rust/src/rustllvm/PassWrapper.cpp

614 lines
18 KiB
C++
Raw Normal View History

// Copyright 2013 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.
2013-08-22 22:58:42 -05:00
#include <stdio.h>
#include "rustllvm.h"
2013-08-22 22:58:42 -05:00
#include "llvm/Support/CBindingWrapping.h"
#include "llvm/Support/FileSystem.h"
2015-03-09 19:46:45 -05:00
#include "llvm/Support/Host.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/AutoUpgrade.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetSubtargetInfo.h"
2013-08-22 22:58:42 -05:00
#include "llvm/Transforms/IPO/PassManagerBuilder.h"
#if LLVM_VERSION_GE(4, 0)
#include "llvm/Transforms/IPO/AlwaysInliner.h"
#endif
2013-08-22 22:58:42 -05:00
#include "llvm-c/Transforms/PassManagerBuilder.h"
2013-08-22 22:58:42 -05:00
using namespace llvm;
using namespace llvm::legacy;
2013-08-22 22:58:42 -05:00
extern cl::opt<bool> EnableARMEHABI;
2013-08-22 22:58:42 -05:00
typedef struct LLVMOpaquePass *LLVMPassRef;
typedef struct LLVMOpaqueTargetMachine *LLVMTargetMachineRef;
DEFINE_STDCXX_CONVERSION_FUNCTIONS(Pass, LLVMPassRef)
DEFINE_STDCXX_CONVERSION_FUNCTIONS(TargetMachine, LLVMTargetMachineRef)
DEFINE_STDCXX_CONVERSION_FUNCTIONS(PassManagerBuilder, LLVMPassManagerBuilderRef)
2013-08-22 22:58:42 -05:00
extern "C" void
LLVMInitializePasses() {
PassRegistry &Registry = *PassRegistry::getPassRegistry();
initializeCore(Registry);
initializeCodeGen(Registry);
initializeScalarOpts(Registry);
initializeVectorization(Registry);
initializeIPO(Registry);
initializeAnalysis(Registry);
#if LLVM_VERSION_EQ(3, 7)
initializeIPA(Registry);
2015-10-24 04:42:23 -05:00
#endif
initializeTransformUtils(Registry);
initializeInstCombine(Registry);
initializeInstrumentation(Registry);
initializeTarget(Registry);
}
enum class LLVMRustPassKind {
Other,
Function,
Module,
};
static LLVMRustPassKind
to_rust(PassKind kind)
{
switch (kind) {
case PT_Function:
return LLVMRustPassKind::Function;
case PT_Module:
return LLVMRustPassKind::Module;
default:
return LLVMRustPassKind::Other;
}
}
extern "C" LLVMPassRef
LLVMRustFindAndCreatePass(const char *PassName) {
StringRef SR(PassName);
2013-08-22 22:58:42 -05:00
PassRegistry *PR = PassRegistry::getPassRegistry();
2013-08-22 22:58:42 -05:00
const PassInfo *PI = PR->getPassInfo(SR);
if (PI) {
return wrap(PI->createPass());
}
return NULL;
}
extern "C" LLVMRustPassKind
LLVMRustPassKind(LLVMPassRef rust_pass) {
assert(rust_pass);
Pass *pass = unwrap(rust_pass);
return to_rust(pass->getPassKind());
}
extern "C" void
LLVMRustAddPass(LLVMPassManagerRef PM, LLVMPassRef rust_pass) {
assert(rust_pass);
Pass *pass = unwrap(rust_pass);
PassManagerBase *pm = unwrap(PM);
pm->add(pass);
2013-08-22 22:58:42 -05:00
}
#ifdef LLVM_COMPONENT_X86
#define SUBTARGET_X86 SUBTARGET(X86)
