyCSEPass());
+    addPass(createEarlyCSEPass(true));
 }
 
 void AMDGPUPassConfig::addStraightLineScalarOptimizationPasses() {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D27106.79238.patch
Type: text/x-patch
Size: 465 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20161124/eeb480ff/attachment.bin>