X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=tools%2Fllvm-bcanalyzer%2Fllvm-bcanalyzer.cpp;h=69880a425a1ddc4ed60841f16b306d135f6699f6;hb=98e3b1abbffa159bb1da01b9f4a123f10f2e5748;hp=4390f4d75ea48ae685a4c380691eb7839fcbe5a2;hpb=1772b12d1332c7fb23155c20e7eeeed92200d053;p=oota-llvm.git diff --git a/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp b/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp index 4390f4d75ea..69880a425a1 100644 --- a/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp +++ b/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp @@ -1,237 +1,314 @@ -//===-- llvm-bcanalyzer.cpp - Byte Code Analyzer --------------------------===// +//===-- llvm-bcanalyzer.cpp - Bitcode Analyzer --------------------------===// // // The LLVM Compiler Infrastructure // -// This file was developed by Reid Spencer and is distributed under the -// University of Illinois Open Source License. See LICENSE.TXT for details. +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// // // This tool may be invoked in the following manner: -// llvm-bcanalyzer [options] - Read LLVM bytecode from stdin -// llvm-bcanalyzer [options] x.bc - Read LLVM bytecode from the x.bc file +// llvm-bcanalyzer [options] - Read LLVM bitcode from stdin +// llvm-bcanalyzer [options] x.bc - Read LLVM bitcode from the x.bc file // // Options: // --help - Output information about command line switches -// --nodetails - Don't print out detailed informaton about individual -// blocks and functions -// --dump - Dump low-level bytecode structure in readable format +// --dump - Dump low-level bitcode structure in readable format // -// This tool provides analytical information about a bytecode file. It is -// intended as an aid to developers of bytecode reading and writing software. It -// produces on std::out a summary of the bytecode file that shows various +// This tool provides analytical information about a bitcode file. It is +// intended as an aid to developers of bitcode reading and writing software. It +// produces on std::out a summary of the bitcode file that shows various // statistics about the contents of the file. By default this information is -// detailed and contains information about individual bytecode blocks and the -// functions in the module. To avoid this more detailed output, use the -// -nodetails option to limit the output to just module level information. -// The tool is also able to print a bytecode file in a straight forward text +// detailed and contains information about individual bitcode blocks and the +// functions in the module. +// The tool is also able to print a bitcode file in a straight forward text // format that shows the containment and relationships of the information in -// the bytecode file (-dump option). +// the bitcode file (-dump option). // //===----------------------------------------------------------------------===// -#include "llvm/Analysis/Verifier.h" #include "llvm/Bitcode/BitstreamReader.h" #include "llvm/Bitcode/LLVMBitCodes.h" -#include "llvm/Bytecode/Analyzer.h" +#include "llvm/Bitcode/ReaderWriter.h" +#include "llvm/IR/Verifier.h" +#include "llvm/ADT/Optional.h" #include "llvm/Support/CommandLine.h" -#include "llvm/Support/Compressor.h" +#include "llvm/Support/Format.h" #include "llvm/Support/ManagedStatic.h" #include "llvm/Support/MemoryBuffer.h" -#include "llvm/System/Signals.h" -#include -#include +#include "llvm/Support/PrettyStackTrace.h" +#include "llvm/Support/Signals.h" +#include "llvm/Support/raw_ostream.h" +#include +#include +#include +#include using namespace llvm; static cl::opt - InputFilename(cl::Positional, cl::desc(""), cl::init("-")); + InputFilename(cl::Positional, cl::desc(""), cl::init("-")); -static cl::opt - OutputFilename("-o", cl::init("-"), cl::desc("")); - -static cl::opt NoDetails("nodetails", cl::desc("Skip detailed output")); -static cl::opt Dump("dump", cl::desc("Dump low level bytecode trace")); -static cl::opt Verify("verify", cl::desc("Progressively verify module")); +static cl::opt Dump("dump", cl::desc("Dump low level bitcode trace")); //===----------------------------------------------------------------------===// // Bitcode specific analysis. //===----------------------------------------------------------------------===// -static