Add NVPTXLowerAlloca pass to convert alloca'ed memory to local address

Summary:
This is done by first adding two additional instructions to convert the
alloca returned address to local and convert it back to generic. Then
replace all uses of alloca instruction with the converted generic
address. Then we can rely NVPTXFavorNonGenericAddrSpace pass to combine
the generic addresscast and the corresponding Load, Store, Bitcast, GEP
Instruction together.

Patched by Xuetian Weng (xweng@google.com). 

Test Plan: test/CodeGen/NVPTX/lower-alloca.ll

Reviewers: jholewinski, jingyue

Reviewed By: jingyue

Subscribers: meheff, broune, eliben, jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D10483

llvm-svn: 239964

1 files changed, 5 insertions, 4 deletions

diff --git a/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp b/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
index e0b193ddf46..c071ee82abc 100644
--- a/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -54,6 +54,7 @@ void initializeNVPTXAllocaHoistingPass(PassRegistry &);
 void initializeNVPTXAssignValidGlobalNamesPass(PassRegistry&);
 void initializeNVPTXFavorNonGenericAddrSpacesPass(PassRegistry &);
 void initializeNVPTXLowerKernelArgsPass(PassRegistry &);
+void initializeNVPTXLowerAllocaPass(PassRegistry &);
 }
 
 extern "C" void LLVMInitializeNVPTXTarget() {
@@ -70,6 +71,7 @@ extern "C" void LLVMInitializeNVPTXTarget() {
   initializeNVPTXFavorNonGenericAddrSpacesPass(
     *PassRegistry::getPassRegistry());
   initializeNVPTXLowerKernelArgsPass(*PassRegistry::getPassRegistry());
+  initializeNVPTXLowerAllocaPass(*PassRegistry::getPassRegistry());
 }
 
 static std::string computeDataLayout(bool is64Bit) {
@@ -166,12 +168,11 @@ void NVPTXPassConfig::addIRPasses() {
   addPass(createNVPTXAssignValidGlobalNamesPass());
   addPass(createGenericToNVVMPass());
   addPass(createNVPTXLowerKernelArgsPass(&getNVPTXTargetMachine()));
-  addPass(createNVPTXFavorNonGenericAddrSpacesPass());
   // NVPTXLowerKernelArgs emits alloca for byval parameters which can often
-  // be eliminated by SROA. We do not run SROA right after NVPTXLowerKernelArgs
-  // because we plan to merge NVPTXLowerKernelArgs and
-  // NVPTXFavorNonGenericAddrSpaces into one pass.
+  // be eliminated by SROA.
   addPass(createSROAPass());
+  addPass(createNVPTXLowerAllocaPass());
+  addPass(createNVPTXFavorNonGenericAddrSpacesPass());
   // FavorNonGenericAddrSpaces shortcuts unnecessary addrspacecasts, and leave
   // them unused. We could remove dead code in an ad-hoc manner, but that
   // requires manual work and might be error-prone.