MergedLoadStoreMotion pass

[oota-llvm.git] / lib / Transforms / IPO / PassManagerBuilder.cpp

diff --git a/lib/Transforms/IPO/PassManagerBuilder.cpp b/lib/Transforms/IPO/PassManagerBuilder.cpp
index 4a28b34468baa0a50e57e7f63d40fefdc549bff9..701fb462b4fdad1e6b50bf1bcdee2f8fab2d4d0e 100644 (file)
--- a/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -53,17 +53,23 @@ static cl::opt<bool>
 RunLoopRerolling("reroll-loops", cl::Hidden,
                  cl::desc("Run the loop rerolling pass"));
 
+static cl::opt<bool> RunLoadCombine("combine-loads", cl::init(false),
+                                    cl::Hidden,
+                                    cl::desc("Run the load combining pass"));
+
 PassManagerBuilder::PassManagerBuilder() {
     OptLevel = 2;
     SizeLevel = 0;
-    LibraryInfo = 0;
-    Inliner = 0;
+    LibraryInfo = nullptr;
+    Inliner = nullptr;
+    DisableTailCalls = false;
     DisableUnitAtATime = false;
     DisableUnrollLoops = false;
     BBVectorize = RunBBVectorization;
     SLPVectorize = RunSLPVectorization;
     LoopVectorize = RunLoopVectorization;
     RerollLoops = RunLoopRerolling;
+    LoadCombine = RunLoadCombine;
 }
 
 PassManagerBuilder::~PassManagerBuilder() {
@@ -128,7 +134,7 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   if (OptLevel == 0) {
     if (Inliner) {
       MPM.add(Inliner);
-      Inliner = 0;
+      Inliner = nullptr;
     }
 
     // FIXME: This is a HACK! The inliner pass above implicitly creates a CGSCC
@@ -150,12 +156,13 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   if (!DisableUnitAtATime) {
     addExtensionsToPM(EP_ModuleOptimizerEarly, MPM);
 
+    MPM.add(createIPSCCPPass());              // IP SCCP
     MPM.add(createGlobalOptimizerPass());     // Optimize out global vars
 
-    MPM.add(createIPSCCPPass());              // IP SCCP
     MPM.add(createDeadArgEliminationPass());  // Dead argument elimination
 
     MPM.add(createInstructionCombiningPass());// Clean up after IPCP & DAE
+    addExtensionsToPM(EP_Peephole, MPM);
     MPM.add(createCFGSimplificationPass());   // Clean up after IPCP & DAE
   }
 
@@ -164,7 +171,7 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
     MPM.add(createPruneEHPass());             // Remove dead EH info
   if (Inliner) {
     MPM.add(Inliner);
-    Inliner = 0;
+    Inliner = nullptr;
   }
   if (!DisableUnitAtATime)
     MPM.add(createFunctionAttrsPass());       // Set readonly/readnone attrs
@@ -182,8 +189,10 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   MPM.add(createCorrelatedValuePropagationPass()); // Propagate conditionals
   MPM.add(createCFGSimplificationPass());     // Merge & remove BBs
   MPM.add(createInstructionCombiningPass());  // Combine silly seq's
+  addExtensionsToPM(EP_Peephole, MPM);
 
-  MPM.add(createTailCallEliminationPass());   // Eliminate tail calls
+  if (!DisableTailCalls)
+    MPM.add(createTailCallEliminationPass()); // Eliminate tail calls
   MPM.add(createCFGSimplificationPass());     // Merge & remove BBs
   MPM.add(createReassociatePass());           // Reassociate expressions
   MPM.add(createLoopRotatePass());            // Rotate Loop
@@ -198,14 +207,17 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
     MPM.add(createSimpleLoopUnrollPass());    // Unroll small loops
   addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
 
-  if (OptLevel > 1)
+  if (OptLevel > 1) {
+    MPM.add(createMergedLoadStoreMotionPass()); // Merge load/stores in diamond
     MPM.add(createGVNPass());                 // Remove redundancies
+  }
   MPM.add(createMemCpyOptPass());             // Remove memcpy / form memset
   MPM.add(createSCCPPass());                  // Constant prop with SCCP
 
   // Run instcombine after redundancy elimination to exploit opportunities
   // opened up by them.
   MPM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, MPM);
   MPM.add(createJumpThreadingPass());         // Thread jumps
   MPM.add(createCorrelatedValuePropagationPass());
   MPM.add(createDeadStoreEliminationPass());  // Delete dead stores
@@ -220,6 +232,7 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   if (BBVectorize) {
     MPM.add(createBBVectorizePass());
     MPM.add(createInstructionCombiningPass());
+    addExtensionsToPM(EP_Peephole, MPM);
     if (OptLevel > 1 && UseGVNAfterVectorization)
       MPM.add(createGVNPass());           // Remove redundancies
     else
@@ -230,9 +243,13 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
       MPM.add(createLoopUnrollPass());
   }
 
+  if (LoadCombine)
+    MPM.add(createLoadCombinePass());
+
   MPM.add(createAggressiveDCEPass());         // Delete dead instructions
   MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
   MPM.add(createInstructionCombiningPass());  // Clean up after everything.
+  addExtensionsToPM(EP_Peephole, MPM);
 
   // FIXME: This is a HACK! The inliner pass above implicitly creates a CGSCC
   // pass manager that we are specifically trying to avoid. To prevent this
@@ -245,6 +262,7 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   // as function calls, so that we can only pass them when the vectorizer
   // changed the code.
   MPM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, MPM);
   MPM.add(createCFGSimplificationPass());
 
   if (!DisableUnrollLoops)
@@ -297,6 +315,7 @@ void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
   // function pointers.  When this happens, we often have to resolve varargs
   // calls, etc, so let instcombine do this.
   PM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, PM);
 
   // Inline small functions
   if (RunInliner)
@@ -315,6 +334,7 @@ void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
 
   // The IPO passes may leave cruft around.  Clean up after them.
   PM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, PM);
   PM.add(createJumpThreadingPass());
 
   // Break up allocas
@@ -328,17 +348,27 @@ void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
   PM.add(createGlobalsModRefPass()); // IP alias analysis.
 
   PM.add(createLICMPass());                 // Hoist loop invariants.
+  PM.add(createMergedLoadStoreMotionPass()); // Merge load/stores in diamonds
   PM.add(createGVNPass(DisableGVNLoadPRE)); // Remove redundancies.
   PM.add(createMemCpyOptPass());            // Remove dead memcpys.
 
   // Nuke dead stores.
   PM.add(createDeadStoreEliminationPass());
 
-  // More loops are countable try to vectorize them.
+  // More loops are countable; try to optimize them.
+  PM.add(createIndVarSimplifyPass());
+  PM.add(createLoopDeletionPass());
   PM.add(createLoopVectorizePass(true, true));
 
+  // More scalar chains could be vectorized due to more alias information
+  PM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
+
+  if (LoadCombine)
+    PM.add(createLoadCombinePass());
+
   // Cleanup and simplify the code after the scalar optimizations.
   PM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, PM);
 
   PM.add(createJumpThreadingPass());