mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-14 23:48:49 +00:00
47c0d49055
(Re-committed after moving the template specialization under the yaml namespace. GCC was complaining about this.) This allows various presentation of this data using an external tool. This was first recommended here[1]. As an example, consider this module: 1 int foo(); 2 int bar(); 3 4 int baz() { 5 return foo() + bar(); 6 } The inliner generates these missed-optimization remarks today (the hotness information is pulled from PGO): remark: /tmp/s.c:5:10: foo will not be inlined into baz (hotness: 30) remark: /tmp/s.c:5:18: bar will not be inlined into baz (hotness: 30) Now with -pass-remarks-output=<yaml-file>, we generate this YAML file: --- !Missed Pass: inline Name: NotInlined DebugLoc: { File: /tmp/s.c, Line: 5, Column: 10 } Function: baz Hotness: 30 Args: - Callee: foo - String: will not be inlined into - Caller: baz ... --- !Missed Pass: inline Name: NotInlined DebugLoc: { File: /tmp/s.c, Line: 5, Column: 18 } Function: baz Hotness: 30 Args: - Callee: bar - String: will not be inlined into - Caller: baz ... This is a summary of the high-level decisions: * There is a new streaming interface to emit optimization remarks. E.g. for the inliner remark above: ORE.emit(DiagnosticInfoOptimizationRemarkMissed( DEBUG_TYPE, "NotInlined", &I) << NV("Callee", Callee) << " will not be inlined into " << NV("Caller", CS.getCaller()) << setIsVerbose()); NV stands for named value and allows the YAML client to process a remark using its name (NotInlined) and the named arguments (Callee and Caller) without parsing the text of the message. Subsequent patches will update ORE users to use the new streaming API. * I am using YAML I/O for writing the YAML file. YAML I/O requires you to specify reading and writing at once but reading is highly non-trivial for some of the more complex LLVM types. Since it's not clear that we (ever) want to use LLVM to parse this YAML file, the code supports and asserts that we're writing only. On the other hand, I did experiment that the class hierarchy starting at DiagnosticInfoOptimizationBase can be mapped back from YAML generated here (see D24479). * The YAML stream is stored in the LLVM context. * In the example, we can probably further specify the IR value used, i.e. print "Function" rather than "Value". * As before hotness is computed in the analysis pass instead of DiganosticInfo. This avoids the layering problem since BFI is in Analysis while DiagnosticInfo is in IR. [1] https://reviews.llvm.org/D19678#419445 Differential Revision: https://reviews.llvm.org/D24587 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@282539 91177308-0d34-0410-b5e6-96231b3b80d8
753 lines
25 KiB
C++
753 lines
25 KiB
C++
//===- opt.cpp - The LLVM Modular Optimizer -------------------------------===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Optimizations may be specified an arbitrary number of times on the command
|
|
// line, They are run in the order specified.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "BreakpointPrinter.h"
|
|
#include "NewPMDriver.h"
|
|
#include "PassPrinters.h"
|
|
#include "llvm/ADT/Triple.h"
|
|
#include "llvm/Analysis/CallGraph.h"
|
|
#include "llvm/Analysis/CallGraphSCCPass.h"
|
|
#include "llvm/Analysis/LoopPass.h"
|
|
#include "llvm/Analysis/RegionPass.h"
|
|
#include "llvm/Analysis/TargetLibraryInfo.h"
|
|
#include "llvm/Analysis/TargetTransformInfo.h"
|
|
#include "llvm/Bitcode/BitcodeWriterPass.h"
|
|
#include "llvm/CodeGen/CommandFlags.h"
|
|
#include "llvm/IR/DataLayout.h"
|
|
#include "llvm/IR/DebugInfo.h"
|
|
#include "llvm/IR/IRPrintingPasses.h"
|
|
#include "llvm/IR/LLVMContext.h"
|
|
#include "llvm/IR/LegacyPassManager.h"
|
|
#include "llvm/IR/LegacyPassNameParser.h"
|
|
#include "llvm/IR/Module.h"
|
|
#include "llvm/IR/Verifier.h"
|
|
#include "llvm/IRReader/IRReader.h"
|
|
#include "llvm/InitializePasses.h"
|
|
#include "llvm/LinkAllIR.h"
|
|
#include "llvm/LinkAllPasses.h"
|
|
#include "llvm/MC/SubtargetFeature.h"
|
|
#include "llvm/Support/Debug.h"
|
|
#include "llvm/Support/FileSystem.h"
|
|
#include "llvm/Support/Host.h"
|
|
#include "llvm/Support/ManagedStatic.h"
|
|
#include "llvm/Support/PluginLoader.h"
|
|
#include "llvm/Support/PrettyStackTrace.h"
|
|
#include "llvm/Support/Signals.h"
|
|
#include "llvm/Support/SourceMgr.h"
|
|
#include "llvm/Support/SystemUtils.h"
|
|
#include "llvm/Support/TargetRegistry.h"
|
|
#include "llvm/Support/TargetSelect.h"
|
|
#include "llvm/Support/ToolOutputFile.h"
|
|
#include "llvm/Support/YAMLTraits.h"
|
|
#include "llvm/Target/TargetMachine.h"
|
|
#include "llvm/Transforms/Coroutines.h"
|
|
#include "llvm/Transforms/IPO/AlwaysInliner.h"
|
|
#include "llvm/Transforms/IPO/PassManagerBuilder.h"
|
|
#include "llvm/Transforms/Utils/Cloning.h"
|
|
#include <algorithm>
|
|
#include <memory>
|
|
using namespace llvm;
|
|
using namespace opt_tool;
|
|
|
|
// The OptimizationList is automatically populated with registered Passes by the
|
|
// PassNameParser.
