X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=tools%2Fllvm-bcanalyzer%2Fllvm-bcanalyzer.cpp;h=b596fe3731004c3d3c50fa6a6a5afe9fc675966e;hb=82a13c9c4811e40d0ff858c508cb54d672ee926e;hp=3f6f3d86ce08db3a7dd4af0db42d706eb5398183;hpb=4238d474b4f8443371a52a4f1fca278170ff2c0e;p=oota-llvm.git diff --git a/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp b/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp index 3f6f3d86ce0..b596fe37310 100644 --- a/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp +++ b/tools/llvm-bcanalyzer/llvm-bcanalyzer.cpp @@ -1,4 +1,4 @@ -//===-- llvm-bcanalyzer.cpp - Byte Code Analyzer --------------------------===// +//===-- llvm-bcanalyzer.cpp - Bitcode Analyzer --------------------------===// // // The LLVM Compiler Infrastructure // @@ -8,56 +8,57 @@ //===----------------------------------------------------------------------===// // // 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/Support/CommandLine.h" -#include "llvm/Support/Compressor.h" #include "llvm/Support/ManagedStatic.h" #include "llvm/Support/MemoryBuffer.h" #include "llvm/System/Signals.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" + " symbolic info is available")); /// CurStreamType - If we can sniff the flavor of this stream, we can produce /// better dump info. @@ -68,13 +69,21 @@ static enum { /// GetBlockName - Return a symbolic block name if known, otherwise return -/// empty. +/// null. static const char *GetBlockName(unsigned BlockID) { - if (CurStreamType != LLVMIRBitstream) return ""; + // Standard blocks for all bitcode files. + if (BlockID < bitc::FIRST_APPLICATION_BLOCKID) { + if (BlockID == bitc::BLOCKINFO_BLOCK_ID) + return "BLOCKINFO_BLOCK"; + return 0; + } + + if (CurStreamType != LLVMIRBitstream) return 0; switch (BlockID) { - default: return ""; + 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"; @@ -83,6 +92,126 @@ static const char *GetBlockName(unsigned BlockID) { } } +/// GetCodeName - Return a symbolic code name if known, otherwise return +/// null. +static const char *GetCodeName(unsigned CodeID, unsigned BlockID) { + // 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"; + } + } + return 0; + } + + if (CurStreamType != LLVMIRBitstream) return 0; + + switch (BlockID) { + default: return 0; + case bitc::MODULE_BLOCK_ID: + switch (CodeID) { + default: return 0; + 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_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::PARAMATTR_BLOCK_ID: + switch (CodeID) { + default: return 0; + case bitc::PARAMATTR_CODE_ENTRY: return "ENTRY"; + } + case bitc::TYPE_BLOCK_ID: + 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"; + } + + 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_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_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::FUNCTION_BLOCK_ID: + switch (CodeID) { + default: return 0; + 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::VALUE_SYMTAB_BLOCK_ID: + switch (CodeID) { + default: return 0; + case bitc::VST_CODE_ENTRY: return "ENTRY"; + case bitc::VST_CODE_BBENTRY: return "BBENTRY"; + } + } +} + struct PerBlockIDStats { /// NumInstances - This the number of times this block ID has been seen. @@ -101,6 +230,9 @@ struct PerBlockIDStats { /// 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) {} @@ -118,19 +250,45 @@ static bool Error(const std::string &Err) { } /// ParseBlock - Read a block, updating statistics, etc. -static bool ParseBlock(BitstreamReader &Stream) { +static bool ParseBlock(BitstreamReader &Stream, unsigned IndentLevel) { + 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++; - if (Stream.EnterSubBlock()) + // BLOCKINFO is a special part of the stream. + if (BlockID == bitc::BLOCKINFO_BLOCK_ID) { + if (Dump) std::cerr << 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; + if (Dump) { + std::cerr << Indent << "<"; + if ((BlockName = GetBlockName(BlockID))) + std::cerr << BlockName; + else + std::cerr << "UnknownBlock" << BlockID; + + if (NonSymbolic && BlockName) + std::cerr << " BlockID=" << BlockID; + + std::cerr << " NumWords=" << NumWords + << " BlockCodeSize=" << Stream.GetAbbrevIDWidth() << ">\n"; + } + SmallVector