Added more llvm dependencies.

This commit is contained in:
Pedro Pinto committed 2017-12-05 09:19:15 -05:00
1 parent bdc83bb95d
commit c4958b25c4
1063 files changed
+277561 -1

No files matched your search

+185
View File
@@ -0,0 +1,185 @@
//===- BitCodes.h - Enum values for the bitcode format ----------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This header Bitcode enum values.
//
// The enum values defined in this file should be considered permanent. If
// new features are added, they should have values added at the end of the
// respective lists.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_BITCODE_BITCODES_H
#define LLVM_BITCODE_BITCODES_H
#include "llvm/ADT/SmallVector.h"
#include "llvm/Support/DataTypes.h"
#include "llvm/Support/ErrorHandling.h"
#include <cassert>
namespace llvm {
/// Offsets of the 32-bit fields of bitcode wrapper header.
static const unsigned BWH_MagicField = 0 * 4;
static const unsigned BWH_VersionField = 1 * 4;
static const unsigned BWH_OffsetField = 2 * 4;
static const unsigned BWH_SizeField = 3 * 4;
static const unsigned BWH_CPUTypeField = 4 * 4;
static const unsigned BWH_HeaderSize = 5 * 4;
namespace bitc {
enum StandardWidths {
BlockIDWidth = 8, // We use VBR-8 for block IDs.
CodeLenWidth = 4, // Codelen are VBR-4.
BlockSizeWidth = 32 // BlockSize up to 2^32 32-bit words = 16GB per block.
};
// The standard abbrev namespace always has a way to exit a block, enter a
// nested block, define abbrevs, and define an unabbreviated record.
enum FixedAbbrevIDs {
END_BLOCK = 0, // Must be zero to guarantee termination for broken bitcode.
ENTER_SUBBLOCK = 1,
/// DEFINE_ABBREV - Defines an abbrev for the current block. It consists
/// of a vbr5 for # operand infos. Each operand info is emitted with a
/// single bit to indicate if it is a literal encoding. If so, the value is
/// emitted with a vbr8. If not, the encoding is emitted as 3 bits followed
/// by the info value as a vbr5 if needed.
DEFINE_ABBREV = 2,
// UNABBREV_RECORDs are emitted with a vbr6 for the record code, followed by
// a vbr6 for the # operands, followed by vbr6's for each operand.
UNABBREV_RECORD = 3,
// This is not a code, this is a marker for the first abbrev assignment.
FIRST_APPLICATION_ABBREV = 4
};
/// StandardBlockIDs - All bitcode files can optionally include a BLOCKINFO
/// block, which contains metadata about other blocks in the file.
enum StandardBlockIDs {
/// BLOCKINFO_BLOCK is used to define metadata about blocks, for example,
/// standard abbrevs that should be available to all blocks of a specified
/// ID.
BLOCKINFO_BLOCK_ID = 0,
// Block IDs 1-7 are reserved for future expansion.
FIRST_APPLICATION_BLOCKID = 8
};
/// BlockInfoCodes - The blockinfo block contains metadata about user-defined
/// blocks.
enum BlockInfoCodes {
// DEFINE_ABBREV has magic semantics here, applying to the current SETBID'd
// block, instead of the BlockInfo block.
BLOCKINFO_CODE_SETBID = 1, // SETBID: [blockid#]
BLOCKINFO_CODE_BLOCKNAME = 2, // BLOCKNAME: [name]
BLOCKINFO_CODE_SETRECORDNAME = 3 // BLOCKINFO_CODE_SETRECORDNAME:
// [id, name]
};
} // End bitc namespace
/// BitCodeAbbrevOp - This describes one or more operands in an abbreviation.
/// This is actually a union of two different things:
/// 1. It could be a literal integer value ("the operand is always 17").
/// 2. It could be an encoding specification ("this operand encoded like so").
///
class BitCodeAbbrevOp {
uint64_t Val; // A literal value or data for an encoding.
bool IsLiteral : 1; // Indicate whether this is a literal value or not.
unsigned Enc : 3; // The encoding to use.
public:
enum Encoding {
Fixed = 1, // A fixed width field, Val specifies number of bits.
VBR = 2, // A VBR field where Val specifies the width of each chunk.
Array = 3, // A sequence of fields, next field species elt encoding.
Char6 = 4, // A 6-bit fixed field which maps to [a-zA-Z0-9._].
Blob = 5 // 32-bit aligned array of 8-bit characters.
};
explicit BitCodeAbbrevOp(uint64_t V) : Val(V), IsLiteral(true) {}
explicit BitCodeAbbrevOp(Encoding E, uint64_t Data = 0)
: Val(Data), IsLiteral(false), Enc(E) {}
bool isLiteral() const { return IsLiteral; }
bool isEncoding() const { return !IsLiteral; }
// Accessors for literals.
uint64_t getLiteralValue() const { assert(isLiteral()); return Val; }
// Accessors for encoding info.
Encoding getEncoding() const { assert(isEncoding()); return (Encoding)Enc; }
uint64_t getEncodingData() const {
assert(isEncoding() && hasEncodingData());
return Val;
}
bool hasEncodingData() const { return hasEncodingData(getEncoding()); }
static bool hasEncodingData(Encoding E) {
switch (E) {
case Fixed:
case VBR:
return true;
case Array:
case Char6:
case Blob:
return false;
}
report_fatal_error("Invalid encoding");
}
/// isChar6 - Return true if this character is legal in the Char6 encoding.
static bool isChar6(char C) {
if (C >= 'a' && C <= 'z') return true;
if (C >= 'A' && C <= 'Z') return true;
if (C >= '0' && C <= '9') return true;
if (C == '.' || C == '_') return true;
return false;
}
static unsigned EncodeChar6(char C) {
if (C >= 'a' && C <= 'z') return C-'a';
if (C >= 'A' && C <= 'Z') return C-'A'+26;
if (C >= '0' && C <= '9') return C-'0'+26+26;
if (C == '.') return 62;
if (C == '_') return 63;
llvm_unreachable("Not a value Char6 character!");
}
static char DecodeChar6(unsigned V) {
assert((V & ~63) == 0 && "Not a Char6 encoded character!");
return "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789._"
[V];
}
};
template <> struct isPodLike<BitCodeAbbrevOp> { static const bool value=true; };
/// BitCodeAbbrev - This class represents an abbreviation record. An
/// abbreviation allows a complex record that has redundancy to be stored in a
/// specialized format instead of the fully-general, fully-vbr, format.
class BitCodeAbbrev {
SmallVector<BitCodeAbbrevOp, 32> OperandList;
public:
unsigned getNumOperandInfos() const {
return static_cast<unsigned>(OperandList.size());
}
const BitCodeAbbrevOp &getOperandInfo(unsigned N) const {
return OperandList[N];
}
void Add(const BitCodeAbbrevOp &OpInfo) {
OperandList.push_back(OpInfo);
}
};
} // End llvm namespace
#endif
+272
View File
@@ -0,0 +1,272 @@
//===- llvm/Bitcode/BitcodeReader.h - Bitcode reader ------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This header defines interfaces to read LLVM bitcode files/streams.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_BITCODE_BITCODEREADER_H
#define LLVM_BITCODE_BITCODEREADER_H
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Bitcode/BitCodes.h"
#include "llvm/IR/ModuleSummaryIndex.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/ErrorOr.h"
#include "llvm/Support/MemoryBuffer.h"
#include <cstdint>
#include <memory>
#include <string>
#include <system_error>
#include <vector>
namespace llvm {
class LLVMContext;
class Module;
// These functions are for converting Expected/Error values to
// ErrorOr/std::error_code for compatibility with legacy clients. FIXME:
// Remove these functions once no longer needed by the C and libLTO APIs.
std::error_code errorToErrorCodeAndEmitErrors(LLVMContext &Ctx, Error Err);
template <typename T>
ErrorOr<T> expectedToErrorOrAndEmitErrors(LLVMContext &Ctx, Expected<T> Val) {
if (!Val)
return errorToErrorCodeAndEmitErrors(Ctx, Val.takeError());
return std::move(*Val);
}
struct BitcodeFileContents;
/// Basic information extracted from a bitcode module to be used for LTO.
struct BitcodeLTOInfo {
bool IsThinLTO;
bool HasSummary;
};
/// Represents a module in a bitcode file.
class BitcodeModule {
// This covers the identification (if present) and module blocks.
ArrayRef<uint8_t> Buffer;
StringRef ModuleIdentifier;
// The string table used to interpret this module.
StringRef Strtab;
// The bitstream location of the IDENTIFICATION_BLOCK.
uint64_t IdentificationBit;
// The bitstream location of this module's MODULE_BLOCK.
uint64_t ModuleBit;
BitcodeModule(ArrayRef<uint8_t> Buffer, StringRef ModuleIdentifier,
uint64_t IdentificationBit, uint64_t ModuleBit)
: Buffer(Buffer), ModuleIdentifier(ModuleIdentifier),
IdentificationBit(IdentificationBit), ModuleBit(ModuleBit) {}
// Calls the ctor.
friend Expected<BitcodeFileContents>
getBitcodeFileContents(MemoryBufferRef Buffer);
Expected<std::unique_ptr<Module>> getModuleImpl(LLVMContext &Context,
bool MaterializeAll,
bool ShouldLazyLoadMetadata,
bool IsImporting);
public:
StringRef getBuffer() const {
return StringRef((const char *)Buffer.begin(), Buffer.size());
}
StringRef getStrtab() const { return Strtab; }
StringRef getModuleIdentifier() const { return ModuleIdentifier; }
/// Read the bitcode module and prepare for lazy deserialization of function
/// bodies. If ShouldLazyLoadMetadata is true, lazily load metadata as well.
/// If IsImporting is true, this module is being parsed for ThinLTO
/// importing into another module.
Expected<std::unique_ptr<Module>> getLazyModule(LLVMContext &Context,
bool ShouldLazyLoadMetadata,
bool IsImporting);
/// Read the entire bitcode module and return it.
Expected<std::unique_ptr<Module>> parseModule(LLVMContext &Context);
/// Returns information about the module to be used for LTO: whether to
/// compile with ThinLTO, and whether it has a summary.
Expected<BitcodeLTOInfo> getLTOInfo();
/// Parse the specified bitcode buffer, returning the module summary index.
Expected<std::unique_ptr<ModuleSummaryIndex>> getSummary();
/// Parse the specified bitcode buffer and merge its module summary index
/// into CombinedIndex.
Error readSummary(ModuleSummaryIndex &CombinedIndex, StringRef ModulePath,
uint64_t ModuleId);
};
struct BitcodeFileContents {
std::vector<BitcodeModule> Mods;
StringRef Symtab, StrtabForSymtab;
};
/// Returns the contents of a bitcode file. This includes the raw contents of
/// the symbol table embedded in the bitcode file. Clients which require a
/// symbol table should prefer to use irsymtab::read instead of this function
/// because it creates a reader for the irsymtab and handles upgrading bitcode
/// files without a symbol table or with an old symbol table.
Expected<BitcodeFileContents> getBitcodeFileContents(MemoryBufferRef Buffer);
/// Returns a list of modules in the specified bitcode buffer.
Expected<std::vector<BitcodeModule>>
getBitcodeModuleList(MemoryBufferRef Buffer);
/// Read the header of the specified bitcode buffer and prepare for lazy
/// deserialization of function bodies. If ShouldLazyLoadMetadata is true,
/// lazily load metadata as well. If IsImporting is true, this module is
/// being parsed for ThinLTO importing into another module.
