llvm-project/llvm/lib/CodeGen/LLVMTargetMachine.cpp

495 lines
18 KiB
C++
Raw Normal View History

2006-09-04 12:16:09 +08:00
//===-- LLVMTargetMachine.cpp - Implement the LLVMTargetMachine class -----===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
2006-09-04 12:16:09 +08:00
//
//===----------------------------------------------------------------------===//
//
// This file implements the LLVMTargetMachine class.
//
//===----------------------------------------------------------------------===//
#include "llvm/Target/TargetMachine.h"
#include "llvm/PassManager.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Analysis/Verifier.h"
#include "llvm/Assembly/PrintModulePass.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/MachineFunctionAnalysis.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/GCStrategy.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/Target/TargetLowering.h"
2006-09-04 12:16:09 +08:00
#include "llvm/Target/TargetOptions.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/Target/TargetAsmInfo.h"
#include "llvm/Target/TargetData.h"
2009-07-16 07:48:37 +08:00
#include "llvm/Target/TargetRegistry.h"
2006-09-04 12:16:09 +08:00
#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/OwningPtr.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/FormattedStream.h"
2006-09-04 12:16:09 +08:00
using namespace llvm;
namespace llvm {
bool EnableFastISel;
}
static cl::opt<bool> DisablePostRA("disable-post-ra", cl::Hidden,
cl::desc("Disable Post Regalloc"));
static cl::opt<bool> DisableBranchFold("disable-branch-fold", cl::Hidden,
cl::desc("Disable branch folding"));
static cl::opt<bool> DisableTailDuplicate("disable-tail-duplicate", cl::Hidden,
cl::desc("Disable tail duplication"));
static cl::opt<bool> DisableEarlyTailDup("disable-early-taildup", cl::Hidden,
cl::desc("Disable pre-register allocation tail duplication"));
static cl::opt<bool> DisableCodePlace("disable-code-place", cl::Hidden,
cl::desc("Disable code placement"));
static cl::opt<bool> DisableSSC("disable-ssc", cl::Hidden,
cl::desc("Disable Stack Slot Coloring"));
static cl::opt<bool> DisableMachineLICM("disable-machine-licm", cl::Hidden,
cl::desc("Disable Machine LICM"));
static cl::opt<bool> DisablePostRAMachineLICM("disable-postra-machine-licm",
cl::Hidden,
cl::desc("Disable Machine LICM"));
static cl::opt<bool> DisableMachineSink("disable-machine-sink", cl::Hidden,
cl::desc("Disable Machine Sinking"));
static cl::opt<bool> DisableLSR("disable-lsr", cl::Hidden,
cl::desc("Disable Loop Strength Reduction Pass"));
static cl::opt<bool> DisableCGP("disable-cgp", cl::Hidden,
cl::desc("Disable Codegen Prepare"));
static cl::opt<bool> PrintLSR("print-lsr-output", cl::Hidden,
cl::desc("Print LLVM IR produced by the loop-reduce pass"));
static cl::opt<bool> PrintISelInput("print-isel-input", cl::Hidden,
cl::desc("Print LLVM IR input to isel pass"));
static cl::opt<bool> PrintGCInfo("print-gc", cl::Hidden,
cl::desc("Dump garbage collector data"));
static cl::opt<bool> ShowMCEncoding("show-mc-encoding", cl::Hidden,
cl::desc("Show encoding in .s output"));
static cl::opt<bool> ShowMCInst("show-mc-inst", cl::Hidden,
cl::desc("Show instruction structure in .s output"));
static cl::opt<bool> EnableMCLogging("enable-mc-api-logging", cl::Hidden,
cl::desc("Enable MC API logging"));
static cl::opt<bool> VerifyMachineCode("verify-machineinstrs", cl::Hidden,
cl::desc("Verify generated machine code"),
cl::init(getenv("LLVM_VERIFY_MACHINEINSTRS")!=NULL));
static cl::opt<cl::boolOrDefault>
AsmVerbose("asm-verbose", cl::desc("Add comments to directives."),
cl::init(cl::BOU_UNSET));
2010-02-03 06:58:13 +08:00
static bool getVerboseAsm() {
switch (AsmVerbose) {
2010-02-03 06:58:13 +08:00
default:
case cl::BOU_UNSET: return TargetMachine::getAsmVerbosityDefault();
case cl::BOU_TRUE: return true;
case cl::BOU_FALSE: return false;
}
}
// Enable or disable FastISel. Both options are needed, because
// FastISel is enabled by default with -fast, and we wish to be
// able to enable or disable fast-isel independently from -O0.
