Add NVPTXPeephole pass to reduce unnecessary address cast

Summary:
This patch first change the register that holds local address for stack
frame to %SPL. Then the new NVPTXPeephole pass will try to scan the
following pattern

   %vreg0<def> = LEA_ADDRi64 <fi#0>, 4
   %vreg1<def> = cvta_to_local %vreg0

and transform it into

   %vreg1<def> = LEA_ADDRi64 %VRFrameLocal, 4

Patched by Xuetian Weng

Test Plan: test/CodeGen/NVPTX/local-stack-frame.ll

Reviewers: jholewinski, jingyue

Reviewed By: jingyue

Subscribers: eliben, jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D10549

llvm-svn: 240587

1 files changed, 2 insertions, 0 deletions

diff --git a/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp b/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
index c071ee82abc..dc3e34f9647 100644
--- a/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -205,6 +205,8 @@ bool NVPTXPassConfig::addInstSelector() {
   if (!ST.hasImageHandles())
     addPass(createNVPTXReplaceImageHandlesPass());
 
+  addPass(createNVPTXPeephole());
+
   return false;
 }