Expected<std::unique_ptr<Module>>
getLazyBitcodeModule(MemoryBufferRef Buffer, LLVMContext &Context,
bool ShouldLazyLoadMetadata = false,
bool IsImporting = false);
/// Like getLazyBitcodeModule, except that the module takes ownership of
/// the memory buffer if successful. If successful, this moves Buffer. On
/// error, this *does not* move Buffer. If IsImporting is true, this module is
/// being parsed for ThinLTO importing into another module.
Expected<std::unique_ptr<Module>> getOwningLazyBitcodeModule(
std::unique_ptr<MemoryBuffer> &&Buffer, LLVMContext &Context,
bool ShouldLazyLoadMetadata = false, bool IsImporting = false);
/// Read the header of the specified bitcode buffer and extract just the
/// triple information. If successful, this returns a string. On error, this
/// returns "".
Expected<std::string> getBitcodeTargetTriple(MemoryBufferRef Buffer);
/// Return true if \p Buffer contains a bitcode file with ObjC code (category
/// or class) in it.
Expected<bool> isBitcodeContainingObjCCategory(MemoryBufferRef Buffer);
/// Read the header of the specified bitcode buffer and extract just the
/// producer string information. If successful, this returns a string. On
/// error, this returns "".
Expected<std::string> getBitcodeProducerString(MemoryBufferRef Buffer);
/// Read the specified bitcode file, returning the module.
Expected<std::unique_ptr<Module>> parseBitcodeFile(MemoryBufferRef Buffer,
LLVMContext &Context);
/// Returns LTO information for the specified bitcode file.
Expected<BitcodeLTOInfo> getBitcodeLTOInfo(MemoryBufferRef Buffer);
/// Parse the specified bitcode buffer, returning the module summary index.
Expected<std::unique_ptr<ModuleSummaryIndex>>
getModuleSummaryIndex(MemoryBufferRef Buffer);
/// Parse the specified bitcode buffer and merge the index into CombinedIndex.
Error readModuleSummaryIndex(MemoryBufferRef Buffer,
ModuleSummaryIndex &CombinedIndex,
uint64_t ModuleId);
/// Parse the module summary index out of an IR file and return the module
/// summary index object if found, or an empty summary if not. If Path refers
/// to an empty file and IgnoreEmptyThinLTOIndexFile is true, then
/// this function will return nullptr.
Expected<std::unique_ptr<ModuleSummaryIndex>>
getModuleSummaryIndexForFile(StringRef Path,
bool IgnoreEmptyThinLTOIndexFile = false);
/// isBitcodeWrapper - Return true if the given bytes are the magic bytes
/// for an LLVM IR bitcode wrapper.
inline bool isBitcodeWrapper(const unsigned char *BufPtr,
const unsigned char *BufEnd) {
// See if you can find the hidden message in the magic bytes :-).
// (Hint: it's a little-endian encoding.)
return BufPtr != BufEnd &&
BufPtr[0] == 0xDE &&
BufPtr[1] == 0xC0 &&
BufPtr[2] == 0x17 &&
BufPtr[3] == 0x0B;
}
/// isRawBitcode - Return true if the given bytes are the magic bytes for
/// raw LLVM IR bitcode (without a wrapper).
inline bool isRawBitcode(const unsigned char *BufPtr,
const unsigned char *BufEnd) {
// These bytes sort of have a hidden message, but it's not in
// little-endian this time, and it's a little redundant.
return BufPtr != BufEnd &&
BufPtr[0] == 'B' &&
BufPtr[1] == 'C' &&
BufPtr[2] == 0xc0 &&
BufPtr[3] == 0xde;
}
/// isBitcode - Return true if the given bytes are the magic bytes for
/// LLVM IR bitcode, either with or without a wrapper.
inline bool isBitcode(const unsigned char *BufPtr,
const unsigned char *BufEnd) {
return isBitcodeWrapper(BufPtr, BufEnd) ||
isRawBitcode(BufPtr, BufEnd);
}
/// SkipBitcodeWrapperHeader - Some systems wrap bc files with a special
/// header for padding or other reasons. The format of this header is:
///
/// struct bc_header {
/// uint32_t Magic; // 0x0B17C0DE
/// uint32_t Version; // Version, currently always 0.
/// uint32_t BitcodeOffset; // Offset to traditional bitcode file.
/// uint32_t BitcodeSize; // Size of traditional bitcode file.
/// ... potentially other gunk ...
/// };
///
/// This function is called when we find a file with a matching magic number.
/// In this case, skip down to the subsection of the file that is actually a
/// BC file.
/// If 'VerifyBufferSize' is true, check that the buffer is large enough to
/// contain the whole bitcode file.
inline bool SkipBitcodeWrapperHeader(const unsigned char *&BufPtr,
const unsigned char *&BufEnd,
bool VerifyBufferSize) {
// Must contain the offset and size field!
if (unsigned(BufEnd - BufPtr) < BWH_SizeField + 4)
return true;
unsigned Offset = support::endian::read32le(&BufPtr[BWH_OffsetField]);
unsigned Size = support::endian::read32le(&BufPtr[BWH_SizeField]);
uint64_t BitcodeOffsetEnd = (uint64_t)Offset + (uint64_t)Size;
// Verify that Offset+Size fits in the file.
if (VerifyBufferSize && BitcodeOffsetEnd > uint64_t(BufEnd-BufPtr))
return true;
BufPtr += Offset;
BufEnd = BufPtr+Size;
return false;
}
const std::error_category &BitcodeErrorCategory();
enum class BitcodeError { CorruptedBitcode = 1 };
inline std::error_code make_error_code(BitcodeError E) {
return std::error_code(static_cast<int>(E), BitcodeErrorCategory());
}
} // end namespace llvm
namespace std {
template <> struct is_error_code_enum<llvm::BitcodeError> : std::true_type {};
} // end namespace std
#endif // LLVM_BITCODE_BITCODEREADER_H
+157
View File
@@ -0,0 +1,157 @@
//===- llvm/Bitcode/BitcodeWriter.h - Bitcode writers -----------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This header defines interfaces to write LLVM bitcode files/streams.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_BITCODE_BITCODEWRITER_H
#define LLVM_BITCODE_BITCODEWRITER_H
#include "llvm/ADT/StringRef.h"
#include "llvm/IR/ModuleSummaryIndex.h"
#include "llvm/MC/StringTableBuilder.h"
#include "llvm/Support/Allocator.h"
#include <map>
#include <memory>
#include <string>
#include <vector>
namespace llvm {
class BitstreamWriter;
class Module;
class raw_ostream;
class BitcodeWriter {
SmallVectorImpl<char> &Buffer;
std::unique_ptr<BitstreamWriter> Stream;
StringTableBuilder StrtabBuilder{StringTableBuilder::RAW};
// Owns any strings created by the irsymtab writer until we create the
// string table.
BumpPtrAllocator Alloc;
bool WroteStrtab = false, WroteSymtab = false;
void writeBlob(unsigned Block, unsigned Record, StringRef Blob);
std::vector<Module *> Mods;
public:
/// Create a BitcodeWriter that writes to Buffer.
BitcodeWriter(SmallVectorImpl<char> &Buffer);
~BitcodeWriter();
/// Attempt to write a symbol table to the bitcode file. This must be called
/// at most once after all modules have been written.
///
/// A reader does not require a symbol table to interpret a bitcode file;
/// the symbol table is needed only to improve link-time performance. So
/// this function may decide not to write a symbol table. It may so decide
/// if, for example, the target is unregistered or the IR is malformed.
void writeSymtab();
/// Write the bitcode file's string table. This must be called exactly once
/// after all modules and the optional symbol table have been written.
void writeStrtab();
/// Copy the string table for another module into this bitcode file. This
/// should be called after copying the module itself into the bitcode file.
void copyStrtab(StringRef Strtab);
/// Write the specified module to the buffer specified at construction time.
///
/// If \c ShouldPreserveUseListOrder, encode the use-list order for each \a
/// Value in \c M. These will be reconstructed exactly when \a M is
/// deserialized.
///
/// If \c Index is supplied, the bitcode will contain the summary index
/// (currently for use in ThinLTO optimization).
///
/// \p GenerateHash enables hashing the Module and including the hash in the
/// bitcode (currently for use in ThinLTO incremental build).
///
/// If \p ModHash is non-null, when GenerateHash is true, the resulting
/// hash is written into ModHash. When GenerateHash is false, that value
/// is used as the hash instead of computing from the generated bitcode.
/// Can be used to produce the same module hash for a minimized bitcode
/// used just for the thin link as in the regular full bitcode that will
/// be used in the backend.
void writeModule(const Module *M, bool ShouldPreserveUseListOrder = false,
const ModuleSummaryIndex *Index = nullptr,
bool GenerateHash = false, ModuleHash *ModHash = nullptr);
/// Write the specified thin link bitcode file (i.e., the minimized bitcode
/// file) to the buffer specified at construction time. The thin link
/// bitcode file is used for thin link, and it only contains the necessary
/// information for thin link.
///
/// ModHash is for use in ThinLTO incremental build, generated while the
/// IR bitcode file writing.
void writeThinLinkBitcode(const Module *M, const ModuleSummaryIndex &Index,
const ModuleHash &ModHash);
void writeIndex(
const ModuleSummaryIndex *Index,
const std::map<std::string, GVSummaryMapTy> *ModuleToSummariesForIndex);
};
/// \brief Write the specified module to the specified raw output stream.
///
/// For streams where it matters, the given stream should be in "binary"
/// mode.
///
/// If \c ShouldPreserveUseListOrder, encode the use-list order for each \a
/// Value in \c M. These will be reconstructed exactly when \a M is
/// deserialized.
///
/// If \c Index is supplied, the bitcode will contain the summary index
/// (currently for use in ThinLTO optimization).
///
/// \p GenerateHash enables hashing the Module and including the hash in the
/// bitcode (currently for use in ThinLTO incremental build).
///
/// If \p ModHash is non-null, when GenerateHash is true, the resulting
/// hash is written into ModHash. When GenerateHash is false, that value
/// is used as the hash instead of computing from the generated bitcode.
/// Can be used to produce the same module hash for a minimized bitcode
/// used just for the thin link as in the regular full bitcode that will
/// be used in the backend.
void WriteBitcodeToFile(const Module *M, raw_ostream &Out,
bool ShouldPreserveUseListOrder = false,
const ModuleSummaryIndex *Index = nullptr,
bool GenerateHash = false,
ModuleHash *ModHash = nullptr);
/// Write the specified thin link bitcode file (i.e., the minimized bitcode
/// file) to the given raw output stream, where it will be written in a new
/// bitcode block. The thin link bitcode file is used for thin link, and it
/// only contains the necessary information for thin link.
///
/// ModHash is for use in ThinLTO incremental build, generated while the IR
/// bitcode file writing.
void WriteThinLinkBitcodeToFile(const Module *M, raw_ostream &Out,
const ModuleSummaryIndex &Index,
const ModuleHash &ModHash);
/// Write the specified module summary index to the given raw output stream,
/// where it will be written in a new bitcode block. This is used when
/// writing the combined index file for ThinLTO. When writing a subset of the
/// index for a distributed backend, provide the \p ModuleToSummariesForIndex
/// map.
void WriteIndexToFile(const ModuleSummaryIndex &Index, raw_ostream &Out,
const std::map<std::string, GVSummaryMapTy>
*ModuleToSummariesForIndex = nullptr);
} // end namespace llvm
#endif // LLVM_BITCODE_BITCODEWRITER_H
@@ -0,0 +1,75 @@
//===-- BitcodeWriterPass.h - Bitcode writing pass --------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
/// \file
///
/// This file provides a bitcode writing pass.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_BITCODE_BITCODEWRITERPASS_H
#define LLVM_BITCODE_BITCODEWRITERPASS_H
#include "llvm/ADT/StringRef.h"
#include "llvm/IR/PassManager.h"
namespace llvm {
class Module;
class ModulePass;
class raw_ostream;
/// \brief Create and return a pass that writes the module to the specified
/// ostream. Note that this pass is designed for use with the legacy pass
/// manager.