static cl::opt<cl::boolOrDefault>
EnableFastISelOption("fast-isel", cl::Hidden,
cl::desc("Enable the \"fast\" instruction selector"));
LLVMTargetMachine::LLVMTargetMachine(const Target &T,
const std::string &Triple)
: TargetMachine(T), TargetTriple(Triple) {
AsmInfo = T.createAsmInfo(TargetTriple);
}
// Set the default code model for the JIT for a generic target.
// FIXME: Is small right here? or .is64Bit() ? Large : Small?
void LLVMTargetMachine::setCodeModelForJIT() {
setCodeModel(CodeModel::Small);
}
// Set the default code model for static compilation for a generic target.
void LLVMTargetMachine::setCodeModelForStatic() {
setCodeModel(CodeModel::Small);
}
bool LLVMTargetMachine::addPassesToEmitFile(PassManagerBase &PM,
formatted_raw_ostream &Out,
CodeGenFileType FileType,
CodeGenOpt::Level OptLevel,
bool DisableVerify) {
// Add common CodeGen passes.
MCContext *Context = 0;
if (addCommonCodeGenPasses(PM, OptLevel, DisableVerify, Context))
return true;
assert(Context != 0 && "Failed to get MCContext");
if (hasMCSaveTempLabels())
Context->setAllowTemporaryLabels(false);
const MCAsmInfo &MAI = *getMCAsmInfo();
OwningPtr<MCStreamer> AsmStreamer;
2006-09-04 12:16:09 +08:00
switch (FileType) {
default: return true;
case CGFT_AssemblyFile: {
MCInstPrinter *InstPrinter =
getTarget().createMCInstPrinter(*this, MAI.getAssemblerDialect(), MAI);
// Create a code emitter if asked to show the encoding.
MCCodeEmitter *MCE = 0;
TargetAsmBackend *TAB = 0;
if (ShowMCEncoding) {
MCE = getTarget().createCodeEmitter(*this, *Context);
TAB = getTarget().createAsmBackend(TargetTriple);
}
MCStreamer *S = getTarget().createAsmStreamer(*Context, Out,
getVerboseAsm(),
hasMCUseLoc(),
hasMCUseCFI(),
InstPrinter,
MCE, TAB,
ShowMCInst);
AsmStreamer.reset(S);
break;
}
case CGFT_ObjectFile: {
// Create the code emitter for the target if it exists. If not, .o file
// emission fails.
MCCodeEmitter *MCE = getTarget().createCodeEmitter(*this, *Context);
TargetAsmBackend *TAB = getTarget().createAsmBackend(TargetTriple);
if (MCE == 0 || TAB == 0)
return true;
AsmStreamer.reset(getTarget().createObjectStreamer(TargetTriple, *Context,
*TAB, Out, MCE,
hasMCRelaxAll(),
hasMCNoExecStack()));
AsmStreamer.get()->InitSections();
break;
}
case CGFT_Null:
// The Null output is intended for use for performance analysis and testing,
// not real users.
AsmStreamer.reset(createNullStreamer(*Context));
break;
2006-09-04 12:16:09 +08:00
}
if (EnableMCLogging)
AsmStreamer.reset(createLoggingStreamer(AsmStreamer.take(), errs()));
// Create the AsmPrinter, which takes ownership of AsmStreamer if successful.
FunctionPass *Printer = getTarget().createAsmPrinter(*this, *AsmStreamer);
if (Printer == 0)
return true;
// If successful, createAsmPrinter took ownership of AsmStreamer.