cl::opt Bitcode("bitcode", cl::desc("Read a bitcode file")); +static cl::opt NoHistogram("disable-histogram", + cl::desc("Do not print per-code histogram")); static cl::opt NonSymbolic("non-symbolic", - cl::desc("Emit numberic info in dump even if" + cl::desc("Emit numeric info in dump even if" " symbolic info is available")); -/// CurStreamType - If we can sniff the flavor of this stream, we can produce -/// better dump info. -static enum { +static cl::opt + BlockInfoFilename("block-info", + cl::desc("Use the BLOCK_INFO from the given file")); + +namespace { + +/// CurStreamTypeType - A type for CurStreamType +enum CurStreamTypeType { UnknownBitstream, LLVMIRBitstream -} CurStreamType; +}; +} /// GetBlockName - Return a symbolic block name if known, otherwise return /// null. -static const char *GetBlockName(unsigned BlockID) { +static const char *GetBlockName(unsigned BlockID, + const BitstreamReader &StreamFile, + CurStreamTypeType CurStreamType) { // Standard blocks for all bitcode files. if (BlockID < bitc::FIRST_APPLICATION_BLOCKID) { if (BlockID == bitc::BLOCKINFO_BLOCK_ID) return "BLOCKINFO_BLOCK"; - return 0; + return nullptr; } - - if (CurStreamType != LLVMIRBitstream) return 0; - + + // Check to see if we have a blockinfo record for this block, with a name. + if (const BitstreamReader::BlockInfo *Info = + StreamFile.getBlockInfo(BlockID)) { + if (!Info->Name.empty()) + return Info->Name.c_str(); + } + + + if (CurStreamType != LLVMIRBitstream) return nullptr; + switch (BlockID) { - default: return 0; - case bitc::MODULE_BLOCK_ID: return "MODULE_BLOCK"; - case bitc::PARAMATTR_BLOCK_ID: return "PARAMATTR_BLOCK"; - case bitc::TYPE_BLOCK_ID: return "TYPE_BLOCK"; - case bitc::CONSTANTS_BLOCK_ID: return "CONSTANTS_BLOCK"; - case bitc::FUNCTION_BLOCK_ID: return "FUNCTION_BLOCK"; - case bitc::TYPE_SYMTAB_BLOCK_ID: return "TYPE_SYMTAB"; - case bitc::VALUE_SYMTAB_BLOCK_ID: return "VALUE_SYMTAB"; + default: return nullptr; + case bitc::MODULE_BLOCK_ID: return "MODULE_BLOCK"; + case bitc::PARAMATTR_BLOCK_ID: return "PARAMATTR_BLOCK"; + case bitc::PARAMATTR_GROUP_BLOCK_ID: return "PARAMATTR_GROUP_BLOCK_ID"; + case bitc::TYPE_BLOCK_ID_NEW: return "TYPE_BLOCK_ID"; + case bitc::CONSTANTS_BLOCK_ID: return "CONSTANTS_BLOCK"; + case bitc::FUNCTION_BLOCK_ID: return "FUNCTION_BLOCK"; + case bitc::VALUE_SYMTAB_BLOCK_ID: return "VALUE_SYMTAB"; + case bitc::METADATA_BLOCK_ID: return "METADATA_BLOCK"; + case bitc::METADATA_ATTACHMENT_ID: return "METADATA_ATTACHMENT_BLOCK"; + case bitc::USELIST_BLOCK_ID: return "USELIST_BLOCK_ID"; } } /// GetCodeName - Return a symbolic code name if known, otherwise return /// null. -static const char *GetCodeName(unsigned CodeID, unsigned BlockID) { +static const char *GetCodeName(unsigned CodeID, unsigned BlockID, + const BitstreamReader &StreamFile, + CurStreamTypeType CurStreamType) { // Standard blocks for all bitcode files. if (BlockID < bitc::FIRST_APPLICATION_BLOCKID) { if (BlockID == bitc::BLOCKINFO_BLOCK_ID) { switch (CodeID) { - default: return 0; - case bitc::MODULE_CODE_VERSION: return "VERSION"; + default: return nullptr; + case bitc::BLOCKINFO_CODE_SETBID: return "SETBID"; + case bitc::BLOCKINFO_CODE_BLOCKNAME: return "BLOCKNAME"; + case bitc::BLOCKINFO_CODE_SETRECORDNAME: return "SETRECORDNAME"; } } - return 0; + return nullptr; + } + + // Check to see if we have a blockinfo record for this record, with a name. + if (const BitstreamReader::BlockInfo *Info = + StreamFile.getBlockInfo(BlockID)) { + for (unsigned i = 0, e = Info->RecordNames.size(); i != e; ++i) + if (Info->RecordNames[i].first == CodeID) + return Info->RecordNames[i].second.c_str(); } - - - if (CurStreamType != LLVMIRBitstream) return 0; - + + + if (CurStreamType != LLVMIRBitstream) return nullptr; + switch (BlockID) { - default: return 0; + default: return nullptr; case bitc::MODULE_BLOCK_ID: switch (CodeID) { - default: return 0; + default: return nullptr; case bitc::MODULE_CODE_VERSION: return "VERSION"; case bitc::MODULE_CODE_TRIPLE: return "TRIPLE"; case bitc::MODULE_CODE_DATALAYOUT: return "DATALAYOUT"; case bitc::MODULE_CODE_ASM: return "ASM"; case bitc::MODULE_CODE_SECTIONNAME: return "SECTIONNAME"; - case bitc::MODULE_CODE_DEPLIB: return "DEPLIB"; + case bitc::MODULE_CODE_DEPLIB: return "DEPLIB"; // FIXME: