blob: 5d3736655093b2ba8204b47217ccc3f974831b52 [file] [log] [blame]
//===- PassManagerBuilder.cpp - Build Standard Pass -----------------------===//
// The LLVM Compiler Infrastructure
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
// This file defines the PassManagerBuilder class, which is used to set up a
// "standard" optimization sequence suitable for languages like C and C++.
#include "llvm/Transforms/IPO/PassManagerBuilder.h"
#include "llvm-c/Transforms/PassManagerBuilder.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/BasicAliasAnalysis.h"
#include "llvm/Analysis/CFLAndersAliasAnalysis.h"
#include "llvm/Analysis/CFLSteensAliasAnalysis.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/InlineCost.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Analysis/ScopedNoAliasAA.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TypeBasedAliasAnalysis.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/ModuleSummaryIndex.h"
#include "llvm/IR/Verifier.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/IPO/ForceFunctionAttrs.h"
#include "llvm/Transforms/IPO/FunctionAttrs.h"
#include "llvm/Transforms/IPO/InferFunctionAttrs.h"
#include "llvm/Transforms/Instrumentation.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Scalar/GVN.h"
#include "llvm/Transforms/Scalar/SimpleLoopUnswitch.h"
#include "llvm/Transforms/Vectorize.h"
using namespace llvm;
static cl::opt<bool>
RunPartialInlining("enable-partial-inlining", cl::init(false), cl::Hidden,
cl::ZeroOrMore, cl::desc("Run Partial inlinining pass"));
static cl::opt<bool>
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>
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>
RunLoopRerolling("reroll-loops", cl::Hidden,
cl::desc("Run the loop rerolling pass"));
static cl::opt<bool> RunNewGVN("enable-newgvn", cl::init(false), cl::Hidden,
cl::desc("Run the NewGVN pass"));
static cl::opt<bool>
cl::init(true), cl::Hidden,
cl::desc("Run the SLP vectorizer (and BB vectorizer) after the Loop "
"vectorizer instead of before"));
// Experimental option to use CFL-AA
enum class CFLAAType { None, Steensgaard, Andersen, Both };
static cl::opt<CFLAAType>
UseCFLAA("use-cfl-aa", cl::init(CFLAAType::None), cl::Hidden,
cl::desc("Enable the new, experimental CFL alias analysis"),
cl::values(clEnumValN(CFLAAType::None, "none", "Disable CFL-AA"),
clEnumValN(CFLAAType::Steensgaard, "steens",
"Enable unification-based CFL-AA"),
clEnumValN(CFLAAType::Andersen, "anders",
"Enable inclusion-based CFL-AA"),
clEnumValN(CFLAAType::Both, "both",
"Enable both variants of CFL-AA")));
static cl::opt<bool> EnableLoopInterchange(
"enable-loopinterchange", cl::init(false), cl::Hidden,
cl::desc("Enable the new, experimental LoopInterchange Pass"));
static cl::opt<bool>
EnablePrepareForThinLTO("prepare-for-thinlto", cl::init(false), cl::Hidden,
cl::desc("Enable preparation for ThinLTO."));
static cl::opt<bool> RunPGOInstrGen(
"profile-generate", cl::init(false), cl::Hidden,
cl::desc("Enable PGO instrumentation."));
static cl::opt<std::string>
PGOOutputFile("profile-generate-file", cl::init(""), cl::Hidden,
cl::desc("Specify the path of profile data file."));
static cl::opt<std::string> RunPGOInstrUse(
"profile-use", cl::init(""), cl::Hidden, cl::value_desc("filename"),
cl::desc("Enable use phase of PGO instrumentation and specify the path "
"of profile data file"));
static cl::opt<bool> UseLoopVersioningLICM(
"enable-loop-versioning-licm", cl::init(false), cl::Hidden,
cl::desc("Enable the experimental Loop Versioning LICM pass"));
static cl::opt<bool>
DisablePreInliner("disable-preinline", cl::init(false), cl::Hidden,
cl::desc("Disable pre-instrumentation inliner"));
static cl::opt<int> PreInlineThreshold(
"preinline-threshold", cl::Hidden, cl::init(75), cl::ZeroOrMore,
cl::desc("Control the amount of inlining in pre-instrumentation inliner "