AsmStreamer.take();
PM.add(Printer);
// Make sure the code model is set.
setCodeModelForStatic();
PM.add(createGCInfoDeleter());
return false;
}
/// addPassesToEmitMachineCode - Add passes to the specified pass manager to
/// get machine code emitted. This uses a JITCodeEmitter object to handle
/// actually outputting the machine code and resolving things like the address
/// of functions. This method should returns true if machine code emission is
/// not supported.
///
bool LLVMTargetMachine::addPassesToEmitMachineCode(PassManagerBase &PM,
JITCodeEmitter &JCE,
CodeGenOpt::Level OptLevel,
bool DisableVerify) {
// Make sure the code model is set.
setCodeModelForJIT();
// Add common CodeGen passes.
MCContext *Ctx = 0;
if (addCommonCodeGenPasses(PM, OptLevel, DisableVerify, Ctx))
return true;
addCodeEmitter(PM, OptLevel, JCE);
PM.add(createGCInfoDeleter());
return false; // success!
}
/// addPassesToEmitMC - Add passes to the specified pass manager to get
/// machine code emitted with the MCJIT. This method returns true if machine
/// code is not supported. It fills the MCContext Ctx pointer which can be
/// used to build custom MCStreamer.
///
bool LLVMTargetMachine::addPassesToEmitMC(PassManagerBase &PM,
MCContext *&Ctx,
raw_ostream &Out,
CodeGenOpt::Level OptLevel,
bool DisableVerify) {
// Add common CodeGen passes.
if (addCommonCodeGenPasses(PM, OptLevel, DisableVerify, Ctx))
return true;
if (hasMCSaveTempLabels())
Ctx->setAllowTemporaryLabels(false);
// Create the code emitter for the target if it exists. If not, .o file
// emission fails.
MCCodeEmitter *MCE = getTarget().createCodeEmitter(*this, *Ctx);
TargetAsmBackend *TAB = getTarget().createAsmBackend(TargetTriple);
if (MCE == 0 || TAB == 0)
return true;
OwningPtr<MCStreamer> AsmStreamer;
AsmStreamer.reset(getTarget().createObjectStreamer(TargetTriple, *Ctx,
*TAB, Out, MCE,
hasMCRelaxAll(),
hasMCNoExecStack()));
AsmStreamer.get()->InitSections();
// Create the AsmPrinter, which takes ownership of AsmStreamer if successful.
FunctionPass *Printer = getTarget().createAsmPrinter(*this, *AsmStreamer);
if (Printer == 0)
return true;
// If successful, createAsmPrinter took ownership of AsmStreamer.
AsmStreamer.take();
PM.add(Printer);
// Make sure the code model is set.
setCodeModelForJIT();
return false; // success!
}
static void printNoVerify(PassManagerBase &PM, const char *Banner) {
if (PrintMachineCode)
PM.add(createMachineFunctionPrinterPass(dbgs(), Banner));
}
static void printAndVerify(PassManagerBase &PM,
const char *Banner) {
if (PrintMachineCode)
PM.add(createMachineFunctionPrinterPass(dbgs(), Banner));
if (VerifyMachineCode)
PM.add(createMachineVerifierPass(Banner));
}
/// addCommonCodeGenPasses - Add standard LLVM codegen passes used for both
/// emitting to assembly files or machine code output.
///
bool LLVMTargetMachine::addCommonCodeGenPasses(PassManagerBase &PM,
CodeGenOpt::Level OptLevel,
bool DisableVerify,
MCContext *&OutContext) {
2006-09-04 12:16:09 +08:00
// Standard LLVM-Level Passes.
// Basic AliasAnalysis support.
// Add TypeBasedAliasAnalysis before BasicAliasAnalysis so that
// BasicAliasAnalysis wins if they disagree. This is intended to help
// support "obvious" type-punning idioms.
PM.add(createTypeBasedAliasAnalysisPass());
PM.add(createBasicAliasAnalysisPass());
// Before running any passes, run the verifier to determine if the input
// coming from the front-end and/or optimizer is valid.
if (!DisableVerify)
PM.add(createVerifierPass());
// Simplify ObjC ARC code. This is done late because it makes re-optimization
// difficult.
