/// Return true if the specified string is the debug type
/// specified on the command line, or if none was specified on the command line
/// with the -debug-only=X option.
bool isCurrentDebugType(const char *DebugType) {
if (CurrentDebugType->empty())
return true;
// See if DebugType is in list. Note: do not use find() as that forces us to
// unnecessarily create an std::string instance.
for (auto &d : *CurrentDebugType) {
if (d == DebugType)
return true;
}
return false;
}
// GetLibSupportInfoOutputFile - Return a file stream to print our output on...
std::ostream *
llvm::GetLibSupportInfoOutputFile() {
std::string &LibSupportInfoOutputFilename = getLibSupportInfoOutputFilename();
if (LibSupportInfoOutputFilename.empty())
return cerr.stream();
if (LibSupportInfoOutputFilename == "-")
return cout.stream();
std::ostream *Result = new std::ofstream(LibSupportInfoOutputFilename.c_str(),
std::ios::app);
if (!Result->good()) {
cerr << "Error opening info-output-file '"
<< LibSupportInfoOutputFilename << " for appending!\n";
delete Result;
return cerr.stream();
}
return Result;
}
// GetLibSupportInfoOutputFile - Return a file stream to print our output on...
raw_ostream *
llvm::GetLibSupportInfoOutputFile() {
std::string &LibSupportInfoOutputFilename = getLibSupportInfoOutputFilename();
if (LibSupportInfoOutputFilename.empty())
return &errs();
if (LibSupportInfoOutputFilename == "-")
return &outs();
std::string Error;
raw_ostream *Result = new raw_fd_ostream(LibSupportInfoOutputFilename.c_str(),
Error, raw_fd_ostream::F_Append);
if (Error.empty())
return Result;
errs() << "Error opening info-output-file '"
<< LibSupportInfoOutputFilename << " for appending!\n";
delete Result;
return &errs();
}
void PassManagerBuilder::populateModulePassManager(
legacy::PassManagerBase &MPM) {
// Allow forcing function attributes as a debugging and tuning aid.
MPM.add(createForceFunctionAttrsLegacyPass());
// If all optimizations are disabled, just run the always-inline pass and,
// if enabled, the function merging pass.
if (OptLevel == 0) {
addPGOInstrPasses(MPM);
if (Inliner) {
MPM.add(Inliner);
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;
}
// Add LibraryInfo if we have some.
if (LibraryInfo)
MPM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
addInitialAliasAnalysisPasses(MPM);
if (!DisableUnitAtATime) {
// Infer attributes about declarations if possible.
MPM.add(createInferFunctionAttrsLegacyPass());
addExtensionsToPM(EP_ModuleOptimizerEarly, MPM);
MPM.add(createIPSCCPPass()); // IP SCCP
MPM.add(createGlobalOptimizerPass()); // Optimize out global vars
// Promote any localized global vars.
MPM.add(createPromoteMemoryToRegisterPass());
MPM.add(createDeadArgEliminationPass()); // Dead argument elimination
addInstructionCombiningPass(MPM); // Clean up after IPCP & DAE
addExtensionsToPM(EP_Peephole, MPM);
MPM.add(createCFGSimplificationPass()); // Clean up after IPCP & DAE
}
if (!PerformThinLTO)
/// PGO instrumentation is added during the compile phase for ThinLTO, do
/// not run it a second time
addPGOInstrPasses(MPM);
if (EnableNonLTOGlobalsModRef)
// We add a module alias analysis pass here. In part due to bugs in the
// analysis infrastructure this "works" in that the analysis stays alive
// for the entire SCC pass run below.
MPM.add(createGlobalsAAWrapperPass());
// Start of CallGraph SCC passes.
if (!DisableUnitAtATime)
MPM.add(createPruneEHPass()); // Remove dead EH info
if (Inliner) {
MPM.add(Inliner);
Inliner = nullptr;
}
if (!DisableUnitAtATime)
MPM.add(createPostOrderFunctionAttrsLegacyPass());
if (OptLevel > 2)
MPM.add(createArgumentPromotionPass()); // Scalarize uninlined fn args
addFunctionSimplificationPasses(MPM);
// If we are planning to perform ThinLTO later, let's not bloat the code with
// unrolling/vectorization/... now. We'll first run the inliner + CGSCC passes
// during ThinLTO and perform the rest of the optimizations afterward.
if (PrepareForThinLTO)
return;
// 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());
// Scheduling LoopVersioningLICM when inlining is over, because after that
// we may see more accurate aliasing. Reason to run this late is that too
// early versioning may prevent further inlining due to increase of code
// size. By placing it just after inlining other optimizations which runs
// later might get benefit of no-alias assumption in clone loop.
if (UseLoopVersioningLICM) {
MPM.add(createLoopVersioningLICMPass()); // Do LoopVersioningLICM
MPM.add(createLICMPass()); // Hoist loop invariants
}
if (!DisableUnitAtATime)
MPM.add(createReversePostOrderFunctionAttrsPass());
if (!DisableUnitAtATime && OptLevel > 1 && !PrepareForLTO)
// Remove avail extern fns and globals definitions if we aren't
// compiling an object file for later LTO. For LTO we want to preserve
// these so they are eligible for inlining at link-time. Note if they
// are unreferenced they will be removed by GlobalDCE later, so
// this only impacts referenced available externally globals.
