#include "llvm/Transforms/IPO/PassManagerBuilder.h"
-
#include "llvm-c/Transforms/PassManagerBuilder.h"
-
-#include "llvm/PassManager.h"
-#include "llvm/DefaultPasses.h"
-#include "llvm/PassManager.h"
+#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/Passes.h"
-#include "llvm/Analysis/Verifier.h"
+#include "llvm/IR/DataLayout.h"
+#include "llvm/IR/Verifier.h"
+#include "llvm/PassManager.h"
#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/ManagedStatic.h"
#include "llvm/Target/TargetLibraryInfo.h"
+#include "llvm/Target/TargetMachine.h"
+#include "llvm/Target/TargetSubtargetInfo.h"
+#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Vectorize.h"
-#include "llvm/Transforms/IPO.h"
-#include "llvm/ADT/SmallVector.h"
-#include "llvm/Support/ManagedStatic.h"
using namespace llvm;
static cl::opt<bool>
-RunVectorization("vectorize", cl::desc("Run vectorization passes"));
+RunLoopVectorization("vectorize-loops", cl::Hidden,
+ cl::desc("Run the Loop vectorization passes"));
+
+static cl::opt<bool>
+RunSLPVectorization("vectorize-slp", cl::Hidden,
+ cl::desc("Run the SLP vectorization passes"));
+
+static cl::opt<bool>
+RunBBVectorization("vectorize-slp-aggressive", cl::Hidden,
+ cl::desc("Run the BB vectorization passes"));
static cl::opt<bool>
UseGVNAfterVectorization("use-gvn-after-vectorization",
cl::init(false), cl::Hidden,
cl::desc("Run GVN instead of Early CSE after vectorization passes"));
+static cl::opt<bool> ExtraVectorizerPasses(
+ "extra-vectorizer-passes", cl::init(false), cl::Hidden,
+ cl::desc("Run cleanup optimization passes after vectorization."));
+
static cl::opt<bool> UseNewSROA("use-new-sroa",
cl::init(true), cl::Hidden,
cl::desc("Enable the new, experimental SROA pass"));
+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"));
+
+static cl::opt<bool>
+RunSLPAfterLoopVectorization("run-slp-after-loop-vectorization",
+ cl::init(true), cl::Hidden,
+ cl::desc("Run the SLP vectorizer (and BB vectorizer) after the Loop "
+ "vectorizer instead of before"));
+
+static cl::opt<bool> UseCFLAA("use-cfl-aa",
+ cl::init(false), cl::Hidden,
+ cl::desc("Enable the new, experimental CFL alias analysis"));
+
+static cl::opt<bool>
+EnableMLSM("mlsm", cl::init(true), cl::Hidden,
+ cl::desc("Enable motion of merged load and store"));
+
PassManagerBuilder::PassManagerBuilder() {
OptLevel = 2;
SizeLevel = 0;
- LibraryInfo = 0;
- Inliner = 0;
- DisableSimplifyLibCalls = false;
+ LibraryInfo = nullptr;
+ Inliner = nullptr;
+ DisableTailCalls = false;
DisableUnitAtATime = false;
DisableUnrollLoops = false;
- Vectorize = RunVectorization;
+ BBVectorize = RunBBVectorization;
+ SLPVectorize = RunSLPVectorization;
+ LoopVectorize = RunLoopVectorization;
+ RerollLoops = RunLoopRerolling;
+ LoadCombine = RunLoadCombine;
+ DisableGVNLoadPRE = false;
+ VerifyInput = false;
+ VerifyOutput = false;
+ StripDebug = false;
+ MergeFunctions = false;
}
PassManagerBuilder::~PassManagerBuilder() {
// Add TypeBasedAliasAnalysis before BasicAliasAnalysis so that
// BasicAliasAnalysis wins if they disagree. This is intended to help
// support "obvious" type-punning idioms.
