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

299 lines
12 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/ADT/OwningPtr.h"
#include "llvm/Assembly/PrintModulePass.h"
#include "llvm/CodeGen/AsmPrinter.h"
#include "llvm/CodeGen/MachineFunctionAnalysis.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCInstrInfo.h"
#include "llvm/MC/MCStreamer.h"
#include "llvm/MC/MCSubtargetInfo.h"
#include "llvm/PassManager.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/FormattedStream.h"
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Target/TargetInstrInfo.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetLoweringObjectFile.h"
#include "llvm/Target/TargetOptions.h"
#include "llvm/Target/TargetRegisterInfo.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include "llvm/Transforms/Scalar.h"
2006-09-04 12:16:09 +08:00
using namespace llvm;
// 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"));
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<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
case cl::BOU_UNSET: return TargetMachine::getAsmVerbosityDefault();
case cl::BOU_TRUE: return true;
case cl::BOU_FALSE: return false;
}
llvm_unreachable("Invalid verbose asm state");
}
LLVMTargetMachine::LLVMTargetMachine(const Target &T, StringRef Triple,
StringRef CPU, StringRef FS,
TargetOptions Options,
Reloc::Model RM, CodeModel::Model CM,
CodeGenOpt::Level OL)
: TargetMachine(T, Triple, CPU, FS, Options) {
CodeGenInfo = T.createMCCodeGenInfo(Triple, RM, CM, OL);
AsmInfo = T.createMCAsmInfo(Triple);
// TargetSelect.h moved to a different directory between LLVM 2.9 and 3.0,
// and if the old one gets included then MCAsmInfo will be NULL and
// we'll crash later.
// Provide the user with a useful error message about what's wrong.
assert(AsmInfo && "MCAsmInfo not initialized."
"Make sure you include the correct TargetSelect.h"
"and that InitializeAllTargetMCs() is being invoked!");
}
Switch TargetTransformInfo from an immutable analysis pass that requires a TargetMachine to construct (and thus isn't always available), to an analysis group that supports layered implementations much like AliasAnalysis does. This is a pretty massive change, with a few parts that I was unable to easily separate (sorry), so I'll walk through it. The first step of this conversion was to make TargetTransformInfo an analysis group, and to sink the nonce implementations in ScalarTargetTransformInfo and VectorTargetTranformInfo into a NoTargetTransformInfo pass. This allows other passes to add a hard requirement on TTI, and assume they will always get at least on implementation. The TargetTransformInfo analysis group leverages the delegation chaining trick that AliasAnalysis uses, where the base class for the analysis group delegates to the previous analysis *pass*, allowing all but tho NoFoo analysis passes to only implement the parts of the interfaces they support. It also introduces a new trick where each pass in the group retains a pointer to the top-most pass that has been initialized. This allows passes to implement one API in terms of another API and benefit when some other pass above them in the stack has more precise results for the second API. The second step of this conversion is to create a pass that implements the TargetTransformInfo analysis using the target-independent abstractions in the code generator. This replaces the ScalarTargetTransformImpl and VectorTargetTransformImpl classes in lib/Target with a single pass in lib/CodeGen called BasicTargetTransformInfo. This class actually provides most of the TTI functionality, basing it upon the TargetLowering abstraction and other information in the target independent code generator. The third step of the conversion adds support to all TargetMachines to register custom analysis passes. This allows building those passes with access to TargetLowering or other target-specific classes, and it also allows each target to customize the set of analysis passes desired in the pass manager. The baseline LLVMTargetMachine implements this interface to add the BasicTTI pass to the pass manager, and all of the tools that want to support target-aware TTI passes call this routine on whatever target machine they end up with to add the appropriate passes. The fourth step of the conversion created target-specific TTI analysis passes for the X86 and ARM backends. These passes contain the custom logic that was previously in their extensions of the ScalarTargetTransformInfo and VectorTargetTransformInfo interfaces. I separated them into their own file, as now all of the interface bits are private and they just expose a function to create the pass itself. Then I extended these target machines to set up a custom set of analysis passes, first adding BasicTTI as a fallback, and then adding their customized TTI implementations. The fourth step required logic that was shared between the target independent layer and the specific targets to move to a different interface, as they no longer derive from each other. As a consequence, a helper functions were added to TargetLowering representing the common logic needed both in the target implementation and the codegen implementation of the TTI pass. While technically this is the only change that could have been committed separately, it would have been a nightmare to extract. The final step of the conversion was just to delete all the old boilerplate. This got rid of the ScalarTargetTransformInfo and VectorTargetTransformInfo classes, all of the support in all of the targets for producing instances of them, and all of the support in the tools for manually constructing a pass based around them. Now that TTI is a relatively normal analysis group, two things become straightforward. First, we can sink it into lib/Analysis which is a more natural layer for it to live. Second, clients of this interface can depend on it *always* being available which will simplify their code and behavior. These (and other) simplifications will follow in subsequent commits, this one is clearly big enough. Finally, I'm very aware that much of the comments and documentation needs to be updated. As soon as I had this working, and plausibly well commented, I wanted to get it committed and in front of the build bots. I'll be doing a few passes over documentation later if it sticks. Commits to update DragonEgg and Clang will be made presently. llvm-svn: 171681
2013-01-07 09:37:14 +08:00
void LLVMTargetMachine::addAnalysisPasses(PassManagerBase &PM) {
PM.add(createBasicTargetTransformInfoPass(getTargetLowering()));
}
/// addPassesToX helper drives creation and initialization of TargetPassConfig.
static MCContext *addPassesToGenerateCode(LLVMTargetMachine *TM,
PassManagerBase &PM,
bool DisableVerify,
AnalysisID StartAfter,
AnalysisID StopAfter) {
// Targets may override createPassConfig to provide a target-specific sublass.