"(default = 75)"));
static cl::opt<bool> EnableEarlyCSEMemSSA(
"enable-earlycse-memssa", cl::init(true), cl::Hidden,
cl::desc("Enable the EarlyCSE w/ MemorySSA pass (default = on)"));
static cl::opt<bool> EnableGVNHoist(
"enable-gvn-hoist", cl::init(false), cl::Hidden,
cl::desc("Enable the GVN hoisting pass (default = off)"));
static cl::opt<bool>
DisableLibCallsShrinkWrap("disable-libcalls-shrinkwrap", cl::init(false),
cl::desc("Disable shrink-wrap library calls"));
static cl::opt<bool>
EnableSimpleLoopUnswitch("enable-simple-loop-unswitch", cl::init(false),
cl::desc("Enable the simple loop unswitch pass."));
static cl::opt<bool> EnableGVNSink(
"enable-gvn-sink", cl::init(false), cl::Hidden,
cl::desc("Enable the GVN sinking pass (default = off)"));
PassManagerBuilder::PassManagerBuilder() {
OptLevel = 2;
SizeLevel = 0;
LibraryInfo = nullptr;
Inliner = nullptr;
DisableUnrollLoops = false;
SLPVectorize = RunSLPVectorization;
LoopVectorize = RunLoopVectorization;
RerollLoops = RunLoopRerolling;
NewGVN = RunNewGVN;
DisableGVNLoadPRE = false;
VerifyInput = false;
VerifyOutput = false;
MergeFunctions = false;
PrepareForLTO = false;
EnablePGOInstrGen = RunPGOInstrGen;
PGOInstrGen = PGOOutputFile;
PGOInstrUse = RunPGOInstrUse;
PrepareForThinLTO = EnablePrepareForThinLTO;
PerformThinLTO = false;
DivergentTarget = false;
PassManagerBuilder::~PassManagerBuilder() {
delete LibraryInfo;
delete Inliner;
/// Set of global extensions, automatically added as part of the standard set.
static ManagedStatic<SmallVector<std::pair<PassManagerBuilder::ExtensionPointTy,
PassManagerBuilder::ExtensionFn>, 8> > GlobalExtensions;
/// 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::addGlobalExtension(
PassManagerBuilder::ExtensionPointTy Ty,
PassManagerBuilder::ExtensionFn Fn) {
GlobalExtensions->push_back(std::make_pair(Ty, std::move(Fn)));
void PassManagerBuilder::addExtension(ExtensionPointTy Ty, ExtensionFn Fn) {
Extensions.push_back(std::make_pair(Ty, std::move(Fn)));
void PassManagerBuilder::addExtensionsToPM(ExtensionPointTy ETy,
legacy::PassManagerBase &PM) const {
if (GlobalExtensionsNotEmpty()) {
for (auto &Ext : *GlobalExtensions) {
if (Ext.first == ETy)
Ext.second(*this, PM);
for (unsigned i = 0, e = Extensions.size(); i != e; ++i)
if (Extensions[i].first == ETy)
Extensions[i].second(*this, PM);
void PassManagerBuilder::addInitialAliasAnalysisPasses(
legacy::PassManagerBase &PM) const {
switch (UseCFLAA) {
case CFLAAType::Steensgaard:
case CFLAAType::Andersen:
case CFLAAType::Both:
// Add TypeBasedAliasAnalysis before BasicAliasAnalysis so that
// BasicAliasAnalysis wins if they disagree. This is intended to help
// support "obvious" type-punning idioms.
void PassManagerBuilder::addInstructionCombiningPass(
legacy::PassManagerBase &PM) const {
bool ExpensiveCombines = OptLevel > 2;
void PassManagerBuilder::populateFunctionPassManager(
legacy::FunctionPassManager &FPM) {
addExtensionsToPM(EP_EarlyAsPossible, FPM);
// Add LibraryInfo if we have some.
if (LibraryInfo)
FPM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
if (OptLevel == 0) return;
// Do PGO instrumentation generation or use pass as the option specified.
void PassManagerBuilder::addPGOInstrPasses(legacy::PassManagerBase &MPM) {
if (!EnablePGOInstrGen && PGOInstrUse.empty() && PGOSampleUse.empty())
// Perform the preinline and cleanup passes for O1 and above.
// And avoid doing them if optimizing for size.
if (OptLevel > 0 && SizeLevel == 0 && !DisablePreInliner &&
PGOSampleUse.empty()) {
// Create preinline pass. We construct an InlineParams object and specify
// the threshold here to avoid the command line options of the regular
// inliner to influence pre-inlining. The only fields of InlineParams we
// care about are DefaultThreshold and HintThreshold.