#else
#define SUBTARGET_X86
#endif
#ifdef LLVM_COMPONENT_ARM
#define SUBTARGET_ARM SUBTARGET(ARM)
#else
#define SUBTARGET_ARM
#endif
#ifdef LLVM_COMPONENT_AARCH64
#define SUBTARGET_AARCH64 SUBTARGET(AArch64)
#else
#define SUBTARGET_AARCH64
#endif
#ifdef LLVM_COMPONENT_MIPS
#define SUBTARGET_MIPS SUBTARGET(Mips)
#else
#define SUBTARGET_MIPS
#endif
#ifdef LLVM_COMPONENT_POWERPC
#define SUBTARGET_PPC SUBTARGET(PPC)
#else
#define SUBTARGET_PPC
#endif
#ifdef LLVM_COMPONENT_SYSTEMZ
#define SUBTARGET_SYSTEMZ SUBTARGET(SystemZ)
#else
#define SUBTARGET_SYSTEMZ
#endif
#ifdef LLVM_COMPONENT_MSP430
#define SUBTARGET_MSP430 SUBTARGET(MSP430)
#else
#define SUBTARGET_MSP430
#endif
#define GEN_SUBTARGETS \
SUBTARGET_X86 \
SUBTARGET_ARM \
SUBTARGET_AARCH64 \
SUBTARGET_MIPS \
SUBTARGET_PPC \
SUBTARGET_SYSTEMZ \
SUBTARGET_MSP430
#define SUBTARGET(x) namespace llvm { \
extern const SubtargetFeatureKV x##FeatureKV[]; \
extern const SubtargetFeatureKV x##SubTypeKV[]; \
}
GEN_SUBTARGETS
#undef SUBTARGET
extern "C" bool
LLVMRustHasFeature(LLVMTargetMachineRef TM,
const char *feature) {
TargetMachine *Target = unwrap(TM);
const MCSubtargetInfo *MCInfo = Target->getMCSubtargetInfo();
const FeatureBitset &Bits = MCInfo->getFeatureBits();
const llvm::SubtargetFeatureKV *FeatureEntry;
#define SUBTARGET(x) \
if (MCInfo->isCPUStringValid(x##SubTypeKV[0].Key)) { \
FeatureEntry = x##FeatureKV; \
} else
GEN_SUBTARGETS {
return false;
}
#undef SUBTARGET
while (strcmp(feature, FeatureEntry->Key) != 0)
FeatureEntry++;
return (Bits & FeatureEntry->Value) == FeatureEntry->Value;
}
enum class LLVMRustCodeModel {
Other,
Default,
JITDefault,
Small,
Kernel,
Medium,
Large,
};
static CodeModel::Model
from_rust(LLVMRustCodeModel model)
{
switch (model) {
case LLVMRustCodeModel::Default:
return CodeModel::Default;
case LLVMRustCodeModel::JITDefault:
return CodeModel::JITDefault;
case LLVMRustCodeModel::Small:
return CodeModel::Small;
case LLVMRustCodeModel::Kernel:
return CodeModel::Kernel;
case LLVMRustCodeModel::Medium:
return CodeModel::Medium;
case LLVMRustCodeModel::Large:
return CodeModel::Large;
default:
2016-08-02 16:25:19 -05:00
llvm_unreachable("Bad CodeModel.");
}
}
enum class LLVMRustCodeGenOptLevel {
Other,
None,
Less,
Default,
Aggressive,
};
static CodeGenOpt::Level
from_rust(LLVMRustCodeGenOptLevel level)
{
switch (level) {
case LLVMRustCodeGenOptLevel::None:
return CodeGenOpt::None;
case LLVMRustCodeGenOptLevel::Less:
return CodeGenOpt::Less;
case LLVMRustCodeGenOptLevel::Default:
return CodeGenOpt::Default;
case LLVMRustCodeGenOptLevel::Aggressive:
return CodeGenOpt::Aggressive;
default:
2016-08-02 16:25:19 -05:00
llvm_unreachable("Bad CodeGenOptLevel.");
}
}
#if LLVM_RUSTLLVM
/// getLongestEntryLength - Return the length of the longest entry in the table.