// Eventually they will be suppressed during codegen, but eliminating
// here enables more opportunity for GlobalDCE as it may make
// globals referenced by available external functions dead
// and saves running remaining passes on the eliminated functions.
MPM.add(createEliminateAvailableExternallyPass());
if (PerformThinLTO) {
// Remove dead fns and globals. Removing unreferenced functions could lead
// to more opportunities for globalopt.
MPM.add(createGlobalDCEPass());
MPM.add(createGlobalOptimizerPass());
// Remove dead fns and globals after globalopt.
MPM.add(createGlobalDCEPass());
addFunctionSimplificationPasses(MPM);
}
if (EnableNonLTOGlobalsModRef)
// We add a fresh GlobalsModRef run at this point. This is particularly
// useful as the above will have inlined, DCE'ed, and function-attr
// propagated everything. We should at this point have a reasonably minimal
// and richly annotated call graph. By computing aliasing and mod/ref
// information for all local globals here, the late loop passes and notably
// the vectorizer will be able to use them to help recognize vectorizable
// memory operations.
//
// Note that this relies on a bug in the pass manager which preserves
// a module analysis into a function pass pipeline (and throughout it) so
// long as the first function pass doesn't invalidate the module analysis.
// Thus both Float2Int and LoopRotate have to preserve AliasAnalysis for
// this to work. Fortunately, it is trivial to preserve AliasAnalysis
// (doing nothing preserves it as it is required to be conservatively
// correct in the face of IR changes).
MPM.add(createGlobalsAAWrapperPass());
if (RunFloat2Int)
MPM.add(createFloat2IntPass());
addExtensionsToPM(EP_VectorizerStart, MPM);
// 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. Disable header duplication at -Oz.
MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1));
// Distribute loops to allow partial vectorization. I.e. isolate dependences
// into separate loop that would otherwise inhibit vectorization.
if (EnableLoopDistribute)
MPM.add(createLoopDistributePass());
MPM.add(createLoopVectorizePass(DisableUnrollLoops, LoopVectorize));
// Eliminate loads by forwarding stores from the previous iteration to loads
// of the current iteration.
if (EnableLoopLoadElim)
MPM.add(createLoopLoadEliminationPass());
// 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.
addInstructionCombiningPass(MPM);
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());
addInstructionCombiningPass(MPM);
MPM.add(createLICMPass());
MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
MPM.add(createCFGSimplificationPass());
addInstructionCombiningPass(MPM);
}
if (RunSLPAfterLoopVectorization) {
if (SLPVectorize) {
MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
if (OptLevel > 1 && ExtraVectorizerPasses) {
MPM.add(createEarlyCSEPass());
}
}
if (BBVectorize) {
MPM.add(createBBVectorizePass());
addInstructionCombiningPass(MPM);
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());
addInstructionCombiningPass(MPM);
if (!DisableUnrollLoops) {
MPM.add(createLoopUnrollPass()); // Unroll small loops
// LoopUnroll may generate some redundency to cleanup.
addInstructionCombiningPass(MPM);
// 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
// GlobalOpt already deletes dead functions and globals, at -O2 try a
// late pass of GlobalDCE. It is capable of deleting dead cycles.
if (OptLevel > 1) {
MPM.add(createGlobalDCEPass()); // Remove dead fns and globals.
MPM.add(createConstantMergePass()); // Merge dup global constants
}
}
if (MergeFunctions)
MPM.add(createMergeFunctionsPass());
addExtensionsToPM(EP_OptimizerLast, MPM);
}
void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
// If all optimizations are disabled, just run the always-inline pass.
if (OptLevel == 0) {
if (Inliner) {
MPM.add(Inliner);
Inliner = 0;
}
// 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())
MPM.add(createBarrierNoopPass());
addExtensionsToPM(EP_EnabledOnOptLevel0, MPM);
return;
}
// Add LibraryInfo if we have some.
if (LibraryInfo) MPM.add(new TargetLibraryInfo(*LibraryInfo));
addInitialAliasAnalysisPasses(MPM);
if (!DisableUnitAtATime) {
addExtensionsToPM(EP_ModuleOptimizerEarly, MPM);
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
MPM.add(createCFGSimplificationPass()); // Clean up after IPCP & DAE
}
// Start of CallGraph SCC passes.
if (!DisableUnitAtATime)
MPM.add(createPruneEHPass()); // Remove dead EH info
if (Inliner) {
MPM.add(Inliner);
Inliner = 0;
}
if (!DisableUnitAtATime)
MPM.add(createFunctionAttrsPass()); // Set readonly/readnone attrs
if (OptLevel > 2)
MPM.add(createArgumentPromotionPass()); // Scalarize uninlined fn args
// Start of function pass.
