#include "llvm/ADT/SmallVector.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/IR/DataLayout.h"
+#include "llvm/IR/FunctionInfo.h"
#include "llvm/IR/Verifier.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ManagedStatic.h"
+#include "llvm/Analysis/BasicAliasAnalysis.h"
+#include "llvm/Analysis/CFLAliasAnalysis.h"
+#include "llvm/Analysis/GlobalsModRef.h"
+#include "llvm/Analysis/ScopedNoAliasAA.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
+#include "llvm/Analysis/TypeBasedAliasAnalysis.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/Scalar.h"
"enable-loopinterchange", cl::init(false), cl::Hidden,
cl::desc("Enable the new, experimental LoopInterchange Pass"));
+static cl::opt<bool> EnableLoopDistribute(
+ "enable-loop-distribute", cl::init(false), cl::Hidden,
+ cl::desc("Enable the new, experimental LoopDistribution Pass"));
+
+static cl::opt<bool> EnableNonLTOGlobalsModRef(
+ "enable-non-lto-gmr", cl::init(true), cl::Hidden,
+ cl::desc(
+ "Enable the GlobalsModRef AliasAnalysis outside of the LTO pipeline."));
+
+static cl::opt<bool> EnableLoopLoadElim(
+ "enable-loop-load-elim", cl::init(false), cl::Hidden,
+ cl::desc("Enable the new, experimental LoopLoadElimination Pass"));
+
PassManagerBuilder::PassManagerBuilder() {
OptLevel = 2;
SizeLevel = 0;
LibraryInfo = nullptr;
Inliner = nullptr;
- DisableTailCalls = false;
+ FunctionIndex = nullptr;
DisableUnitAtATime = false;
DisableUnrollLoops = false;
BBVectorize = RunBBVectorization;
VerifyInput = false;
VerifyOutput = false;
MergeFunctions = false;
+ PrepareForLTO = false;
}
PassManagerBuilder::~PassManagerBuilder() {
// 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());
+ PM.add(createCFLAAWrapperPass());
+ PM.add(createTypeBasedAAWrapperPass());
+ PM.add(createScopedNoAliasAAWrapperPass());
}
void PassManagerBuilder::populateFunctionPassManager(
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
MPM.add(createCFGSimplificationPass()); // Clean up after IPCP & DAE
}
+ 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
// Start of function pass.
// Break up aggregate allocas, using SSAUpdater.
if (UseNewSROA)
- MPM.add(createSROAPass(/*RequiresDomTree*/ false));
+ MPM.add(createSROAPass());
else
MPM.add(createScalarReplAggregatesPass(-1, false));
MPM.add(createEarlyCSEPass()); // Catch trivial redundancies
MPM.add(createInstructionCombiningPass()); // Combine silly seq's
addExtensionsToPM(EP_Peephole, MPM);
- if (!DisableTailCalls)
- MPM.add(createTailCallEliminationPass()); // Eliminate tail calls
+ 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(createCFGSimplificationPass());
MPM.add(createInstructionCombiningPass());
MPM.add(createIndVarSimplifyPass()); // Canonicalize indvars
MPM.add(createLoopIdiomPass()); // Recognize idioms like memset.
// we must insert a no-op module pass to reset the pass manager.
MPM.add(createBarrierNoopPass());
+ 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 (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.
- MPM.add(createLoopRotatePass());
+ // 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
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());
+ // 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
// Provide AliasAnalysis services for optimizations.
addInitialAliasAnalysisPasses(PM);
+ if (FunctionIndex)
+ PM.add(createFunctionImportPass(FunctionIndex));
+
// 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.
PM.add(createIPSCCPPass());
// Now that we internalized some globals, see if we can hack on them!
+ PM.add(createFunctionAttrsPass()); // Add norecurse if possible.
PM.add(createGlobalOptimizerPass());
+ // Promote any localized global vars.
+ PM.add(createPromoteMemoryToRegisterPass());
// Linking modules together can lead to duplicated global constants, only
// keep one copy of each constant.
// Run a few AA driven optimizations here and now, to cleanup the code.
PM.add(createFunctionAttrsPass()); // Add nocapture.
- PM.add(createGlobalsModRefPass()); // IP alias analysis.
+ PM.add(createGlobalsAAWrapperPass()); // IP alias analysis.
PM.add(createLICMPass()); // Hoist loop invariants.
if (EnableMLSM)
PM.add(createLoopVectorizePass(true, LoopVectorize));
+ // 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.
+ PM.add(createInstructionCombiningPass()); // Initial cleanup
+ PM.add(createCFGSimplificationPass()); // if-convert
+ PM.add(createSCCPPass()); // Propagate exposed constants
+ PM.add(createInstructionCombiningPass()); // Clean up again
+ PM.add(createBitTrackingDCEPass());
+
// More scalar chains could be vectorized due to more alias information
if (RunSLPAfterLoopVectorization)
if (SLPVectorize)
// Delete basic blocks, which optimization passes may have killed.
PM.add(createCFGSimplificationPass());
+ // Drop bodies of available externally objects to improve GlobalDCE.
+ PM.add(createEliminateAvailableExternallyPass());
+
// Now that we have optimized the program, discard unreachable functions.
PM.add(createGlobalDCEPass());
if (OptLevel > 1)
addLTOOptimizationPasses(PM);
+ // Create a function that performs CFI checks for cross-DSO calls with targets
+ // in the current module.
+ PM.add(createCrossDSOCFIPass());
+
// 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.