PM.add(createObjCARCContractPass());
2006-09-04 12:16:09 +08:00
// Run loop strength reduction before anything else.
if (OptLevel != CodeGenOpt::None && !DisableLSR) {
PM.add(createLoopStrengthReducePass(getTargetLowering()));
if (PrintLSR)
PM.add(createPrintFunctionPass("\n\n*** Code after LSR ***\n", &dbgs()));
}
PM.add(createGCLoweringPass());
// Make sure that no unreachable blocks are instruction selected.
PM.add(createUnreachableBlockEliminationPass());
Add a new codegen pass that normalizes dwarf exception handling code in preparation for code generation. The main thing it does is handle the case when eh.exception calls (and, in a future patch, eh.selector calls) are far away from landing pads. Right now in practice you only find eh.exception calls close to landing pads: either in a landing pad (the common case) or in a landing pad successor, due to loop passes shifting them about. However future exception handling improvements will result in calls far from landing pads: (1) Inlining of rewinds. Consider the following case: In function @f: ... invoke @g to label %normal unwind label %unwinds ... unwinds: %ex = call i8* @llvm.eh.exception() ... In function @g: ... invoke @something to label %continue unwind label %handler ... handler: %ex = call i8* @llvm.eh.exception() ... perform cleanups ... "rethrow exception" Now inline @g into @f. Currently this is turned into: In function @f: ... invoke @something to label %continue unwind label %handler ... handler: %ex = call i8* @llvm.eh.exception() ... perform cleanups ... invoke "rethrow exception" to label %normal unwind label %unwinds unwinds: %ex = call i8* @llvm.eh.exception() ... However we would like to simplify invoke of "rethrow exception" into a branch to the %unwinds label. Then %unwinds is no longer a landing pad, and the eh.exception call there is then far away from any landing pads. (2) Using the unwind instruction for cleanups. It would be nice to have codegen handle the following case: invoke @something to label %continue unwind label %run_cleanups ... handler: ... perform cleanups ... unwind This requires turning "unwind" into a library call, which necessarily takes a pointer to the exception as an argument (this patch also does this unwind lowering). But that means you are using eh.exception again far from a landing pad. (3) Bugpoint simplifications. When bugpoint is simplifying exception handling code it often generates eh.exception calls far from a landing pad, which then causes codegen to assert. Bugpoint then latches on to this assertion and loses sight of the original problem. Note that it is currently rare for this pass to actually do anything. And in fact it normally shouldn't do anything at all given the code coming out of llvm-gcc! But it does fire a few times in the testsuite. As far as I can see this is almost always due to the LoopStrengthReduce codegen pass introducing pointless loop preheader blocks which are landing pads and only contain a branch to another block. This other block contains an eh.exception call. So probably by tweaking LoopStrengthReduce a bit this can be avoided. llvm-svn: 72276
2009-05-23 04:36:31 +08:00
// Turn exception handling constructs into something the code generators can
// handle.
switch (getMCAsmInfo()->getExceptionHandlingType()) {
case ExceptionHandling::SjLj:
// SjLj piggy-backs on dwarf for this bit. The cleanups done apply to both
// Dwarf EH prepare needs to be run after SjLj prepare. Otherwise,
// catch info can get misplaced when a selector ends up more than one block
// removed from the parent invoke(s). This could happen when a landing
// pad is shared by multiple invokes and is also a target of a normal
// edge from elsewhere.
PM.add(createSjLjEHPass(getTargetLowering()));
// FALLTHROUGH
case ExceptionHandling::DwarfCFI:
case ExceptionHandling::ARM:
case ExceptionHandling::Win64:
PM.add(createDwarfEHPass(this));
break;
case ExceptionHandling::None:
PM.add(createLowerInvokePass(getTargetLowering()));
// The lower invoke pass may create unreachable code. Remove it.
