llvm-project/llvm/lib/LTO/LTOCodeGenerator.cpp

694 lines
22 KiB
C++
Raw Normal View History

//===-LTOCodeGenerator.cpp - LLVM Link Time Optimizer ---------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
2012-03-31 18:50:14 +08:00
//
//===----------------------------------------------------------------------===//
//
2012-03-31 18:50:14 +08:00
// This file implements the Link Time Optimization library. This library is
// intended to be used by linker to optimize code at link time.
//
//===----------------------------------------------------------------------===//
#include "llvm/LTO/legacy/LTOCodeGenerator.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Bitcode/BitcodeWriter.h"
#include "llvm/CodeGen/ParallelCG.h"
#include "llvm/CodeGen/RuntimeLibcalls.h"
#include "llvm/Config/config.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Mangler.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Verifier.h"
#include "llvm/InitializePasses.h"
#include "llvm/LTO/LTO.h"
#include "llvm/LTO/legacy/LTOModule.h"
#include "llvm/LTO/legacy/UpdateCompilerUsed.h"
#include "llvm/Linker/Linker.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/SubtargetFeature.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Host.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/Support/Signals.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/TargetSelect.h"
#include "llvm/Support/ToolOutputFile.h"
#include "llvm/Support/YAMLTraits.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Target/TargetRegisterInfo.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/IPO/Internalize.h"
#include "llvm/Transforms/IPO/PassManagerBuilder.h"
#include "llvm/Transforms/ObjCARC.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
#include <system_error>
using namespace llvm;
const char* LTOCodeGenerator::getVersionString() {
#ifdef LLVM_VERSION_INFO
return PACKAGE_NAME " version " PACKAGE_VERSION ", " LLVM_VERSION_INFO;
#else
return PACKAGE_NAME " version " PACKAGE_VERSION;
#endif
}
namespace llvm {
cl::opt<bool> LTODiscardValueNames(
"lto-discard-value-names",
cl::desc("Strip names from Value during LTO (other than GlobalValue)."),
#ifdef NDEBUG
cl::init(true),
#else
cl::init(false),
#endif
cl::Hidden);
cl::opt<std::string>
LTORemarksFilename("lto-pass-remarks-output",
cl::desc("Output filename for pass remarks"),
cl::value_desc("filename"));
cl::opt<bool> LTOPassRemarksWithHotness(
"lto-pass-remarks-with-hotness",
cl::desc("With PGO, include profile count in optimization remarks"),
cl::Hidden);
}
LTOCodeGenerator::LTOCodeGenerator(LLVMContext &Context)
: Context(Context), MergedModule(new Module("ld-temp.o", Context)),
TheLinker(new Linker(*MergedModule)) {
Context.setDiscardValueNames(LTODiscardValueNames);
Context.enableDebugTypeODRUniquing();
initializeLTOPasses();
}
LTOCodeGenerator::~LTOCodeGenerator() {}
2015-09-01 18:13:49 +08:00
// Initialize LTO passes. Please keep this function in sync with
// PassManagerBuilder::populateLTOPassManager(), and make sure all LTO
// passes are initialized.
void LTOCodeGenerator::initializeLTOPasses() {
PassRegistry &R = *PassRegistry::getPassRegistry();
initializeInternalizeLegacyPassPass(R);
initializeIPSCCPLegacyPassPass(R);
initializeGlobalOptLegacyPassPass(R);
initializeConstantMergeLegacyPassPass(R);
initializeDAHPass(R);
initializeInstructionCombiningPassPass(R);
initializeSimpleInlinerPass(R);
initializePruneEHPass(R);
initializeGlobalDCELegacyPassPass(R);
initializeArgPromotionPass(R);
initializeJumpThreadingPass(R);
[PM] Port SROA to the new pass manager. In some ways this is a very boring port to the new pass manager as there are no interesting analyses or dependencies or other oddities. However, this does introduce the first good example of a transformation pass with non-trivial state porting to the new pass manager. I've tried to carve out patterns here to replicate elsewhere, and would appreciate comments on whether folks like these patterns: - A common need in the new pass manager is to effectively lift the pass class and some of its state into a public header file. Prior to this, LLVM used anonymous namespaces to provide "module private" types and utilities, but that doesn't scale to cases where a public header file is needed and the new pass manager will exacerbate that. The pattern I've adopted here is to use the namespace-cased-name of the core pass (what would be a module if we had them) as a module-private namespace. Then utility and other code can be declared and defined in this namespace. At some point in the future, we could even have (conditionally compiled) code that used modules features when available to do the same basic thing. - I've split the actual pass run method in two in order to expose a private method usable by the old pass manager to wrap the new class with a minimum of duplicated code. I actually looked at a bunch of ways to automate or generate these, but they are all quite terrible IMO. The fundamental need is to extract the set of analyses which need to cross this interface boundary, and that will end up being too unpredictable to effectively encapsulate IMO. This is also a relatively small amount of boiler plate that will live a relatively short time, so I'm not too worried about the fact that it is boiler plate. The rest of the patch is totally boring but results in a massive diff (sorry). It just moves code around and removes or adds qualifiers to reflect the new name and nesting structure. Differential Revision: http://reviews.llvm.org/D12773 llvm-svn: 247501