///
/// If \c ShouldPreserveUseListOrder, encode use-list order so it can be
/// reproduced when deserialized.
///
/// If \c EmitSummaryIndex, emit the summary index (currently for use in ThinLTO
/// optimization).
///
/// If \c EmitModuleHash, compute and emit the module hash in the bitcode
/// (currently for use in ThinLTO incremental build).
ModulePass *createBitcodeWriterPass(raw_ostream &Str,
bool ShouldPreserveUseListOrder = false,
bool EmitSummaryIndex = false,
bool EmitModuleHash = false);
/// \brief Pass for writing a module of IR out to a bitcode file.
///
/// Note that this is intended for use with the new pass manager. To construct
/// a pass for the legacy pass manager, use the function above.
class BitcodeWriterPass : public PassInfoMixin<BitcodeWriterPass> {
raw_ostream &OS;
bool ShouldPreserveUseListOrder;
bool EmitSummaryIndex;
bool EmitModuleHash;
public:
/// \brief Construct a bitcode writer pass around a particular output stream.
///
/// If \c ShouldPreserveUseListOrder, encode use-list order so it can be
/// reproduced when deserialized.
///
/// If \c EmitSummaryIndex, emit the summary index (currently
/// for use in ThinLTO optimization).
explicit BitcodeWriterPass(raw_ostream &OS,
bool ShouldPreserveUseListOrder = false,
bool EmitSummaryIndex = false,
bool EmitModuleHash = false)
: OS(OS), ShouldPreserveUseListOrder(ShouldPreserveUseListOrder),
EmitSummaryIndex(EmitSummaryIndex), EmitModuleHash(EmitModuleHash) {}
/// \brief Run the bitcode writer pass, and output the module to the selected
/// output stream.
PreservedAnalyses run(Module &M, ModuleAnalysisManager &);
};
}
#endif
@@ -0,0 +1,506 @@
//===- BitstreamReader.h - Low-level bitstream reader interface -*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This header defines the BitstreamReader class. This class can be used to
// read an arbitrary bitstream, regardless of its contents.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_BITCODE_BITSTREAMREADER_H
#define LLVM_BITCODE_BITSTREAMREADER_H
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Bitcode/BitCodes.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/MemoryBuffer.h"
#include <algorithm>
#include <cassert>
#include <climits>
#include <cstddef>
#include <cstdint>
#include <memory>
#include <string>
#include <utility>
#include <vector>
namespace llvm {
/// This class maintains the abbreviations read from a block info block.
class BitstreamBlockInfo {
public:
/// This contains information emitted to BLOCKINFO_BLOCK blocks. These
/// describe abbreviations that all blocks of the specified ID inherit.
struct BlockInfo {
unsigned BlockID;
std::vector<std::shared_ptr<BitCodeAbbrev>> Abbrevs;
std::string Name;
std::vector<std::pair<unsigned, std::string>> RecordNames;
};
private:
std::vector<BlockInfo> BlockInfoRecords;
public:
/// If there is block info for the specified ID, return it, otherwise return
/// null.
const BlockInfo *getBlockInfo(unsigned BlockID) const {
// Common case, the most recent entry matches BlockID.
if (!BlockInfoRecords.empty() && BlockInfoRecords.back().BlockID == BlockID)
return &BlockInfoRecords.back();
for (unsigned i = 0, e = static_cast<unsigned>(BlockInfoRecords.size());
i != e; ++i)
if (BlockInfoRecords[i].BlockID == BlockID)
return &BlockInfoRecords[i];
return nullptr;
}
BlockInfo &getOrCreateBlockInfo(unsigned BlockID) {
if (const BlockInfo *BI = getBlockInfo(BlockID))
return *const_cast<BlockInfo*>(BI);
// Otherwise, add a new record.
BlockInfoRecords.emplace_back();
BlockInfoRecords.back().BlockID = BlockID;
return BlockInfoRecords.back();
}
};
/// This represents a position within a bitstream. There may be multiple
/// independent cursors reading within one bitstream, each maintaining their
/// own local state.
class SimpleBitstreamCursor {
ArrayRef<uint8_t> BitcodeBytes;
size_t NextChar = 0;
public:
/// This is the current data we have pulled from the stream but have not
/// returned to the client. This is specifically and intentionally defined to
/// follow the word size of the host machine for efficiency. We use word_t in
/// places that are aware of this to make it perfectly explicit what is going
/// on.
using word_t = size_t;
private:
word_t CurWord = 0;
/// This is the number of bits in CurWord that are valid. This is always from
/// [0...bits_of(size_t)-1] inclusive.
unsigned BitsInCurWord = 0;
public:
static const size_t MaxChunkSize = sizeof(word_t) * 8;
SimpleBitstreamCursor() = default;
explicit SimpleBitstreamCursor(ArrayRef<uint8_t> BitcodeBytes)
: BitcodeBytes(BitcodeBytes) {}
explicit SimpleBitstreamCursor(StringRef BitcodeBytes)
: BitcodeBytes(reinterpret_cast<const uint8_t *>(BitcodeBytes.data()),
BitcodeBytes.size()) {}
explicit SimpleBitstreamCursor(MemoryBufferRef BitcodeBytes)
: SimpleBitstreamCursor(BitcodeBytes.getBuffer()) {}
bool canSkipToPos(size_t pos) const {
// pos can be skipped to if it is a valid address or one byte past the end.
return pos <= BitcodeBytes.size();
}
bool AtEndOfStream() {
return BitsInCurWord == 0 && BitcodeBytes.size() <= NextChar;
}
/// Return the bit # of the bit we are reading.
uint64_t GetCurrentBitNo() const {
return NextChar*CHAR_BIT - BitsInCurWord;
}
// Return the byte # of the current bit.
uint64_t getCurrentByteNo() const { return GetCurrentBitNo() / 8; }
ArrayRef<uint8_t> getBitcodeBytes() const { return BitcodeBytes; }
/// Reset the stream to the specified bit number.
void JumpToBit(uint64_t BitNo) {
size_t ByteNo = size_t(BitNo/8) & ~(sizeof(word_t)-1);
unsigned WordBitNo = unsigned(BitNo & (sizeof(word_t)*8-1));
assert(canSkipToPos(ByteNo) && "Invalid location");
// Move the cursor to the right word.
NextChar = ByteNo;
BitsInCurWord = 0;
// Skip over any bits that are already consumed.
if (WordBitNo)
Read(WordBitNo);
}
/// Get a pointer into the bitstream at the specified byte offset.
const uint8_t *getPointerToByte(uint64_t ByteNo, uint64_t NumBytes) {
return BitcodeBytes.data() + ByteNo;
}
/// Get a pointer into the bitstream at the specified bit offset.
///
/// The bit offset must be on a byte boundary.
const uint8_t *getPointerToBit(uint64_t BitNo, uint64_t NumBytes) {
assert(!(BitNo % 8) && "Expected bit on byte boundary");
return getPointerToByte(BitNo / 8, NumBytes);
}
void fillCurWord() {
if (NextChar >= BitcodeBytes.size())
report_fatal_error("Unexpected end of file");
// Read the next word from the stream.
const uint8_t *NextCharPtr = BitcodeBytes.data() + NextChar;
unsigned BytesRead;
if (BitcodeBytes.size() >= NextChar + sizeof(word_t)) {
BytesRead = sizeof(word_t);
CurWord =
support::endian::read<word_t, support::little, support::unaligned>(
NextCharPtr);
} else {
// Short read.
BytesRead = BitcodeBytes.size() - NextChar;
CurWord = 0;
for (unsigned B = 0; B != BytesRead; ++B)
CurWord |= uint64_t(NextCharPtr[B]) << (B * 8);
}
NextChar += BytesRead;
BitsInCurWord = BytesRead * 8;
}
word_t Read(unsigned NumBits) {
static const unsigned BitsInWord = MaxChunkSize;
assert(NumBits && NumBits <= BitsInWord &&
"Cannot return zero or more than BitsInWord bits!");
static const unsigned Mask = sizeof(word_t) > 4 ? 0x3f : 0x1f;
// If the field is fully contained by CurWord, return it quickly.
if (BitsInCurWord >= NumBits) {
word_t R = CurWord & (~word_t(0) >> (BitsInWord - NumBits));
// Use a mask to avoid undefined behavior.
CurWord >>= (NumBits & Mask);
BitsInCurWord -= NumBits;
return R;
}
word_t R = BitsInCurWord ? CurWord : 0;
unsigned BitsLeft = NumBits - BitsInCurWord;
fillCurWord();
// If we run out of data, abort.
if (BitsLeft > BitsInCurWord)
report_fatal_error("Unexpected end of file");
word_t R2 = CurWord & (~word_t(0) >> (BitsInWord - BitsLeft));
// Use a mask to avoid undefined behavior.
CurWord >>= (BitsLeft & Mask);
BitsInCurWord -= BitsLeft;
R |= R2 << (NumBits - BitsLeft);
return R;
}
uint32_t ReadVBR(unsigned NumBits) {
uint32_t Piece = Read(NumBits);
if ((Piece & (1U << (NumBits-1))) == 0)
return Piece;
uint32_t Result = 0;
unsigned NextBit = 0;
while (true) {
Result |= (Piece & ((1U << (NumBits-1))-1)) << NextBit;
if ((Piece & (1U << (NumBits-1))) == 0)
return Result;
NextBit += NumBits-1;
Piece = Read(NumBits);
}
}
// Read a VBR that may have a value up to 64-bits in size. The chunk size of
// the VBR must still be <= 32 bits though.
uint64_t ReadVBR64(unsigned NumBits) {
uint32_t Piece = Read(NumBits);
if ((Piece & (1U << (NumBits-1))) == 0)
return uint64_t(Piece);
uint64_t Result = 0;
unsigned NextBit = 0;
while (true) {
Result |= uint64_t(Piece & ((1U << (NumBits-1))-1)) << NextBit;
if ((Piece & (1U << (NumBits-1))) == 0)
return Result;
NextBit += NumBits-1;
Piece = Read(NumBits);
}
}
void SkipToFourByteBoundary() {
// If word_t is 64-bits and if we've read less than 32 bits, just dump
// the bits we have up to the next 32-bit boundary.
if (sizeof(word_t) > 4 &&
BitsInCurWord >= 32) {
CurWord >>= BitsInCurWord-32;
BitsInCurWord = 32;
return;
}
BitsInCurWord = 0;
}
/// Skip to the end of the file.
void skipToEnd() { NextChar = BitcodeBytes.size(); }
};
/// When advancing through a bitstream cursor, each advance can discover a few
/// different kinds of entries:
struct BitstreamEntry {
enum {
Error, // Malformed bitcode was found.
EndBlock, // We've reached the end of the current block, (or the end of the
// file, which is treated like a series of EndBlock records.
SubBlock, // This is the start of a new subblock of a specific ID.
Record // This is a record with a specific AbbrevID.