|
|
//
|
|
static cl::list<const PassInfo*, bool, PassNameParser>
|
|
PassList(cl::desc("Optimizations available:"));
|
|
|
|
// This flag specifies a textual description of the optimization pass pipeline
|
|
// to run over the module. This flag switches opt to use the new pass manager
|
|
// infrastructure, completely disabling all of the flags specific to the old
|
|
// pass management.
|
|
static cl::opt<std::string> PassPipeline(
|
|
"passes",
|
|
cl::desc("A textual description of the pass pipeline for optimizing"),
|
|
cl::Hidden);
|
|
|
|
// Other command line options...
|
|
//
|
|
static cl::opt<std::string>
|
|
InputFilename(cl::Positional, cl::desc("<input bitcode file>"),
|
|
cl::init("-"), cl::value_desc("filename"));
|
|
|
|
static cl::opt<std::string>
|
|
OutputFilename("o", cl::desc("Override output filename"),
|
|
cl::value_desc("filename"));
|
|
|
|
static cl::opt<bool>
|
|
Force("f", cl::desc("Enable binary output on terminals"));
|
|
|
|
static cl::opt<bool>
|
|
PrintEachXForm("p", cl::desc("Print module after each transformation"));
|
|
|
|
static cl::opt<bool>
|
|
NoOutput("disable-output",
|
|
cl::desc("Do not write result bitcode file"), cl::Hidden);
|
|
|
|
static cl::opt<bool>
|
|
OutputAssembly("S", cl::desc("Write output as LLVM assembly"));
|
|
|
|
static cl::opt<bool>
|
|
NoVerify("disable-verify", cl::desc("Do not run the verifier"), cl::Hidden);
|
|
|
|
static cl::opt<bool>
|
|
VerifyEach("verify-each", cl::desc("Verify after each transform"));
|
|
|
|
static cl::opt<bool>
|
|
DisableDITypeMap("disable-debug-info-type-map",
|
|
cl::desc("Don't use a uniquing type map for debug info"));
|
|
|
|
static cl::opt<bool>
|
|
StripDebug("strip-debug",
|
|
cl::desc("Strip debugger symbol info from translation unit"));
|
|
|
|
static cl::opt<bool>
|
|
DisableInline("disable-inlining", cl::desc("Do not run the inliner pass"));
|
|
|
|
static cl::opt<bool>
|
|
DisableOptimizations("disable-opt",
|
|
cl::desc("Do not run any optimization passes"));
|
|
|
|
static cl::opt<bool>
|
|
StandardLinkOpts("std-link-opts",
|
|
cl::desc("Include the standard link time optimizations"));
|
|
|
|
static cl::opt<bool>
|
|
OptLevelO0("O0",
|
|
cl::desc("Optimization level 0. Similar to clang -O0"));
|
|
|
|
static cl::opt<bool>
|
|
OptLevelO1("O1",
|
|
cl::desc("Optimization level 1. Similar to clang -O1"));
|
|
|
|
static cl::opt<bool>
|
|
OptLevelO2("O2",
|
|
cl::desc("Optimization level 2. Similar to clang -O2"));
|
|
|
|
static cl::opt<bool>
|
|
OptLevelOs("Os",
|
|
cl::desc("Like -O2 with extra optimizations for size. Similar to clang -Os"));
|
|
|
|
static cl::opt<bool>
|
|
OptLevelOz("Oz",
|
|
cl::desc("Like -Os but reduces code size further. Similar to clang -Oz"));
|
|
|
|
static cl::opt<bool>
|
|
OptLevelO3("O3",
|
|
cl::desc("Optimization level 3. Similar to clang -O3"));
|
|
|
|
static cl::opt<unsigned>
|
|
CodeGenOptLevel("codegen-opt-level",
|
|
cl::desc("Override optimization level for codegen hooks"));
|
|
|
|
static cl::opt<std::string>
|
|