Record; // Read all the records for this block. @@ -146,13 +304,26 @@ static bool ParseBlock(BitstreamReader &Stream) { return Error("Error at end of block"); uint64_t BlockBitEnd = Stream.GetCurrentBitNo(); BlockStats.NumBits += BlockBitEnd-BlockBitStart; + if (Dump) { + std::cerr << Indent << "\n"; + else + std::cerr << "UnknownBlock" << BlockID << ">\n"; + } return false; } - case bitc::ENTER_SUBBLOCK: - if (ParseBlock(Stream)) + case bitc::ENTER_SUBBLOCK: { + uint64_t SubBlockBitStart = Stream.GetCurrentBitNo(); + if (ParseBlock(Stream, IndentLevel+1)) return true; ++BlockStats.NumSubBlocks; + uint64_t SubBlockBitEnd = Stream.GetCurrentBitNo(); + + // Don't include subblock sizes in the size of this block. + BlockBitStart += SubBlockBitEnd-SubBlockBitStart; break; + } case bitc::DEFINE_ABBREV: Stream.ReadAbbrevRecord(); ++BlockStats.NumAbbrevs; @@ -164,8 +335,29 @@ static bool ParseBlock(BitstreamReader &Stream) { Record.clear(); unsigned Code = Stream.ReadRecord(AbbrevID, Record); - // TODO: Compute per-blockid/code stats. - Code = Code; + + // Increment the # occurrences of this code. + if (BlockStats.CodeFreq.size() <= Code) + BlockStats.CodeFreq.resize(Code+1); + BlockStats.CodeFreq[Code]++; + + if (Dump) { + std::cerr << Indent << " <"; + if (const char *CodeName = GetCodeName(Code, BlockID)) + std::cerr << CodeName; + 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"; + } + break; } } @@ -219,15 +411,18 @@ static int AnalyzeBitcode() { if (Code != bitc::ENTER_SUBBLOCK) return Error("Invalid record at top-level"); - if (ParseBlock(Stream)) + if (ParseBlock(Stream, 0)) return true; ++NumTopBlocks; } + if (Dump) std::cerr << "\n\n"; + + uint64_t BufferSizeBits = Buffer->getBufferSize()*8; // Print a summary of the read file. std::cerr << "Summary of " << InputFilename << ":\n"; std::cerr << " Total size: "; - PrintSize(Buffer->getBufferSize()*8); + PrintSize(BufferSizeBits); std::cerr << "\n"; std::cerr << " Stream type: "; switch (CurStreamType) { @@ -243,8 +438,7 @@ static int AnalyzeBitcode() { for (std::map::iterator I = BlockIDStats.begin(), E = BlockIDStats.end(); I != E; ++I) { std::cerr << " Block ID #" << I->first; - const char *BlockName = GetBlockName(I->first); - if (BlockName[0]) + if (const char *BlockName = GetBlockName(I->first)) std::cerr << " (" << BlockName << ")"; std::cerr << ":\n"; @@ -253,68 +447,58 @@ static int AnalyzeBitcode() { std::cerr << " Total Size: "; PrintSize(Stats.NumBits); std::cerr << "\n"; - std::cerr << " Average Size: "; - PrintSize(Stats.NumBits/(double)Stats.NumInstances); - std::cerr << "\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"; - std::cerr << " % Abbrev Recs: " << (Stats.NumAbbreviatedRecords/ - (double)Stats.NumRecords)*100 << "\n"; + std::cerr << " % of file: " + << Stats.NumBits/(double)BufferSizeBits*100 << "\n"; + if (Stats.NumInstances > 1) { + std::cerr << " Average Size: "; + PrintSize(Stats.NumBits/(double)Stats.NumInstances); + std::cerr << "\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"; + } else { + std::cerr << " Num SubBlocks: " << Stats.NumSubBlocks << "\n"; + std::cerr << " Num Abbrevs: " << Stats.NumAbbrevs << "\n"; + std::cerr << " Num Records: " << Stats.NumRecords << "\n"; + } + if (Stats.NumRecords) + std::cerr << " % Abbrev Recs: " << (Stats.NumAbbreviatedRecords/ + (double)Stats.NumRecords)*100 << "\n"; std::cerr << "\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]) + FreqPairs.push_back(std::make_pair(Freq, i)); + std::stable_sort(FreqPairs.begin(), FreqPairs.end()); + std::reverse(FreqPairs.begin(), FreqPairs.end()); + + std::cerr << "\tCode Histogram:\n"; + for (unsigned i = 0, e = FreqPairs.size(); i != e; ++i) { + std::cerr << "\t\t" << FreqPairs[i].first << "\t"; + if (const char *CodeName = GetCodeName(FreqPairs[i].second, I->first)) + std::cerr << CodeName << "\n"; + else + std::cerr << "UnknownCode" << FreqPairs[i].second << "\n"; + } + std::cerr << "\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"); + cl::ParseCommandLineOptions(argc, argv, "llvm-bcanalyzer file analyzer\n"); 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"; - } - - 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(); }