} Kind;
unsigned ID;
static BitstreamEntry getError() {
BitstreamEntry E; E.Kind = Error; return E;
}
static BitstreamEntry getEndBlock() {
BitstreamEntry E; E.Kind = EndBlock; return E;
}
static BitstreamEntry getSubBlock(unsigned ID) {
BitstreamEntry E; E.Kind = SubBlock; E.ID = ID; return E;
}
static BitstreamEntry getRecord(unsigned AbbrevID) {
BitstreamEntry E; E.Kind = Record; E.ID = AbbrevID; return E;
}
};
/// This represents a position within a bitcode file, implemented on top of a
/// SimpleBitstreamCursor.
///
/// Unlike iterators, BitstreamCursors are heavy-weight objects that should not
/// be passed by value.
class BitstreamCursor : SimpleBitstreamCursor {
// This is the declared size of code values used for the current block, in
// bits.
unsigned CurCodeSize = 2;
/// Abbrevs installed at in this block.
std::vector<std::shared_ptr<BitCodeAbbrev>> CurAbbrevs;
struct Block {
unsigned PrevCodeSize;
std::vector<std::shared_ptr<BitCodeAbbrev>> PrevAbbrevs;
explicit Block(unsigned PCS) : PrevCodeSize(PCS) {}
};
/// This tracks the codesize of parent blocks.
SmallVector<Block, 8> BlockScope;
BitstreamBlockInfo *BlockInfo = nullptr;
public:
static const size_t MaxChunkSize = sizeof(word_t) * 8;
BitstreamCursor() = default;
explicit BitstreamCursor(ArrayRef<uint8_t> BitcodeBytes)
: SimpleBitstreamCursor(BitcodeBytes) {}
explicit BitstreamCursor(StringRef BitcodeBytes)
: SimpleBitstreamCursor(BitcodeBytes) {}
explicit BitstreamCursor(MemoryBufferRef BitcodeBytes)
: SimpleBitstreamCursor(BitcodeBytes) {}
using SimpleBitstreamCursor::canSkipToPos;
using SimpleBitstreamCursor::AtEndOfStream;
using SimpleBitstreamCursor::getBitcodeBytes;
using SimpleBitstreamCursor::GetCurrentBitNo;
using SimpleBitstreamCursor::getCurrentByteNo;
using SimpleBitstreamCursor::getPointerToByte;
using SimpleBitstreamCursor::JumpToBit;
using SimpleBitstreamCursor::fillCurWord;
using SimpleBitstreamCursor::Read;
using SimpleBitstreamCursor::ReadVBR;
using SimpleBitstreamCursor::ReadVBR64;
/// Return the number of bits used to encode an abbrev #.
unsigned getAbbrevIDWidth() const { return CurCodeSize; }
/// Flags that modify the behavior of advance().
enum {
/// If this flag is used, the advance() method does not automatically pop
/// the block scope when the end of a block is reached.
AF_DontPopBlockAtEnd = 1,
/// If this flag is used, abbrev entries are returned just like normal
/// records.
AF_DontAutoprocessAbbrevs = 2
};
/// Advance the current bitstream, returning the next entry in the stream.
BitstreamEntry advance(unsigned Flags = 0) {
while (true) {
if (AtEndOfStream())
return BitstreamEntry::getError();
unsigned Code = ReadCode();
if (Code == bitc::END_BLOCK) {
// Pop the end of the block unless Flags tells us not to.
if (!(Flags & AF_DontPopBlockAtEnd) && ReadBlockEnd())
return BitstreamEntry::getError();
return BitstreamEntry::getEndBlock();
}
if (Code == bitc::ENTER_SUBBLOCK)
return BitstreamEntry::getSubBlock(ReadSubBlockID());
if (Code == bitc::DEFINE_ABBREV &&
!(Flags & AF_DontAutoprocessAbbrevs)) {
// We read and accumulate abbrev's, the client can't do anything with
// them anyway.
ReadAbbrevRecord();
continue;
}
return BitstreamEntry::getRecord(Code);
}
}
/// This is a convenience function for clients that don't expect any
/// subblocks. This just skips over them automatically.
BitstreamEntry advanceSkippingSubblocks(unsigned Flags = 0) {
while (true) {
// If we found a normal entry, return it.
BitstreamEntry Entry = advance(Flags);
if (Entry.Kind != BitstreamEntry::SubBlock)
return Entry;
// If we found a sub-block, just skip over it and check the next entry.
if (SkipBlock())
return BitstreamEntry::getError();
}
}
unsigned ReadCode() {
return Read(CurCodeSize);
}
// Block header:
// [ENTER_SUBBLOCK, blockid, newcodelen, <align4bytes>, blocklen]
/// Having read the ENTER_SUBBLOCK code, read the BlockID for the block.
unsigned ReadSubBlockID() {
return ReadVBR(bitc::BlockIDWidth);
}
/// Having read the ENTER_SUBBLOCK abbrevid and a BlockID, skip over the body
/// of this block. If the block record is malformed, return true.
bool SkipBlock() {
// Read and ignore the codelen value. Since we are skipping this block, we
// don't care what code widths are used inside of it.
ReadVBR(bitc::CodeLenWidth);
SkipToFourByteBoundary();
unsigned NumFourBytes = Read(bitc::BlockSizeWidth);
// Check that the block wasn't partially defined, and that the offset isn't
// bogus.
size_t SkipTo = GetCurrentBitNo() + NumFourBytes*4*8;
if (AtEndOfStream() || !canSkipToPos(SkipTo/8))
return true;
JumpToBit(SkipTo);
return false;
}
/// Having read the ENTER_SUBBLOCK abbrevid, enter the block, and return true
/// if the block has an error.
bool EnterSubBlock(unsigned BlockID, unsigned *NumWordsP = nullptr);
bool ReadBlockEnd() {
if (BlockScope.empty()) return true;
// Block tail:
// [END_BLOCK, <align4bytes>]
SkipToFourByteBoundary();
popBlockScope();
return false;
}
private:
void popBlockScope() {
CurCodeSize = BlockScope.back().PrevCodeSize;
CurAbbrevs = std::move(BlockScope.back().PrevAbbrevs);
BlockScope.pop_back();
}
//===--------------------------------------------------------------------===//
// Record Processing
//===--------------------------------------------------------------------===//
public:
/// Return the abbreviation for the specified AbbrevId.
const BitCodeAbbrev *getAbbrev(unsigned AbbrevID) {
unsigned AbbrevNo = AbbrevID - bitc::FIRST_APPLICATION_ABBREV;
if (AbbrevNo >= CurAbbrevs.size())
report_fatal_error("Invalid abbrev number");
return CurAbbrevs[AbbrevNo].get();
}
/// Read the current record and discard it, returning the code for the record.
unsigned skipRecord(unsigned AbbrevID);
unsigned readRecord(unsigned AbbrevID, SmallVectorImpl<uint64_t> &Vals,
StringRef *Blob = nullptr);
//===--------------------------------------------------------------------===//
// Abbrev Processing
//===--------------------------------------------------------------------===//
void ReadAbbrevRecord();
/// Read and return a block info block from the bitstream. If an error was
/// encountered, return None.
///
/// \param ReadBlockInfoNames Whether to read block/record name information in
/// the BlockInfo block. Only llvm-bcanalyzer uses this.
Optional<BitstreamBlockInfo>
ReadBlockInfoBlock(bool ReadBlockInfoNames = false);
/// Set the block info to be used by this BitstreamCursor to interpret
/// abbreviated records.
void setBlockInfo(BitstreamBlockInfo *BI) { BlockInfo = BI; }
};
} // end llvm namespace
#endif // LLVM_BITCODE_BITSTREAMREADER_H
@@ -0,0 +1,550 @@
//===- BitstreamWriter.h - Low-level bitstream writer interface -*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This header defines the BitstreamWriter class. This class can be used to
// write an arbitrary bitstream, regardless of its contents.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_BITCODE_BITSTREAMWRITER_H
#define LLVM_BITCODE_BITSTREAMWRITER_H
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Bitcode/BitCodes.h"
#include "llvm/Support/Endian.h"
#include <vector>
namespace llvm {
class BitstreamWriter {
SmallVectorImpl<char> &Out;
/// CurBit - Always between 0 and 31 inclusive, specifies the next bit to use.
unsigned CurBit;
/// CurValue - The current value. Only bits < CurBit are valid.
uint32_t CurValue;
/// CurCodeSize - This is the declared size of code values used for the
/// current block, in bits.
unsigned CurCodeSize;
/// BlockInfoCurBID - When emitting a BLOCKINFO_BLOCK, this is the currently
/// selected BLOCK ID.
unsigned BlockInfoCurBID;
/// CurAbbrevs - Abbrevs installed at in this block.
std::vector<std::shared_ptr<BitCodeAbbrev>> CurAbbrevs;
struct Block {
unsigned PrevCodeSize;
size_t StartSizeWord;
std::vector<std::shared_ptr<BitCodeAbbrev>> PrevAbbrevs;
Block(unsigned PCS, size_t SSW) : PrevCodeSize(PCS), StartSizeWord(SSW) {}
};
/// BlockScope - This tracks the current blocks that we have entered.
std::vector<Block> BlockScope;
/// BlockInfo - This contains information emitted to BLOCKINFO_BLOCK blocks.
/// These describe abbreviations that all blocks of the specified ID inherit.
struct BlockInfo {
unsigned BlockID;
std::vector<std::shared_ptr<BitCodeAbbrev>> Abbrevs;
};
std::vector<BlockInfo> BlockInfoRecords;
void WriteByte(unsigned char Value) {
Out.push_back(Value);
}
void WriteWord(unsigned Value) {
Value = support::endian::byte_swap<uint32_t, support::little>(Value);
Out.append(reinterpret_cast<const char *>(&Value),
reinterpret_cast<const char *>(&Value + 1));
}
size_t GetBufferOffset() const { return Out.size(); }
size_t GetWordIndex() const {
size_t Offset = GetBufferOffset();
assert((Offset & 3) == 0 && "Not 32-bit aligned");
return Offset / 4;
}
public:
explicit BitstreamWriter(SmallVectorImpl<char> &O)
: Out(O), CurBit(0), CurValue(0), CurCodeSize(2) {}
~BitstreamWriter() {
assert(CurBit == 0 && "Unflushed data remaining");
assert(BlockScope.empty() && CurAbbrevs.empty() && "Block imbalance");
}
/// \brief Retrieve the current position in the stream, in bits.
uint64_t GetCurrentBitNo() const { return GetBufferOffset() * 8 + CurBit; }
/// \brief Retrieve the number of bits currently used to encode an abbrev ID.
unsigned GetAbbrevIDWidth() const { return CurCodeSize; }
//===--------------------------------------------------------------------===//
// Basic Primitives for emitting bits to the stream.
//===--------------------------------------------------------------------===//
/// Backpatch a 32-bit word in the output at the given bit offset
/// with the specified value.
void BackpatchWord(uint64_t BitNo, unsigned NewWord) {
using namespace llvm::support;
unsigned ByteNo = BitNo / 8;
assert((!endian::readAtBitAlignment<uint32_t, little, unaligned>(
&Out[ByteNo], BitNo & 7)) &&
"Expected to be patching over 0-value placeholders");
endian::writeAtBitAlignment<uint32_t, little, unaligned>(
&Out[ByteNo], NewWord, BitNo & 7);
}
void BackpatchWord64(uint64_t BitNo, uint64_t Val) {
BackpatchWord(BitNo, (uint32_t)Val);
BackpatchWord(BitNo + 32, (uint32_t)(Val >> 32));
}
void Emit(uint32_t Val, unsigned NumBits) {
assert(NumBits && NumBits <= 32 && "Invalid value size!");
assert((Val & ~(~0U >> (32-NumBits))) == 0 && "High bits set!");
CurValue |= Val << CurBit;
if (CurBit + NumBits < 32) {
CurBit += NumBits;
return;
}
// Add the current word.