TargetTriple("mtriple", cl::desc("Override target triple for module"));
|
|
|
|
static cl::opt<bool>
|
|
UnitAtATime("funit-at-a-time",
|
|
cl::desc("Enable IPO. This corresponds to gcc's -funit-at-a-time"),
|
|
cl::init(true));
|
|
|
|
static cl::opt<bool>
|
|
DisableLoopUnrolling("disable-loop-unrolling",
|
|
cl::desc("Disable loop unrolling in all relevant passes"),
|
|
cl::init(false));
|
|
static cl::opt<bool>
|
|
DisableLoopVectorization("disable-loop-vectorization",
|
|
cl::desc("Disable the loop vectorization pass"),
|
|
cl::init(false));
|
|
|
|
static cl::opt<bool>
|
|
DisableSLPVectorization("disable-slp-vectorization",
|
|
cl::desc("Disable the slp vectorization pass"),
|
|
cl::init(false));
|
|
|
|
static cl::opt<bool> EmitSummaryIndex("module-summary",
|
|
cl::desc("Emit module summary index"),
|
|
cl::init(false));
|
|
|
|
static cl::opt<bool> EmitModuleHash("module-hash", cl::desc("Emit module hash"),
|
|
cl::init(false));
|
|
|
|
static cl::opt<bool>
|
|
DisableSimplifyLibCalls("disable-simplify-libcalls",
|
|
cl::desc("Disable simplify-libcalls"));
|
|
|
|
static cl::opt<bool>
|
|
Quiet("q", cl::desc("Obsolete option"), cl::Hidden);
|
|
|
|
static cl::alias
|
|
QuietA("quiet", cl::desc("Alias for -q"), cl::aliasopt(Quiet));
|
|
|
|
static cl::opt<bool>
|
|
AnalyzeOnly("analyze", cl::desc("Only perform analysis, no optimization"));
|
|
|
|
static cl::opt<bool>
|
|
PrintBreakpoints("print-breakpoints-for-testing",
|
|
cl::desc("Print select breakpoints location for testing"));
|
|
|
|
static cl::opt<std::string>
|
|
DefaultDataLayout("default-data-layout",
|
|
cl::desc("data layout string to use if not specified by module"),
|
|
cl::value_desc("layout-string"), cl::init(""));
|
|
|
|
static cl::opt<bool> PreserveBitcodeUseListOrder(
|
|
"preserve-bc-uselistorder",
|
|
cl::desc("Preserve use-list order when writing LLVM bitcode."),
|
|
cl::init(true), cl::Hidden);
|
|
|
|
static cl::opt<bool> PreserveAssemblyUseListOrder(
|
|
"preserve-ll-uselistorder",
|
|
cl::desc("Preserve use-list order when writing LLVM assembly."),
|
|
cl::init(false), cl::Hidden);
|
|
|
|
static cl::opt<bool>
|
|
RunTwice("run-twice",
|
|
cl::desc("Run all passes twice, re-using the same pass manager."),
|
|
cl::init(false), cl::Hidden);
|
|
|
|
static cl::opt<bool> DiscardValueNames(
|
|
"discard-value-names",
|
|
cl::desc("Discard names from Value (other than GlobalValue)."),
|
|
cl::init(false), cl::Hidden);
|
|
|
|
static cl::opt<bool> Coroutines(
|
|
"enable-coroutines",
|
|
cl::desc("Enable coroutine passes."),
|
|
cl::init(false), cl::Hidden);
|
|
|
|
static cl::opt<bool> PassRemarksWithHotness(
|
|
"pass-remarks-with-hotness",
|
|
cl::desc("With PGO, include profile count in optimization remarks"),
|
|
cl::Hidden);
|
|
|
|
static cl::opt<std::string>
|
|
RemarksFilename("pass-remarks-output",
|
|
cl::desc("YAML output filename for pass remarks"),
|
|
cl::value_desc("filename"));
|
|
|
|
static inline void addPass(legacy::PassManagerBase &PM, Pass *P) {
|
|
// Add the pass to the pass manager...