///
static size_t getLongestEntryLength(ArrayRef<SubtargetFeatureKV> Table) {
size_t MaxLen = 0;
for (auto &I : Table)
MaxLen = std::max(MaxLen, std::strlen(I.Key));
return MaxLen;
}
extern "C" void
LLVMRustPrintTargetCPUs(LLVMTargetMachineRef TM) {
const TargetMachine *Target = unwrap(TM);
const MCSubtargetInfo *MCInfo = Target->getMCSubtargetInfo();
const ArrayRef<SubtargetFeatureKV> CPUTable = MCInfo->getCPUTable();
unsigned MaxCPULen = getLongestEntryLength(CPUTable);
printf("Available CPUs for this target:\n");
for (auto &CPU : CPUTable)
printf(" %-*s - %s.\n", MaxCPULen, CPU.Key, CPU.Desc);
printf("\n");
}
extern "C" void
LLVMRustPrintTargetFeatures(LLVMTargetMachineRef TM) {
const TargetMachine *Target = unwrap(TM);
const MCSubtargetInfo *MCInfo = Target->getMCSubtargetInfo();
const ArrayRef<SubtargetFeatureKV> FeatTable = MCInfo->getFeatureTable();
unsigned MaxFeatLen = getLongestEntryLength(FeatTable);
printf("Available features for this target:\n");
for (auto &Feature : FeatTable)
printf(" %-*s - %s.\n", MaxFeatLen, Feature.Key, Feature.Desc);
printf("\n");
printf("Use +feature to enable a feature, or -feature to disable it.\n"
"For example, rustc -C -target-cpu=mycpu -C target-feature=+feature1,-feature2\n\n");
}
#else
extern "C" void
LLVMRustPrintTargetCPUs(LLVMTargetMachineRef) {
printf("Target CPU help is not supported by this LLVM version.\n\n");
}
extern "C" void
LLVMRustPrintTargetFeatures(LLVMTargetMachineRef) {
printf("Target features help is not supported by this LLVM version.\n\n");
}
#endif
2013-08-22 22:58:42 -05:00
extern "C" LLVMTargetMachineRef
LLVMRustCreateTargetMachine(const char *triple,
const char *cpu,
const char *feature,
LLVMRustCodeModel rust_CM,
LLVMRelocMode Reloc,
LLVMRustCodeGenOptLevel rust_OptLevel,
bool UseSoftFloat,
bool PositionIndependentExecutable,
rustc: Enable -f{function,data}-sections The compiler has previously been producing binaries on the order of 1.8MB for hello world programs "fn main() {}". This is largely a result of the compilation model used by compiling entire libraries into a single object file and because static linking is favored by default. When linking, linkers will pull in the entire contents of an object file if any symbol from the object file is used. This means that if any symbol from a rust library is used, the entire library is pulled in unconditionally, regardless of whether the library is used or not. Traditional C/C++ projects do not normally encounter these large executable problems because their archives (rust's rlibs) are composed of many objects. Because of this, linkers can eliminate entire objects from being in the final executable. With rustc, however, the linker does not have the opportunity to leave out entire object files. In order to get similar benefits from dead code stripping at link time, this commit enables the -ffunction-sections and -fdata-sections flags in LLVM, as well as passing --gc-sections to the linker *by default*. This means that each function and each global will be placed into its own section, allowing the linker to GC all unused functions and data symbols. By enabling these flags, rust is able to generate much smaller binaries default. On linux, a hello world binary went from 1.8MB to 597K (a 67% reduction in size). The output size of dynamic libraries remained constant, but the output size of rlibs increased, as seen below: libarena - 2.27% bigger ( 292872 => 299508) libcollections - 0.64% bigger ( 6765884 => 6809076) libflate - 0.83% bigger ( 186516 => 188060) libfourcc - 14.71% bigger ( 307290 => 352498) libgetopts - 4.42% bigger ( 761468 => 795102) libglob - 2.73% bigger ( 899932 => 924542) libgreen - 9.63% bigger ( 1281718 => 1405124) libhexfloat - 13.88% bigger ( 333738 => 380060) liblibc - 10.79% bigger ( 551280 => 610736) liblog - 10.93% bigger ( 218208 => 242060) libnative - 8.26% bigger ( 1362096 => 1474658) libnum - 2.34% bigger ( 2583400 => 2643916) librand - 1.72% bigger ( 1608684 => 1636394) libregex - 6.50% bigger ( 1747768 => 1861398) librustc - 4.21% bigger (151820192 => 158218924) librustdoc - 8.96% bigger ( 13142604 => 14320544) librustuv - 4.13% bigger ( 4366896 => 4547304) libsemver - 2.66% bigger ( 396166 => 406686) libserialize - 1.91% bigger ( 6878396 => 7009822) libstd - 3.59% bigger ( 39485286 => 40902218) libsync - 3.95% bigger ( 1386390 => 1441204) libsyntax - 4.96% bigger ( 35757202 => 37530798) libterm - 13.99% bigger ( 924580 => 1053902) libtest - 6.04% bigger ( 2455720 => 2604092) libtime - 2.84% bigger ( 1075708 => 1106242) liburl - 6.53% bigger ( 590458 => 629004) libuuid - 4.63% bigger ( 326350 => 341466) libworkcache - 8.45% bigger ( 1230702 => 1334750) This increase in size is a result of encoding many more section names into each object file (rlib). These increases are moderate enough that this change seems worthwhile to me, due to the drastic improvements seen in the final artifacts. The overall increase of the stage2 target folder (not the size of an install) went from 337MB to 348MB (3% increase). Additionally, linking is generally slower when executed with all these new sections plus the --gc-sections flag. The stage0 compiler takes 1.4s to link the `rustc` binary, where the stage1 compiler takes 1.9s to link the binary. Three megabytes are shaved off the binary. I found this increase in link time to be acceptable relative to the benefits of code size gained. This commit only enables --gc-sections for *executables*, not dynamic libraries. LLVM does all the heavy lifting when producing an object file for a dynamic library, so there is little else for the linker to do (remember that we only have one object file). I conducted similar experiments by putting a *module's* functions and data symbols into its own section (granularity moved to a module level instead of a function/static level). The size benefits of a hello world were seen to be on the order of 400K rather than 1.2MB. It seemed that enough benefit was gained using ffunction-sections that this route was less desirable, despite the lesser increases in binary rlib size.
2014-04-28 19:17:18 -05:00
bool FunctionSections,
bool DataSections) {
#if LLVM_VERSION_LE(3, 8)
Reloc::Model RM;
#else
Optional<Reloc::Model> RM;
#endif
auto CM = from_rust(rust_CM);
auto OptLevel = from_rust(rust_OptLevel);
switch (Reloc){
case LLVMRelocStatic:
RM = Reloc::Static;
break;
case LLVMRelocPIC:
RM = Reloc::PIC_;
break;
case LLVMRelocDynamicNoPic:
RM = Reloc::DynamicNoPIC;
break;
default:
#if LLVM_VERSION_LE(3, 8)
RM = Reloc::Default;
#endif
break;
}
2013-08-22 22:58:42 -05:00
std::string Error;
Triple Trip(Triple::normalize(triple));
const llvm::Target *TheTarget = TargetRegistry::lookupTarget(Trip.getTriple(),
Error);
if (TheTarget == NULL) {
LLVMRustSetLastError(Error.c_str());
2013-08-22 22:58:42 -05:00
return NULL;
}
2015-03-09 19:46:45 -05:00
StringRef real_cpu = cpu;
if (real_cpu == "native") {
real_cpu = sys::getHostCPUName();
}
2013-08-22 22:58:42 -05:00
TargetOptions Options;
#if LLVM_VERSION_LE(3, 8)
Options.PositionIndependentExecutable = PositionIndependentExecutable;
#endif
2013-12-27 14:31:49 -06:00
Options.FloatABIType = FloatABI::Default;
if (UseSoftFloat) {
Options.FloatABIType = FloatABI::Soft;
}
Options.DataSections = DataSections;
Options.FunctionSections = FunctionSections;
2013-08-22 22:58:42 -05:00
TargetMachine *TM = TheTarget->createTargetMachine(Trip.getTriple(),
2015-03-09 19:46:45 -05:00
real_cpu,
2013-08-22 22:58:42 -05:00
feature,
Options,
RM,
CM,
OptLevel);
return wrap(TM);
}
extern "C" void
LLVMRustDisposeTargetMachine(LLVMTargetMachineRef TM) {
delete unwrap(TM);
}
// Unfortunately, LLVM doesn't expose a C API to add the corresponding analysis
// passes for a target to a pass manager. We export that functionality through
// this function.
extern "C" void
LLVMRustAddAnalysisPasses(LLVMTargetMachineRef TM,
LLVMPassManagerRef PMR,
LLVMModuleRef M) {
PassManagerBase *PM = unwrap(PMR);
PM->add(createTargetTransformInfoWrapperPass(
unwrap(TM)->getTargetIRAnalysis()));
}
extern "C" void
LLVMRustConfigurePassManagerBuilder(LLVMPassManagerBuilderRef PMB,
LLVMRustCodeGenOptLevel OptLevel,
bool MergeFunctions,
bool SLPVectorize,
bool LoopVectorize) {
// Ignore mergefunc for now as enabling it causes crashes.