WriteWord(CurValue);
if (CurBit)
CurValue = Val >> (32-CurBit);
else
CurValue = 0;
CurBit = (CurBit+NumBits) & 31;
}
void FlushToWord() {
if (CurBit) {
WriteWord(CurValue);
CurBit = 0;
CurValue = 0;
}
}
void EmitVBR(uint32_t Val, unsigned NumBits) {
assert(NumBits <= 32 && "Too many bits to emit!");
uint32_t Threshold = 1U << (NumBits-1);
// Emit the bits with VBR encoding, NumBits-1 bits at a time.
while (Val >= Threshold) {
Emit((Val & ((1 << (NumBits-1))-1)) | (1 << (NumBits-1)), NumBits);
Val >>= NumBits-1;
}
Emit(Val, NumBits);
}
void EmitVBR64(uint64_t Val, unsigned NumBits) {
assert(NumBits <= 32 && "Too many bits to emit!");
if ((uint32_t)Val == Val)
return EmitVBR((uint32_t)Val, NumBits);
uint32_t Threshold = 1U << (NumBits-1);
// Emit the bits with VBR encoding, NumBits-1 bits at a time.
while (Val >= Threshold) {
Emit(((uint32_t)Val & ((1 << (NumBits-1))-1)) |
(1 << (NumBits-1)), NumBits);
Val >>= NumBits-1;
}
Emit((uint32_t)Val, NumBits);
}
/// EmitCode - Emit the specified code.
void EmitCode(unsigned Val) {
Emit(Val, CurCodeSize);
}
//===--------------------------------------------------------------------===//
// Block Manipulation
//===--------------------------------------------------------------------===//
/// getBlockInfo - If there is block info for the specified ID, return it,
/// otherwise return null.
BlockInfo *getBlockInfo(unsigned BlockID) {
// Common case, the most recent entry matches BlockID.
if (!BlockInfoRecords.empty() && BlockInfoRecords.back().BlockID == BlockID)
return &BlockInfoRecords.back();
for (unsigned i = 0, e = static_cast<unsigned>(BlockInfoRecords.size());
i != e; ++i)
if (BlockInfoRecords[i].BlockID == BlockID)
return &BlockInfoRecords[i];
return nullptr;
}
void EnterSubblock(unsigned BlockID, unsigned CodeLen) {
// Block header:
// [ENTER_SUBBLOCK, blockid, newcodelen, <align4bytes>, blocklen]
EmitCode(bitc::ENTER_SUBBLOCK);
EmitVBR(BlockID, bitc::BlockIDWidth);
EmitVBR(CodeLen, bitc::CodeLenWidth);
FlushToWord();
size_t BlockSizeWordIndex = GetWordIndex();
unsigned OldCodeSize = CurCodeSize;
// Emit a placeholder, which will be replaced when the block is popped.
Emit(0, bitc::BlockSizeWidth);
CurCodeSize = CodeLen;
// Push the outer block's abbrev set onto the stack, start out with an
// empty abbrev set.
BlockScope.emplace_back(OldCodeSize, BlockSizeWordIndex);
BlockScope.back().PrevAbbrevs.swap(CurAbbrevs);
// If there is a blockinfo for this BlockID, add all the predefined abbrevs
// to the abbrev list.
if (BlockInfo *Info = getBlockInfo(BlockID)) {
CurAbbrevs.insert(CurAbbrevs.end(), Info->Abbrevs.begin(),
Info->Abbrevs.end());
}
}
void ExitBlock() {
assert(!BlockScope.empty() && "Block scope imbalance!");
const Block &B = BlockScope.back();
// Block tail:
// [END_BLOCK, <align4bytes>]
EmitCode(bitc::END_BLOCK);
FlushToWord();
// Compute the size of the block, in words, not counting the size field.
size_t SizeInWords = GetWordIndex() - B.StartSizeWord - 1;
uint64_t BitNo = uint64_t(B.StartSizeWord) * 32;
// Update the block size field in the header of this sub-block.
BackpatchWord(BitNo, SizeInWords);
// Restore the inner block's code size and abbrev table.
CurCodeSize = B.PrevCodeSize;
CurAbbrevs = std::move(B.PrevAbbrevs);
BlockScope.pop_back();
}
//===--------------------------------------------------------------------===//
// Record Emission
//===--------------------------------------------------------------------===//
private:
/// EmitAbbreviatedLiteral - Emit a literal value according to its abbrev
/// record. This is a no-op, since the abbrev specifies the literal to use.
template<typename uintty>
void EmitAbbreviatedLiteral(const BitCodeAbbrevOp &Op, uintty V) {
assert(Op.isLiteral() && "Not a literal");
// If the abbrev specifies the literal value to use, don't emit
// anything.
assert(V == Op.getLiteralValue() &&
"Invalid abbrev for record!");
}
/// EmitAbbreviatedField - Emit a single scalar field value with the specified
/// encoding.
template<typename uintty>
void EmitAbbreviatedField(const BitCodeAbbrevOp &Op, uintty V) {
assert(!Op.isLiteral() && "Literals should use EmitAbbreviatedLiteral!");
// Encode the value as we are commanded.
switch (Op.getEncoding()) {
default: llvm_unreachable("Unknown encoding!");
case BitCodeAbbrevOp::Fixed:
if (Op.getEncodingData())
Emit((unsigned)V, (unsigned)Op.getEncodingData());
break;
case BitCodeAbbrevOp::VBR:
if (Op.getEncodingData())
EmitVBR64(V, (unsigned)Op.getEncodingData());
break;
case BitCodeAbbrevOp::Char6:
Emit(BitCodeAbbrevOp::EncodeChar6((char)V), 6);
break;
}
}
/// EmitRecordWithAbbrevImpl - This is the core implementation of the record
/// emission code. If BlobData is non-null, then it specifies an array of
/// data that should be emitted as part of the Blob or Array operand that is
/// known to exist at the end of the record. If Code is specified, then
/// it is the record code to emit before the Vals, which must not contain
/// the code.
template <typename uintty>
void EmitRecordWithAbbrevImpl(unsigned Abbrev, ArrayRef<uintty> Vals,
StringRef Blob, Optional<unsigned> Code) {
const char *BlobData = Blob.data();
unsigned BlobLen = (unsigned) Blob.size();
unsigned AbbrevNo = Abbrev-bitc::FIRST_APPLICATION_ABBREV;
assert(AbbrevNo < CurAbbrevs.size() && "Invalid abbrev #!");
const BitCodeAbbrev *Abbv = CurAbbrevs[AbbrevNo].get();
EmitCode(Abbrev);
unsigned i = 0, e = static_cast<unsigned>(Abbv->getNumOperandInfos());
if (Code) {
assert(e && "Expected non-empty abbreviation");
const BitCodeAbbrevOp &Op = Abbv->getOperandInfo(i++);
if (Op.isLiteral())
EmitAbbreviatedLiteral(Op, Code.getValue());
else {
assert(Op.getEncoding() != BitCodeAbbrevOp::Array &&
Op.getEncoding() != BitCodeAbbrevOp::Blob &&
"Expected literal or scalar");
EmitAbbreviatedField(Op, Code.getValue());
}
}
unsigned RecordIdx = 0;
for (; i != e; ++i) {
const BitCodeAbbrevOp &Op = Abbv->getOperandInfo(i);
if (Op.isLiteral()) {
assert(RecordIdx < Vals.size() && "Invalid abbrev/record");
EmitAbbreviatedLiteral(Op, Vals[RecordIdx]);
++RecordIdx;
} else if (Op.getEncoding() == BitCodeAbbrevOp::Array) {
// Array case.
assert(i + 2 == e && "array op not second to last?");
const BitCodeAbbrevOp &EltEnc = Abbv->getOperandInfo(++i);
// If this record has blob data, emit it, otherwise we must have record
// entries to encode this way.
if (BlobData) {
assert(RecordIdx == Vals.size() &&
"Blob data and record entries specified for array!");
// Emit a vbr6 to indicate the number of elements present.
EmitVBR(static_cast<uint32_t>(BlobLen), 6);
// Emit each field.
for (unsigned i = 0; i != BlobLen; ++i)
EmitAbbreviatedField(EltEnc, (unsigned char)BlobData[i]);
// Know that blob data is consumed for assertion below.
BlobData = nullptr;
} else {
// Emit a vbr6 to indicate the number of elements present.
EmitVBR(static_cast<uint32_t>(Vals.size()-RecordIdx), 6);
// Emit each field.
for (unsigned e = Vals.size(); RecordIdx != e; ++RecordIdx)
EmitAbbreviatedField(EltEnc, Vals[RecordIdx]);
}
} else if (Op.getEncoding() == BitCodeAbbrevOp::Blob) {
// If this record has blob data, emit it, otherwise we must have record
// entries to encode this way.
if (BlobData) {
assert(RecordIdx == Vals.size() &&
"Blob data and record entries specified for blob operand!");
assert(Blob.data() == BlobData && "BlobData got moved");
assert(Blob.size() == BlobLen && "BlobLen got changed");
emitBlob(Blob);
BlobData = nullptr;
} else {
emitBlob(Vals.slice(RecordIdx));
}
} else { // Single scalar field.
assert(RecordIdx < Vals.size() && "Invalid abbrev/record");
EmitAbbreviatedField(Op, Vals[RecordIdx]);
++RecordIdx;
}
}
assert(RecordIdx == Vals.size() && "Not all record operands emitted!");
assert(BlobData == nullptr &&
"Blob data specified for record that doesn't use it!");
}
public:
/// Emit a blob, including flushing before and tail-padding.
template <class UIntTy>
void emitBlob(ArrayRef<UIntTy> Bytes, bool ShouldEmitSize = true) {
// Emit a vbr6 to indicate the number of elements present.
if (ShouldEmitSize)
EmitVBR(static_cast<uint32_t>(Bytes.size()), 6);
// Flush to a 32-bit alignment boundary.
FlushToWord();
// Emit literal bytes.
for (const auto &B : Bytes) {
assert(isUInt<8>(B) && "Value too large to emit as byte");
WriteByte((unsigned char)B);
}
// Align end to 32-bits.
while (GetBufferOffset() & 3)
WriteByte(0);
}
void emitBlob(StringRef Bytes, bool ShouldEmitSize = true) {
emitBlob(makeArrayRef((const uint8_t *)Bytes.data(), Bytes.size()),
ShouldEmitSize);
}
/// EmitRecord - Emit the specified record to the stream, using an abbrev if
/// we have one to compress the output.
template <typename Container>
void EmitRecord(unsigned Code, const Container &Vals, unsigned Abbrev = 0) {
if (!Abbrev) {
// If we don't have an abbrev to use, emit this in its fully unabbreviated
// form.
auto Count = static_cast<uint32_t>(makeArrayRef(Vals).size());
EmitCode(bitc::UNABBREV_RECORD);
EmitVBR(Code, 6);
EmitVBR(Count, 6);
for (unsigned i = 0, e = Count; i != e; ++i)
EmitVBR64(Vals[i], 6);
return;
}
EmitRecordWithAbbrevImpl(Abbrev, makeArrayRef(Vals), StringRef(), Code);
}
/// EmitRecordWithAbbrev - Emit a record with the specified abbreviation.