TargetPassConfig *PassConfig = TM->createPassConfig(PM);
PassConfig->setStartStopPasses(StartAfter, StopAfter);
// Set PassConfig options provided by TargetMachine.
PassConfig->setDisableVerify(DisableVerify);
PM.add(PassConfig);
PassConfig->addIRPasses();
PassConfig->addCodeGenPrepare();
PassConfig->addPassesToHandleExceptions();
PassConfig->addISelPrepare();
// Install a MachineModuleInfo class, which is an immutable pass that holds
// all the per-module stuff we're generating, including MCContext.
MachineModuleInfo *MMI =
new MachineModuleInfo(*TM->getMCAsmInfo(), *TM->getRegisterInfo(),
&TM->getTargetLowering()->getObjFileLowering());
PM.add(MMI);
2012-02-18 01:35:10 +08:00
MCContext *Context = &MMI->getContext(); // Return the MCContext by-ref.
// Set up a MachineFunction for the rest of CodeGen to work on.
PM.add(new MachineFunctionAnalysis(*TM));
// Enable FastISel with -fast, but allow that to be overridden.
if (EnableFastISelOption == cl::BOU_TRUE ||
(TM->getOptLevel() == CodeGenOpt::None &&
EnableFastISelOption != cl::BOU_FALSE))
TM->setFastISel(true);
// Ask the target for an isel.
if (PassConfig->addInstSelector())
return NULL;
PassConfig->addMachinePasses();
PassConfig->setInitialized();
return Context;
}
bool LLVMTargetMachine::addPassesToEmitFile(PassManagerBase &PM,
formatted_raw_ostream &Out,
CodeGenFileType FileType,
bool DisableVerify,
AnalysisID StartAfter,
AnalysisID StopAfter) {
// Add common CodeGen passes.
MCContext *Context = addPassesToGenerateCode(this, PM, DisableVerify,
StartAfter, StopAfter);
if (!Context)
return true;
if (StopAfter) {
// FIXME: The intent is that this should eventually write out a YAML file,
// containing the LLVM IR, the machine-level IR (when stopping after a
// machine-level pass), and whatever other information is needed to
// deserialize the code and resume compilation. For now, just write the
// LLVM IR.
PM.add(createPrintModulePass(&Out));
return false;
}
if (hasMCSaveTempLabels())
Context->setAllowTemporaryLabels(false);
const MCAsmInfo &MAI = *getMCAsmInfo();
const MCRegisterInfo &MRI = *getRegisterInfo();
const MCSubtargetInfo &STI = getSubtarget<MCSubtargetInfo>();
OwningPtr<MCStreamer> AsmStreamer;
2006-09-04 12:16:09 +08:00
switch (FileType) {
case CGFT_AssemblyFile: {
MCInstPrinter *InstPrinter =
getTarget().createMCInstPrinter(MAI.getAssemblerDialect(), MAI,
*getInstrInfo(),
Context->getRegisterInfo(), STI);
// Create a code emitter if asked to show the encoding.
MCCodeEmitter *MCE = 0;
MCAsmBackend *MAB = 0;
if (ShowMCEncoding) {
const MCSubtargetInfo &STI = getSubtarget<MCSubtargetInfo>();
MCE = getTarget().createMCCodeEmitter(*getInstrInfo(), MRI, STI,
*Context);
MAB = getTarget().createMCAsmBackend(getTargetTriple(), TargetCPU);
}
MCStreamer *S = getTarget().createAsmStreamer(*Context, Out,
getVerboseAsm(),
hasMCUseLoc(),
hasMCUseCFI(),
hasMCUseDwarfDirectory(),
InstPrinter,
MCE, MAB,
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().createMCCodeEmitter(*getInstrInfo(), MRI,
STI, *Context);
2012-11-22 22:10:40 +08:00
MCAsmBackend *MAB = getTarget().createMCAsmBackend(getTargetTriple(),
TargetCPU);
if (MCE == 0 || MAB == 0)
return true;
AsmStreamer.reset(getTarget().createMCObjectStreamer(getTargetTriple(),
*Context, *MAB, Out,
MCE, hasMCRelaxAll(),
hasMCNoExecStack()));
AsmStreamer.get()->setAutoInitSections(true);
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
}
// 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);
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,
bool DisableVerify) {
// Add common CodeGen passes.
MCContext *Context = addPassesToGenerateCode(this, PM, DisableVerify, 0, 0);
if (!Context)
return true;
addCodeEmitter(PM, 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,
bool DisableVerify) {
// Add common CodeGen passes.
Ctx = addPassesToGenerateCode(this, PM, DisableVerify, 0, 0);
if (!Ctx)
return true;
if (hasMCSaveTempLabels())
Ctx->setAllowTemporaryLabels(false);
// Create the code emitter for the target if it exists. If not, .o file
// emission fails.
const MCRegisterInfo &MRI = *getRegisterInfo();
const MCSubtargetInfo &STI = getSubtarget<MCSubtargetInfo>();
MCCodeEmitter *MCE = getTarget().createMCCodeEmitter(*getInstrInfo(), MRI,
STI, *Ctx);
MCAsmBackend *MAB = getTarget().createMCAsmBackend(getTargetTriple(), TargetCPU);
if (MCE == 0 || MAB == 0)
return true;
OwningPtr<MCStreamer> AsmStreamer;
AsmStreamer.reset(getTarget().createMCObjectStreamer(getTargetTriple(), *Ctx,
*MAB, 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);
return false; // success!
}