2015-09-12 17:09:14 +08:00
initializeSROALegacyPassPass(R);
initializePostOrderFunctionAttrsLegacyPassPass(R);
[PM] Port ReversePostOrderFunctionAttrs to the new PM Below are my super rough notes when porting. They can probably serve as a basic guide for porting other passes to the new PM. As I port more passes I'll expand and generalize this and make a proper docs/HowToPortToNewPassManager.rst document. There is also missing documentation for general concepts and API's in the new PM which will require some documentation. Once there is proper documentation in place we can put up a list of passes that have to be ported and game-ify/crowdsource the rest of the porting (at least of the middle end; the backend is still unclear). I will however be taking personal responsibility for ensuring that the LLD/ELF LTO pipeline is ported in a timely fashion. The remaining passes to be ported are (do something like `git grep "<the string in the bullet point below>"` to find the pass): General Scalar: [ ] Simplify the CFG [ ] Jump Threading [ ] MemCpy Optimization [ ] Promote Memory to Register [ ] MergedLoadStoreMotion [ ] Lazy Value Information Analysis General IPO: [ ] Dead Argument Elimination [ ] Deduce function attributes in RPO Loop stuff / vectorization stuff: [ ] Alignment from assumptions [ ] Canonicalize natural loops [ ] Delete dead loops [ ] Loop Access Analysis [ ] Loop Invariant Code Motion [ ] Loop Vectorization [ ] SLP Vectorizer [ ] Unroll loops Devirtualization / CFI: [ ] Cross-DSO CFI [ ] Whole program devirtualization [ ] Lower bitset metadata CGSCC passes: [ ] Function Integration/Inlining [ ] Remove unused exception handling info [ ] Promote 'by reference' arguments to scalars Please let me know if you are interested in working on any of the passes in the above list (e.g. reply to the post-commit thread for this patch). I'll probably be tackling "General Scalar" and "General IPO" first FWIW. Steps as I port "Deduce function attributes in RPO" --------------------------------------------------- (note: if you are doing any work based on these notes, please leave a note in the post-commit review thread for this commit with any improvements / suggestions / incompleteness you ran into!) Note: "Deduce function attributes in RPO" is a module pass. 1. Do preparatory refactoring. Do preparatory factoring. In this case all I had to do was to pull out a static helper (r272503). (TODO: give more advice here e.g. if pass holds state or something) 2. Rename the old pass class. llvm/lib/Transforms/IPO/FunctionAttrs.cpp Rename class ReversePostOrderFunctionAttrs -> ReversePostOrderFunctionAttrsLegacyPass in preparation for adding a class ReversePostOrderFunctionAttrs as the pass in the new PM. (edit: actually wait what? The new class name will be ReversePostOrderFunctionAttrsPass, so it doesn't conflict. So this step is sort of useless churn). llvm/include/llvm/InitializePasses.h llvm/lib/LTO/LTOCodeGenerator.cpp llvm/lib/Transforms/IPO/IPO.cpp llvm/lib/Transforms/IPO/FunctionAttrs.cpp Rename initializeReversePostOrderFunctionAttrsPass -> initializeReversePostOrderFunctionAttrsLegacyPassPass (note that the "PassPass" thing falls out of `s/ReversePostOrderFunctionAttrs/ReversePostOrderFunctionAttrsLegacyPass/`) Note that the INITIALIZE_PASS macro is what creates this identifier name, so renaming the class requires this renaming too. Note that createReversePostOrderFunctionAttrsPass does not need to be renamed since its name is not generated from the class name. 3. Add the new PM pass class. In the new PM all passes need to have their declaration in a header somewhere, so you will often need to add a header. In this case llvm/include/llvm/Transforms/IPO/FunctionAttrs.h is already there because PostOrderFunctionAttrsPass was already ported. The file-level comment from the .cpp file can be used as the file-level comment for the new header. You may want to tweak the wording slightly from "this file implements" to "this file provides" or similar. Add declaration for the new PM pass in this header: class ReversePostOrderFunctionAttrsPass : public PassInfoMixin<ReversePostOrderFunctionAttrsPass> { public: PreservedAnalyses run(Module &M, AnalysisManager<Module> &AM); }; Its name should end with `Pass` for consistency (note that this doesn't collide with the names of most old PM passes). E.g. call it `<name of the old PM pass>Pass`. Also, move the doxygen comment from the old PM pass to the declaration of this class in the header. Also, include the declaration for the new PM class `llvm/Transforms/IPO/FunctionAttrs.h` at the top of the file (in this case, it was already done when the other pass in this file was ported). Now define the `run` method for the new class. The main things here are: a) Use AM.getResult<...