//unwrap(PMB)->MergeFunctions = MergeFunctions;
unwrap(PMB)->SLPVectorize = SLPVectorize;
unwrap(PMB)->OptLevel = from_rust(OptLevel);
unwrap(PMB)->LoopVectorize = LoopVectorize;
2013-08-22 22:58:42 -05:00
}
// Unfortunately, the LLVM C API doesn't provide a way to set the `LibraryInfo`
// field of a PassManagerBuilder, we expose our own method of doing so.
extern "C" void
LLVMRustAddBuilderLibraryInfo(LLVMPassManagerBuilderRef PMB,
LLVMModuleRef M,
bool DisableSimplifyLibCalls) {
2013-08-22 22:58:42 -05:00
Triple TargetTriple(unwrap(M)->getTargetTriple());
TargetLibraryInfoImpl *TLI = new TargetLibraryInfoImpl(TargetTriple);
if (DisableSimplifyLibCalls)
TLI->disableAllFunctions();
unwrap(PMB)->LibraryInfo = TLI;
2013-08-22 22:58:42 -05:00
}
// Unfortunately, the LLVM C API doesn't provide a way to create the
// TargetLibraryInfo pass, so we use this method to do so.
extern "C" void
LLVMRustAddLibraryInfo(LLVMPassManagerRef PMB,
LLVMModuleRef M,
bool DisableSimplifyLibCalls) {
2013-08-22 22:58:42 -05:00
Triple TargetTriple(unwrap(M)->getTargetTriple());
TargetLibraryInfoImpl TLII(TargetTriple);
if (DisableSimplifyLibCalls)
TLII.disableAllFunctions();
unwrap(PMB)->add(new TargetLibraryInfoWrapperPass(TLII));
2013-08-22 22:58:42 -05:00
}
// Unfortunately, the LLVM C API doesn't provide an easy way of iterating over
// all the functions in a module, so we do that manually here. You'll find
// similar code in clang's BackendUtil.cpp file.
extern "C" void
LLVMRustRunFunctionPassManager(LLVMPassManagerRef PM, LLVMModuleRef M) {
llvm::legacy::FunctionPassManager *P = unwrap<llvm::legacy::FunctionPassManager>(PM);
2013-08-22 22:58:42 -05:00
P->doInitialization();
// Upgrade all calls to old intrinsics first.
for (Module::iterator I = unwrap(M)->begin(),
E = unwrap(M)->end(); I != E;)
UpgradeCallsToIntrinsic(&*I++); // must be post-increment, as we remove
2013-08-22 22:58:42 -05:00
for (Module::iterator I = unwrap(M)->begin(),
E = unwrap(M)->end(); I != E; ++I)
if (!I->isDeclaration())
P->run(*I);
2013-08-22 22:58:42 -05:00
P->doFinalization();
}
extern "C" void
LLVMRustSetLLVMOptions(int Argc, char **Argv) {
2013-08-22 22:58:42 -05:00
// Initializing the command-line options more than once is not allowed. So,
// check if they've already been initialized. (This could happen if we're
// being called from rustpkg, for example). If the arguments change, then
// that's just kinda unfortunate.
static bool initialized = false;
if (initialized) return;
initialized = true;
cl::ParseCommandLineOptions(Argc, Argv);
2013-08-22 22:58:42 -05:00
}
enum class LLVMRustFileType {
Other,
AssemblyFile,
ObjectFile,
};
static TargetMachine::CodeGenFileType
from_rust(LLVMRustFileType type)
{
switch (type) {
case LLVMRustFileType::AssemblyFile:
return TargetMachine::CGFT_AssemblyFile;
case LLVMRustFileType::ObjectFile:
return TargetMachine::CGFT_ObjectFile;
default:
2016-08-02 16:25:19 -05:00
llvm_unreachable("Bad FileType.");
}
}
extern "C" LLVMRustResult
2013-08-22 22:58:42 -05:00
LLVMRustWriteOutputFile(LLVMTargetMachineRef Target,
LLVMPassManagerRef PMR,
LLVMModuleRef M,
const char *path,
LLVMRustFileType rust_FileType) {
llvm::legacy::PassManager *PM = unwrap<llvm::legacy::PassManager>(PMR);
auto FileType = from_rust(rust_FileType);
2013-08-22 22:58:42 -05:00
std::string ErrorInfo;
2014-09-30 16:20:22 -05:00
std::error_code EC;
raw_fd_ostream OS(path, EC, sys::fs::F_None);
if (EC)
ErrorInfo = EC.message();
2013-08-22 22:58:42 -05:00
if (ErrorInfo != "") {
LLVMRustSetLastError(ErrorInfo.c_str());
return LLVMRustResult::Failure;
2013-08-22 22:58:42 -05:00
}
unwrap(Target)->addPassesToEmitFile(*PM, OS, FileType, false);
2013-08-22 22:58:42 -05:00
PM->run(*unwrap(M));
// Apparently `addPassesToEmitFile` adds a pointer to our on-the-stack output
// stream (OS), so the only real safe place to delete this is here? Don't we
// wish this was written in Rust?