Remove in 4.0 case bitc::MODULE_CODE_GLOBALVAR: return "GLOBALVAR"; case bitc::MODULE_CODE_FUNCTION: return "FUNCTION"; case bitc::MODULE_CODE_ALIAS: return "ALIAS"; case bitc::MODULE_CODE_PURGEVALS: return "PURGEVALS"; + case bitc::MODULE_CODE_GCNAME: return "GCNAME"; } case bitc::PARAMATTR_BLOCK_ID: switch (CodeID) { - default: return 0; - case bitc::PARAMATTR_CODE_ENTRY: return "ENTRY"; + default: return nullptr; + case bitc::PARAMATTR_CODE_ENTRY_OLD: return "ENTRY"; + case bitc::PARAMATTR_CODE_ENTRY: return "ENTRY"; + case bitc::PARAMATTR_GRP_CODE_ENTRY: return "ENTRY"; } - case bitc::TYPE_BLOCK_ID: + case bitc::TYPE_BLOCK_ID_NEW: switch (CodeID) { - default: return 0; - case bitc::TYPE_CODE_NUMENTRY: return "NUMENTRY"; - case bitc::TYPE_CODE_VOID: return "VOID"; - case bitc::TYPE_CODE_FLOAT: return "FLOAT"; - case bitc::TYPE_CODE_DOUBLE: return "DOUBLE"; - case bitc::TYPE_CODE_LABEL: return "LABEL"; - case bitc::TYPE_CODE_OPAQUE: return "OPAQUE"; - case bitc::TYPE_CODE_INTEGER: return "INTEGER"; - case bitc::TYPE_CODE_POINTER: return "POINTER"; - case bitc::TYPE_CODE_FUNCTION: return "FUNCTION"; - case bitc::TYPE_CODE_STRUCT: return "STRUCT"; - case bitc::TYPE_CODE_ARRAY: return "ARRAY"; - case bitc::TYPE_CODE_VECTOR: return "VECTOR"; + default: return nullptr; + case bitc::TYPE_CODE_NUMENTRY: return "NUMENTRY"; + case bitc::TYPE_CODE_VOID: return "VOID"; + case bitc::TYPE_CODE_FLOAT: return "FLOAT"; + case bitc::TYPE_CODE_DOUBLE: return "DOUBLE"; + case bitc::TYPE_CODE_LABEL: return "LABEL"; + case bitc::TYPE_CODE_OPAQUE: return "OPAQUE"; + case bitc::TYPE_CODE_INTEGER: return "INTEGER"; + case bitc::TYPE_CODE_POINTER: return "POINTER"; + case bitc::TYPE_CODE_ARRAY: return "ARRAY"; + case bitc::TYPE_CODE_VECTOR: return "VECTOR"; + case bitc::TYPE_CODE_X86_FP80: return "X86_FP80"; + case bitc::TYPE_CODE_FP128: return "FP128"; + case bitc::TYPE_CODE_PPC_FP128: return "PPC_FP128"; + case bitc::TYPE_CODE_METADATA: return "METADATA"; + case bitc::TYPE_CODE_STRUCT_ANON: return "STRUCT_ANON"; + case bitc::TYPE_CODE_STRUCT_NAME: return "STRUCT_NAME"; + case bitc::TYPE_CODE_STRUCT_NAMED: return "STRUCT_NAMED"; + case bitc::TYPE_CODE_FUNCTION: return "FUNCTION"; } - + case bitc::CONSTANTS_BLOCK_ID: switch (CodeID) { - default: return 0; - case bitc::CST_CODE_SETTYPE: return "SETTYPE"; - case bitc::CST_CODE_NULL: return "NULL"; - case bitc::CST_CODE_UNDEF: return "UNDEF"; - case bitc::CST_CODE_INTEGER: return "INTEGER"; - case bitc::CST_CODE_WIDE_INTEGER: return "WIDE_INTEGER"; - case bitc::CST_CODE_FLOAT: return "FLOAT"; - case bitc::CST_CODE_AGGREGATE: return "AGGREGATE"; - case bitc::CST_CODE_CE_BINOP: return "CE_BINOP"; - case bitc::CST_CODE_CE_CAST: return "CE_CAST"; - case bitc::CST_CODE_CE_GEP: return "CE_GEP"; - case bitc::CST_CODE_CE_SELECT: return "CE_SELECT"; - case bitc::CST_CODE_CE_EXTRACTELT: return "CE_EXTRACTELT"; - case bitc::CST_CODE_CE_INSERTELT: return "CE_INSERTELT"; - case bitc::CST_CODE_CE_SHUFFLEVEC: return "CE_SHUFFLEVEC"; - case bitc::CST_CODE_CE_CMP: return "CE_CMP"; - } + default: return nullptr; + case bitc::CST_CODE_SETTYPE: return "SETTYPE"; + case bitc::CST_CODE_NULL: return "NULL"; + case bitc::CST_CODE_UNDEF: return "UNDEF"; + case bitc::CST_CODE_INTEGER: return "INTEGER"; + case bitc::CST_CODE_WIDE_INTEGER: return "WIDE_INTEGER"; + case bitc::CST_CODE_FLOAT: return "FLOAT"; + case bitc::CST_CODE_AGGREGATE: return "AGGREGATE"; + case bitc::CST_CODE_STRING: return "STRING"; + case bitc::CST_CODE_CSTRING: return "CSTRING"; + case bitc::CST_CODE_CE_BINOP: return "CE_BINOP"; + case bitc::CST_CODE_CE_CAST: return "CE_CAST"; + case bitc::CST_CODE_CE_GEP: return "CE_GEP"; + case bitc::CST_CODE_CE_INBOUNDS_GEP: return "CE_INBOUNDS_GEP"; + case bitc::CST_CODE_CE_SELECT: return "CE_SELECT"; + case bitc::CST_CODE_CE_EXTRACTELT: return "CE_EXTRACTELT"; + case bitc::CST_CODE_CE_INSERTELT: return "CE_INSERTELT"; + case bitc::CST_CODE_CE_SHUFFLEVEC: return "CE_SHUFFLEVEC"; + case bitc::CST_CODE_CE_CMP: return "CE_CMP"; + case bitc::CST_CODE_INLINEASM: return "INLINEASM"; + case bitc::CST_CODE_CE_SHUFVEC_EX: return "CE_SHUFVEC_EX"; + case bitc::CST_CODE_BLOCKADDRESS: return "CST_CODE_BLOCKADDRESS"; + case bitc::CST_CODE_DATA: return "DATA"; + } case bitc::FUNCTION_BLOCK_ID: switch (CodeID) { - default: return 0; + default: return nullptr; case bitc::FUNC_CODE_DECLAREBLOCKS: return "DECLAREBLOCKS"; - - case bitc::FUNC_CODE_INST_BINOP: return "INST_BINOP"; - case bitc::FUNC_CODE_INST_CAST: return "INST_CAST"; - case bitc::FUNC_CODE_INST_GEP: return "INST_GEP"; - case bitc::FUNC_CODE_INST_SELECT: return "INST_SELECT"; - case bitc::FUNC_CODE_INST_EXTRACTELT: return "INST_EXTRACTELT"; - case bitc::FUNC_CODE_INST_INSERTELT: return "INST_INSERTELT"; - case bitc::FUNC_CODE_INST_SHUFFLEVEC: return "INST_SHUFFLEVEC"; - case bitc::FUNC_CODE_INST_CMP: return "INST_CMP"; - - case bitc::FUNC_CODE_INST_RET: return "INST_RET"; - case bitc::FUNC_CODE_INST_BR: return "INST_BR"; - case bitc::FUNC_CODE_INST_SWITCH: return "INST_SWITCH"; - case bitc::FUNC_CODE_INST_INVOKE: return "INST_INVOKE"; - case bitc::FUNC_CODE_INST_UNWIND: return "INST_UNWIND"; - case bitc::FUNC_CODE_INST_UNREACHABLE: return "INST_UNREACHABLE"; - - case bitc::FUNC_CODE_INST_PHI: return "INST_PHI"; - case bitc::FUNC_CODE_INST_MALLOC: return "INST_MALLOC"; - case bitc::FUNC_CODE_INST_FREE: return "INST_FREE"; - case bitc::FUNC_CODE_INST_ALLOCA: return "INST_ALLOCA"; - case bitc::FUNC_CODE_INST_LOAD: return "INST_LOAD"; - case bitc::FUNC_CODE_INST_STORE: return "INST_STORE"; - case bitc::FUNC_CODE_INST_CALL: return "INST_CALL"; - case bitc::FUNC_CODE_INST_VAARG: return "INST_VAARG"; - } - case bitc::TYPE_SYMTAB_BLOCK_ID: - switch (CodeID) { - default: return 0; - case bitc::TST_CODE_ENTRY: return "ENTRY"; + + case bitc::FUNC_CODE_INST_BINOP: return "INST_BINOP"; + case bitc::FUNC_CODE_INST_CAST: return "INST_CAST"; + case bitc::FUNC_CODE_INST_GEP: return "INST_GEP"; + case bitc::FUNC_CODE_INST_INBOUNDS_GEP: return "INST_INBOUNDS_GEP"; + case bitc::FUNC_CODE_INST_SELECT: return "INST_SELECT"; + case bitc::FUNC_CODE_INST_EXTRACTELT: return "INST_EXTRACTELT"; + case bitc::FUNC_CODE_INST_INSERTELT: return "INST_INSERTELT"; + case bitc::FUNC_CODE_INST_SHUFFLEVEC: return "INST_SHUFFLEVEC"; + case bitc::FUNC_CODE_INST_CMP: return "INST_CMP"; + + case bitc::FUNC_CODE_INST_RET: return "INST_RET"; + case bitc::FUNC_CODE_INST_BR: return "INST_BR"; + case bitc::FUNC_CODE_INST_SWITCH: return "INST_SWITCH"; + case bitc::FUNC_CODE_INST_INVOKE: return "INST_INVOKE"; + case bitc::FUNC_CODE_INST_UNREACHABLE: return "INST_UNREACHABLE"; + + case bitc::FUNC_CODE_INST_PHI: return "INST_PHI"; + case bitc::FUNC_CODE_INST_ALLOCA: return "INST_ALLOCA"; + case bitc::FUNC_CODE_INST_LOAD: return "INST_LOAD"; + case bitc::FUNC_CODE_INST_VAARG: return "INST_VAARG"; + case bitc::FUNC_CODE_INST_STORE: return "INST_STORE"; + case bitc::FUNC_CODE_INST_EXTRACTVAL: return "INST_EXTRACTVAL"; + case bitc::FUNC_CODE_INST_INSERTVAL: return "INST_INSERTVAL"; + case bitc::FUNC_CODE_INST_CMP2: return "INST_CMP2"; + case bitc::FUNC_CODE_INST_VSELECT: return "INST_VSELECT"; + case bitc::FUNC_CODE_DEBUG_LOC_AGAIN: return "DEBUG_LOC_AGAIN"; + case bitc::FUNC_CODE_INST_CALL: return "INST_CALL"; + case bitc::FUNC_CODE_DEBUG_LOC: return "DEBUG_LOC"; } case bitc::VALUE_SYMTAB_BLOCK_ID: switch (CodeID) { - default: return 0; + default: return nullptr; case bitc::VST_CODE_ENTRY: return "ENTRY"; case bitc::VST_CODE_BBENTRY: return "BBENTRY"; } + case bitc::METADATA_ATTACHMENT_ID: + switch(CodeID) { + default:return nullptr; + case bitc::METADATA_ATTACHMENT: return "METADATA_ATTACHMENT"; + } + case bitc::METADATA_BLOCK_ID: + switch(CodeID) { + default:return nullptr; + case bitc::METADATA_STRING: return "METADATA_STRING"; + case bitc::METADATA_NAME: return "METADATA_NAME"; + case bitc::METADATA_KIND: return "METADATA_KIND"; + case bitc::METADATA_NODE: return "METADATA_NODE"; + case bitc::METADATA_VALUE: return "METADATA_VALUE"; + case bitc::METADATA_OLD_NODE: return "METADATA_OLD_NODE"; + case bitc::METADATA_OLD_FN_NODE: return "METADATA_OLD_FN_NODE"; + case bitc::METADATA_NAMED_NODE: return "METADATA_NAMED_NODE"; + } + case bitc::USELIST_BLOCK_ID: + switch(CodeID) { + default:return nullptr; + case bitc::USELIST_CODE_DEFAULT: return "USELIST_CODE_DEFAULT"; + case bitc::USELIST_CODE_BB: return "USELIST_CODE_BB"; + } } } +struct PerRecordStats { + unsigned NumInstances; + unsigned NumAbbrev; + uint64_t TotalBits; + + PerRecordStats() : NumInstances(0), NumAbbrev(0), TotalBits(0) {} +}; struct PerBlockIDStats { /// NumInstances - This the number of times this block ID has been seen. unsigned NumInstances; - + /// NumBits - The total size in bits of all of these blocks. uint64_t NumBits; - + /// NumSubBlocks - The total number of blocks these blocks contain. unsigned NumSubBlocks; - + /// NumAbbrevs - The total number of abbreviations. unsigned NumAbbrevs; - - /// NumRecords - The total number of records these blocks contain, and the + + /// NumRecords - The total number of records these blocks contain, and the /// number that are abbreviated. unsigned NumRecords, NumAbbreviatedRecords; - + + /// CodeFreq - Keep track of the number of times we see each code. + std::vector CodeFreq; + PerBlockIDStats() : NumInstances(0), NumBits(0), NumSubBlocks(0), NumAbbrevs(0), NumRecords(0), NumAbbreviatedRecords(0) {} @@ -243,51 +320,52 @@ static std::map BlockIDStats; /// Error - All bitcode analysis errors go through this function, making this a /// good place to breakpoint if debugging. -static bool Error(const std::string &Err) { - std::cerr << Err << "\n"; +static bool Error(const Twine &Err) { + errs() << Err << "\n"; return true; } /// ParseBlock - Read a block, updating statistics, etc. -static bool ParseBlock(BitstreamReader &Stream, unsigned IndentLevel) { +static bool ParseBlock(BitstreamCursor &Stream, unsigned BlockID, + unsigned IndentLevel, CurStreamTypeType CurStreamType) { std::string Indent(IndentLevel*2, ' '); uint64_t BlockBitStart = Stream.GetCurrentBitNo(); - unsigned BlockID = Stream.ReadSubBlockID(); // Get the statistics for this BlockID. PerBlockIDStats &BlockStats = BlockIDStats[BlockID]; - + BlockStats.NumInstances++; - + // BLOCKINFO is a special part of the stream. if (BlockID == bitc::BLOCKINFO_BLOCK_ID) { - if (Dump) std::cerr << Indent << "\n"; + if (Dump) outs() << Indent << "\n"; if (Stream.ReadBlockInfoBlock()) return Error("Malformed BlockInfoBlock"); uint64_t BlockBitEnd = Stream.GetCurrentBitNo(); BlockStats.NumBits += BlockBitEnd-BlockBitStart; return false; } - + unsigned NumWords = 0; if (Stream.EnterSubBlock(BlockID, &NumWords)) return Error("Malformed block record"); - const char *BlockName = 0; + const char *BlockName = nullptr; if (Dump) { - std::cerr << Indent << "<"; - if ((BlockName = GetBlockName(BlockID))) - std::cerr << BlockName; + outs() << Indent << "<"; + if ((BlockName = GetBlockName(BlockID, *Stream.getBitStreamReader(), + CurStreamType))) + outs() << BlockName; else - std::cerr << "UnknownBlock" << BlockID; - + outs() << "UnknownBlock" << BlockID; + if (NonSymbolic && BlockName) - std::cerr << " BlockID=" << BlockID; - - std::cerr << " NumWords=" << NumWords - << " BlockCodeSize=" << Stream.GetAbbrevIDWidth() << ">\n"; + outs() << " BlockID=" << BlockID; + + outs() << " NumWords=" << NumWords + << " BlockCodeSize=" << Stream.getAbbrevIDWidth() << ">\n"; } - + SmallVector Record; // Read all the records for this block. @@ -295,87 +373,143 @@ static bool ParseBlock(BitstreamReader &Stream, unsigned IndentLevel) { if (Stream.AtEndOfStream()) return Error("Premature end of bitstream"); - // Read the code for this record. - unsigned AbbrevID = Stream.ReadCode(); - switch (AbbrevID) { - case bitc::END_BLOCK: { - if (Stream.ReadBlockEnd()) - return Error("Error at end of block"); + uint64_t RecordStartBit = Stream.GetCurrentBitNo(); + + BitstreamEntry Entry = + Stream.advance(BitstreamCursor::AF_DontAutoprocessAbbrevs); + + switch (Entry.Kind) { + case BitstreamEntry::Error: + return Error("malformed bitcode file"); + case BitstreamEntry::EndBlock: { uint64_t BlockBitEnd = Stream.GetCurrentBitNo(); BlockStats.NumBits += BlockBitEnd-BlockBitStart; if (Dump) { - std::cerr << Indent << "\n"; + outs() << BlockName << ">\n"; else - std::cerr << "UnknownBlock" << BlockID << ">\n"; + outs() << "UnknownBlock" << BlockID << ">\n"; } return false; - } - case bitc::ENTER_SUBBLOCK: - if (ParseBlock(Stream, IndentLevel+1)) + } + + case BitstreamEntry::SubBlock: { + uint64_t SubBlockBitStart = Stream.GetCurrentBitNo(); + if (ParseBlock(Stream, Entry.ID, IndentLevel+1, CurStreamType)) return true; ++BlockStats.NumSubBlocks; + uint64_t SubBlockBitEnd = Stream.GetCurrentBitNo(); + + // Don't include subblock sizes in the size of this block. + BlockBitStart += SubBlockBitEnd-SubBlockBitStart; + continue; + } + case