>(M) to get results instead of `getAnalysis<...>()` b) If the old PM pass would have returned "false" (i.e. `Changed == false`), then you should return PreservedAnalyses::all(); c) In the old PM getAnalysisUsage method, observe the calls `AU.addPreserved<...>();`. In the case `Changed == true`, for each preserved analysis you should do call `PA.preserve<...>()` on a PreservedAnalyses object and return it. E.g.: PreservedAnalyses PA; PA.preserve<CallGraphAnalysis>(); return PA; Note that calls to skipModule/skipFunction are not supported in the new PM currently, so optnone and optimization bisect support do not work. You can just drop those calls for now. 4. Add the pass to the new PM pass registry to make it available in opt. In llvm/lib/Passes/PassBuilder.cpp add a #include for your header. `#include "llvm/Transforms/IPO/FunctionAttrs.h"` In this case there is already an include (from when PostOrderFunctionAttrsPass was ported). Add your pass to llvm/lib/Passes/PassRegistry.def In this case, I added `MODULE_PASS("rpo-functionattrs", ReversePostOrderFunctionAttrsPass())` The string is from the `INITIALIZE_PASS*` macros used in the old pass manager. Then choose a test that uses the pass and use the new PM `-passes=...` to run it. E.g. in this case there is a test that does: ; RUN: opt < %s -basicaa -functionattrs -rpo-functionattrs -S | FileCheck %s I have added the line: ; RUN: opt < %s -aa-pipeline=basic-aa -passes='require<targetlibinfo>,cgscc(function-attrs),rpo-functionattrs' -S | FileCheck %s The `-aa-pipeline=basic-aa` and `require<targetlibinfo>,cgscc(function-attrs)` are what is needed to run functionattrs in the new PM (note that in the new PM "functionattrs" becomes "function-attrs" for some reason). This is just pulled from `readattrs.ll` which contains the change from when functionattrs was ported to the new PM. Adding rpo-functionattrs causes the pass that was just ported to run. llvm-svn: 272505
2016-06-12 15:48:51 +08:00
initializeReversePostOrderFunctionAttrsLegacyPassPass(R);
[PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible with the new pass manager, and no longer relying on analysis groups. This builds essentially a ground-up new AA infrastructure stack for LLVM. The core ideas are the same that are used throughout the new pass manager: type erased polymorphism and direct composition. The design is as follows: - FunctionAAResults is a type-erasing alias analysis results aggregation interface to walk a single query across a range of results from different alias analyses. Currently this is function-specific as we always assume that aliasing queries are *within* a function. - AAResultBase is a CRTP utility providing stub implementations of various parts of the alias analysis result concept, notably in several cases in terms of other more general parts of the interface. This can be used to implement only a narrow part of the interface rather than the entire interface. This isn't really ideal, this logic should be hoisted into FunctionAAResults as currently it will cause a significant amount of redundant work, but it faithfully models the behavior of the prior infrastructure. - All the alias analysis passes are ported to be wrapper passes for the legacy PM and new-style analysis passes for the new PM with a shared result object. In some cases (most notably CFL), this is an extremely naive approach that we should revisit when we can specialize for the new pass manager. - BasicAA has been restructured to reflect that it is much more fundamentally a function analysis because it uses dominator trees and loop info that need to be constructed for each function. All of the references to getting alias analysis results have been updated to use the new aggregation interface. All the preservation and other pass management code has been updated accordingly. The way the FunctionAAResultsWrapperPass works is to detect the available alias analyses when run, and add them to the results object. This means that we should be able to continue to respect when various passes are added to the pipeline, for example adding CFL or adding TBAA passes should just cause their results to be available