#include "llvm-c/Transforms/PassManagerBuilder.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/Passes.h"
+#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Verifier.h"
-#include "llvm/PassManager.h"
+#include "llvm/IR/LegacyPassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ManagedStatic.h"
-#include "llvm/Target/TargetLibraryInfo.h"
+#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Target/TargetMachine.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Vectorize.h"
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"));
RunLoopRerolling("reroll-loops", cl::Hidden,
cl::desc("Run the loop rerolling pass"));
+static cl::opt<bool>
+RunFloat2Int("float-to-int", cl::Hidden, cl::init(true),
+ cl::desc("Run the float2int (float demotion) 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(false), cl::Hidden,
+ 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"));
+
+static cl::opt<bool> EnableLoopInterchange(
+ "enable-loopinterchange", cl::init(false), cl::Hidden,
+ cl::desc("Enable the new, experimental LoopInterchange Pass"));
PassManagerBuilder::PassManagerBuilder() {
OptLevel = 2;
RerollLoops = RunLoopRerolling;
LoadCombine = RunLoadCombine;
DisableGVNLoadPRE = false;
+ VerifyInput = false;
+ VerifyOutput = false;
+ MergeFunctions = false;
}
PassManagerBuilder::~PassManagerBuilder() {
}
void PassManagerBuilder::addExtensionsToPM(ExtensionPointTy ETy,
- PassManagerBase &PM) const {
+ legacy::PassManagerBase &PM) const {
for (unsigned i = 0, e = GlobalExtensions->size(); i != e; ++i)
if ((*GlobalExtensions)[i].first == ETy)
(*GlobalExtensions)[i].second(*this, PM);
Extensions[i].second(*this, PM);
}
-void
-PassManagerBuilder::addInitialAliasAnalysisPasses(PassManagerBase &PM) const {
+void PassManagerBuilder::addInitialAliasAnalysisPasses(
+ legacy::PassManagerBase &PM) const {
// 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::populateFunctionPassManager(FunctionPassManager &FPM) {
+void PassManagerBuilder::populateFunctionPassManager(
+ legacy::FunctionPassManager &FPM) {
addExtensionsToPM(EP_EarlyAsPossible, FPM);
// Add LibraryInfo if we have some.
- if (LibraryInfo) FPM.add(new TargetLibraryInfo(*LibraryInfo));
+ if (LibraryInfo)
+ FPM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
if (OptLevel == 0) return;
FPM.add(createLowerExpectIntrinsicPass());
}
-void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
- // If all optimizations are disabled, just run the always-inline pass.
+void PassManagerBuilder::populateModulePassManager(
+ legacy::PassManagerBase &MPM) {
+ // 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 = nullptr;
}
- // FIXME: This 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 must insert a no-op module pass to reset the pass
- // manager to get the same behavior as EP_OptimizerLast in non-O0 builds.
- if (!GlobalExtensions->empty() || !Extensions.empty())
+ // 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);
}
// Add LibraryInfo if we have some.
- if (LibraryInfo) MPM.add(new TargetLibraryInfo(*LibraryInfo));
+ if (LibraryInfo)
+ MPM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
addInitialAliasAnalysisPasses(MPM);
MPM.add(createTailCallEliminationPass()); // Eliminate tail calls
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
MPM.add(createReassociatePass()); // Reassociate expressions
- MPM.add(createLoopRotatePass()); // Rotate Loop
+ // Rotate Loop - disable header duplication at -Oz
+ MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1));
MPM.add(createLICMPass()); // Hoist loop invariants
MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
MPM.add(createInstructionCombiningPass());
MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars
MPM.add(createLoopIdiomPass()); // Recognize idioms like memset.
MPM.add(createLoopDeletionPass()); // Delete dead loops
-
+ if (EnableLoopInterchange) {
+ MPM.add(createLoopInterchangePass()); // Interchange loops
+ MPM.add(createCFGSimplificationPass());
+ }
if (!DisableUnrollLoops)
MPM.add(createSimpleLoopUnrollPass()); // Unroll small loops
addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
if (OptLevel > 1) {
- MPM.add(createMergedLoadStoreMotionPass()); // Merge load/stores in diamond
+ 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
+ // Delete dead bit computations (instcombine runs after to fold away the dead
+ // computations, and then ADCE will run later to exploit any new DCE
+ // opportunities that creates).
+ MPM.add(createBitTrackingDCEPass()); // Delete dead bit computations
+
// Run instcombine after redundancy elimination to exploit opportunities
// opened up by them.
MPM.add(createInstructionCombiningPass());
MPM.add(createJumpThreadingPass()); // Thread jumps
MPM.add(createCorrelatedValuePropagationPass());
MPM.add(createDeadStoreEliminationPass()); // Delete dead stores
+ MPM.add(createLICMPass());
addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
// 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());
+
+ if (RunFloat2Int)
+ MPM.add(createFloat2IntPass());
+
+ // 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.