InlineParams IP;
IP.DefaultThreshold = PreInlineThreshold;
// FIXME: The hint threshold has the same value used by the regular inliner.
// This should probably be lowered after performance testing.
IP.HintThreshold = 325;
MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
MPM.add(createInstructionCombiningPass()); // Combine silly seq's
addExtensionsToPM(EP_Peephole, MPM);
if (EnablePGOInstrGen) {
// Add the profile lowering pass.
InstrProfOptions Options;
if (!PGOInstrGen.empty())
Options.InstrProfileOutput = PGOInstrGen;
Options.DoCounterPromotion = true;
if (!PGOInstrUse.empty())
// Indirect call promotion that promotes intra-module targets only.
// For ThinLTO this is done earlier due to interactions with globalopt
// for imported functions. We don't run this at -O0.
if (OptLevel > 0)
createPGOIndirectCallPromotionLegacyPass(false, !PGOSampleUse.empty()));
void PassManagerBuilder::addFunctionSimplificationPasses(
legacy::PassManagerBase &MPM) {
// Start of function pass.
// Break up aggregate allocas, using SSAUpdater.
MPM.add(createEarlyCSEPass(EnableEarlyCSEMemSSA)); // Catch trivial redundancies
if (EnableGVNHoist)
if (EnableGVNSink) {
// Speculative execution if the target has divergent branches; otherwise nop.
MPM.add(createJumpThreadingPass()); // Thread jumps.
MPM.add(createCorrelatedValuePropagationPass()); // Propagate conditionals
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
// Combine silly seq's
if (SizeLevel == 0 && !DisableLibCallsShrinkWrap)
addExtensionsToPM(EP_Peephole, MPM);
// Optimize memory intrinsic calls based on the profiled size information.
if (SizeLevel == 0)
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
if (EnableSimpleLoopUnswitch)
MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3, DivergentTarget));
MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars
MPM.add(createLoopIdiomPass()); // Recognize idioms like memset.
addExtensionsToPM(EP_LateLoopOptimizations, MPM);
MPM.add(createLoopDeletionPass()); // Delete dead loops
if (EnableLoopInterchange) {
MPM.add(createLoopInterchangePass()); // Interchange loops
if (!DisableUnrollLoops)
MPM.add(createSimpleLoopUnrollPass(OptLevel)); // Unroll small loops
addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
if (OptLevel > 1) {
MPM.add(createMergedLoadStoreMotionPass()); // Merge ld/st in diamonds
MPM.add(NewGVN ? createNewGVNPass()
: 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.
addExtensionsToPM(EP_Peephole, MPM);
MPM.add(createJumpThreadingPass()); // Thread jumps
MPM.add(createDeadStoreEliminationPass()); // Delete dead stores
addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
if (RerollLoops)
if (!RunSLPAfterLoopVectorization && SLPVectorize)
MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
MPM.add(createAggressiveDCEPass()); // Delete dead instructions
MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
// Clean up after everything.
addExtensionsToPM(EP_Peephole, MPM);
void PassManagerBuilder::populateModulePassManager(
legacy::PassManagerBase &MPM) {
if (!PGOSampleUse.empty()) {
// Allow forcing function attributes as a debugging and tuning aid.
// If all optimizations are disabled, just run the always-inline pass and,
// if enabled, the function merging pass.
if (OptLevel == 0) {
if (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)
else if (GlobalExtensionsNotEmpty() || !Extensions.empty())
if (PerformThinLTO) {
// Drop available_externally and unreferenced globals. This is necessary
// with ThinLTO in order to avoid leaving undefined references to dead
// globals in the object file.
addExtensionsToPM(EP_EnabledOnOptLevel0, MPM);
// Rename anon globals to be able to export them in the summary.