+ if (UseCFLAA)
+ PM.add(createCFLAliasAnalysisPass());
PM.add(createTypeBasedAliasAnalysisPass());
+ PM.add(createScopedNoAliasAAPass());
PM.add(createBasicAliasAnalysisPass());
}
}
void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
- // If all optimizations are disabled, just run the always-inline pass.
+ // If all optimizations are disabled, just run the always-inline pass and,
+ // if enabled, the function merging pass.
if (OptLevel == 0) {
if (Inliner) {
MPM.add(Inliner);
- Inliner = 0;
+ Inliner = nullptr;
}
+
+ // FIXME: The BarrierNoopPass is a HACK! The inliner pass above implicitly
+ // creates a CGSCC pass manager, but we don't want to add extensions into
+ // that pass manager. To prevent this we insert a no-op module pass to reset
+ // the pass manager to get the same behavior as EP_OptimizerLast in non-O0
+ // builds. The function merging pass is
+ if (MergeFunctions)
+ MPM.add(createMergeFunctionsPass());
+ else if (!GlobalExtensions->empty() || !Extensions.empty())
+ MPM.add(createBarrierNoopPass());
+
addExtensionsToPM(EP_EnabledOnOptLevel0, MPM);
return;
}
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
}
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
else
MPM.add(createScalarReplAggregatesPass(-1, false));
MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
- if (!DisableSimplifyLibCalls)
- MPM.add(createSimplifyLibCallsPass()); // Library Call Optimizations
MPM.add(createJumpThreadingPass()); // Thread jumps.
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
MPM.add(createLoopIdiomPass()); // Recognize idioms like memset.
MPM.add(createLoopDeletionPass()); // Delete dead loops
- if (Vectorize) {
- MPM.add(createLoopVectorizePass());
- MPM.add(createLICMPass());
- }
-
if (!DisableUnrollLoops)
- MPM.add(createLoopUnrollPass()); // Unroll small loops
+ MPM.add(createSimpleLoopUnrollPass()); // Unroll small loops
addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
- if (OptLevel > 1)
- MPM.add(createGVNPass()); // Remove redundancies
+ if (OptLevel > 1) {
+ if (EnableMLSM)
+ MPM.add(createMergedLoadStoreMotionPass()); // Merge ld/st in diamonds
+ MPM.add(createGVNPass(DisableGVNLoadPRE)); // 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
addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
- if (Vectorize) {
- MPM.add(createBBVectorizePass());
- MPM.add(createInstructionCombiningPass());
- if (OptLevel > 1 && UseGVNAfterVectorization)
- MPM.add(createGVNPass()); // Remove redundancies
- else
- MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
+ if (RerollLoops)
+ MPM.add(createLoopRerollPass());
+ if (!RunSLPAfterLoopVectorization) {
+ if (SLPVectorize)
+ MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
+
+ if (BBVectorize) {
+ MPM.add(createBBVectorizePass());
+ MPM.add(createInstructionCombiningPass());
+ addExtensionsToPM(EP_Peephole, MPM);
+ if (OptLevel > 1 && UseGVNAfterVectorization)
+ MPM.add(createGVNPass(DisableGVNLoadPRE)); // Remove redundancies
+ else
+ MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
+
+ // BBVectorize may have significantly shortened a loop body; unroll again.
+ if (!DisableUnrollLoops)
+ MPM.add(createLoopUnrollPass());
+ }
}
+ if (LoadCombine)
+ MPM.add(createLoadCombinePass());
+
MPM.add(createAggressiveDCEPass()); // Delete dead instructions
- MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
+ 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
+ // we must insert a no-op module pass to reset the pass manager.
+ MPM.add(createBarrierNoopPass());
+
+ // Re-rotate loops in all our loop nests. These may have fallout out of
+ // rotated form due to GVN or other transformations, and the vectorizer relies
+ // on the rotated form.