/// Unlike EmitRecord, the code for the record should be included in Vals as
/// the first entry.
template <typename Container>
void EmitRecordWithAbbrev(unsigned Abbrev, const Container &Vals) {
EmitRecordWithAbbrevImpl(Abbrev, makeArrayRef(Vals), StringRef(), None);
}
/// EmitRecordWithBlob - Emit the specified record to the stream, using an
/// abbrev that includes a blob at the end. The blob data to emit is
/// specified by the pointer and length specified at the end. In contrast to
/// EmitRecord, this routine expects that the first entry in Vals is the code
/// of the record.
template <typename Container>
void EmitRecordWithBlob(unsigned Abbrev, const Container &Vals,
StringRef Blob) {
EmitRecordWithAbbrevImpl(Abbrev, makeArrayRef(Vals), Blob, None);
}
template <typename Container>
void EmitRecordWithBlob(unsigned Abbrev, const Container &Vals,
const char *BlobData, unsigned BlobLen) {
return EmitRecordWithAbbrevImpl(Abbrev, makeArrayRef(Vals),
StringRef(BlobData, BlobLen), None);
}
/// EmitRecordWithArray - Just like EmitRecordWithBlob, works with records
/// that end with an array.
template <typename Container>
void EmitRecordWithArray(unsigned Abbrev, const Container &Vals,
StringRef Array) {
EmitRecordWithAbbrevImpl(Abbrev, makeArrayRef(Vals), Array, None);
}
template <typename Container>
void EmitRecordWithArray(unsigned Abbrev, const Container &Vals,
const char *ArrayData, unsigned ArrayLen) {
return EmitRecordWithAbbrevImpl(Abbrev, makeArrayRef(Vals),
StringRef(ArrayData, ArrayLen), None);
}
//===--------------------------------------------------------------------===//
// Abbrev Emission
//===--------------------------------------------------------------------===//
private:
// Emit the abbreviation as a DEFINE_ABBREV record.
void EncodeAbbrev(const BitCodeAbbrev &Abbv) {
EmitCode(bitc::DEFINE_ABBREV);
EmitVBR(Abbv.getNumOperandInfos(), 5);
for (unsigned i = 0, e = static_cast<unsigned>(Abbv.getNumOperandInfos());
i != e; ++i) {
const BitCodeAbbrevOp &Op = Abbv.getOperandInfo(i);
Emit(Op.isLiteral(), 1);
if (Op.isLiteral()) {
EmitVBR64(Op.getLiteralValue(), 8);
} else {
Emit(Op.getEncoding(), 3);
if (Op.hasEncodingData())
EmitVBR64(Op.getEncodingData(), 5);
}
}
}
public:
/// EmitAbbrev - This emits an abbreviation to the stream. Note that this
/// method takes ownership of the specified abbrev.
unsigned EmitAbbrev(std::shared_ptr<BitCodeAbbrev> Abbv) {
// Emit the abbreviation as a record.
EncodeAbbrev(*Abbv);
CurAbbrevs.push_back(std::move(Abbv));
return static_cast<unsigned>(CurAbbrevs.size())-1 +
bitc::FIRST_APPLICATION_ABBREV;
}
//===--------------------------------------------------------------------===//
// BlockInfo Block Emission
//===--------------------------------------------------------------------===//
/// EnterBlockInfoBlock - Start emitting the BLOCKINFO_BLOCK.
void EnterBlockInfoBlock() {
EnterSubblock(bitc::BLOCKINFO_BLOCK_ID, 2);
BlockInfoCurBID = ~0U;
BlockInfoRecords.clear();
}
private:
/// SwitchToBlockID - If we aren't already talking about the specified block
/// ID, emit a BLOCKINFO_CODE_SETBID record.
void SwitchToBlockID(unsigned BlockID) {
if (BlockInfoCurBID == BlockID) return;
SmallVector<unsigned, 2> V;
V.push_back(BlockID);
EmitRecord(bitc::BLOCKINFO_CODE_SETBID, V);
BlockInfoCurBID = BlockID;
}
BlockInfo &getOrCreateBlockInfo(unsigned BlockID) {
if (BlockInfo *BI = getBlockInfo(BlockID))
return *BI;
// Otherwise, add a new record.
BlockInfoRecords.emplace_back();
BlockInfoRecords.back().BlockID = BlockID;
return BlockInfoRecords.back();
}
public:
/// EmitBlockInfoAbbrev - Emit a DEFINE_ABBREV record for the specified
/// BlockID.
unsigned EmitBlockInfoAbbrev(unsigned BlockID, std::shared_ptr<BitCodeAbbrev> Abbv) {
SwitchToBlockID(BlockID);
EncodeAbbrev(*Abbv);
// Add the abbrev to the specified block record.
BlockInfo &Info = getOrCreateBlockInfo(BlockID);
Info.Abbrevs.push_back(std::move(Abbv));
return Info.Abbrevs.size()-1+bitc::FIRST_APPLICATION_ABBREV;
}
};
} // End llvm namespace
#endif
+584
View File
@@ -0,0 +1,584 @@
//===- LLVMBitCodes.h - Enum values for the LLVM bitcode format -*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This header defines Bitcode enum values for LLVM IR bitcode files.
//
// The enum values defined in this file should be considered permanent. If
// new features are added, they should have values added at the end of the
// respective lists.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_BITCODE_LLVMBITCODES_H
#define LLVM_BITCODE_LLVMBITCODES_H
#include "llvm/Bitcode/BitCodes.h"
namespace llvm {
namespace bitc {
// The only top-level block types are MODULE, IDENTIFICATION, STRTAB and SYMTAB.
enum BlockIDs {
// Blocks
MODULE_BLOCK_ID = FIRST_APPLICATION_BLOCKID,
// Module sub-block id's.
PARAMATTR_BLOCK_ID,
PARAMATTR_GROUP_BLOCK_ID,
CONSTANTS_BLOCK_ID,
FUNCTION_BLOCK_ID,
// Block intended to contains information on the bitcode versioning.
// Can be used to provide better error messages when we fail to parse a
// bitcode file.
IDENTIFICATION_BLOCK_ID,
VALUE_SYMTAB_BLOCK_ID,
METADATA_BLOCK_ID,
METADATA_ATTACHMENT_ID,
TYPE_BLOCK_ID_NEW,
USELIST_BLOCK_ID,
MODULE_STRTAB_BLOCK_ID,
GLOBALVAL_SUMMARY_BLOCK_ID,
OPERAND_BUNDLE_TAGS_BLOCK_ID,
METADATA_KIND_BLOCK_ID,
STRTAB_BLOCK_ID,
FULL_LTO_GLOBALVAL_SUMMARY_BLOCK_ID,
SYMTAB_BLOCK_ID,
SYNC_SCOPE_NAMES_BLOCK_ID,
};
/// Identification block contains a string that describes the producer details,
/// and an epoch that defines the auto-upgrade capability.
enum IdentificationCodes {
IDENTIFICATION_CODE_STRING = 1, // IDENTIFICATION: [strchr x N]
IDENTIFICATION_CODE_EPOCH = 2, // EPOCH: [epoch#]
};
/// The epoch that defines the auto-upgrade compatibility for the bitcode.
///
/// LLVM guarantees in a major release that a minor release can read bitcode
/// generated by previous minor releases. We translate this by making the reader
/// accepting only bitcode with the same epoch, except for the X.0 release which
/// also accepts N-1.
enum { BITCODE_CURRENT_EPOCH = 0 };
/// MODULE blocks have a number of optional fields and subblocks.
enum ModuleCodes {
MODULE_CODE_VERSION = 1, // VERSION: [version#]
MODULE_CODE_TRIPLE = 2, // TRIPLE: [strchr x N]
MODULE_CODE_DATALAYOUT = 3, // DATALAYOUT: [strchr x N]
MODULE_CODE_ASM = 4, // ASM: [strchr x N]
MODULE_CODE_SECTIONNAME = 5, // SECTIONNAME: [strchr x N]
// FIXME: Remove DEPLIB in 4.0.
MODULE_CODE_DEPLIB = 6, // DEPLIB: [strchr x N]
// GLOBALVAR: [pointer type, isconst, initid,
// linkage, alignment, section, visibility, threadlocal]
MODULE_CODE_GLOBALVAR = 7,
// FUNCTION: [type, callingconv, isproto, linkage, paramattrs, alignment,
// section, visibility, gc, unnamed_addr]
MODULE_CODE_FUNCTION = 8,
// ALIAS: [alias type, aliasee val#, linkage, visibility]
MODULE_CODE_ALIAS_OLD = 9,
MODULE_CODE_GCNAME = 11, // GCNAME: [strchr x N]
MODULE_CODE_COMDAT = 12, // COMDAT: [selection_kind, name]
MODULE_CODE_VSTOFFSET = 13, // VSTOFFSET: [offset]
// ALIAS: [alias value type, addrspace, aliasee val#, linkage, visibility]
MODULE_CODE_ALIAS = 14,
MODULE_CODE_METADATA_VALUES_UNUSED = 15,
// SOURCE_FILENAME: [namechar x N]
MODULE_CODE_SOURCE_FILENAME = 16,
// HASH: [5*i32]
MODULE_CODE_HASH = 17,
// IFUNC: [ifunc value type, addrspace, resolver val#, linkage, visibility]
MODULE_CODE_IFUNC = 18,
};
/// PARAMATTR blocks have code for defining a parameter attribute set.
enum AttributeCodes {
// FIXME: Remove `PARAMATTR_CODE_ENTRY_OLD' in 4.0
PARAMATTR_CODE_ENTRY_OLD = 1, // ENTRY: [paramidx0, attr0,
// paramidx1, attr1...]
PARAMATTR_CODE_ENTRY = 2, // ENTRY: [attrgrp0, attrgrp1, ...]
PARAMATTR_GRP_CODE_ENTRY = 3 // ENTRY: [grpid, idx, attr0, attr1, ...]
};
/// TYPE blocks have codes for each type primitive they use.
enum TypeCodes {
TYPE_CODE_NUMENTRY = 1, // NUMENTRY: [numentries]
// Type Codes
TYPE_CODE_VOID = 2, // VOID
TYPE_CODE_FLOAT = 3, // FLOAT
TYPE_CODE_DOUBLE = 4, // DOUBLE
TYPE_CODE_LABEL = 5, // LABEL
TYPE_CODE_OPAQUE = 6, // OPAQUE
TYPE_CODE_INTEGER = 7, // INTEGER: [width]
TYPE_CODE_POINTER = 8, // POINTER: [pointee type]
TYPE_CODE_FUNCTION_OLD = 9, // FUNCTION: [vararg, attrid, retty,
// paramty x N]
TYPE_CODE_HALF = 10, // HALF
TYPE_CODE_ARRAY = 11, // ARRAY: [numelts, eltty]
TYPE_CODE_VECTOR = 12, // VECTOR: [numelts, eltty]
// These are not with the other floating point types because they're
// a late addition, and putting them in the right place breaks
// binary compatibility.