delete PM;
return LLVMRustResult::Success;
2013-08-22 22:58:42 -05:00
}
extern "C" void
LLVMRustPrintModule(LLVMPassManagerRef PMR,
LLVMModuleRef M,
const char* path) {
llvm::legacy::PassManager *PM = unwrap<llvm::legacy::PassManager>(PMR);
2013-08-22 22:58:42 -05:00
std::string ErrorInfo;
2014-09-30 16:20:22 -05:00
std::error_code EC;
raw_fd_ostream OS(path, EC, sys::fs::F_None);
if (EC)
ErrorInfo = EC.message();
2013-08-22 22:58:42 -05:00
formatted_raw_ostream FOS(OS);
PM->add(createPrintModulePass(FOS));
2013-08-22 22:58:42 -05:00
PM->run(*unwrap(M));
}
extern "C" void
LLVMRustPrintPasses() {
LLVMInitializePasses();
struct MyListener : PassRegistrationListener {
void passEnumerate(const PassInfo *info) {
if (info->getPassArgument() && *info->getPassArgument()) {
printf("%15s - %s\n", info->getPassArgument(),
info->getPassName());
}
}
} listener;
PassRegistry *PR = PassRegistry::getPassRegistry();
PR->enumerateWith(&listener);
}
2013-08-22 22:58:42 -05:00
extern "C" void
LLVMRustAddAlwaysInlinePass(LLVMPassManagerBuilderRef PMB, bool AddLifetimes) {
#if LLVM_VERSION_GE(4, 0)
unwrap(PMB)->Inliner = llvm::createAlwaysInlinerLegacyPass(AddLifetimes);
#else
2013-08-22 22:58:42 -05:00
unwrap(PMB)->Inliner = createAlwaysInlinerPass(AddLifetimes);
#endif
}
Implement LTO This commit implements LTO for rust leveraging LLVM's passes. What this means is: * When compiling an rlib, in addition to insdering foo.o into the archive, also insert foo.bc (the LLVM bytecode) of the optimized module. * When the compiler detects the -Z lto option, it will attempt to perform LTO on a staticlib or binary output. The compiler will emit an error if a dylib or rlib output is being generated. * The actual act of performing LTO is as follows: 1. Force all upstream libraries to have an rlib version available. 2. Load the bytecode of each upstream library from the rlib. 3. Link all this bytecode into the current LLVM module (just using llvm apis) 4. Run an internalization pass which internalizes all symbols except those found reachable for the local crate of compilation. 5. Run the LLVM LTO pass manager over this entire module 6a. If assembling an archive, then add all upstream rlibs into the output archive. This ignores all of the object/bitcode/metadata files rust generated and placed inside the rlibs. 6b. If linking a binary, create copies of all upstream rlibs, remove the rust-generated object-file, and then link everything as usual. As I have explained in #10741, this process is excruciatingly slow, so this is *not* turned on by default, and it is also why I have decided to hide it behind a -Z flag for now. The good news is that the binary sizes are about as small as they can be as a result of LTO, so it's definitely working. Closes #10741 Closes #10740
2013-12-03 01:19:29 -06:00
extern "C" void
LLVMRustRunRestrictionPass(LLVMModuleRef M, char **symbols, size_t len) {
llvm::legacy::PassManager passes;
#if LLVM_VERSION_LE(3, 8)
Implement LTO This commit implements LTO for rust leveraging LLVM's passes. What this means is: * When compiling an rlib, in addition to insdering foo.o into the archive, also insert foo.bc (the LLVM bytecode) of the optimized module. * When the compiler detects the -Z lto option, it will attempt to perform LTO on a staticlib or binary output. The compiler will emit an error if a dylib or rlib output is being generated. * The actual act of performing LTO is as follows: 1. Force all upstream libraries to have an rlib version available. 2. Load the bytecode of each upstream library from the rlib. 3. Link all this bytecode into the current LLVM module (just using llvm apis) 4. Run an internalization pass which internalizes all symbols except those found reachable for the local crate of compilation. 