// Break up aggregate allocas, using SSAUpdater.
if (UseNewSROA)
MPM.add(createSROAPass(/*RequiresDomTree*/ false));
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
MPM.add(createTailCallEliminationPass()); // Eliminate tail calls
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
MPM.add(createReassociatePass()); // Reassociate expressions
MPM.add(createLoopRotatePass()); // Rotate Loop
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 (LoopVectorize && OptLevel > 1 && SizeLevel < 2)
MPM.add(createLoopVectorizePass());
if (!DisableUnrollLoops)
MPM.add(createLoopUnrollPass()); // Unroll small loops
addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
if (OptLevel > 1)
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());
MPM.add(createJumpThreadingPass()); // Thread jumps
MPM.add(createCorrelatedValuePropagationPass());
MPM.add(createDeadStoreEliminationPass()); // Delete dead stores
addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
if (SLPVectorize)
MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
if (BBVectorize) {
MPM.add(createBBVectorizePass());
MPM.add(createInstructionCombiningPass());
if (OptLevel > 1 && UseGVNAfterVectorization)
MPM.add(createGVNPass()); // Remove redundancies
else
MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
// BBVectorize may have significantly shortened a loop body; unroll again.
if (!DisableUnrollLoops)
MPM.add(createLoopUnrollPass());
}
MPM.add(createAggressiveDCEPass()); // Delete dead instructions
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
MPM.add(createInstructionCombiningPass()); // Clean up after everything.
if (!DisableUnitAtATime) {
// FIXME: We shouldn't bother with this anymore.
MPM.add(createStripDeadPrototypesPass()); // Get rid of dead prototypes
// GlobalOpt already deletes dead functions and globals, at -O2 try a
// late pass of GlobalDCE. It is capable of deleting dead cycles.
if (OptLevel > 1) {
MPM.add(createGlobalDCEPass()); // Remove dead fns and globals.
MPM.add(createConstantMergePass()); // Merge dup global constants
}
}
addExtensionsToPM(EP_OptimizerLast, MPM);
}
/// Check if GlobalExtensions is constructed and not empty.
/// Since GlobalExtensions is a managed static, calling 'empty()' will trigger
/// the construction of the object.
static bool GlobalExtensionsNotEmpty() {
return GlobalExtensions.isConstructed() && !GlobalExtensions->empty();
}
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: 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;
}
// Add LibraryInfo if we have some.
if (LibraryInfo)
MPM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
addInitialAliasAnalysisPasses(MPM);
if (!DisableUnitAtATime) {
addExtensionsToPM(EP_ModuleOptimizerEarly, MPM);
MPM.add(createIPSCCPPass()); // IP SCCP
MPM.add(createGlobalOptimizerPass()); // Optimize out global vars
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
}
// Start of CallGraph SCC passes.
if (!DisableUnitAtATime)
MPM.add(createPruneEHPass()); // Remove dead EH info
if (Inliner) {
MPM.add(Inliner);
Inliner = nullptr;
}
if (!DisableUnitAtATime)
MPM.add(createFunctionAttrsPass()); // Set readonly/readnone attrs
if (OptLevel > 2)
MPM.add(createArgumentPromotionPass()); // Scalarize uninlined fn args
// Start of function pass.
// Break up aggregate allocas, using SSAUpdater.
if (UseNewSROA)
MPM.add(createSROAPass(/*RequiresDomTree*/ false));
else
MPM.add(createScalarReplAggregatesPass(-1, false));
MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
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
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
MPM.add(createReassociatePass()); // Reassociate expressions
// 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) {
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());
addExtensionsToPM(EP_Peephole, MPM);
MPM.add(createJumpThreadingPass()); // Thread jumps
MPM.add(createCorrelatedValuePropagationPass());
MPM.add(createDeadStoreEliminationPass()); // Delete dead stores
MPM.add(createLICMPass());
addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
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(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());
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. Disable header duplication at -Oz.
MPM.add(createLoopRotatePass(SizeLevel == 2 ? 0 : -1));
// Distribute loops to allow partial vectorization. I.e. isolate dependences
// into separate loop that would otherwise inhibit vectorization.
if (EnableLoopDistribute)
MPM.add(createLoopDistributePass());
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
// LoopUnroll may generate some redundency to cleanup.
MPM.add(createInstructionCombiningPass());
// 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
// GlobalOpt already deletes dead functions and globals, at -O2 try a
// late pass of GlobalDCE. It is capable of deleting dead cycles.
if (OptLevel > 1) {
if (!PrepareForLTO) {
// Remove avail extern fns and globals definitions if we aren't
// compiling an object file for later LTO. For LTO we want to preserve
// these so they are eligible for inlining at link-time. Note if they
// are unreferenced they will be removed by GlobalDCE below, so
// this only impacts referenced available externally globals.
// Eventually they will be suppressed during codegen, but eliminating
// here enables more opportunity for GlobalDCE as it may make
// globals referenced by available external functions dead.
MPM.add(createEliminateAvailableExternallyPass());
}
MPM.add(createGlobalDCEPass()); // Remove dead fns and globals.
MPM.add(createConstantMergePass()); // Merge dup global constants
}
}
if (MergeFunctions)
MPM.add(createMergeFunctionsPass());
addExtensionsToPM(EP_OptimizerLast, MPM);
}