|
|
PM.add(P);
|
|
|
|
// If we are verifying all of the intermediate steps, add the verifier...
|
|
if (VerifyEach)
|
|
PM.add(createVerifierPass());
|
|
}
|
|
|
|
/// This routine adds optimization passes based on selected optimization level,
|
|
/// OptLevel.
|
|
///
|
|
/// OptLevel - Optimization Level
|
|
static void AddOptimizationPasses(legacy::PassManagerBase &MPM,
|
|
legacy::FunctionPassManager &FPM,
|
|
TargetMachine *TM, unsigned OptLevel,
|
|
unsigned SizeLevel) {
|
|
if (!NoVerify || VerifyEach)
|
|
FPM.add(createVerifierPass()); // Verify that input is correct
|
|
|
|
PassManagerBuilder Builder;
|
|
Builder.OptLevel = OptLevel;
|
|
Builder.SizeLevel = SizeLevel;
|
|
|
|
if (DisableInline) {
|
|
// No inlining pass
|
|
} else if (OptLevel > 1) {
|
|
Builder.Inliner = createFunctionInliningPass(OptLevel, SizeLevel);
|
|
} else {
|
|
Builder.Inliner = createAlwaysInlinerLegacyPass();
|
|
}
|
|
Builder.DisableUnitAtATime = !UnitAtATime;
|
|
Builder.DisableUnrollLoops = (DisableLoopUnrolling.getNumOccurrences() > 0) ?
|
|
DisableLoopUnrolling : OptLevel == 0;
|
|
|
|
// This is final, unless there is a #pragma vectorize enable
|
|
if (DisableLoopVectorization)
|
|
Builder.LoopVectorize = false;
|
|
// If option wasn't forced via cmd line (-vectorize-loops, -loop-vectorize)
|
|
else if (!Builder.LoopVectorize)
|
|
Builder.LoopVectorize = OptLevel > 1 && SizeLevel < 2;
|
|
|
|
// When #pragma vectorize is on for SLP, do the same as above
|
|
Builder.SLPVectorize =
|
|
DisableSLPVectorization ? false : OptLevel > 1 && SizeLevel < 2;
|
|
|
|
// Add target-specific passes that need to run as early as possible.
|
|
if (TM)
|
|
Builder.addExtension(
|
|
PassManagerBuilder::EP_EarlyAsPossible,
|
|
[&](const PassManagerBuilder &, legacy::PassManagerBase &PM) {
|
|
TM->addEarlyAsPossiblePasses(PM);
|
|
});
|
|
|
|
if (Coroutines)
|
|
addCoroutinePassesToExtensionPoints(Builder);
|
|
|
|
Builder.populateFunctionPassManager(FPM);
|
|
Builder.populateModulePassManager(MPM);
|
|
}
|
|
|
|
static void AddStandardLinkPasses(legacy::PassManagerBase &PM) {
|
|
PassManagerBuilder Builder;
|
|
Builder.VerifyInput = true;
|
|
if (DisableOptimizations)
|
|
Builder.OptLevel = 0;
|
|
|
|
if (!DisableInline)
|
|
Builder.Inliner = createFunctionInliningPass();
|
|
Builder.populateLTOPassManager(PM);
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// CodeGen-related helper functions.
|
|
//
|
|
|
|
static CodeGenOpt::Level GetCodeGenOptLevel() {
|
|
if (CodeGenOptLevel.getNumOccurrences())
|
|
return static_cast<CodeGenOpt::Level>(unsigned(CodeGenOptLevel));
|
|
if (OptLevelO1)
|
|
return CodeGenOpt::Less;
|
|
if (OptLevelO2)
|
|
return CodeGenOpt::Default;
|
|
if (OptLevelO3)
|
|
return CodeGenOpt::Aggressive;
|
|
return CodeGenOpt::None;
|
|
}
|
|
|
|
// Returns the TargetMachine instance or zero if no triple is provided.
