[NVPTX] run SeparateConstOffsetFromGEP before SLSR

Summary:
We pick this order because SeparateConstOffsetFromGEP may create more
opportunities for SLSR.

Test Plan:
reassociate-geps-and-slsr.ll
no performance regression on internal benchmarks

Reviewers: meheff

Subscribers: llvm-commits, jholewinski

Differential Revision: http://reviews.llvm.org/D9230

llvm-svn: 235632

1 files changed, 6 insertions, 4 deletions

diff --git a/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp b/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
index f9545cc1d41..dc8e8a29528 100644
--- a/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -168,11 +168,13 @@ void NVPTXPassConfig::addIRPasses() {
   // them unused. We could remove dead code in an ad-hoc manner, but that
   // requires manual work and might be error-prone.
   addPass(createDeadCodeEliminationPass());
-  addPass(createStraightLineStrengthReducePass());
   addPass(createSeparateConstOffsetFromGEPPass());
-  // The SeparateConstOffsetFromGEP pass creates variadic bases that can be used
-  // by multiple GEPs. Run GVN or EarlyCSE to really reuse them. GVN generates
-  // significantly better code than EarlyCSE for some of our benchmarks.
+  // ReassociateGEPs exposes more opportunites for SLSR. See
+  // the example in reassociate-geps-and-slsr.ll.
+  addPass(createStraightLineStrengthReducePass());
+  // SeparateConstOffsetFromGEP and SLSR creates common expressions which GVN or
+  // EarlyCSE can reuse. GVN generates significantly better code than EarlyCSE
+  // for some of our benchmarks.
   if (getOptLevel() == CodeGenOpt::Aggressive)
     addPass(createGVNPass());
   else