// This has to be done after we add the extensions to the pass manager
// as there could be passes (e.g. Adddress sanitizer) which introduce
// new unnamed globals.
if (PrepareForThinLTO)
// Add LibraryInfo if we have some.
if (LibraryInfo)
MPM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
// For ThinLTO there are two passes of indirect call promotion. The
// first is during the compile phase when PerformThinLTO=false and
// intra-module indirect call targets are promoted. The second is during
// the ThinLTO backend when PerformThinLTO=true, when we promote imported
// inter-module indirect calls. For that we perform indirect call promotion
// earlier in the pass pipeline, here before globalopt. Otherwise imported
// available_externally functions look unreferenced and are removed.
if (PerformThinLTO)
MPM.add(createPGOIndirectCallPromotionLegacyPass(/*InLTO = */ true,
// For SamplePGO in ThinLTO compile phase, we do not want to unroll loops
// as it will change the CFG too much to make the 2nd profile annotation
// in backend more difficult.
bool PrepareForThinLTOUsingPGOSampleProfile =
PrepareForThinLTO && !PGOSampleUse.empty();
if (PrepareForThinLTOUsingPGOSampleProfile)
DisableUnrollLoops = true;
// Infer attributes about declarations if possible.
addExtensionsToPM(EP_ModuleOptimizerEarly, MPM);
if (OptLevel > 2)
MPM.add(createIPSCCPPass()); // IP SCCP
MPM.add(createGlobalOptimizerPass()); // Optimize out global vars
// Promote any localized global vars.
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
// For SamplePGO in ThinLTO compile phase, we do not want to do indirect
// call promotion as it will change the CFG too much to make the 2nd
// profile annotation in backend more difficult.
// PGO instrumentation is added during the compile phase for ThinLTO, do
// not run it a second time
if (!PerformThinLTO && !PrepareForThinLTOUsingPGOSampleProfile)
// 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.
// Start of CallGraph SCC passes.
MPM.add(createPruneEHPass()); // Remove dead EH info
bool RunInliner = false;
if (Inliner) {
Inliner = nullptr;
RunInliner = true;
if (OptLevel > 2)
MPM.add(createArgumentPromotionPass()); // Scalarize uninlined fn args
addExtensionsToPM(EP_CGSCCOptimizerLate, 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.
if (RunPartialInlining)
if (OptLevel > 1 && !PrepareForLTO && !PrepareForThinLTO)
// 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.
// The inliner performs some kind of dead code elimination as it goes,
// but there are cases that are not really caught by it. We might
// at some point consider teaching the inliner about them, but it
// is OK for now to run GlobalOpt + GlobalDCE in tandem as their
// benefits generally outweight the cost, making the whole pipeline
// faster.
if (RunInliner) {
// 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) {
// Ensure we perform any last passes, but do so before renaming anonymous
// globals in case the passes add any.
addExtensionsToPM(EP_OptimizerLast, MPM);
// Rename anon globals to be able to export them in the summary.
if (PerformThinLTO)
// Optimize globals now when performing ThinLTO, this enables more
// optimizations later.
// 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
// 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).
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. This is
// currently only performed for loops marked with the metadata
// llvm.loop.distribute=true or when -enable-loop-distribute is specified.
MPM.add(createLoopVectorizePass(DisableUnrollLoops, LoopVectorize));
// Eliminate loads by forwarding stores from the previous iteration to loads
// of the current iteration.
// 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.
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(createLoopUnswitchPass(SizeLevel || OptLevel < 3, DivergentTarget));
if (RunSLPAfterLoopVectorization && SLPVectorize) {
MPM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
if (OptLevel > 1 && ExtraVectorizerPasses) {
addExtensionsToPM(EP_Peephole, MPM);
// Switches to lookup tables and other transforms that may not be considered
// canonical by other IR passes.
MPM.add(createCFGSimplificationPass(1, true, true, false));
if (!DisableUnrollLoops) {
MPM.add(createLoopUnrollPass(OptLevel)); // Unroll small loops
// LoopUnroll may generate some redundency to cleanup.
// 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.
// After vectorization and unrolling, assume intrinsics may tell us more
// about pointer alignments.
// 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)
// LoopSink pass sinks instructions hoisted by LICM, which serves as a
// canonicalization pass that enables other optimizations. As a result,
// LoopSink pass needs to be a very late IR pass to avoid undoing LICM
// result too early.
// Get rid of LCSSA nodes.
// This hoists/decomposes div/rem ops. It should run after other sink/hoist
// passes to avoid re-sinking, but before SimplifyCFG because it can allow
// flattening of blocks.
// LoopSink (and other loop passes since the last simplifyCFG) might have
// resulted in single-entry-single-exit or empty blocks. Clean up the CFG.
addExtensionsToPM(EP_OptimizerLast, MPM);
void PassManagerBuilder::addLTOOptimizationPasses(legacy::PassManagerBase &PM) {
// Remove unused virtual tables to improve the quality of code generated by
// whole-program devirtualization and bitset lowering.