|
|
static TargetMachine* GetTargetMachine(Triple TheTriple, StringRef CPUStr,
|
|
StringRef FeaturesStr,
|
|
const TargetOptions &Options) {
|
|
std::string Error;
|
|
const Target *TheTarget = TargetRegistry::lookupTarget(MArch, TheTriple,
|
|
Error);
|
|
// Some modules don't specify a triple, and this is okay.
|
|
if (!TheTarget) {
|
|
return nullptr;
|
|
}
|
|
|
|
return TheTarget->createTargetMachine(TheTriple.getTriple(), CPUStr,
|
|
FeaturesStr, Options, getRelocModel(),
|
|
CMModel, GetCodeGenOptLevel());
|
|
}
|
|
|
|
#ifdef LINK_POLLY_INTO_TOOLS
|
|
namespace polly {
|
|
void initializePollyPasses(llvm::PassRegistry &Registry);
|
|
}
|
|
#endif
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// main for opt
|
|
//
|
|
int main(int argc, char **argv) {
|
|
sys::PrintStackTraceOnErrorSignal(argv[0]);
|
|
llvm::PrettyStackTraceProgram X(argc, argv);
|
|
|
|
// Enable debug stream buffering.
|
|
EnableDebugBuffering = true;
|
|
|
|
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
|
|
LLVMContext Context;
|
|
|
|
InitializeAllTargets();
|
|
InitializeAllTargetMCs();
|
|
InitializeAllAsmPrinters();
|
|
|
|
// Initialize passes
|
|
PassRegistry &Registry = *PassRegistry::getPassRegistry();
|
|
initializeCore(Registry);
|
|
initializeCoroutines(Registry);
|
|
initializeScalarOpts(Registry);
|
|
initializeObjCARCOpts(Registry);
|
|
initializeVectorization(Registry);
|
|
initializeIPO(Registry);
|
|
initializeAnalysis(Registry);
|
|
initializeTransformUtils(Registry);
|
|
initializeInstCombine(Registry);
|
|
initializeInstrumentation(Registry);
|
|
initializeTarget(Registry);
|
|
// For codegen passes, only passes that do IR to IR transformation are
|
|
// supported.
|
|
initializeCodeGenPreparePass(Registry);
|
|
initializeAtomicExpandPass(Registry);
|
|
initializeRewriteSymbolsLegacyPassPass(Registry);
|
|
initializeWinEHPreparePass(Registry);
|
|
initializeDwarfEHPreparePass(Registry);
|
|
initializeSafeStackPass(Registry);
|
|
initializeSjLjEHPreparePass(Registry);
|
|
initializePreISelIntrinsicLoweringLegacyPassPass(Registry);
|
|
initializeGlobalMergePass(Registry);
|
|
initializeInterleavedAccessPass(Registry);
|
|
initializeCountingFunctionInserterPass(Registry);
|
|
initializeUnreachableBlockElimLegacyPassPass(Registry);
|
|
|
|
#ifdef LINK_POLLY_INTO_TOOLS
|
|
polly::initializePollyPasses(Registry);
|
|
#endif
|
|
|
|
cl::ParseCommandLineOptions(argc, argv,
|
|
"llvm .bc -> .bc modular optimizer and analysis printer\n");
|
|
|
|
if (AnalyzeOnly && NoOutput) {
|
|
errs() << argv[0] << ": analyze mode conflicts with no-output mode.\n";
|
|
return 1;
|
|
}
|
|
|
|
SMDiagnostic Err;
|
|
|
|
Context.setDiscardValueNames(DiscardValueNames);
|
|
if (!DisableDITypeMap)
|
|
Context.enableDebugTypeODRUniquing();
|
|
|
|
if (PassRemarksWithHotness)
|
|
Context.setDiagnosticHotnessRequested(true);
|
|
|
|
std::unique_ptr<tool_output_file> YamlFile;
|
|
if (RemarksFilename != "") {
|
|
std::error_code EC;
|
|
YamlFile = llvm::make_unique<tool_output_file>(RemarksFilename, EC,
|
|
sys::fs::F_None);
|
|
if (EC) {
|
|
errs() << EC.message() << '\n';
|
|
return 1;
|
|
}
|
|
Context.setDiagnosticsOutputFile(new yaml::Output(YamlFile->os()));
|
|
}
|
|
|
|
// Load the input module...
|
|
std::unique_ptr<Module> M = parseIRFile(InputFilename, Err, Context);
|
|
|
|
if (!M) {
|
|
Err.print(argv[0], errs());
|
|
return 1;
|
|
}
|
|
|
|
// Strip debug info before running the verifier.
