Add an optimization that does CSE in a group of similar GEPs.

This optimization merges the common part of a group of GEPs, so we can compute
each pointer address by adding a simple offset to the common part.

The optimization is currently only enabled for the NVPTX backend, where it has
a large payoff on some benchmarks.

Review: http://reviews.llvm.org/D3462

Patch by Jingyue Wu.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207783 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/InitializePasses.h

@@ -238,6 +238,7 @@ void initializeSimpleInlinerPass(PassRegistry&);
 void initializeRegisterCoalescerPass(PassRegistry&);
 void initializeSingleLoopExtractorPass(PassRegistry&);
 void initializeSinkingPass(PassRegistry&);
+void initializeSeparateConstOffsetFromGEPPass(PassRegistry &);
 void initializeSlotIndexesPass(PassRegistry&);
 void initializeSpillPlacementPass(PassRegistry&);
 void initializeStackProtectorPass(PassRegistry&);

include/llvm/LinkAllPasses.h

@@ -156,6 +156,7 @@ namespace {
       (void) llvm::createBBVectorizePass();
       (void) llvm::createPartiallyInlineLibCallsPass();
       (void) llvm::createScalarizerPass();
+      (void) llvm::createSeparateConstOffsetFromGEPPass();
 
       (void)new llvm::IntervalPartition();
       (void)new llvm::FindUsedTypes();

include/llvm/Transforms/Scalar.h

@@ -377,6 +377,12 @@ FunctionPass *createScalarizerPass();
 // AddDiscriminators - Add DWARF path discriminators to the IR.
 FunctionPass *createAddDiscriminatorsPass();
 
+//===----------------------------------------------------------------------===//
+//
+// SeparateConstOffsetFromGEP - Split GEPs for better CSE
+//
+FunctionPass *createSeparateConstOffsetFromGEPPass();
+
 } // End llvm namespace
 
 #endif

lib/Target/NVPTX/NVPTXTargetMachine.cpp

@@ -147,10 +147,23 @@ void NVPTXPassConfig::addIRPasses() {
   addPass(createNVPTXAssignValidGlobalNamesPass());
   addPass(createGenericToNVVMPass());
   addPass(createNVPTXFavorNonGenericAddrSpacesPass());
-  // The FavorNonGenericAddrSpaces pass may remove instructions and leave some
-  // values unused. Therefore, we run a DCE pass right afterwards. We could
-  // remove unused values in an ad-hoc manner, but it requires manual work and
-  // might be error-prone.
+  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.
+  if (getOptLevel() == CodeGenOpt::Aggressive)
+    addPass(createGVNPass());
+  else
+    addPass(createEarlyCSEPass());
+  // Both FavorNonGenericAddrSpaces and SeparateConstOffsetFromGEP may leave
+  // some dead code.  We could remove dead code in an ad-hoc manner, but that
+  // requires manual work and might be error-prone.
+  //
+  // The FavorNonGenericAddrSpaces pass shortcuts unnecessary addrspacecasts,
+  // and leave them unused.
+  //
+  // SeparateConstOffsetFromGEP rebuilds a new index from the old index, and the
+  // old index and some of its intermediate results may become unused.
   addPass(createDeadCodeEliminationPass());
 }
 

lib/Transforms/Scalar/Scalar.cpp

@@ -64,6 +64,7 @@ void llvm::initializeScalarOpts(PassRegistry &Registry) {
   initializeStructurizeCFGPass(Registry);
   initializeSinkingPass(Registry);
   initializeTailCallElimPass(Registry);
+  initializeSeparateConstOffsetFromGEPPass(Registry);
 }
 
 void LLVMInitializeScalarOpts(LLVMPassRegistryRef R) {