BitstreamEntry::Record: + // The interesting case. break; - case bitc::DEFINE_ABBREV: + } + + if (Entry.ID == bitc::DEFINE_ABBREV) { Stream.ReadAbbrevRecord(); ++BlockStats.NumAbbrevs; - break; - default: - ++BlockStats.NumRecords; - if (AbbrevID != bitc::UNABBREV_RECORD) - ++BlockStats.NumAbbreviatedRecords; - - Record.clear(); - unsigned Code = Stream.ReadRecord(AbbrevID, Record); - // TODO: Compute per-blockid/code stats. - - if (Dump) { - std::cerr << Indent << " <"; - if (const char *CodeName = GetCodeName(Code, BlockID)) - std::cerr << CodeName; + continue; + } + + Record.clear(); + + ++BlockStats.NumRecords; + + StringRef Blob; + unsigned Code = Stream.readRecord(Entry.ID, Record, &Blob); + + // Increment the # occurrences of this code. + if (BlockStats.CodeFreq.size() <= Code) + BlockStats.CodeFreq.resize(Code+1); + BlockStats.CodeFreq[Code].NumInstances++; + BlockStats.CodeFreq[Code].TotalBits += + Stream.GetCurrentBitNo()-RecordStartBit; + if (Entry.ID != bitc::UNABBREV_RECORD) { + BlockStats.CodeFreq[Code].NumAbbrev++; + ++BlockStats.NumAbbreviatedRecords; + } + + if (Dump) { + outs() << Indent << " <"; + if (const char *CodeName = + GetCodeName(Code, BlockID, *Stream.getBitStreamReader(), + CurStreamType)) + outs() << CodeName; + else + outs() << "UnknownCode" << Code; + if (NonSymbolic && + GetCodeName(Code, BlockID, *Stream.getBitStreamReader(), + CurStreamType)) + outs() << " codeid=" << Code; + if (Entry.ID != bitc::UNABBREV_RECORD) + outs() << " abbrevid=" << Entry.ID; + + for (unsigned i = 0, e = Record.size(); i != e; ++i) + outs() << " op" << i << "=" << (int64_t)Record[i]; + + outs() << "/>"; + + if (Blob.data()) { + outs() << " blob data = "; + bool BlobIsPrintable = true; + for (unsigned i = 0, e = Blob.size(); i != e; ++i) + if (!isprint(static_cast(Blob[i]))) { + BlobIsPrintable = false; + break; + } + + if (BlobIsPrintable) + outs() << "'" << Blob << "'"; else - std::cerr << "UnknownCode" << Code; - if (NonSymbolic && GetCodeName(Code, BlockID)) - std::cerr << " codeid=" << Code; - if (AbbrevID != bitc::UNABBREV_RECORD) - std::cerr << " abbrevid=" << AbbrevID; - - for (unsigned i = 0, e = Record.size(); i != e; ++i) - std::cerr << " op" << i << "=" << (int64_t)Record[i]; - - std::cerr << "/>\n"; + outs() << "unprintable, " << Blob.size() << " bytes."; } - - break; + + outs() << "\n"; } } } static void PrintSize(double Bits) { - std::cerr << Bits << "b/" << Bits/8 << "B/" << Bits/32 << "W"; + outs() << format("%.2f/%.2fB/%luW", Bits, Bits/8,(unsigned long)(Bits/32)); +} +static void PrintSize(uint64_t Bits) { + outs() << format("%lub/%.2fB/%luW", (unsigned long)Bits, + (double)Bits/8, (unsigned long)(Bits/32)); } - -/// AnalyzeBitcode - Analyze the bitcode file specified by InputFilename. -static int AnalyzeBitcode() { +static bool openBitcodeFile(StringRef Path, + std::unique_ptr &MemBuf, + BitstreamReader &StreamFile, + BitstreamCursor &Stream, + CurStreamTypeType &CurStreamType) { // Read the input file. - MemoryBuffer *Buffer; - if (InputFilename == "-") - Buffer = MemoryBuffer::getSTDIN(); - else - Buffer = MemoryBuffer::getFile(&InputFilename[0], InputFilename.size()); - - if (Buffer == 0) - return Error("Error reading '" + InputFilename + "'."); - - if (Buffer->getBufferSize() & 3) + ErrorOr> MemBufOrErr = + MemoryBuffer::getFileOrSTDIN(Path); + if (std::error_code EC = MemBufOrErr.getError()) + return Error(Twine("Error reading '") + Path + "': " + EC.message()); + MemBuf = std::move(MemBufOrErr.get()); + + if (MemBuf->getBufferSize() & 3) return Error("Bitcode stream should be a multiple of 4 bytes in length"); - - unsigned char *BufPtr = (unsigned char *)Buffer->getBufferStart(); - BitstreamReader Stream(BufPtr, BufPtr+Buffer->getBufferSize()); - + const unsigned char *BufPtr = (const unsigned char *)MemBuf->getBufferStart(); + const unsigned char *EndBufPtr = BufPtr + MemBuf->getBufferSize(); + + // If we have a wrapper header, parse it and ignore the non-bc file contents. + // The magic number is 0x0B17C0DE stored in little endian. + if (isBitcodeWrapper(BufPtr, EndBufPtr)) + if (SkipBitcodeWrapperHeader(BufPtr, EndBufPtr, true)) + return Error("Invalid bitcode wrapper header"); + + StreamFile = BitstreamReader(BufPtr, EndBufPtr); + Stream = BitstreamCursor(StreamFile); + StreamFile.CollectBlockInfoNames(); + // Read the stream signature. char Signature[6]; Signature[0] = Stream.Read(8); @@ -384,7 +518,7 @@ static int AnalyzeBitcode() { Signature[3] = Stream.Read(4); Signature[4] = Stream.Read(4); Signature[5] = Stream.Read(4); - + // Autodetect the file contents, if it is one we know. CurStreamType = UnknownBitstream; if (Signature[0] == 'B' && Signature[1] == 'C' && @@ -392,115 +526,163 @@ static int AnalyzeBitcode() { Signature[4] == 0xE && Signature[5] == 0xD) CurStreamType = LLVMIRBitstream; + return false; +} + +/// AnalyzeBitcode - Analyze the bitcode file specified by InputFilename. +static int AnalyzeBitcode() { + std::unique_ptr StreamBuffer; + BitstreamReader StreamFile; + BitstreamCursor Stream; + CurStreamTypeType CurStreamType; + if (openBitcodeFile(InputFilename, StreamBuffer, StreamFile, Stream, + CurStreamType)) + return true; + + // Read block info from BlockInfoFilename, if specified. + // The block info must be a top-level block. + if (!BlockInfoFilename.empty()) { + std::unique_ptr BlockInfoBuffer; + BitstreamReader BlockInfoFile; + BitstreamCursor BlockInfoCursor; + CurStreamTypeType BlockInfoStreamType; + if (openBitcodeFile(BlockInfoFilename, BlockInfoBuffer, BlockInfoFile, + BlockInfoCursor, BlockInfoStreamType)) + return true; + + while (!BlockInfoCursor.AtEndOfStream()) { + unsigned Code = BlockInfoCursor.ReadCode(); + if (Code != bitc::ENTER_SUBBLOCK) + return Error("Invalid record at top-level in block info file"); + + unsigned BlockID = BlockInfoCursor.ReadSubBlockID(); + if (BlockID == bitc::BLOCKINFO_BLOCK_ID) { + if (BlockInfoCursor.ReadBlockInfoBlock()) + return Error("Malformed BlockInfoBlock in block info file"); + break; + } + + BlockInfoCursor.SkipBlock(); + } + + StreamFile.takeBlockInfo(std::move(BlockInfoFile)); + } + unsigned NumTopBlocks = 0; - + // Parse the top-level structure. We only allow blocks at the top-level. while (!Stream.AtEndOfStream()) { unsigned Code = Stream.ReadCode(); if (Code != bitc::ENTER_SUBBLOCK) return Error("Invalid record at top-level"); - - if (ParseBlock(Stream, 0)) + + unsigned BlockID = Stream.ReadSubBlockID(); + + if (ParseBlock(Stream, BlockID, 0, CurStreamType)) return true; ++NumTopBlocks; } - - if (Dump) std::cerr << "\n\n"; - - uint64_t BufferSizeBits = Buffer->getBufferSize()*8; + + if (Dump) outs() << "\n\n"; + + uint64_t BufferSizeBits = StreamFile.getBitcodeBytes().getExtent() * CHAR_BIT; // Print a summary of the read file. - std::cerr << "Summary of " << InputFilename << ":\n"; - std::cerr << " Total size: "; + outs() << "Summary of " << InputFilename << ":\n"; + outs() << " Total size: "; PrintSize(BufferSizeBits); - std::cerr << "\n"; - std::cerr << " Stream type: "; + outs() << "\n"; + outs() << " Stream type: "; switch (CurStreamType) { - default: assert(0 && "Unknown bitstream type"); - case UnknownBitstream: std::cerr << "unknown\n"; break; - case LLVMIRBitstream: std::cerr << "LLVM IR\n"; break; + case UnknownBitstream: outs() << "unknown\n"; break; + case LLVMIRBitstream: outs() << "LLVM IR\n"; break; } - std::cerr << " # Toplevel Blocks: " << NumTopBlocks << "\n"; - std::cerr << "\n"; + outs() << " # Toplevel Blocks: " << NumTopBlocks << "\n"; + outs() << "\n"; // Emit per-block stats. - std::cerr << "Per-block Summary:\n"; + outs() << "Per-block Summary:\n"; for (std::map::iterator I = BlockIDStats.begin(), E = BlockIDStats.end(); I != E; ++I) { - std::cerr << " Block ID #" << I->first; - if (const char *BlockName = GetBlockName(I->first)) - std::cerr << " (" << BlockName << ")"; - std::cerr << ":\n"; - + outs() << " Block ID #" << I->first; + if (const char *BlockName = GetBlockName(I->first, StreamFile, + CurStreamType)) + outs() << " (" << BlockName << ")"; + outs() << ":\n"; + const PerBlockIDStats &Stats = I->second; - std::cerr << " Num Instances: " << Stats.NumInstances << "\n"; - std::cerr << " Total Size: "; + outs() << " Num Instances: " << Stats.NumInstances << "\n"; + outs() << " Total Size: "; PrintSize(Stats.NumBits); - std::cerr << "\n"; - std::cerr << " Average Size: "; - PrintSize(Stats.NumBits/(double)Stats.NumInstances); - std::cerr << "\n"; - std::cerr << " % of file: " - << Stats.NumBits/(double)BufferSizeBits*100 << "\n"; - std::cerr << " Tot/Avg SubBlocks: " << Stats.NumSubBlocks << "/" - << Stats.NumSubBlocks/(double)Stats.NumInstances << "\n"; - std::cerr << " Tot/Avg Abbrevs: " << Stats.NumAbbrevs << "/" - << Stats.NumAbbrevs/(double)Stats.NumInstances << "\n"; - std::cerr << " Tot/Avg Records: " << Stats.NumRecords << "/" - << Stats.NumRecords/(double)Stats.NumInstances << "\n"; - if (Stats.NumRecords) - std::cerr << " % Abbrev Recs: " << (Stats.NumAbbreviatedRecords/ - (double)Stats.NumRecords)*100 << "\n"; - std::cerr << "\n"; + outs() << "\n"; + double pct = (Stats.NumBits * 100.0) / BufferSizeBits; + outs() << " Percent of file: " << format("%2.4f%%", pct) << "\n"; + if (Stats.NumInstances > 1) { + outs() << " Average Size: "; + PrintSize(Stats.NumBits/(double)Stats.NumInstances); + outs() << "\n"; + outs() << " Tot/Avg SubBlocks: " << Stats.NumSubBlocks << "/" + << Stats.NumSubBlocks/(double)Stats.NumInstances << "\n"; + outs() << " Tot/Avg Abbrevs: " << Stats.NumAbbrevs << "/" + << Stats.NumAbbrevs/(double)Stats.NumInstances << "\n"; + outs() << " Tot/Avg Records: " << Stats.NumRecords << "/" + << Stats.NumRecords/(double)Stats.NumInstances << "\n"; + } else { + outs() << " Num SubBlocks: " << Stats.NumSubBlocks << "\n"; + outs() << " Num Abbrevs: " << Stats.NumAbbrevs << "\n"; + outs() << " Num Records: " << Stats.NumRecords << "\n"; + } + if (Stats.NumRecords) { + double pct = (Stats.NumAbbreviatedRecords * 100.0) / Stats.NumRecords; + outs() << " Percent Abbrevs: " << format("%2.4f%%", pct) << "\n"; + } + outs() << "\n"; + + // Print a histogram of the codes we see. + if (!NoHistogram && !Stats.CodeFreq.empty()) { + std::vector > FreqPairs; // + for (unsigned i = 0, e = Stats.CodeFreq.size(); i != e; ++i) + if (unsigned Freq = Stats.CodeFreq[i].NumInstances) + FreqPairs.push_back(std::make_pair(Freq, i)); + std::stable_sort(FreqPairs.begin(), FreqPairs.end()); + std::reverse(FreqPairs.begin(), FreqPairs.end()); + + outs() << "\tRecord Histogram:\n"; + outs() << "\t\t Count # Bits %% Abv Record Kind\n"; + for (unsigned i = 0, e = FreqPairs.size(); i != e; ++i) { + const PerRecordStats &RecStats = Stats.CodeFreq[FreqPairs[i].second]; + + outs() << format("\t\t%7d %9lu", + RecStats.NumInstances, + (unsigned long)RecStats.TotalBits); + + if (RecStats.NumAbbrev) + outs() << + format("%7.2f ", + (double)RecStats.NumAbbrev/RecStats.NumInstances*100); + else + outs() << " "; + + if (const char *CodeName = + GetCodeName(FreqPairs[i].second, I->first, StreamFile, + CurStreamType)) + outs() << CodeName << "\n"; + else + outs() << "UnknownCode" << FreqPairs[i].second << "\n"; + } + outs() << "\n"; + + } } return 0; } -//===----------------------------------------------------------------------===// -// Bytecode specific analysis. -//===----------------------------------------------------------------------===// - int main(int argc, char **argv) { - llvm_shutdown_obj X; // Call llvm_shutdown() on exit. - cl::ParseCommandLineOptions(argc, argv, " llvm-bcanalyzer file analyzer\n"); - + // Print a stack trace if we signal out. sys::PrintStackTraceOnErrorSignal(); - - if (Bitcode) - return AnalyzeBitcode(); - - try { - std::ostream *Out = &std::cout; // Default to printing to stdout... - std::string ErrorMessage; - BytecodeAnalysis bca; - - /// Determine what to generate - bca.detailedResults = !NoDetails; - bca.progressiveVerify = Verify; - - /// Analyze the bytecode file - Module* M = AnalyzeBytecodeFile(InputFilename, bca, - Compressor::decompressToNewBuffer, - &ErrorMessage, (Dump?Out:0)); - - // All that bcanalyzer does is write the gathered statistics to the output - PrintBytecodeAnalysis(bca,*Out); - - if (M && Verify) { - std::string verificationMsg; - if (verifyModule(*M, ReturnStatusAction, &verificationMsg)) - std::cerr << "Final Verification Message: " << verificationMsg << "\n"; - } + PrettyStackTraceProgram X(argc, argv); + llvm_shutdown_obj Y; // Call llvm_shutdown() on exit. + cl::ParseCommandLineOptions(argc, argv, "llvm-bcanalyzer file analyzer\n"); - if (Out != &std::cout) { - ((std::ofstream*)Out)->close(); - delete Out; - } - return 0; - } catch (const std::string& msg) { - std::cerr << argv[0] << ": " << msg << "\n"; - } catch (...) { - std::cerr << argv[0] << ": Unexpected unknown exception occurred.\n"; - } - return 1; + return AnalyzeBitcode(); }