TYPE_CODE_X86_FP80 = 13, // X86 LONG DOUBLE
TYPE_CODE_FP128 = 14, // LONG DOUBLE (112 bit mantissa)
TYPE_CODE_PPC_FP128 = 15, // PPC LONG DOUBLE (2 doubles)
TYPE_CODE_METADATA = 16, // METADATA
TYPE_CODE_X86_MMX = 17, // X86 MMX
TYPE_CODE_STRUCT_ANON = 18, // STRUCT_ANON: [ispacked, eltty x N]
TYPE_CODE_STRUCT_NAME = 19, // STRUCT_NAME: [strchr x N]
TYPE_CODE_STRUCT_NAMED = 20, // STRUCT_NAMED: [ispacked, eltty x N]
TYPE_CODE_FUNCTION = 21, // FUNCTION: [vararg, retty, paramty x N]
TYPE_CODE_TOKEN = 22 // TOKEN
};
enum OperandBundleTagCode {
OPERAND_BUNDLE_TAG = 1, // TAG: [strchr x N]
};
enum SyncScopeNameCode {
SYNC_SCOPE_NAME = 1,
};
// Value symbol table codes.
enum ValueSymtabCodes {
VST_CODE_ENTRY = 1, // VST_ENTRY: [valueid, namechar x N]
VST_CODE_BBENTRY = 2, // VST_BBENTRY: [bbid, namechar x N]
VST_CODE_FNENTRY = 3, // VST_FNENTRY: [valueid, offset, namechar x N]
// VST_COMBINED_ENTRY: [valueid, refguid]
VST_CODE_COMBINED_ENTRY = 5
};
// The module path symbol table only has one code (MST_CODE_ENTRY).
enum ModulePathSymtabCodes {
MST_CODE_ENTRY = 1, // MST_ENTRY: [modid, namechar x N]
MST_CODE_HASH = 2, // MST_HASH: [5*i32]
};
// The summary section uses different codes in the per-module
// and combined index cases.
enum GlobalValueSummarySymtabCodes {
// PERMODULE: [valueid, flags, instcount, numrefs, numrefs x valueid,
// n x (valueid)]
FS_PERMODULE = 1,
// PERMODULE_PROFILE: [valueid, flags, instcount, numrefs,
// numrefs x valueid,
// n x (valueid, hotness)]
FS_PERMODULE_PROFILE = 2,
// PERMODULE_GLOBALVAR_INIT_REFS: [valueid, flags, n x valueid]
FS_PERMODULE_GLOBALVAR_INIT_REFS = 3,
// COMBINED: [valueid, modid, flags, instcount, numrefs, numrefs x valueid,
// n x (valueid)]
FS_COMBINED = 4,
// COMBINED_PROFILE: [valueid, modid, flags, instcount, numrefs,
// numrefs x valueid,
// n x (valueid, hotness)]
FS_COMBINED_PROFILE = 5,
// COMBINED_GLOBALVAR_INIT_REFS: [valueid, modid, flags, n x valueid]
FS_COMBINED_GLOBALVAR_INIT_REFS = 6,
// ALIAS: [valueid, flags, valueid]
FS_ALIAS = 7,
// COMBINED_ALIAS: [valueid, modid, flags, valueid]
FS_COMBINED_ALIAS = 8,
// COMBINED_ORIGINAL_NAME: [original_name_hash]
FS_COMBINED_ORIGINAL_NAME = 9,
// VERSION of the summary, bumped when adding flags for instance.
FS_VERSION = 10,
// The list of llvm.type.test type identifiers used by the following function
// that are used other than by an llvm.assume.
// [n x typeid]
FS_TYPE_TESTS = 11,
// The list of virtual calls made by this function using
// llvm.assume(llvm.type.test) intrinsics that do not have all constant
// integer arguments.
// [n x (typeid, offset)]
FS_TYPE_TEST_ASSUME_VCALLS = 12,
// The list of virtual calls made by this function using
// llvm.type.checked.load intrinsics that do not have all constant integer
// arguments.
// [n x (typeid, offset)]
FS_TYPE_CHECKED_LOAD_VCALLS = 13,
// Identifies a virtual call made by this function using an
// llvm.assume(llvm.type.test) intrinsic with all constant integer arguments.
// [typeid, offset, n x arg]
FS_TYPE_TEST_ASSUME_CONST_VCALL = 14,
// Identifies a virtual call made by this function using an
// llvm.type.checked.load intrinsic with all constant integer arguments.
// [typeid, offset, n x arg]
FS_TYPE_CHECKED_LOAD_CONST_VCALL = 15,
// Assigns a GUID to a value ID. This normally appears only in combined
// summaries, but it can also appear in per-module summaries for PGO data.
// [valueid, guid]
FS_VALUE_GUID = 16,
// The list of local functions with CFI jump tables. Function names are
// strings in strtab.
// [n * name]
FS_CFI_FUNCTION_DEFS = 17,
// The list of external functions with CFI jump tables. Function names are
// strings in strtab.
// [n * name]
FS_CFI_FUNCTION_DECLS = 18,
};
enum MetadataCodes {
METADATA_STRING_OLD = 1, // MDSTRING: [values]
METADATA_VALUE = 2, // VALUE: [type num, value num]
METADATA_NODE = 3, // NODE: [n x md num]
METADATA_NAME = 4, // STRING: [values]
METADATA_DISTINCT_NODE = 5, // DISTINCT_NODE: [n x md num]
METADATA_KIND = 6, // [n x [id, name]]
METADATA_LOCATION = 7, // [distinct, line, col, scope, inlined-at?]
METADATA_OLD_NODE = 8, // OLD_NODE: [n x (type num, value num)]
METADATA_OLD_FN_NODE = 9, // OLD_FN_NODE: [n x (type num, value num)]
METADATA_NAMED_NODE = 10, // NAMED_NODE: [n x mdnodes]
METADATA_ATTACHMENT = 11, // [m x [value, [n x [id, mdnode]]]
METADATA_GENERIC_DEBUG = 12, // [distinct, tag, vers, header, n x md num]
METADATA_SUBRANGE = 13, // [distinct, count, lo]
METADATA_ENUMERATOR = 14, // [distinct, value, name]
METADATA_BASIC_TYPE = 15, // [distinct, tag, name, size, align, enc]
METADATA_FILE = 16, // [distinct, filename, directory, checksumkind, checksum]
METADATA_DERIVED_TYPE = 17, // [distinct, ...]
METADATA_COMPOSITE_TYPE = 18, // [distinct, ...]
METADATA_SUBROUTINE_TYPE = 19, // [distinct, flags, types, cc]
METADATA_COMPILE_UNIT = 20, // [distinct, ...]
METADATA_SUBPROGRAM = 21, // [distinct, ...]
METADATA_LEXICAL_BLOCK = 22, // [distinct, scope, file, line, column]
METADATA_LEXICAL_BLOCK_FILE = 23, //[distinct, scope, file, discriminator]
METADATA_NAMESPACE = 24, // [distinct, scope, file, name, line, exportSymbols]
METADATA_TEMPLATE_TYPE = 25, // [distinct, scope, name, type, ...]
METADATA_TEMPLATE_VALUE = 26, // [distinct, scope, name, type, value, ...]
METADATA_GLOBAL_VAR = 27, // [distinct, ...]
METADATA_LOCAL_VAR = 28, // [distinct, ...]
METADATA_EXPRESSION = 29, // [distinct, n x element]
METADATA_OBJC_PROPERTY = 30, // [distinct, name, file, line, ...]
METADATA_IMPORTED_ENTITY = 31, // [distinct, tag, scope, entity, line, name]
METADATA_MODULE = 32, // [distinct, scope, name, ...]
METADATA_MACRO = 33, // [distinct, macinfo, line, name, value]
METADATA_MACRO_FILE = 34, // [distinct, macinfo, line, file, ...]
METADATA_STRINGS = 35, // [count, offset] blob([lengths][chars])
METADATA_GLOBAL_DECL_ATTACHMENT = 36, // [valueid, n x [id, mdnode]]
METADATA_GLOBAL_VAR_EXPR = 37, // [distinct, var, expr]
METADATA_INDEX_OFFSET = 38, // [offset]
METADATA_INDEX = 39, // [bitpos]
};
// The constants block (CONSTANTS_BLOCK_ID) describes emission for each
// constant and maintains an implicit current type value.
enum ConstantsCodes {
CST_CODE_SETTYPE = 1, // SETTYPE: [typeid]
CST_CODE_NULL = 2, // NULL
CST_CODE_UNDEF = 3, // UNDEF
CST_CODE_INTEGER = 4, // INTEGER: [intval]
CST_CODE_WIDE_INTEGER = 5, // WIDE_INTEGER: [n x intval]
CST_CODE_FLOAT = 6, // FLOAT: [fpval]
CST_CODE_AGGREGATE = 7, // AGGREGATE: [n x value number]
CST_CODE_STRING = 8, // STRING: [values]
CST_CODE_CSTRING = 9, // CSTRING: [values]
CST_CODE_CE_BINOP = 10, // CE_BINOP: [opcode, opval, opval]
CST_CODE_CE_CAST = 11, // CE_CAST: [opcode, opty, opval]
CST_CODE_CE_GEP = 12, // CE_GEP: [n x operands]
CST_CODE_CE_SELECT = 13, // CE_SELECT: [opval, opval, opval]
CST_CODE_CE_EXTRACTELT = 14, // CE_EXTRACTELT: [opty, opval, opval]
CST_CODE_CE_INSERTELT = 15, // CE_INSERTELT: [opval, opval, opval]
CST_CODE_CE_SHUFFLEVEC = 16, // CE_SHUFFLEVEC: [opval, opval, opval]
CST_CODE_CE_CMP = 17, // CE_CMP: [opty, opval, opval, pred]
CST_CODE_INLINEASM_OLD = 18, // INLINEASM: [sideeffect|alignstack,
// asmstr,conststr]
CST_CODE_CE_SHUFVEC_EX = 19, // SHUFVEC_EX: [opty, opval, opval, opval]
CST_CODE_CE_INBOUNDS_GEP = 20, // INBOUNDS_GEP: [n x operands]
CST_CODE_BLOCKADDRESS = 21, // CST_CODE_BLOCKADDRESS [fnty, fnval, bb#]
CST_CODE_DATA = 22, // DATA: [n x elements]
CST_CODE_INLINEASM = 23, // INLINEASM: [sideeffect|alignstack|
// asmdialect,asmstr,conststr]
CST_CODE_CE_GEP_WITH_INRANGE_INDEX = 24, // [opty, flags, n x operands]
};
/// CastOpcodes - These are values used in the bitcode files to encode which
/// cast a CST_CODE_CE_CAST or a XXX refers to. The values of these enums
/// have no fixed relation to the LLVM IR enum values. Changing these will
/// break compatibility with old files.
enum CastOpcodes {
CAST_TRUNC = 0,
CAST_ZEXT = 1,
CAST_SEXT = 2,
CAST_FPTOUI = 3,
CAST_FPTOSI = 4,
CAST_UITOFP = 5,
CAST_SITOFP = 6,
CAST_FPTRUNC = 7,
CAST_FPEXT = 8,
CAST_PTRTOINT = 9,
CAST_INTTOPTR = 10,
CAST_BITCAST = 11,
CAST_ADDRSPACECAST = 12
};
/// BinaryOpcodes - These are values used in the bitcode files to encode which
/// binop a CST_CODE_CE_BINOP or a XXX refers to. The values of these enums
/// have no fixed relation to the LLVM IR enum values. Changing these will
/// break compatibility with old files.
enum BinaryOpcodes {
BINOP_ADD = 0,
BINOP_SUB = 1,
BINOP_MUL = 2,
BINOP_UDIV = 3,
BINOP_SDIV = 4, // overloaded for FP
BINOP_UREM = 5,
BINOP_SREM = 6, // overloaded for FP
BINOP_SHL = 7,
BINOP_LSHR = 8,
BINOP_ASHR = 9,
BINOP_AND = 10,
BINOP_OR = 11,
BINOP_XOR = 12
};
/// These are values used in the bitcode files to encode AtomicRMW operations.