+ if (ExtraVectorizerPasses)
+ MPM.add(createLoopRotatePass());
+
+ MPM.add(createLoopVectorizePass(DisableUnrollLoops, LoopVectorize));
+ // FIXME: Because of #pragma vectorize enable, the passes below are always
+ // inserted in the pipeline, even when the vectorizer doesn't run (ex. when
+ // on -O1 and no #pragma is found). Would be good to have these two passes
+ // as function calls, so that we can only pass them when the vectorizer
+ // changed the code.
+ MPM.add(createInstructionCombiningPass());
+ if (OptLevel > 1 && ExtraVectorizerPasses) {
+ // At higher optimization levels, try to clean up any runtime overlap and
+ // alignment checks inserted by the vectorizer. We want to track correllated
+ // runtime checks for two inner loops in the same outer loop, fold any
+ // common computations, hoist loop-invariant aspects out of any outer loop,
+ // and unswitch the runtime checks if possible. Once hoisted, we may have
+ // dead (or speculatable) control flows or more combining opportunities.
+ MPM.add(createEarlyCSEPass());
+ MPM.add(createCorrelatedValuePropagationPass());
+ MPM.add(createInstructionCombiningPass());
+ MPM.add(createLICMPass());
+ MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
+ MPM.add(createCFGSimplificationPass());
+ MPM.add(createInstructionCombiningPass());
+ }
+
+ if (RunSLPAfterLoopVectorization) {
+ if (SLPVectorize) {
+ MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
+ if (OptLevel > 1 && ExtraVectorizerPasses) {
+ MPM.add(createEarlyCSEPass());
+ }
+ }
+
+ if (BBVectorize) {
+ MPM.add(createBBVectorizePass());
+ MPM.add(createInstructionCombiningPass());
+ addExtensionsToPM(EP_Peephole, MPM);
+ if (OptLevel > 1 && UseGVNAfterVectorization)
+ MPM.add(createGVNPass(DisableGVNLoadPRE)); // Remove redundancies
+ else
+ MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
+
+ // BBVectorize may have significantly shortened a loop body; unroll again.
+ if (!DisableUnrollLoops)
+ MPM.add(createLoopUnrollPass());
+ }
+ }
+
+ addExtensionsToPM(EP_Peephole, MPM);
+ MPM.add(createCFGSimplificationPass());
+ MPM.add(createInstructionCombiningPass());
+
+ if (!DisableUnrollLoops)
+ MPM.add(createLoopUnrollPass()); // Unroll small loops
+
+ // After vectorization and unrolling, assume intrinsics may tell us more
+ // about pointer alignments.
+ MPM.add(createAlignmentFromAssumptionsPass());
if (!DisableUnitAtATime) {
// FIXME: We shouldn't bother with this anymore.
MPM.add(createConstantMergePass()); // Merge dup global constants
}
}
+
+ if (MergeFunctions)
+ MPM.add(createMergeFunctionsPass());
+
addExtensionsToPM(EP_OptimizerLast, MPM);
}
-void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
- bool Internalize,
- bool RunInliner,
- bool DisableGVNLoadPRE) {
+void PassManagerBuilder::addLTOOptimizationPasses(PassManagerBase &PM) {
// Provide AliasAnalysis services for optimizations.
addInitialAliasAnalysisPasses(PM);
- // Now that composite has been compiled, scan through the module, looking
- // for a main function. If main is defined, mark all other functions
- // internal.
- if (Internalize)
- PM.add(createInternalizePass(true));
-
// Propagate constants at call sites into the functions they call. This
// opens opportunities for globalopt (and inlining) by substituting function
// pointers passed as arguments to direct uses of functions.
// 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)
- PM.add(createFunctionInliningPass());
+ bool RunInliner = Inliner;
+ if (RunInliner) {
+ PM.add(Inliner);
+ Inliner = nullptr;
+ }
PM.add(createPruneEHPass()); // Remove dead EH info.
// The IPO passes may leave cruft around. Clean up after them.
PM.add(createInstructionCombiningPass());
+ addExtensionsToPM(EP_Peephole, PM);
PM.add(createJumpThreadingPass());
+
// Break up allocas
if (UseNewSROA)
PM.add(createSROAPass());
PM.add(createGlobalsModRefPass()); // IP alias analysis.