and to get folded into this. The exception to this rule is BasicAA which really needs to be a function pass due to using dominator trees and loop info. As a consequence, the FunctionAAResultsWrapperPass directly depends on BasicAA and always includes it in the aggregation. This has significant implications for preserving analyses. Generally, most passes shouldn't bother preserving FunctionAAResultsWrapperPass because rebuilding the results just updates the set of known AA passes. The exception to this rule are LoopPass instances which need to preserve all the function analyses that the loop pass manager will end up needing. This means preserving both BasicAAWrapperPass and the aggregating FunctionAAResultsWrapperPass. Now, when preserving an alias analysis, you do so by directly preserving that analysis. This is only necessary for non-immutable-pass-provided alias analyses though, and there are only three of interest: BasicAA, GlobalsAA (formerly GlobalsModRef), and SCEVAA. Usually BasicAA is preserved when needed because it (like DominatorTree and LoopInfo) is marked as a CFG-only pass. I've expanded GlobalsAA into the preserved set everywhere we previously were preserving all of AliasAnalysis, and I've added SCEVAA in the intersection of that with where we preserve SCEV itself. One significant challenge to all of this is that the CGSCC passes were actually using the alias analysis implementations by taking advantage of a pretty amazing set of loop holes in the old pass manager's analysis management code which allowed analysis groups to slide through in many cases. Moving away from analysis groups makes this problem much more obvious. To fix it, I've leveraged the flexibility the design of the new PM components provides to just directly construct the relevant alias analyses for the relevant functions in the IPO passes that need them. This is a bit hacky, but should go away with the new pass manager, and is already in many ways cleaner than the prior state. Another significant challenge is that various facilities of the old alias analysis infrastructure just don't fit any more. The most significant of these is the alias analysis 'counter' pass. That pass relied on the ability to snoop on AA queries at different points in the analysis group chain. Instead, I'm planning to build printing functionality directly into the aggregation layer. I've not included that in this patch merely to keep it smaller. Note that all of this needs a nearly complete rewrite of the AA documentation. I'm planning to do that, but I'd like to make sure the new design settles, and to flesh out a bit more of what it looks like in the new pass manager first. Differential Revision: http://reviews.llvm.org/D12080 llvm-svn: 247167
2015-09-10 01:55:00 +08:00
initializeGlobalsAAWrapperPassPass(R);
initializeLegacyLICMPassPass(R);
initializeMergedLoadStoreMotionLegacyPassPass(R);
initializeGVNLegacyPassPass(R);
initializeMemCpyOptLegacyPassPass(R);
initializeDCELegacyPassPass(R);
initializeCFGSimplifyPassPass(R);
}
void LTOCodeGenerator::setAsmUndefinedRefs(LTOModule *Mod) {
const std::vector<StringRef> &undefs = Mod->getAsmUndefinedRefs();
for (int i = 0, e = undefs.size(); i != e; ++i)
AsmUndefinedRefs[undefs[i]] = 1;
}
bool LTOCodeGenerator::addModule(LTOModule *Mod) {
assert(&Mod->getModule().getContext() == &Context &&
"Expected module in same context");
bool ret = TheLinker->linkInModule(Mod->takeModule());
setAsmUndefinedRefs(Mod);
// We've just changed the input, so let's make sure we verify it.
HasVerifiedInput = false;
return !ret;
}
2012-03-31 18:50:14 +08:00
void LTOCodeGenerator::setModule(std::unique_ptr<LTOModule> Mod) {
assert(&Mod->getModule().getContext() == &Context &&
"Expected module in same context");
AsmUndefinedRefs.clear();
MergedModule = Mod->takeModule();
TheLinker = make_unique<Linker>(*MergedModule);
setAsmUndefinedRefs(&*Mod);
// We've just changed the input, so let's make sure we verify it.
HasVerifiedInput = false;
}
void LTOCodeGenerator::setTargetOptions(const TargetOptions &Options) {
this->Options = Options;
}
void LTOCodeGenerator::setDebugInfo(lto_debug_model Debug) {
switch (Debug) {
case LTO_DEBUG_MODEL_NONE:
EmitDwarfDebugInfo = false;
return;
case LTO_DEBUG_MODEL_DWARF:
EmitDwarfDebugInfo = true;
return;
}
llvm_unreachable("Unknown debug format!");
}
void LTOCodeGenerator::setOptLevel(unsigned Level) {
OptLevel = Level;
switch (OptLevel) {
case 0:
CGOptLevel = CodeGenOpt::None;
return;
case 1:
CGOptLevel = CodeGenOpt::Less;
return;
case 2:
CGOptLevel = CodeGenOpt::Default;
return;
case 3:
CGOptLevel = CodeGenOpt::Aggressive;
return;
}
llvm_unreachable("Unknown optimization level!");
}
bool LTOCodeGenerator::writeMergedModules(StringRef Path) {
if (!determineTarget())
return false;
// We always run the verifier once on the merged module.
