llvm/tools/llvm-ir2vec/lib/IRUtils/IRUtils.cpp

//===- IRUtils.cpp - IR2Vec Embedding Generation ----------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This file implements the IR2VecTool class for IR2Vec embedding generation
/// from LLVM IR. It has no dependency on Machine IR.
///
//===----------------------------------------------------------------------===//

#include "IRUtils.h"
#include "llvm/Analysis/IR2Vec.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/PassInstrumentation.h"
#include "llvm/IR/PassManager.h"
#include "llvm/IR/Type.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/Errc.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/WithColor.h"
#include "llvm/Support/raw_ostream.h"

#define DEBUG_TYPE "ir2vec"

namespace llvm {
namespace ir2vec {

Expected<std::shared_ptr<Vocabulary>> loadVocabulary(StringRef VocabPath) {
  auto VocabOrErr = Vocabulary::fromFile(VocabPath);
  if (!VocabOrErr)
    return VocabOrErr.takeError();

  auto V = std::make_shared<Vocabulary>(std::move(*VocabOrErr));

  if (!V->isValid())
    return createStringError(errc::invalid_argument,
                             "Failed to initialize IR2Vec vocabulary");
  return V;
}

Error IR2VecTool::setVocabulary(std::shared_ptr<Vocabulary> V) {
  if (!V)
    return createStringError(errc::invalid_argument,
                             "Null pointer provided for vocabulary. Will not "
                             "set IR2VecTool vocabulary.");
  if (!V->isValid())
    return createStringError(
        errc::invalid_argument,
        "Vocabulary is not valid. Will not set IR2VecTool vocabulary.");
  Vocab = std::move(V);
  return Error::success();
}

TripletResult IR2VecTool::generateTriplets(const Function &F) const {
  if (F.isDeclaration())
    return {};

  TripletResult Result;
  Result.MaxRelation = 0;

  unsigned MaxRelation = NextRelation;
  unsigned PrevOpcode = 0;
  bool HasPrevOpcode = false;

  for (const BasicBlock &BB : F) {
    for (const auto &I : BB) {
      if (I.isDebugOrPseudoInst())
        continue;
      unsigned Opcode = Vocabulary::getIndex(I.getOpcode());
      unsigned TypeID = Vocabulary::getIndex(I.getType()->getTypeID());

      // Add "Next" relationship with previous instruction
      if (HasPrevOpcode) {
        Result.Triplets.push_back({PrevOpcode, Opcode, NextRelation});
        LLVM_DEBUG(dbgs() << Vocabulary::getVocabKeyForOpcode(PrevOpcode + 1)
                          << '\t'
                          << Vocabulary::getVocabKeyForOpcode(Opcode + 1)
                          << '\t' << "Next\n");
      }

      // Add "Type" relationship
      Result.Triplets.push_back({Opcode, TypeID, TypeRelation});
      LLVM_DEBUG(
          dbgs() << Vocabulary::getVocabKeyForOpcode(Opcode + 1) << '\t'
                 << Vocabulary::getVocabKeyForTypeID(I.getType()->getTypeID())
                 << '\t' << "Type\n");

      // Add "Arg" relationships
      unsigned ArgIndex = 0;
      for (const Use &U : I.operands()) {
        unsigned OperandID = Vocabulary::getIndex(*U.get());
        unsigned RelationID = ArgRelation + ArgIndex;
        Result.Triplets.push_back({Opcode, OperandID, RelationID});

        LLVM_DEBUG({
          StringRef OperandStr = Vocabulary::getVocabKeyForOperandKind(
              Vocabulary::getOperandKind(U.get()));
          dbgs() << Vocabulary::getVocabKeyForOpcode(Opcode + 1) << '\t'
                 << OperandStr << '\t' << "Arg" << ArgIndex << '\n';
        });

        ++ArgIndex;
      }
      // Only update MaxRelation if there were operands
      if (ArgIndex > 0)
        MaxRelation = std::max(MaxRelation, ArgRelation + ArgIndex - 1);
      PrevOpcode = Opcode;
      HasPrevOpcode = true;
    }
  }

  Result.MaxRelation = MaxRelation;
  return Result;
}

TripletResult IR2VecTool::generateTriplets() const {
  TripletResult Result;
  Result.MaxRelation = NextRelation;

  for (const Function &F : M.getFunctionDefs()) {
    TripletResult FuncResult = generateTriplets(F);
    Result.MaxRelation = std::max(Result.MaxRelation, FuncResult.MaxRelation);
    Result.Triplets.insert(Result.Triplets.end(), FuncResult.Triplets.begin(),
                           FuncResult.Triplets.end());
  }

  return Result;
}

void IR2VecTool::writeTripletsToStream(raw_ostream &OS) const {
  auto Result = generateTriplets();
  OS << "MAX_RELATION=" << Result.MaxRelation << '\n';
  for (const auto &T : Result.Triplets)
    OS << T.Head << '\t' << T.Tail << '\t' << T.Relation << '\n';
}