PM.add(createLICMPass()); // Hoist loop invariants.
+ if (EnableMLSM)
+ PM.add(createMergedLoadStoreMotionPass()); // Merge ld/st 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 optimize them.
+ PM.add(createIndVarSimplifyPass());
+ PM.add(createLoopDeletionPass());
+ PM.add(createLoopVectorizePass(true, LoopVectorize));
+
+ // More scalar chains could be vectorized due to more alias information
+ if (RunSLPAfterLoopVectorization)
+ if (SLPVectorize)
+ PM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
+
+ // After vectorization, assume intrinsics may tell us more about pointer
+ // alignments.
+ PM.add(createAlignmentFromAssumptionsPass());
+
+ if (LoadCombine)
+ PM.add(createLoadCombinePass());
+
// Cleanup and simplify the code after the scalar optimizations.
PM.add(createInstructionCombiningPass());
+ addExtensionsToPM(EP_Peephole, PM);
PM.add(createJumpThreadingPass());
// Now that we have optimized the program, discard unreachable functions.
PM.add(createGlobalDCEPass());
+
+ // FIXME: this is profitable (for compiler time) to do at -O0 too, but
+ // currently it damages debug info.
+ if (MergeFunctions)
+ PM.add(createMergeFunctionsPass());
}
-LLVMPassManagerBuilderRef LLVMPassManagerBuilderCreate(void) {
+void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
+ TargetMachine *TM) {
+ if (TM) {
+ PM.add(new DataLayoutPass());
+ TM->addAnalysisPasses(PM);
+ }
+
+ if (LibraryInfo)
+ PM.add(new TargetLibraryInfo(*LibraryInfo));
+
+ if (VerifyInput)
+ PM.add(createVerifierPass());
+
+ if (StripDebug)
+ PM.add(createStripSymbolsPass(true));
+
+ if (VerifyInput)
+ PM.add(createDebugInfoVerifierPass());
+
+ if (OptLevel != 0)
+ addLTOOptimizationPasses(PM);
+
+ if (VerifyOutput) {
+ PM.add(createVerifierPass());
+ PM.add(createDebugInfoVerifierPass());
+ }
+}
+
+inline PassManagerBuilder *unwrap(LLVMPassManagerBuilderRef P) {
+ return reinterpret_cast<PassManagerBuilder*>(P);
+}
+
+inline LLVMPassManagerBuilderRef wrap(PassManagerBuilder *P) {
+ return reinterpret_cast<LLVMPassManagerBuilderRef>(P);
+}
+
+LLVMPassManagerBuilderRef LLVMPassManagerBuilderCreate() {
PassManagerBuilder *PMB = new PassManagerBuilder();
return wrap(PMB);
}
void
LLVMPassManagerBuilderSetDisableSimplifyLibCalls(LLVMPassManagerBuilderRef PMB,
LLVMBool Value) {
- PassManagerBuilder *Builder = unwrap(PMB);
- Builder->DisableSimplifyLibCalls = Value;
+ // NOTE: The simplify-libcalls pass has been removed.
}
void
void LLVMPassManagerBuilderPopulateLTOPassManager(LLVMPassManagerBuilderRef PMB,
LLVMPassManagerRef PM,
- bool Internalize,
- bool RunInliner) {
+ LLVMBool Internalize,
+ LLVMBool RunInliner) {
PassManagerBuilder *Builder = unwrap(PMB);
PassManagerBase *LPM = unwrap(PM);
- Builder->populateLTOPassManager(*LPM, Internalize, RunInliner);
+
+ // A small backwards compatibility hack. populateLTOPassManager used to take
+ // an RunInliner option.
+ if (RunInliner && !Builder->Inliner)
+ Builder->Inliner = createFunctionInliningPass();
+
+ Builder->populateLTOPassManager(*LPM);
}