verifyMergedModuleOnce();
// mark which symbols can not be internalized
applyScopeRestrictions();
// create output file
std::error_code EC;
ToolOutputFile Out(Path, EC, sys::fs::F_None);
if (EC) {
std::string ErrMsg = "could not open bitcode file for writing: ";
ErrMsg += Path.str() + ": " + EC.message();
emitError(ErrMsg);
return false;
}
2012-03-31 18:50:14 +08:00
// write bitcode to it
WriteBitcodeToFile(MergedModule.get(), Out.os(), ShouldEmbedUselists);
Out.os().close();
if (Out.os().has_error()) {
std::string ErrMsg = "could not write bitcode file: ";
ErrMsg += Path.str() + ": " + Out.os().error().message();
emitError(ErrMsg);
Out.os().clear_error();
return false;
}
2012-03-31 18:50:14 +08:00
Out.keep();
return true;
}
bool LTOCodeGenerator::compileOptimizedToFile(const char **Name) {
// make unique temp output file to put generated code
SmallString<128> Filename;
int FD;
StringRef Extension
(FileType == TargetMachine::CGFT_AssemblyFile ? "s" : "o");
std::error_code EC =
sys::fs::createTemporaryFile("lto-llvm", Extension, FD, Filename);
if (EC) {
emitError(EC.message());
return false;
}
// generate object file
ToolOutputFile objFile(Filename, FD);
bool genResult = compileOptimized(&objFile.os());
objFile.os().close();
if (objFile.os().has_error()) {
emitError((Twine("could not write object file: ") + Filename + ": " +
objFile.os().error().message())
.str());
objFile.os().clear_error();
sys::fs::remove(Twine(Filename));
return false;
}
objFile.keep();
if (!genResult) {
sys::fs::remove(Twine(Filename));
return false;
}
NativeObjectPath = Filename.c_str();
*Name = NativeObjectPath.c_str();
return true;
}
std::unique_ptr<MemoryBuffer>
LTOCodeGenerator::compileOptimized() {
const char *name;
if (!compileOptimizedToFile(&name))
return nullptr;
// read .o file into memory buffer
ErrorOr<std::unique_ptr<MemoryBuffer>> BufferOrErr =
MemoryBuffer::getFile(name, -1, false);
if (std::error_code EC = BufferOrErr.getError()) {
emitError(EC.message());
sys::fs::remove(NativeObjectPath);
return nullptr;
}
// remove temp files
sys::fs::remove(NativeObjectPath);
return std::move(*BufferOrErr);
}
bool LTOCodeGenerator::compile_to_file(const char **Name, bool DisableVerify,
bool DisableInline,
bool DisableGVNLoadPRE,
bool DisableVectorization) {
if (!optimize(DisableVerify, DisableInline, DisableGVNLoadPRE,
DisableVectorization))
return false;
return compileOptimizedToFile(Name);
}
std::unique_ptr<MemoryBuffer>
LTOCodeGenerator::compile(bool DisableVerify, bool DisableInline,
bool DisableGVNLoadPRE, bool DisableVectorization) {
if (!optimize(DisableVerify, DisableInline, DisableGVNLoadPRE,
DisableVectorization))
return nullptr;
return compileOptimized();
}
bool LTOCodeGenerator::determineTarget() {
if (TargetMach)
return true;
TripleStr = MergedModule->getTargetTriple();
if (TripleStr.empty()) {
TripleStr = sys::getDefaultTargetTriple();
MergedModule->setTargetTriple(TripleStr);
}
llvm::Triple Triple(TripleStr);
// create target machine from info for merged modules
std::string ErrMsg;
MArch = TargetRegistry::lookupTarget(TripleStr, ErrMsg);
if (!MArch) {
emitError(ErrMsg);
return false;
}
// Construct LTOModule, hand over ownership of module and target. Use MAttr as
// the default set of features.
SubtargetFeatures Features(MAttr);
Features.getDefaultSubtargetFeatures(Triple);
FeatureStr = Features.getString();
// Set a default CPU for Darwin triples.
if (MCpu.empty() && Triple.isOSDarwin()) {
if (Triple.getArch() == llvm::Triple::x86_64)
MCpu = "core2";
else if (Triple.getArch() == llvm::Triple::x86)
MCpu = "yonah";
else if (Triple.getArch() == llvm::Triple::aarch64)
MCpu = "cyclone";
}
TargetMach = createTargetMachine();
return true;
}
std::unique_ptr<TargetMachine> LTOCodeGenerator::createTargetMachine() {
return std::unique_ptr<TargetMachine>(MArch->createTargetMachine(
TripleStr, MCpu, FeatureStr, Options, RelocModel, None, CGOptLevel));
}
// If a linkonce global is present in the MustPreserveSymbols, we need to make
// sure we honor this. To force the compiler to not drop it, we add it to the
// "llvm.compiler.used" global.