// Provide AliasAnalysis services for optimizations.
// Allow forcing function attributes as a debugging and tuning aid.
// Infer attributes about declarations if possible.
if (OptLevel > 1) {
// Split call-site with more constrained arguments.
// Indirect call promotion. This should promote all the targets that are
// left by the earlier promotion pass that promotes intra-module targets.
// This two-step promotion is to save the compile time. For LTO, it should
// produce the same result as if we only do promotion here.
createPGOIndirectCallPromotionLegacyPass(true, !PGOSampleUse.empty()));
// 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.
// Attach metadata to indirect call sites indicating the set of functions
// they may target at run-time. This should follow IPSCCP.
// Infer attributes about definitions. The readnone attribute in particular is
// required for virtual constant propagation.
// Split globals using inrange annotations on GEP indices. This can help
// improve the quality of generated code when virtual constant propagation or
// control flow integrity are enabled.
// Apply whole-program devirtualization and virtual constant propagation.
PM.add(createWholeProgramDevirtPass(ExportSummary, nullptr));
// That's all we need at opt level 1.
if (OptLevel == 1)
// Now that we internalized some globals, see if we can hack on them!
// Promote any localized global vars.
// Linking modules together can lead to duplicated global constants, only
// keep one copy of each constant.
// Remove unused arguments from functions.
// Reduce the code after globalopt and ipsccp. Both can open up significant
// simplification opportunities, and both can propagate functions through
// function pointers. When this happens, we often have to resolve varargs
// calls, etc, so let instcombine do this.
addExtensionsToPM(EP_Peephole, PM);
// Inline small functions
bool RunInliner = Inliner;
if (RunInliner) {
Inliner = nullptr;
PM.add(createPruneEHPass()); // Remove dead EH info.
// Optimize globals again if we ran the inliner.
if (RunInliner)
PM.add(createGlobalDCEPass()); // Remove dead functions.
// If we didn't decide to inline a function, check to see if we can
// transform it to pass arguments by value instead of by reference.
// The IPO passes may leave cruft around. Clean up after them.
addExtensionsToPM(EP_Peephole, PM);
// Break up allocas
// Run a few AA driven optimizations here and now, to cleanup the code.
PM.add(createPostOrderFunctionAttrsLegacyPass()); // Add nocapture.
PM.add(createGlobalsAAWrapperPass()); // IP alias analysis.
PM.add(createLICMPass()); // Hoist loop invariants.
PM.add(createMergedLoadStoreMotionPass()); // Merge ld/st in diamonds.
PM.add(NewGVN ? createNewGVNPass()
: createGVNPass(DisableGVNLoadPRE)); // Remove redundancies.
PM.add(createMemCpyOptPass()); // Remove dead memcpys.
// Nuke dead stores.
// More loops are countable; try to optimize them.
if (EnableLoopInterchange)
if (!DisableUnrollLoops)
PM.add(createSimpleLoopUnrollPass(OptLevel)); // Unroll small loops
PM.add(createLoopVectorizePass(true, LoopVectorize));
// The vectorizer may have significantly shortened a loop body; unroll again.
if (!DisableUnrollLoops)
// Now that we've optimized loops (in particular loop induction variables),
// we may have exposed more scalar opportunities. Run parts of the scalar
// optimizer again at this point.
addInstructionCombiningPass(PM); // Initial cleanup
PM.add(createCFGSimplificationPass()); // if-convert
PM.add(createSCCPPass()); // Propagate exposed constants
addInstructionCombiningPass(PM); // Clean up again
// 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.
// Cleanup and simplify the code after the scalar optimizations.
addExtensionsToPM(EP_Peephole, PM);
void PassManagerBuilder::addLateLTOOptimizationPasses(
legacy::PassManagerBase &PM) {
// Delete basic blocks, which optimization passes may have killed.
// Drop bodies of available externally objects to improve GlobalDCE.
// Now that we have optimized the program, discard unreachable functions.