PM.add(createUnreachableBlockEliminationPass());
break;
}
Add a new codegen pass that normalizes dwarf exception handling code in preparation for code generation. The main thing it does is handle the case when eh.exception calls (and, in a future patch, eh.selector calls) are far away from landing pads. Right now in practice you only find eh.exception calls close to landing pads: either in a landing pad (the common case) or in a landing pad successor, due to loop passes shifting them about. However future exception handling improvements will result in calls far from landing pads: (1) Inlining of rewinds. Consider the following case: In function @f: ... invoke @g to label %normal unwind label %unwinds ... unwinds: %ex = call i8* @llvm.eh.exception() ... In function @g: ... invoke @something to label %continue unwind label %handler ... handler: %ex = call i8* @llvm.eh.exception() ... perform cleanups ... "rethrow exception" Now inline @g into @f. Currently this is turned into: In function @f: ... invoke @something to label %continue unwind label %handler ... handler: %ex = call i8* @llvm.eh.exception() ... perform cleanups ... invoke "rethrow exception" to label %normal unwind label %unwinds unwinds: %ex = call i8* @llvm.eh.exception() ... However we would like to simplify invoke of "rethrow exception" into a branch to the %unwinds label. Then %unwinds is no longer a landing pad, and the eh.exception call there is then far away from any landing pads. (2) Using the unwind instruction for cleanups. It would be nice to have codegen handle the following case: invoke @something to label %continue unwind label %run_cleanups ... handler: ... perform cleanups ... unwind This requires turning "unwind" into a library call, which necessarily takes a pointer to the exception as an argument (this patch also does this unwind lowering). But that means you are using eh.exception again far from a landing pad. (3) Bugpoint simplifications. When bugpoint is simplifying exception handling code it often generates eh.exception calls far from a landing pad, which then causes codegen to assert. Bugpoint then latches on to this assertion and loses sight of the original problem. Note that it is currently rare for this pass to actually do anything. And in fact it normally shouldn't do anything at all given the code coming out of llvm-gcc! But it does fire a few times in the testsuite. As far as I can see this is almost always due to the LoopStrengthReduce codegen pass introducing pointless loop preheader blocks which are landing pads and only contain a branch to another block. This other block contains an eh.exception call. So probably by tweaking LoopStrengthReduce a bit this can be avoided. llvm-svn: 72276
2009-05-23 04:36:31 +08:00
if (OptLevel != CodeGenOpt::None && !DisableCGP)
PM.add(createCodeGenPreparePass(getTargetLowering()));
PM.add(createStackProtectorPass(getTargetLowering()));
addPreISel(PM, OptLevel);
if (PrintISelInput)
PM.add(createPrintFunctionPass("\n\n"
"*** Final LLVM Code input to ISel ***\n",
&dbgs()));
// All passes which modify the LLVM IR are now complete; run the verifier
// to ensure that the IR is valid.
if (!DisableVerify)
PM.add(createVerifierPass());
// Standard Lower-Level Passes.
// Install a MachineModuleInfo class, which is an immutable pass that holds
// all the per-module stuff we're generating, including MCContext.
TargetAsmInfo *TAI = new TargetAsmInfo(*this);
MachineModuleInfo *MMI = new MachineModuleInfo(*getMCAsmInfo(), TAI);
PM.add(MMI);
OutContext = &MMI->getContext(); // Return the MCContext specifically by-ref.
// Set up a MachineFunction for the rest of CodeGen to work on.
PM.add(new MachineFunctionAnalysis(*this, OptLevel));
// Enable FastISel with -fast, but allow that to be overridden.
if (EnableFastISelOption == cl::BOU_TRUE ||
(OptLevel == CodeGenOpt::None && EnableFastISelOption != cl::BOU_FALSE))
EnableFastISel = true;
2006-09-04 12:16:09 +08:00
// Ask the target for an isel.
if (addInstSelector(PM, OptLevel))
2006-09-04 12:16:09 +08:00
return true;
2006-09-04 12:16:09 +08:00
// Print the instruction selected machine code...
printAndVerify(PM, "After Instruction Selection");
// Expand pseudo-instructions emitted by ISel.
