From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Mon, 6 Jul 2015 17:02:20 +0000 (+0000)
Subject: AMDGPU: Run SIInsertWaits as pre-emit pass
X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=commitdiff_plain;h=b560f9ca2fee8c4e060d486367cf19f3b1774921

AMDGPU: Run SIInsertWaits as pre-emit pass

Running this after the scheduler enables scheduling
waits later so other ALU instructions can run while
this would be waiting.

When combined with enabling the post-RA scheduler, this
gives about a ~20% improvement on sgemm.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@241473 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index a9a911a8efe..f3955659d93 100644
--- a/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -280,10 +280,10 @@ void GCNPassConfig::addPostRegAlloc() {
 }
 
 void GCNPassConfig::addPreSched2() {
-  addPass(createSIInsertWaits(*TM), false);
 }
 
 void GCNPassConfig::addPreEmitPass() {
+  addPass(createSIInsertWaits(*TM), false);
   addPass(createSILowerControlFlowPass(*TM), false);
 }