|
|
if (StripDebug)
|
|
StripDebugInfo(*M);
|
|
|
|
// Immediately run the verifier to catch any problems before starting up the
|
|
// pass pipelines. Otherwise we can crash on broken code during
|
|
// doInitialization().
|
|
if (!NoVerify && verifyModule(*M, &errs())) {
|
|
errs() << argv[0] << ": " << InputFilename
|
|
<< ": error: input module is broken!\n";
|
|
return 1;
|
|
}
|
|
|
|
// If we are supposed to override the target triple, do so now.
|
|
if (!TargetTriple.empty())
|
|
M->setTargetTriple(Triple::normalize(TargetTriple));
|
|
|
|
// Figure out what stream we are supposed to write to...
|
|
std::unique_ptr<tool_output_file> Out;
|
|
if (NoOutput) {
|
|
if (!OutputFilename.empty())
|
|
errs() << "WARNING: The -o (output filename) option is ignored when\n"
|
|
"the --disable-output option is used.\n";
|
|
} else {
|
|
// Default to standard output.
|
|
if (OutputFilename.empty())
|
|
OutputFilename = "-";
|
|
|
|
std::error_code EC;
|
|
Out.reset(new tool_output_file(OutputFilename, EC, sys::fs::F_None));
|
|
if (EC) {
|
|
errs() << EC.message() << '\n';
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
Triple ModuleTriple(M->getTargetTriple());
|
|
std::string CPUStr, FeaturesStr;
|
|
TargetMachine *Machine = nullptr;
|
|
const TargetOptions Options = InitTargetOptionsFromCodeGenFlags();
|
|
|
|
if (ModuleTriple.getArch()) {
|
|
CPUStr = getCPUStr();
|
|
FeaturesStr = getFeaturesStr();
|
|
Machine = GetTargetMachine(ModuleTriple, CPUStr, FeaturesStr, Options);
|
|
}
|
|
|
|
std::unique_ptr<TargetMachine> TM(Machine);
|
|
|
|
// Override function attributes based on CPUStr, FeaturesStr, and command line
|
|
// flags.
|
|
setFunctionAttributes(CPUStr, FeaturesStr, *M);
|
|
|
|
// If the output is set to be emitted to standard out, and standard out is a
|
|
// console, print out a warning message and refuse to do it. We don't
|
|
// impress anyone by spewing tons of binary goo to a terminal.
|
|
if (!Force && !NoOutput && !AnalyzeOnly && !OutputAssembly)
|
|
if (CheckBitcodeOutputToConsole(Out->os(), !Quiet))
|
|
NoOutput = true;
|
|
|
|
if (PassPipeline.getNumOccurrences() > 0) {
|
|
OutputKind OK = OK_NoOutput;
|
|
if (!NoOutput)
|
|
OK = OutputAssembly ? OK_OutputAssembly : OK_OutputBitcode;
|
|
|
|
VerifierKind VK = VK_VerifyInAndOut;
|
|
if (NoVerify)
|
|
VK = VK_NoVerifier;
|
|
else if (VerifyEach)
|
|
VK = VK_VerifyEachPass;
|
|
|
|
// The user has asked to use the new pass manager and provided a pipeline
|
|
// string. Hand off the rest of the functionality to the new code for that
|
|
// layer.
|
|
return runPassPipeline(argv[0], *M, TM.get(), Out.get(),
|
|
PassPipeline, OK, VK, PreserveAssemblyUseListOrder,
|
|
PreserveBitcodeUseListOrder, EmitSummaryIndex,
|
|
EmitModuleHash)
|
|
? 0
|
|
: 1;
|
|
}
|
|
|
|
// Create a PassManager to hold and optimize the collection of passes we are
|
|
// about to build.
|
|
//
|
|
legacy::PassManager Passes;
|
|
|
|
// Add an appropriate TargetLibraryInfo pass for the module's triple.
|
|
TargetLibraryInfoImpl TLII(ModuleTriple);
|
|
|
|
// The -disable-simplify-libcalls flag actually disables all builtin optzns.
|
|
if (DisableSimplifyLibCalls)
|
|
TLII.disableAllFunctions();
|
|
Passes.add(new TargetLibraryInfoWrapperPass(TLII));
|
|
|
|
// Add an appropriate DataLayout instance for this module.