+ 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
// 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)
+ if (SLPVectorize) {
MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
+ if (OptLevel > 1 && ExtraVectorizerPasses) {
+ MPM.add(createEarlyCSEPass());
+ }
+ }
if (BBVectorize) {
MPM.add(createBBVectorizePass());
addExtensionsToPM(EP_Peephole, MPM);
MPM.add(createCFGSimplificationPass());
+ MPM.add(createInstructionCombiningPass());
- if (!DisableUnrollLoops)
+ if (!DisableUnrollLoops) {
MPM.add(createLoopUnrollPass()); // Unroll small loops
+ // This is a barrier pass to avoid combine LICM pass and loop unroll pass
+ // within same loop pass manager.
+ MPM.add(createInstructionSimplifierPass());
+
+ // Runtime unrolling will introduce runtime check in loop prologue. If the
+ // unrolled loop is a inner loop, then the prologue will be inside the
+ // outer loop. LICM pass can help to promote the runtime check out if the
+ // checked value is loop invariant.
+ MPM.add(createLICMPass());
+ }
+
+ // 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(createStripDeadPrototypesPass()); // Get rid of dead prototypes
MPM.add(createConstantMergePass()); // Merge dup global constants
}
}
+
+ if (MergeFunctions)
+ MPM.add(createMergeFunctionsPass());
+
addExtensionsToPM(EP_OptimizerLast, MPM);
}
-void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM) {
+void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
// Provide AliasAnalysis services for optimizations.
addInitialAliasAnalysisPasses(PM);
PM.add(createGlobalsModRefPass()); // IP alias analysis.
PM.add(createLICMPass()); // Hoist loop invariants.
- PM.add(createMergedLoadStoreMotionPass()); // Merge load/stores in diamonds
+ if (EnableMLSM)
+ PM.add(createMergedLoadStoreMotionPass()); // Merge ld/st in diamonds.
PM.add(createGVNPass(DisableGVNLoadPRE)); // Remove redundancies.
PM.add(createMemCpyOptPass()); // Remove dead memcpys.
// More loops are countable; try to optimize them.
PM.add(createIndVarSimplifyPass());
PM.add(createLoopDeletionPass());
- PM.add(createLoopVectorizePass(true, true));
+ if (EnableLoopInterchange)
+ PM.add(createLoopInterchangePass());
+
+ PM.add(createLoopVectorizePass(true, LoopVectorize));
// More scalar chains could be vectorized due to more alias information
- PM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
+ 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());
addExtensionsToPM(EP_Peephole, PM);
PM.add(createJumpThreadingPass());
+}
+void PassManagerBuilder::addLateLTOOptimizationPasses(
+ legacy::PassManagerBase &PM) {
// Delete basic blocks, which optimization passes may have killed.
PM.add(createCFGSimplificationPass());
// 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());
+}
+
+void PassManagerBuilder::populateLTOPassManager(legacy::PassManagerBase &PM) {
+ if (LibraryInfo)
+ PM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
+
+ if (VerifyInput)
+ PM.add(createVerifierPass());
+
+ if (OptLevel > 1)
+ addLTOOptimizationPasses(PM);
+
+ // Lower bit sets to globals. This pass supports Clang's control flow
+ // integrity mechanisms (-fsanitize=cfi*) and needs to run at link time if CFI
+ // is enabled. The pass does nothing if CFI is disabled.
+ PM.add(createLowerBitSetsPass());
+
+ if (OptLevel != 0)
+ addLateLTOOptimizationPasses(PM);
+
+ if (VerifyOutput)
+ PM.add(createVerifierPass());
}
inline PassManagerBuilder *unwrap(LLVMPassManagerBuilderRef P) {
LLVMPassManagerBuilderPopulateFunctionPassManager(LLVMPassManagerBuilderRef PMB,
LLVMPassManagerRef PM) {
PassManagerBuilder *Builder = unwrap(PMB);
- FunctionPassManager *FPM = unwrap<FunctionPassManager>(PM);
+ legacy::FunctionPassManager *FPM = unwrap<legacy::FunctionPassManager>(PM);
Builder->populateFunctionPassManager(*FPM);
}
LLVMPassManagerBuilderPopulateModulePassManager(LLVMPassManagerBuilderRef PMB,
LLVMPassManagerRef PM) {
PassManagerBuilder *Builder = unwrap(PMB);
- PassManagerBase *MPM = unwrap(PM);
+ legacy::PassManagerBase *MPM = unwrap(PM);
Builder->populateModulePassManager(*MPM);
}
LLVMBool Internalize,
LLVMBool RunInliner) {
PassManagerBuilder *Builder = unwrap(PMB);
- PassManagerBase *LPM = unwrap(PM);
+ legacy::PassManagerBase *LPM = unwrap(PM);
// A small backwards compatibility hack. populateLTOPassManager used to take
// an RunInliner option.
projects / oota-llvm.git / blobdiff