// FIXME: this is profitable (for compiler time) to do at -O0 too, but
// currently it damages debug info.
if (MergeFunctions)
void PassManagerBuilder::populateThinLTOPassManager(
legacy::PassManagerBase &PM) {
PerformThinLTO = true;
if (VerifyInput)
if (ImportSummary) {
// These passes import type identifier resolutions for whole-program
// devirtualization and CFI. They must run early because other passes may
// disturb the specific instruction patterns that these passes look for,
// creating dependencies on resolutions that may not appear in the summary.
// For example, GVN may transform the pattern assume(type.test) appearing in
// two basic blocks into assume(phi(type.test, type.test)), which would
// transform a dependency on a WPD resolution into a dependency on a type
// identifier resolution for CFI.
// Also, WPD has access to more precise information than ICP and can
// devirtualize more effectively, so it should operate on the IR first.
PM.add(createWholeProgramDevirtPass(nullptr, ImportSummary));
PM.add(createLowerTypeTestsPass(nullptr, ImportSummary));
if (VerifyOutput)
PerformThinLTO = false;
void PassManagerBuilder::populateLTOPassManager(legacy::PassManagerBase &PM) {
if (LibraryInfo)
PM.add(new TargetLibraryInfoWrapperPass(*LibraryInfo));
if (VerifyInput)
if (OptLevel != 0)
else {
// The whole-program-devirt pass needs to run at -O0 because only it knows
// about the llvm.type.checked.load intrinsic: it needs to both lower the
// intrinsic itself and handle it in the summary.
PM.add(createWholeProgramDevirtPass(ExportSummary, nullptr));
// Create a function that performs CFI checks for cross-DSO calls with targets
// in the current module.
// Lower type metadata and the type.test intrinsic. 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(createLowerTypeTestsPass(ExportSummary, nullptr));
if (OptLevel != 0)
if (VerifyOutput)
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 LLVMPassManagerBuilderDispose(LLVMPassManagerBuilderRef PMB) {
PassManagerBuilder *Builder = unwrap(PMB);
delete Builder;
LLVMPassManagerBuilderSetOptLevel(LLVMPassManagerBuilderRef PMB,
unsigned OptLevel) {
PassManagerBuilder *Builder = unwrap(PMB);
Builder->OptLevel = OptLevel;
LLVMPassManagerBuilderSetSizeLevel(LLVMPassManagerBuilderRef PMB,
unsigned SizeLevel) {
PassManagerBuilder *Builder = unwrap(PMB);
Builder->SizeLevel = SizeLevel;
LLVMPassManagerBuilderSetDisableUnitAtATime(LLVMPassManagerBuilderRef PMB,
LLVMBool Value) {
// NOTE: The DisableUnitAtATime switch has been removed.
LLVMPassManagerBuilderSetDisableUnrollLoops(LLVMPassManagerBuilderRef PMB,
LLVMBool Value) {
PassManagerBuilder *Builder = unwrap(PMB);
Builder->DisableUnrollLoops = Value;
LLVMPassManagerBuilderSetDisableSimplifyLibCalls(LLVMPassManagerBuilderRef PMB,
LLVMBool Value) {
// NOTE: The simplify-libcalls pass has been removed.
LLVMPassManagerBuilderUseInlinerWithThreshold(LLVMPassManagerBuilderRef PMB,
unsigned Threshold) {
PassManagerBuilder *Builder = unwrap(PMB);
Builder->Inliner = createFunctionInliningPass(Threshold);
LLVMPassManagerBuilderPopulateFunctionPassManager(LLVMPassManagerBuilderRef PMB,
LLVMPassManagerRef PM) {
PassManagerBuilder *Builder = unwrap(PMB);
legacy::FunctionPassManager *FPM = unwrap<legacy::FunctionPassManager>(PM);
LLVMPassManagerBuilderPopulateModulePassManager(LLVMPassManagerBuilderRef PMB,
LLVMPassManagerRef PM) {
PassManagerBuilder *Builder = unwrap(PMB);
legacy::PassManagerBase *MPM = unwrap(PM);
void LLVMPassManagerBuilderPopulateLTOPassManager(LLVMPassManagerBuilderRef PMB,
LLVMPassManagerRef PM,
LLVMBool Internalize,
LLVMBool RunInliner) {
PassManagerBuilder *Builder = unwrap(PMB);
legacy::PassManagerBase *LPM = unwrap(PM);
// A small backwards compatibility hack. populateLTOPassManager used to take
// an RunInliner option.
if (RunInliner && !Builder->Inliner)
Builder->Inliner = createFunctionInliningPass();