/// The values of these enums have no fixed relation to the LLVM IR enum
/// values. Changing these will break compatibility with old files.
enum RMWOperations {
RMW_XCHG = 0,
RMW_ADD = 1,
RMW_SUB = 2,
RMW_AND = 3,
RMW_NAND = 4,
RMW_OR = 5,
RMW_XOR = 6,
RMW_MAX = 7,
RMW_MIN = 8,
RMW_UMAX = 9,
RMW_UMIN = 10
};
/// OverflowingBinaryOperatorOptionalFlags - Flags for serializing
/// OverflowingBinaryOperator's SubclassOptionalData contents.
enum OverflowingBinaryOperatorOptionalFlags {
OBO_NO_UNSIGNED_WRAP = 0,
OBO_NO_SIGNED_WRAP = 1
};
/// PossiblyExactOperatorOptionalFlags - Flags for serializing
/// PossiblyExactOperator's SubclassOptionalData contents.
enum PossiblyExactOperatorOptionalFlags { PEO_EXACT = 0 };
/// Encoded AtomicOrdering values.
enum AtomicOrderingCodes {
ORDERING_NOTATOMIC = 0,
ORDERING_UNORDERED = 1,
ORDERING_MONOTONIC = 2,
ORDERING_ACQUIRE = 3,
ORDERING_RELEASE = 4,
ORDERING_ACQREL = 5,
ORDERING_SEQCST = 6
};
/// Markers and flags for call instruction.
enum CallMarkersFlags {
CALL_TAIL = 0,
CALL_CCONV = 1,
CALL_MUSTTAIL = 14,
CALL_EXPLICIT_TYPE = 15,
CALL_NOTAIL = 16,
CALL_FMF = 17 // Call has optional fast-math-flags.
};
// The function body block (FUNCTION_BLOCK_ID) describes function bodies. It
// can contain a constant block (CONSTANTS_BLOCK_ID).
enum FunctionCodes {
FUNC_CODE_DECLAREBLOCKS = 1, // DECLAREBLOCKS: [n]
FUNC_CODE_INST_BINOP = 2, // BINOP: [opcode, ty, opval, opval]
FUNC_CODE_INST_CAST = 3, // CAST: [opcode, ty, opty, opval]
FUNC_CODE_INST_GEP_OLD = 4, // GEP: [n x operands]
FUNC_CODE_INST_SELECT = 5, // SELECT: [ty, opval, opval, opval]
FUNC_CODE_INST_EXTRACTELT = 6, // EXTRACTELT: [opty, opval, opval]
FUNC_CODE_INST_INSERTELT = 7, // INSERTELT: [ty, opval, opval, opval]
FUNC_CODE_INST_SHUFFLEVEC = 8, // SHUFFLEVEC: [ty, opval, opval, opval]
FUNC_CODE_INST_CMP = 9, // CMP: [opty, opval, opval, pred]
FUNC_CODE_INST_RET = 10, // RET: [opty,opval<both optional>]
FUNC_CODE_INST_BR = 11, // BR: [bb#, bb#, cond] or [bb#]
FUNC_CODE_INST_SWITCH = 12, // SWITCH: [opty, op0, op1, ...]
FUNC_CODE_INST_INVOKE = 13, // INVOKE: [attr, fnty, op0,op1, ...]
// 14 is unused.
FUNC_CODE_INST_UNREACHABLE = 15, // UNREACHABLE
FUNC_CODE_INST_PHI = 16, // PHI: [ty, val0,bb0, ...]
// 17 is unused.
// 18 is unused.
FUNC_CODE_INST_ALLOCA = 19, // ALLOCA: [instty, opty, op, align]
FUNC_CODE_INST_LOAD = 20, // LOAD: [opty, op, align, vol]
// 21 is unused.
// 22 is unused.
FUNC_CODE_INST_VAARG = 23, // VAARG: [valistty, valist, instty]
// This store code encodes the pointer type, rather than the value type
// this is so information only available in the pointer type (e.g. address
// spaces) is retained.
FUNC_CODE_INST_STORE_OLD = 24, // STORE: [ptrty,ptr,val, align, vol]
// 25 is unused.
FUNC_CODE_INST_EXTRACTVAL = 26, // EXTRACTVAL: [n x operands]
FUNC_CODE_INST_INSERTVAL = 27, // INSERTVAL: [n x operands]
// fcmp/icmp returning Int1TY or vector of Int1Ty. Same as CMP, exists to
// support legacy vicmp/vfcmp instructions.
FUNC_CODE_INST_CMP2 = 28, // CMP2: [opty, opval, opval, pred]
// new select on i1 or [N x i1]
FUNC_CODE_INST_VSELECT = 29, // VSELECT: [ty,opval,opval,predty,pred]
FUNC_CODE_INST_INBOUNDS_GEP_OLD = 30, // INBOUNDS_GEP: [n x operands]
FUNC_CODE_INST_INDIRECTBR = 31, // INDIRECTBR: [opty, op0, op1, ...]
// 32 is unused.
FUNC_CODE_DEBUG_LOC_AGAIN = 33, // DEBUG_LOC_AGAIN
FUNC_CODE_INST_CALL = 34, // CALL: [attr, cc, fnty, fnid, args...]
FUNC_CODE_DEBUG_LOC = 35, // DEBUG_LOC: [Line,Col,ScopeVal, IAVal]
FUNC_CODE_INST_FENCE = 36, // FENCE: [ordering, synchscope]
FUNC_CODE_INST_CMPXCHG_OLD = 37, // CMPXCHG: [ptrty,ptr,cmp,new, align, vol,
// ordering, synchscope]
FUNC_CODE_INST_ATOMICRMW = 38, // ATOMICRMW: [ptrty,ptr,val, operation,
// align, vol,
// ordering, synchscope]
FUNC_CODE_INST_RESUME = 39, // RESUME: [opval]
FUNC_CODE_INST_LANDINGPAD_OLD =
40, // LANDINGPAD: [ty,val,val,num,id0,val0...]
FUNC_CODE_INST_LOADATOMIC = 41, // LOAD: [opty, op, align, vol,
// ordering, synchscope]
FUNC_CODE_INST_STOREATOMIC_OLD = 42, // STORE: [ptrty,ptr,val, align, vol
// ordering, synchscope]
FUNC_CODE_INST_GEP = 43, // GEP: [inbounds, n x operands]
FUNC_CODE_INST_STORE = 44, // STORE: [ptrty,ptr,valty,val, align, vol]
FUNC_CODE_INST_STOREATOMIC = 45, // STORE: [ptrty,ptr,val, align, vol
FUNC_CODE_INST_CMPXCHG = 46, // CMPXCHG: [ptrty,ptr,valty,cmp,new, align,
// vol,ordering,synchscope]
FUNC_CODE_INST_LANDINGPAD = 47, // LANDINGPAD: [ty,val,num,id0,val0...]
FUNC_CODE_INST_CLEANUPRET = 48, // CLEANUPRET: [val] or [val,bb#]
FUNC_CODE_INST_CATCHRET = 49, // CATCHRET: [val,bb#]
FUNC_CODE_INST_CATCHPAD = 50, // CATCHPAD: [bb#,bb#,num,args...]
FUNC_CODE_INST_CLEANUPPAD = 51, // CLEANUPPAD: [num,args...]
FUNC_CODE_INST_CATCHSWITCH =
52, // CATCHSWITCH: [num,args...] or [num,args...,bb]
// 53 is unused.
// 54 is unused.
FUNC_CODE_OPERAND_BUNDLE = 55, // OPERAND_BUNDLE: [tag#, value...]
};
enum UseListCodes {
USELIST_CODE_DEFAULT = 1, // DEFAULT: [index..., value-id]
USELIST_CODE_BB = 2 // BB: [index..., bb-id]
};
enum AttributeKindCodes {
// = 0 is unused
ATTR_KIND_ALIGNMENT = 1,
ATTR_KIND_ALWAYS_INLINE = 2,
ATTR_KIND_BY_VAL = 3,
ATTR_KIND_INLINE_HINT = 4,
ATTR_KIND_IN_REG = 5,
ATTR_KIND_MIN_SIZE = 6,
ATTR_KIND_NAKED = 7,
ATTR_KIND_NEST = 8,
ATTR_KIND_NO_ALIAS = 9,
ATTR_KIND_NO_BUILTIN = 10,
ATTR_KIND_NO_CAPTURE = 11,
ATTR_KIND_NO_DUPLICATE = 12,
ATTR_KIND_NO_IMPLICIT_FLOAT = 13,
ATTR_KIND_NO_INLINE = 14,
ATTR_KIND_NON_LAZY_BIND = 15,
ATTR_KIND_NO_RED_ZONE = 16,
ATTR_KIND_NO_RETURN = 17,
ATTR_KIND_NO_UNWIND = 18,
ATTR_KIND_OPTIMIZE_FOR_SIZE = 19,
ATTR_KIND_READ_NONE = 20,
ATTR_KIND_READ_ONLY = 21,
ATTR_KIND_RETURNED = 22,
ATTR_KIND_RETURNS_TWICE = 23,
ATTR_KIND_S_EXT = 24,
ATTR_KIND_STACK_ALIGNMENT = 25,
ATTR_KIND_STACK_PROTECT = 26,
ATTR_KIND_STACK_PROTECT_REQ = 27,
ATTR_KIND_STACK_PROTECT_STRONG = 28,
ATTR_KIND_STRUCT_RET = 29,
ATTR_KIND_SANITIZE_ADDRESS = 30,
ATTR_KIND_SANITIZE_THREAD = 31,
ATTR_KIND_SANITIZE_MEMORY = 32,
ATTR_KIND_UW_TABLE = 33,
ATTR_KIND_Z_EXT = 34,
ATTR_KIND_BUILTIN = 35,
ATTR_KIND_COLD = 36,
ATTR_KIND_OPTIMIZE_NONE = 37,
ATTR_KIND_IN_ALLOCA = 38,
ATTR_KIND_NON_NULL = 39,
ATTR_KIND_JUMP_TABLE = 40,
ATTR_KIND_DEREFERENCEABLE = 41,
ATTR_KIND_DEREFERENCEABLE_OR_NULL = 42,
ATTR_KIND_CONVERGENT = 43,
ATTR_KIND_SAFESTACK = 44,
ATTR_KIND_ARGMEMONLY = 45,
ATTR_KIND_SWIFT_SELF = 46,
ATTR_KIND_SWIFT_ERROR = 47,
ATTR_KIND_NO_RECURSE = 48,
ATTR_KIND_INACCESSIBLEMEM_ONLY = 49,
ATTR_KIND_INACCESSIBLEMEM_OR_ARGMEMONLY = 50,
ATTR_KIND_ALLOC_SIZE = 51,
ATTR_KIND_WRITEONLY = 52,
ATTR_KIND_SPECULATABLE = 53,
ATTR_KIND_STRICT_FP = 54,
};
enum ComdatSelectionKindCodes {
COMDAT_SELECTION_KIND_ANY = 1,
COMDAT_SELECTION_KIND_EXACT_MATCH = 2,
COMDAT_SELECTION_KIND_LARGEST = 3,
COMDAT_SELECTION_KIND_NO_DUPLICATES = 4,
COMDAT_SELECTION_KIND_SAME_SIZE = 5,
};
enum StrtabCodes {
STRTAB_BLOB = 1,
};
enum SymtabCodes {
SYMTAB_BLOB = 1,
};
} // End bitc namespace
} // End llvm namespace
#endif