void LTOCodeGenerator::preserveDiscardableGVs(
Module &TheModule,
llvm::function_ref<bool(const GlobalValue &)> mustPreserveGV) {
std::vector<GlobalValue *> Used;
auto mayPreserveGlobal = [&](GlobalValue &GV) {
if (!GV.isDiscardableIfUnused() || GV.isDeclaration() ||
!mustPreserveGV(GV))
return;
if (GV.hasAvailableExternallyLinkage())
return emitWarning(
(Twine("Linker asked to preserve available_externally global: '") +
GV.getName() + "'").str());
if (GV.hasInternalLinkage())
return emitWarning((Twine("Linker asked to preserve internal global: '") +
GV.getName() + "'").str());
Used.push_back(&GV);
};
for (auto &GV : TheModule)
mayPreserveGlobal(GV);
for (auto &GV : TheModule.globals())
mayPreserveGlobal(GV);
for (auto &GV : TheModule.aliases())
mayPreserveGlobal(GV);
if (Used.empty())
return;
appendToCompilerUsed(TheModule, Used);
}
void LTOCodeGenerator::applyScopeRestrictions() {
if (ScopeRestrictionsDone)
return;
// Declare a callback for the internalize pass that will ask for every
// candidate GlobalValue if it can be internalized or not.
Mangler Mang;
SmallString<64> MangledName;
auto mustPreserveGV = [&](const GlobalValue &GV) -> bool {
// Unnamed globals can't be mangled, but they can't be preserved either.
if (!GV.hasName())
return false;
// Need to mangle the GV as the "MustPreserveSymbols" StringSet is filled
// with the linker supplied name, which on Darwin includes a leading
// underscore.
MangledName.clear();
MangledName.reserve(GV.getName().size() + 1);
Mang.getNameWithPrefix(MangledName, &GV, /*CannotUsePrivateLabel=*/false);
return MustPreserveSymbols.count(MangledName);
};
// Preserve linkonce value on linker request
preserveDiscardableGVs(*MergedModule, mustPreserveGV);
if (!ShouldInternalize)
return;
if (ShouldRestoreGlobalsLinkage) {
// Record the linkage type of non-local symbols so they can be restored
// prior
// to module splitting.
auto RecordLinkage = [&](const GlobalValue &GV) {
if (!GV.hasAvailableExternallyLinkage() && !GV.hasLocalLinkage() &&
GV.hasName())
ExternalSymbols.insert(std::make_pair(GV.getName(), GV.getLinkage()));
};
for (auto &GV : *MergedModule)
RecordLinkage(GV);
for (auto &GV : MergedModule->globals())
RecordLinkage(GV);
for (auto &GV : MergedModule->aliases())
RecordLinkage(GV);
}
// Update the llvm.compiler_used globals to force preserving libcalls and
// symbols referenced from asm
updateCompilerUsed(*MergedModule, *TargetMach, AsmUndefinedRefs);
internalizeModule(*MergedModule, mustPreserveGV);
2012-03-31 18:50:14 +08:00
ScopeRestrictionsDone = true;
}
/// Restore original linkage for symbols that may have been internalized
void LTOCodeGenerator::restoreLinkageForExternals() {
if (!ShouldInternalize || !ShouldRestoreGlobalsLinkage)
return;
assert(ScopeRestrictionsDone &&
"Cannot externalize without internalization!");
if (ExternalSymbols.empty())
return;
auto externalize = [this](GlobalValue &GV) {
if (!GV.hasLocalLinkage() || !GV.hasName())
return;
auto I = ExternalSymbols.find(GV.getName());
if (I == ExternalSymbols.end())
return;
GV.setLinkage(I->second);
};
std::for_each(MergedModule->begin(), MergedModule->end(), externalize);
std::for_each(MergedModule->global_begin(), MergedModule->global_end(),
externalize);
std::for_each(MergedModule->alias_begin(), MergedModule->alias_end(),
externalize);
}
void LTOCodeGenerator::verifyMergedModuleOnce() {
// Only run on the first call.
if (HasVerifiedInput)
return;
HasVerifiedInput = true;
bool BrokenDebugInfo = false;
if (verifyModule(*MergedModule, &dbgs(), &BrokenDebugInfo))
report_fatal_error("Broken module found, compilation aborted!");
if (BrokenDebugInfo) {
emitWarning("Invalid debug info found, debug info will be stripped");
StripDebugInfo(*MergedModule);
}
}
void LTOCodeGenerator::finishOptimizationRemarks() {
if (DiagnosticOutputFile) {
DiagnosticOutputFile->keep();
// FIXME: LTOCodeGenerator dtor is not invoked on Darwin
DiagnosticOutputFile->os().flush();
}
}
/// Optimize merged modules using various IPO passes
bool LTOCodeGenerator::optimize(bool DisableVerify, bool DisableInline,
bool DisableGVNLoadPRE,
bool DisableVectorization) {
if (!this->determineTarget())
return false;
auto DiagFileOrErr = lto::setupOptimizationRemarks(
Context, LTORemarksFilename, LTOPassRemarksWithHotness);
if (!DiagFileOrErr) {
errs() << "Error: " << toString(DiagFileOrErr.takeError()) << "\n";
report_fatal_error("Can't get an output file for the remarks");
}
DiagnosticOutputFile = std::move(*DiagFileOrErr);
// We always run the verifier once on the merged module, the `DisableVerify`
// parameter only applies to subsequent verify.
verifyMergedModuleOnce();
// Mark which symbols can not be internalized
this->applyScopeRestrictions();
// Instantiate the pass manager to organize the passes.
legacy::PassManager passes;
// Add an appropriate DataLayout instance for this module...
