Skip to content

[NFC][IR2Vec] Minor refactoring of opcode access in vocabulary #147585

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: users/svkeerthy/06-20-vocab_changes
Choose a base branch
from
Open

[NFC][IR2Vec] Minor refactoring of opcode access in vocabulary #147585

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions llvm/include/llvm/Analysis/IR2Vec.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,15 +163,18 @@ class Vocabulary {
static constexpr unsigned MaxOperandKinds =
static_cast<unsigned>(OperandKind::MaxOperandKind);

/// Helper function to get vocabulary key for a given Opcode
static StringRef getVocabKeyForOpcode(unsigned Opcode);

/// Helper function to get vocabulary key for a given TypeID
static StringRef getVocabKeyForTypeID(Type::TypeID TypeID);

/// Helper function to get vocabulary key for a given OperandKind
static StringRef getVocabKeyForOperandKind(OperandKind Kind);

/// Helper function to classify an operand into OperandKind
static OperandKind getOperandKind(const Value *Op);

/// Helper function to get vocabulary key for a given TypeID
static StringRef getVocabKeyForTypeID(Type::TypeID TypeID);

public:
Vocabulary() = default;
Vocabulary(VocabVector &&Vocab);
Expand Down
45 changes: 24 additions & 21 deletions llvm/lib/Analysis/IR2Vec.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,6 +243,17 @@ const ir2vec::Embedding &Vocabulary::operator[](const Value *Arg) const {
return Vocab[MaxOpcodes + MaxTypeIDs + static_cast<unsigned>(ArgKind)];
}

StringRef Vocabulary::getVocabKeyForOpcode(unsigned Opcode) {
assert(Opcode >= 1 && Opcode <= MaxOpcodes && "Invalid opcode");
#define HANDLE_INST(NUM, OPCODE, CLASS) \
if (Opcode == NUM) { \
return #OPCODE; \
}
#include "llvm/IR/Instruction.def"
#undef HANDLE_INST
return "UnknownOpcode";
}

StringRef Vocabulary::getVocabKeyForTypeID(Type::TypeID TypeID) {
switch (TypeID) {
case Type::VoidTyID:
Expand Down Expand Up @@ -280,6 +291,7 @@ StringRef Vocabulary::getVocabKeyForTypeID(Type::TypeID TypeID) {
default:
return "UnknownTy";
}
return "UnknownTy";
}

// Operand kinds supported by IR2Vec - string mappings
Expand All @@ -297,9 +309,9 @@ StringRef Vocabulary::getVocabKeyForOperandKind(Vocabulary::OperandKind Kind) {
OPERAND_KINDS
#undef OPERAND_KIND
case Vocabulary::OperandKind::MaxOperandKind:
llvm_unreachable("Invalid OperandKind");
return "UnknownOperand";
}
llvm_unreachable("Unknown OperandKind");
return "UnknownOperand";
}

#undef OPERAND_KINDS
Expand Down Expand Up @@ -332,14 +344,8 @@ StringRef Vocabulary::getStringKey(unsigned Pos) {
assert(Pos < MaxOpcodes + MaxTypeIDs + MaxOperandKinds &&
"Position out of bounds in vocabulary");
// Opcode
if (Pos < MaxOpcodes) {
#define HANDLE_INST(NUM, OPCODE, CLASS) \
if (Pos == NUM - 1) { \
return #OPCODE; \
}
#include "llvm/IR/Instruction.def"
#undef HANDLE_INST
}
if (Pos < MaxOpcodes)
return getVocabKeyForOpcode(Pos + 1);
// Type
if (Pos < MaxOpcodes + MaxTypeIDs)
return getVocabKeyForTypeID(static_cast<Type::TypeID>(Pos - MaxOpcodes));
Expand Down Expand Up @@ -447,21 +453,18 @@ void IR2VecVocabAnalysis::generateNumMappedVocab() {
// Handle Opcodes
std::vector<Embedding> NumericOpcodeEmbeddings(Vocabulary::MaxOpcodes,
Embedding(Dim, 0));
#define HANDLE_INST(NUM, OPCODE, CLASS) \
{ \
auto It = OpcVocab.find(#OPCODE); \
if (It != OpcVocab.end()) \
NumericOpcodeEmbeddings[NUM - 1] = It->second; \
else \
handleMissingEntity(#OPCODE); \
for (unsigned Opcode : seq(0u, Vocabulary::MaxOpcodes)) {
StringRef VocabKey = Vocabulary::getVocabKeyForOpcode(Opcode + 1);
auto It = OpcVocab.find(VocabKey.str());
if (It != OpcVocab.end())
NumericOpcodeEmbeddings[Opcode] = It->second;
else
handleMissingEntity(VocabKey.str());
}
#include "llvm/IR/Instruction.def"
#undef HANDLE_INST
Vocab.insert(Vocab.end(), NumericOpcodeEmbeddings.begin(),
NumericOpcodeEmbeddings.end());

// Handle Types using direct iteration through TypeID enum
// We iterate through all possible TypeID values and map them to embeddings
// Handle Types
std::vector<Embedding> NumericTypeEmbeddings(Vocabulary::MaxTypeIDs,
Embedding(Dim, 0));
for (unsigned TypeID : seq(0u, Vocabulary::MaxTypeIDs)) {
Expand Down
Loading