|
|
const DataLayout &DL = M->getDataLayout();
|
|
if (DL.isDefault() && !DefaultDataLayout.empty()) {
|
|
M->setDataLayout(DefaultDataLayout);
|
|
}
|
|
|
|
// Add internal analysis passes from the target machine.
|
|
Passes.add(createTargetTransformInfoWrapperPass(TM ? TM->getTargetIRAnalysis()
|
|
: TargetIRAnalysis()));
|
|
|
|
std::unique_ptr<legacy::FunctionPassManager> FPasses;
|
|
if (OptLevelO0 || OptLevelO1 || OptLevelO2 || OptLevelOs || OptLevelOz ||
|
|
OptLevelO3) {
|
|
FPasses.reset(new legacy::FunctionPassManager(M.get()));
|
|
FPasses->add(createTargetTransformInfoWrapperPass(
|
|
TM ? TM->getTargetIRAnalysis() : TargetIRAnalysis()));
|
|
}
|
|
|
|
if (PrintBreakpoints) {
|
|
// Default to standard output.
|
|
if (!Out) {
|
|
if (OutputFilename.empty())
|
|
OutputFilename = "-";
|
|
|
|
std::error_code EC;
|
|
Out = llvm::make_unique<tool_output_file>(OutputFilename, EC,
|
|
sys::fs::F_None);
|
|
if (EC) {
|
|
errs() << EC.message() << '\n';
|
|
return 1;
|
|
}
|
|
}
|
|
Passes.add(createBreakpointPrinter(Out->os()));
|
|
NoOutput = true;
|
|
}
|
|
|
|
// Create a new optimization pass for each one specified on the command line
|
|
for (unsigned i = 0; i < PassList.size(); ++i) {
|
|
if (StandardLinkOpts &&
|
|
StandardLinkOpts.getPosition() < PassList.getPosition(i)) {
|
|
AddStandardLinkPasses(Passes);
|
|
StandardLinkOpts = false;
|
|
}
|
|
|
|
if (OptLevelO0 && OptLevelO0.getPosition() < PassList.getPosition(i)) {
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 0, 0);
|
|
OptLevelO0 = false;
|
|
}
|
|
|
|
if (OptLevelO1 && OptLevelO1.getPosition() < PassList.getPosition(i)) {
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 1, 0);
|
|
OptLevelO1 = false;
|
|
}
|
|
|
|
if (OptLevelO2 && OptLevelO2.getPosition() < PassList.getPosition(i)) {
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 2, 0);
|
|
OptLevelO2 = false;
|
|
}
|
|
|
|
if (OptLevelOs && OptLevelOs.getPosition() < PassList.getPosition(i)) {
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 2, 1);
|
|
OptLevelOs = false;
|
|
}
|
|
|
|
if (OptLevelOz && OptLevelOz.getPosition() < PassList.getPosition(i)) {
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 2, 2);
|
|
OptLevelOz = false;
|
|
}
|
|
|
|
if (OptLevelO3 && OptLevelO3.getPosition() < PassList.getPosition(i)) {
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 3, 0);
|
|
OptLevelO3 = false;
|
|
}
|
|
|
|
const PassInfo *PassInf = PassList[i];
|
|
Pass *P = nullptr;
|
|
if (PassInf->getTargetMachineCtor())
|
|
P = PassInf->getTargetMachineCtor()(TM.get());
|
|
else if (PassInf->getNormalCtor())
|
|
P = PassInf->getNormalCtor()();
|
|
else
|
|
errs() << argv[0] << ": cannot create pass: "
|
|
<< PassInf->getPassName() << "\n";
|
|
if (P) {
|
|
PassKind Kind = P->getPassKind();
|
|
addPass(Passes, P);
|
|
|
|
if (AnalyzeOnly) {
|
|
switch (Kind) {
|
|
case PT_BasicBlock:
|
|
Passes.add(createBasicBlockPassPrinter(PassInf, Out->os(), Quiet));
|
|
break;
|
|
case PT_Region:
|
|
Passes.add(createRegionPassPrinter(PassInf, Out->os(), Quiet));
|
|
break;
|
|
case PT_Loop:
|
|
Passes.add(createLoopPassPrinter(PassInf, Out->os(), Quiet));
|
|
break;
|
|
case PT_Function:
|
|
Passes.add(createFunctionPassPrinter(PassInf, Out->os(), Quiet));
|
|
break;
|
|
case PT_CallGraphSCC:
|
|
Passes.add(createCallGraphPassPrinter(PassInf, Out->os(), Quiet));
|
|
break;
|
|
default:
|
|
Passes.add(createModulePassPrinter(PassInf, Out->os(), Quiet));