MergedModule->setDataLayout(TargetMach->createDataLayout());
2012-03-31 18:50:14 +08:00
passes.add(
createTargetTransformInfoWrapperPass(TargetMach->getTargetIRAnalysis()));
Triple TargetTriple(TargetMach->getTargetTriple());
PassManagerBuilder PMB;
PMB.DisableGVNLoadPRE = DisableGVNLoadPRE;
PMB.LoopVectorize = !DisableVectorization;
PMB.SLPVectorize = !DisableVectorization;
if (!DisableInline)
PMB.Inliner = createFunctionInliningPass();
[PM] Rework how the TargetLibraryInfo pass integrates with the new pass manager to support the actual uses of it. =] When I ported instcombine to the new pass manager I discover that it didn't work because TLI wasn't available in the right places. This is a somewhat surprising and/or subtle aspect of the new pass manager design that came up before but I think is useful to be reminded of: While the new pass manager *allows* a function pass to query a module analysis, it requires that the module analysis is already run and cached prior to the function pass manager starting up, possibly with a 'require<foo>' style utility in the pass pipeline. This is an intentional hurdle because using a module analysis from a function pass *requires* that the module analysis is run prior to entering the function pass manager. Otherwise the other functions in the module could be in who-knows-what state, etc. A somewhat surprising consequence of this design decision (at least to me) is that you have to design a function pass that leverages a module analysis to do so as an optional feature. Even if that means your function pass does no work in the absence of the module analysis, you have to handle that possibility and remain conservatively correct. This is a natural consequence of things being able to invalidate the module analysis and us being unable to re-run it. And it's a generally good thing because it lets us reorder passes arbitrarily without breaking correctness, etc. This ends up causing problems in one case. What if we have a module analysis that is *definitionally* impossible to invalidate. In the places this might come up, the analysis is usually also definitionally trivial to run even while other transformation passes run on the module, regardless of the state of anything. And so, it follows that it is natural to have a hard requirement on such analyses from a function pass. It turns out, that TargetLibraryInfo is just such an analysis, and InstCombine has a hard requirement on it. The approach I've taken here is to produce an analysis that models this flexibility by making it both a module and a function analysis. This exposes the fact that it is in fact safe to compute at any point. We can even make it a valid CGSCC analysis at some point if that is useful. However, we don't want to have a copy of the actual target library info state for each function! This state is specific to the triple. The somewhat direct and blunt approach here is to turn TLI into a pimpl, with the state and mutators in the implementation class and the query routines primarily in the wrapper. Then the analysis can lazily construct and cache the implementations, keyed on the triple, and on-demand produce wrappers of them for each function. One minor annoyance is that we will end up with a wrapper for each function in the module. While this is a bit wasteful (one pointer per function) it seems tolerable. And it has the advantage of ensuring that we pay the absolute minimum synchronization cost to access this information should we end up with a nice parallel function pass manager in the future. We could look into trying to mark when analysis results are especially cheap to recompute and more eagerly GC-ing the cached results, or we could look at supporting a variant of analyses whose results are specifically *not* cached and expected to just be used and discarded by the consumer. Either way, these seem like incremental enhancements that should happen when we start profiling the memory and CPU usage of the new pass manager and not before. The other minor annoyance is that if we end up using the TLI in both a module pass and a function pass, those will be produced by two separate analyses, and thus will point to separate copies of the implementation state. While a minor issue, I dislike this and would like to find a way to cleanly allow a single analysis instance to be used across multiple IR unit managers. But I don't have a good solution to this today, and I don't want to hold up all of the work waiting to come up with one. This too seems like a reasonable thing to incrementally improve later. llvm-svn: 226981
2015-01-24 10:06:09 +08:00
PMB.LibraryInfo = new TargetLibraryInfoImpl(TargetTriple);
if (Freestanding)
PMB.LibraryInfo->disableAllFunctions();
PMB.OptLevel = OptLevel;
PMB.VerifyInput = !DisableVerify;
PMB.VerifyOutput = !DisableVerify;
PMB.populateLTOPassManager(passes);
// Run our queue of passes all at once now, efficiently.
passes.run(*MergedModule);
return true;
}
bool LTOCodeGenerator::compileOptimized(ArrayRef<raw_pwrite_stream *> Out) {
if (!this->determineTarget())
return false;
// We always run the verifier once on the merged module. If it has already
// been called in optimize(), this call will return early.
verifyMergedModuleOnce();
legacy::PassManager preCodeGenPasses;
// If the bitcode files contain ARC code and were compiled with optimization,
// the ObjCARCContractPass must be run, so do it unconditionally here.
preCodeGenPasses.add(createObjCARCContractPass());
preCodeGenPasses.run(*MergedModule);
// Re-externalize globals that may have been internalized to increase scope
// for splitting
restoreLinkageForExternals();
// Do code generation. We need to preserve the module in case the client calls
// writeMergedModules() after compilation, but we only need to allow this at
// parallelism level 1. This is achieved by having splitCodeGen return the
// original module at parallelism level 1 which we then assign back to
// MergedModule.