PM.add(createExpandISelPseudosPass());
// Optimize PHIs before DCE: removing dead PHI cycles may make more
// instructions dead.
if (OptLevel != CodeGenOpt::None)
PM.add(createOptimizePHIsPass());
// If the target requests it, assign local variables to stack slots relative
// to one another and simplify frame index references where possible.
PM.add(createLocalStackSlotAllocationPass());
if (OptLevel != CodeGenOpt::None) {
// With optimization, dead code should already be eliminated. However
// there is one known exception: lowered code for arguments that are only
// used by tail calls, where the tail calls reuse the incoming stack
// arguments directly (see t11 in test/CodeGen/X86/sibcall.ll).
PM.add(createDeadMachineInstructionElimPass());
printAndVerify(PM, "After codegen DCE pass");
if (!DisableMachineLICM)
PM.add(createMachineLICMPass());
PM.add(createMachineCSEPass());
if (!DisableMachineSink)
PM.add(createMachineSinkingPass());
printAndVerify(PM, "After Machine LICM, CSE and Sinking passes");
PM.add(createPeepholeOptimizerPass());
printAndVerify(PM, "After codegen peephole optimization pass");
}
// Pre-ra tail duplication.
if (OptLevel != CodeGenOpt::None && !DisableEarlyTailDup) {
PM.add(createTailDuplicatePass(true));
printAndVerify(PM, "After Pre-RegAlloc TailDuplicate");
}
2008-04-24 02:26:03 +08:00
// Run pre-ra passes.
if (addPreRegAlloc(PM, OptLevel))
printAndVerify(PM, "After PreRegAlloc passes");
2008-04-24 02:26:03 +08:00
// Perform register allocation.
PM.add(createRegisterAllocator(OptLevel));
printAndVerify(PM, "After Register Allocation");
// Perform stack slot coloring and post-ra machine LICM.
if (OptLevel != CodeGenOpt::None) {
// FIXME: Re-enable coloring with register when it's capable of adding
// kill markers.
if (!DisableSSC)
PM.add(createStackSlotColoringPass(false));
// Run post-ra machine LICM to hoist reloads / remats.
if (!DisablePostRAMachineLICM)
PM.add(createMachineLICMPass(false));
printAndVerify(PM, "After StackSlotColoring and postra Machine LICM");
}
// Run post-ra passes.
if (addPostRegAlloc(PM, OptLevel))
printAndVerify(PM, "After PostRegAlloc passes");
PM.add(createLowerSubregsPass());
printAndVerify(PM, "After LowerSubregs");
2006-09-04 12:16:09 +08:00
// Insert prolog/epilog code. Eliminate abstract frame index references...
PM.add(createPrologEpilogCodeInserter());
printAndVerify(PM, "After PrologEpilogCodeInserter");
// Run pre-sched2 passes.
if (addPreSched2(PM, OptLevel))
printAndVerify(PM, "After PreSched2 passes");
// Second pass scheduler.
if (OptLevel != CodeGenOpt::None && !DisablePostRA) {
PM.add(createPostRAScheduler(OptLevel));
printAndVerify(PM, "After PostRAScheduler");
}
// Branch folding must be run after regalloc and prolog/epilog insertion.
if (OptLevel != CodeGenOpt::None && !DisableBranchFold) {
PM.add(createBranchFoldingPass(getEnableTailMergeDefault()));
printNoVerify(PM, "After BranchFolding");
}
// Tail duplication.
if (OptLevel != CodeGenOpt::None && !DisableTailDuplicate) {
PM.add(createTailDuplicatePass(false));
printNoVerify(PM, "After TailDuplicate");
}
PM.add(createGCMachineCodeAnalysisPass());
if (PrintGCInfo)
PM.add(createGCInfoPrinter(dbgs()));
if (OptLevel != CodeGenOpt::None && !DisableCodePlace) {
PM.add(createCodePlacementOptPass());
printNoVerify(PM, "After CodePlacementOpt");
}
if (addPreEmitPass(PM, OptLevel))
printNoVerify(PM, "After PreEmit passes");
return false;
2006-09-04 12:16:09 +08:00
}