5. Run the LLVM LTO pass manager over this entire module 6a. If assembling an archive, then add all upstream rlibs into the output archive. This ignores all of the object/bitcode/metadata files rust generated and placed inside the rlibs. 6b. If linking a binary, create copies of all upstream rlibs, remove the rust-generated object-file, and then link everything as usual. As I have explained in #10741, this process is excruciatingly slow, so this is *not* turned on by default, and it is also why I have decided to hide it behind a -Z flag for now. The good news is that the binary sizes are about as small as they can be as a result of LTO, so it's definitely working. Closes #10741 Closes #10740
2013-12-03 01:19:29 -06:00
ArrayRef<const char*> ref(symbols, len);
passes.add(llvm::createInternalizePass(ref));
#else
auto PreserveFunctions = [=](const GlobalValue &GV) {
for (size_t i=0; i<len; i++) {
if (GV.getName() == symbols[i]) {
return true;
}
}
return false;
};
passes.add(llvm::createInternalizePass(PreserveFunctions));
#endif
Implement LTO This commit implements LTO for rust leveraging LLVM's passes. What this means is: * When compiling an rlib, in addition to insdering foo.o into the archive, also insert foo.bc (the LLVM bytecode) of the optimized module. * When the compiler detects the -Z lto option, it will attempt to perform LTO on a staticlib or binary output. The compiler will emit an error if a dylib or rlib output is being generated. * The actual act of performing LTO is as follows: 1. Force all upstream libraries to have an rlib version available. 2. Load the bytecode of each upstream library from the rlib. 3. Link all this bytecode into the current LLVM module (just using llvm apis) 4. Run an internalization pass which internalizes all symbols except those found reachable for the local crate of compilation. 5. Run the LLVM LTO pass manager over this entire module 6a. If assembling an archive, then add all upstream rlibs into the output archive. This ignores all of the object/bitcode/metadata files rust generated and placed inside the rlibs. 6b. If linking a binary, create copies of all upstream rlibs, remove the rust-generated object-file, and then link everything as usual. As I have explained in #10741, this process is excruciatingly slow, so this is *not* turned on by default, and it is also why I have decided to hide it behind a -Z flag for now. The good news is that the binary sizes are about as small as they can be as a result of LTO, so it's definitely working. Closes #10741 Closes #10740
2013-12-03 01:19:29 -06:00
passes.run(*unwrap(M));
}
extern "C" void
LLVMRustMarkAllFunctionsNounwind(LLVMModuleRef M) {
for (Module::iterator GV = unwrap(M)->begin(),
E = unwrap(M)->end(); GV != E; ++GV) {
GV->setDoesNotThrow();
Function *F = dyn_cast<Function>(GV);
if (F == NULL)
continue;
for (Function::iterator B = F->begin(), BE = F->end(); B != BE; ++B) {
for (BasicBlock::iterator I = B->begin(), IE = B->end();
I != IE; ++I) {
if (isa<InvokeInst>(I)) {
InvokeInst *CI = cast<InvokeInst>(I);
CI->setDoesNotThrow();
}
}
}
}
}
extern "C" void
LLVMRustSetDataLayoutFromTargetMachine(LLVMModuleRef Module,
LLVMTargetMachineRef TMR) {
TargetMachine *Target = unwrap(TMR);
unwrap(Module)->setDataLayout(Target->createDataLayout());
}
extern "C" LLVMTargetDataRef
LLVMRustGetModuleDataLayout(LLVMModuleRef M) {
return wrap(&unwrap(M)->getDataLayout());
}
extern "C" void
LLVMRustSetModulePIELevel(LLVMModuleRef M) {
#if LLVM_VERSION_GE(3, 9)
unwrap(M)->setPIELevel(PIELevel::Level::Large);
#endif
}