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (PrintEachXForm)
|
|
Passes.add(
|
|
createPrintModulePass(errs(), "", PreserveAssemblyUseListOrder));
|
|
}
|
|
|
|
if (StandardLinkOpts) {
|
|
AddStandardLinkPasses(Passes);
|
|
StandardLinkOpts = false;
|
|
}
|
|
|
|
if (OptLevelO0)
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 0, 0);
|
|
|
|
if (OptLevelO1)
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 1, 0);
|
|
|
|
if (OptLevelO2)
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 2, 0);
|
|
|
|
if (OptLevelOs)
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 2, 1);
|
|
|
|
if (OptLevelOz)
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 2, 2);
|
|
|
|
if (OptLevelO3)
|
|
AddOptimizationPasses(Passes, *FPasses, TM.get(), 3, 0);
|
|
|
|
if (FPasses) {
|
|
FPasses->doInitialization();
|
|
for (Function &F : *M)
|
|
FPasses->run(F);
|
|
FPasses->doFinalization();
|
|
}
|
|
|
|
// Check that the module is well formed on completion of optimization
|
|
if (!NoVerify && !VerifyEach)
|
|
Passes.add(createVerifierPass());
|
|
|
|
// In run twice mode, we want to make sure the output is bit-by-bit
|
|
// equivalent if we run the pass manager again, so setup two buffers and
|
|
// a stream to write to them. Note that llc does something similar and it
|
|
// may be worth to abstract this out in the future.
|
|
SmallVector<char, 0> Buffer;
|
|
SmallVector<char, 0> CompileTwiceBuffer;
|
|
std::unique_ptr<raw_svector_ostream> BOS;
|
|
raw_ostream *OS = nullptr;
|
|
|
|
// Write bitcode or assembly to the output as the last step...
|
|
if (!NoOutput && !AnalyzeOnly) {
|
|
assert(Out);
|
|
OS = &Out->os();
|
|
if (RunTwice) {
|
|
BOS = make_unique<raw_svector_ostream>(Buffer);
|
|
OS = BOS.get();
|
|
}
|
|
if (OutputAssembly) {
|
|
if (EmitSummaryIndex)
|
|
report_fatal_error("Text output is incompatible with -module-summary");
|
|
if (EmitModuleHash)
|
|
report_fatal_error("Text output is incompatible with -module-hash");
|
|
Passes.add(createPrintModulePass(*OS, "", PreserveAssemblyUseListOrder));
|
|
} else
|
|
Passes.add(createBitcodeWriterPass(*OS, PreserveBitcodeUseListOrder,
|
|
EmitSummaryIndex, EmitModuleHash));
|
|
}
|
|
|
|
// Before executing passes, print the final values of the LLVM options.
|
|
cl::PrintOptionValues();
|
|
|
|
// If requested, run all passes again with the same pass manager to catch
|
|
// bugs caused by persistent state in the passes
|
|
if (RunTwice) {
|
|
std::unique_ptr<Module> M2(CloneModule(M.get()));
|
|
Passes.run(*M2);
|
|
CompileTwiceBuffer = Buffer;
|
|
Buffer.clear();
|
|
}
|
|
|
|
// Now that we have all of the passes ready, run them.
|
|
Passes.run(*M);
|
|
|
|
// Compare the two outputs and make sure they're the same
|
|
if (RunTwice) {
|
|
assert(Out);
|
|
if (Buffer.size() != CompileTwiceBuffer.size() ||
|
|
(memcmp(Buffer.data(), CompileTwiceBuffer.data(), Buffer.size()) !=
|
|
0)) {
|
|
errs() << "Running the pass manager twice changed the output.\n"
|
|
"Writing the result of the second run to the specified output.\n"
|
|
"To generate the one-run comparison binary, just run without\n"
|
|
"the compile-twice option\n";
|
|
Out->os() << BOS->str();
|
|
Out->keep();
|
|
if (YamlFile)
|
|
YamlFile->keep();
|
|
return 1;
|
|
}
|
|
Out->os() << BOS->str();
|
|
}
|
|
|
|
// Declare success.
|
|
if (!NoOutput || PrintBreakpoints)
|
|
Out->keep();
|
|
|
|
if (YamlFile)
|
|
YamlFile->keep();
|
|
|
|
return 0;
|
|
}
|