-//===-- 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/Support/CommandLine.h"
-#include "llvm/Support/Compressor.h"
#include "llvm/Support/ManagedStatic.h"
#include "llvm/Support/MemoryBuffer.h"
#include "llvm/System/Signals.h"
+#include <map>
#include <fstream>
#include <iostream>
+#include <algorithm>
using namespace llvm;
static cl::opt<std::string>
- InputFilename(cl::Positional, cl::desc("<input bytecode>"), cl::init("-"));
+ InputFilename(cl::Positional, cl::desc("<input bitcode>"), cl::init("-"));
static cl::opt<std::string>
OutputFilename("-o", cl::init("-"), cl::desc("<output file>"));
-static cl::opt<bool> NoDetails("nodetails", cl::desc("Skip detailed output"));
-static cl::opt<bool> Dump("dump", cl::desc("Dump low level bytecode trace"));
-static cl::opt<bool> Verify("verify", cl::desc("Progressively verify module"));
+static cl::opt<bool> Dump("dump", cl::desc("Dump low level bitcode trace"));
//===----------------------------------------------------------------------===//
// Bitcode specific analysis.
//===----------------------------------------------------------------------===//
-static cl::opt<bool> Bitcode("bitcode", cl::desc("Read a bitcode file"));
+static cl::opt<bool> NoHistogram("disable-histogram",
+ cl::desc("Do not print per-code histogram"));
static cl::opt<bool>
NonSymbolic("non-symbolic",
/// GetBlockName - Return a symbolic block name if known, otherwise return
/// null.
static const char *GetBlockName(unsigned BlockID) {
+ // 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 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";
/// 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) {
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_META: return "META";
case bitc::TYPE_CODE_VOID: return "VOID";
case bitc::TYPE_CODE_FLOAT: return "FLOAT";
case bitc::TYPE_CODE_DOUBLE: return "DOUBLE";
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_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) {
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::FUNC_CODE_INST_STORE2: return "INST_STORE2";
+ case bitc::FUNC_CODE_INST_GETRESULT: return "INST_GETRESULT";
}
case bitc::TYPE_SYMTAB_BLOCK_ID:
switch (CodeID) {
switch (CodeID) {
default: return 0;
case bitc::VST_CODE_ENTRY: return "ENTRY";
+ case bitc::VST_CODE_BBENTRY: return "BBENTRY";
}
}
}
/// number that are abbreviated.
unsigned NumRecords, NumAbbreviatedRecords;
+ /// CodeFreq - Keep track of the number of times we see each code.
+ std::vector<unsigned> CodeFreq;
+
PerBlockIDStats()
: NumInstances(0), NumBits(0),
NumSubBlocks(0), NumAbbrevs(0), NumRecords(0), NumAbbreviatedRecords(0) {}
/// ParseBlock - Read a block, updating statistics, etc.
static bool ParseBlock(BitstreamReader &Stream, unsigned IndentLevel) {
+ std::string Indent(IndentLevel*2, ' ');
uint64_t BlockBitStart = Stream.GetCurrentBitNo();
unsigned BlockID = Stream.ReadSubBlockID();
BlockStats.NumInstances++;
+ // BLOCKINFO is a special part of the stream.
+ if (BlockID == bitc::BLOCKINFO_BLOCK_ID) {
+ if (Dump) std::cerr << Indent << "<BLOCKINFO_BLOCK/>\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(&NumWords))
+ if (Stream.EnterSubBlock(BlockID, &NumWords))
return Error("Malformed block record");
- std::string Indent(IndentLevel*2, ' ');
const char *BlockName = 0;
if (Dump) {
std::cerr << Indent << "<";
}
return false;
}
- case bitc::ENTER_SUBBLOCK:
+ 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;
Record.clear();
unsigned Code = Stream.ReadRecord(AbbrevID, Record);
- // TODO: Compute per-blockid/code stats.
+
+ // Increment the # occurrences of this code.
+ if (BlockStats.CodeFreq.size() <= Code)
+ BlockStats.CodeFreq.resize(Code+1);
+ BlockStats.CodeFreq[Code]++;
if (Dump) {
std::cerr << Indent << " <";
for (unsigned i = 0, e = Record.size(); i != e; ++i)
std::cerr << " op" << i << "=" << (int64_t)Record[i];
- std::cerr << ">\n";
+ std::cerr << "/>\n";
}
break;
/// AnalyzeBitcode - Analyze the bitcode file specified by InputFilename.
static int AnalyzeBitcode() {
// Read the input file.
- MemoryBuffer *Buffer;
- if (InputFilename == "-")
- Buffer = MemoryBuffer::getSTDIN();
- else
- Buffer = MemoryBuffer::getFile(&InputFilename[0], InputFilename.size());
+ MemoryBuffer *Buffer = MemoryBuffer::getFileOrSTDIN(InputFilename.c_str());
if (Buffer == 0)
return Error("Error reading '" + InputFilename + "'.");
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 << " % 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";
- std::cerr << " % Abbrev Recs: " << (Stats.NumAbbreviatedRecords/
- (double)Stats.NumRecords)*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<std::pair<unsigned, unsigned> > FreqPairs; // <freq,code>
+ 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();
}