MergedModule = splitCodeGen(std::move(MergedModule), Out, {},
[&]() { return createTargetMachine(); }, FileType,
ShouldRestoreGlobalsLinkage);
// If statistics were requested, print them out after codegen.
if (llvm::AreStatisticsEnabled())
llvm::PrintStatistics();
reportAndResetTimings();
finishOptimizationRemarks();
return true;
}
/// setCodeGenDebugOptions - Set codegen debugging options to aid in debugging
/// LTO problems.
void LTOCodeGenerator::setCodeGenDebugOptions(StringRef Options) {
for (std::pair<StringRef, StringRef> o = getToken(Options); !o.first.empty();
o = getToken(o.second))
CodegenOptions.push_back(o.first);
}
void LTOCodeGenerator::parseCodeGenDebugOptions() {
// if options were requested, set them
if (!CodegenOptions.empty()) {
// ParseCommandLineOptions() expects argv[0] to be program name.
std::vector<const char *> CodegenArgv(1, "libLLVMLTO");
for (std::string &Arg : CodegenOptions)
CodegenArgv.push_back(Arg.c_str());
cl::ParseCommandLineOptions(CodegenArgv.size(), CodegenArgv.data());
}
}
void LTOCodeGenerator::DiagnosticHandler(const DiagnosticInfo &DI) {
// Map the LLVM internal diagnostic severity to the LTO diagnostic severity.
lto_codegen_diagnostic_severity_t Severity;
switch (DI.getSeverity()) {
case DS_Error:
Severity = LTO_DS_ERROR;
break;
case DS_Warning:
Severity = LTO_DS_WARNING;
break;
case DS_Remark:
Severity = LTO_DS_REMARK;
break;
case DS_Note:
Severity = LTO_DS_NOTE;
break;
}
// Create the string that will be reported to the external diagnostic handler.
std::string MsgStorage;
raw_string_ostream Stream(MsgStorage);
DiagnosticPrinterRawOStream DP(Stream);
DI.print(DP);
Stream.flush();
// If this method has been called it means someone has set up an external
// diagnostic handler. Assert on that.
assert(DiagHandler && "Invalid diagnostic handler");
(*DiagHandler)(Severity, MsgStorage.c_str(), DiagContext);
}
namespace {
struct LTODiagnosticHandler : public DiagnosticHandler {
LTOCodeGenerator *CodeGenerator;
LTODiagnosticHandler(LTOCodeGenerator *CodeGenPtr)
: CodeGenerator(CodeGenPtr) {}
bool handleDiagnostics(const DiagnosticInfo &DI) override {
CodeGenerator->DiagnosticHandler(DI);
return true;
}
};
}
void
LTOCodeGenerator::setDiagnosticHandler(lto_diagnostic_handler_t DiagHandler,
void *Ctxt) {
this->DiagHandler = DiagHandler;
this->DiagContext = Ctxt;
if (!DiagHandler)
return Context.setDiagnosticHandler(nullptr);
// Register the LTOCodeGenerator stub in the LLVMContext to forward the
// diagnostic to the external DiagHandler.
Context.setDiagnosticHandler(llvm::make_unique<LTODiagnosticHandler>(this),
true);
}
namespace {
class LTODiagnosticInfo : public DiagnosticInfo {
const Twine &Msg;
public:
LTODiagnosticInfo(const Twine &DiagMsg, DiagnosticSeverity Severity=DS_Error)
: DiagnosticInfo(DK_Linker, Severity), Msg(DiagMsg) {}
void print(DiagnosticPrinter &DP) const override { DP << Msg; }
};
}
void LTOCodeGenerator::emitError(const std::string &ErrMsg) {
if (DiagHandler)
(*DiagHandler)(LTO_DS_ERROR, ErrMsg.c_str(), DiagContext);
else
Context.diagnose(LTODiagnosticInfo(ErrMsg));
}
void LTOCodeGenerator::emitWarning(const std::string &ErrMsg) {
if (DiagHandler)
(*DiagHandler)(LTO_DS_WARNING, ErrMsg.c_str(), DiagContext);
else
Context.diagnose(LTODiagnosticInfo(ErrMsg, DS_Warning));
}