EntityList IR2VecTool::collectEntityMappings() {
  auto EntityLen = Vocabulary::getCanonicalSize();
  EntityList Result;
  for (unsigned EntityID = 0; EntityID < EntityLen; ++EntityID)
    Result.push_back(Vocabulary::getStringKey(EntityID).str());
  return Result;
}

void IR2VecTool::writeEntitiesToStream(raw_ostream &OS) {
  auto Entities = collectEntityMappings();
  OS << Entities.size() << "\n";
  for (unsigned EntityID = 0; EntityID < Entities.size(); ++EntityID)
    OS << Entities[EntityID] << '\t' << EntityID << '\n';
}

Expected<std::unique_ptr<Embedder>>
IR2VecTool::createIR2VecEmbedder(const Function &F, IR2VecKind Kind) const {
  if (!Vocab || !Vocab->isValid())
    return createStringError(
        errc::invalid_argument,
        "Vocabulary is not valid. IR2VecTool not initialized.");

  if (F.isDeclaration())
    return createStringError(errc::invalid_argument,
                             "Function is a declaration.");

  auto Emb = Embedder::create(Kind, F, *Vocab);
  if (!Emb)
    return createStringError(errc::invalid_argument,
                             "Failed to create embedder for function '%s'.",
                             F.getName().str().c_str());

  return std::move(Emb);
}

Expected<Embedding> IR2VecTool::getFunctionEmbedding(const Function &F,
                                                     IR2VecKind Kind) const {
  auto Emb = createIR2VecEmbedder(F, Kind);
  if (!Emb)
    return Emb.takeError();

  return (*Emb)->getFunctionVector();
}

Expected<FuncEmbMap>
IR2VecTool::getFunctionEmbeddingsMap(IR2VecKind Kind) const {
  FuncEmbMap Result;

  for (const Function &F : M.getFunctionDefs()) {
    auto Emb = getFunctionEmbedding(F, Kind);
    if (!Emb)
      return Emb.takeError();
    Result.try_emplace(&F, std::move(*Emb));
  }

  return Result;
}

Expected<BBEmbeddingsMap>
IR2VecTool::getBBEmbeddingsMap(const Function &F, IR2VecKind Kind) const {
  auto Emb = createIR2VecEmbedder(F, Kind);
  if (!Emb)
    return Emb.takeError();

  BBEmbeddingsMap Result;

  for (const BasicBlock &BB : F)
    Result.try_emplace(&BB, (*Emb)->getBBVector(BB));

  return Result;
}

Expected<InstEmbeddingsMap>
IR2VecTool::getInstEmbeddingsMap(const Function &F, IR2VecKind Kind) const {
  auto Emb = createIR2VecEmbedder(F, Kind);
  if (!Emb)
    return Emb.takeError();

  InstEmbeddingsMap Result;

  for (const Instruction &I : instructions(F))
    Result.try_emplace(&I, (*Emb)->getInstVector(I));

  return Result;
}

void IR2VecTool::writeEmbeddingsToStream(raw_ostream &OS,
                                         EmbeddingLevel Level) const {
  for (const Function &F : M.getFunctionDefs())
    writeEmbeddingsToStream(F, OS, Level);
}

void IR2VecTool::writeEmbeddingsToStream(const Function &F, raw_ostream &OS,
                                         EmbeddingLevel Level) const {
  auto IR2VecEmbedderObj = createIR2VecEmbedder(F, IR2VecEmbeddingKind);
  if (!IR2VecEmbedderObj) {
    WithColor::error(errs(), ToolName)
        << toString(IR2VecEmbedderObj.takeError()) << "\n";
    return;
  }
  auto Emb = std::move(*IR2VecEmbedderObj);

  OS << "Function: " << F.getName() << "\n";

  // Generate embeddings based on the specified level
  switch (Level) {
  case FunctionLevel:
    Emb->getFunctionVector().print(OS);
    break;
  case BasicBlockLevel:
    for (const BasicBlock &BB : F) {
      OS << BB.getName() << ":";
      Emb->getBBVector(BB).print(OS);
    }
    break;
  case InstructionLevel:
    for (const Instruction &I : instructions(F)) {
      OS << I;
      Emb->getInstVector(I).print(OS);
    }
    break;
  }
}

} // namespace ir2vec
} // namespace llvm