[llvm] Adding IR2Vec as an analysis pass (PR #134004)

[S. VenkataKeerthy via llvm-commits]

================
@@ -0,0 +1,429 @@
+//===- IR2VecAnalysis.cpp - IR2Vec Analysis Implementation ----------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM
+// Exceptions. See the LICENSE file for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// This file implements the IR2Vec algorithm.
+///
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Analysis/IR2VecAnalysis.h"
+
+#include "llvm/ADT/MapVector.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/PassManager.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/Errc.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/Format.h"
+#include "llvm/Support/JSON.h"
+#include "llvm/Support/MemoryBuffer.h"
+
+using namespace llvm;
+using namespace ir2vec;
+
+#define DEBUG_TYPE "ir2vec"
+
+STATISTIC(DataMissCounter, "Number of data misses in the vocabulary");
+
+/// IR2Vec computes two kinds of embeddings: Symbolic and Flow-aware.
+/// Symbolic embeddings capture the "syntactic" and "statistical correlation"
+/// of the IR entities. Flow-aware embeddings build on top of symbolic
+/// embeddings and additionally capture the flow information in the IR.
+/// IR2VecKind is used to specify the type of embeddings to generate.
+// FIXME: Currently we support only Symbolic.  Add support for
+// Flow-aware in upcoming patches.
+enum class IR2VecKind { Symbolic, Flowaware };
+
+static cl::OptionCategory IR2VecAnalysisCategory("IR2Vec Analysis Options");
+
+cl::opt<IR2VecKind>
+    IR2VecMode("ir2vec-mode",
+               cl::desc("Choose type of embeddings to generate:"),
+               cl::values(clEnumValN(IR2VecKind::Symbolic, "symbolic",
+                                     "Generates symbolic embeddings"),
+                          clEnumValN(IR2VecKind::Flowaware, "flowaware",
+                                     "Generates flow-aware embeddings")),
+               cl::init(IR2VecKind::Symbolic), cl::cat(IR2VecAnalysisCategory));
+
+// FIXME: Use a default vocab when not specified
+static cl::opt<std::string>
+    VocabFile("ir2vec-vocab-path", cl::Optional,
+              cl::desc("Path to the vocabulary file for IR2Vec"), cl::init(""),
+              cl::cat(IR2VecAnalysisCategory));
+
+AnalysisKey IR2VecVocabAnalysis::Key;
+AnalysisKey IR2VecAnalysis::Key;
+
+// ==----------------------------------------------------------------------===//
+// Embeddings and its subclasses
+//===----------------------------------------------------------------------===//
+
+namespace {
+/// Embeddings provides the interface to generate vector representations for
+/// instructions, basic blocks, and functions. The vector
+/// representations are generated using IR2Vec algorithms.
+///
+/// The Embeddings class is an abstract class and it is intended to be
+/// subclassed for different IR2Vec algorithms like Symbolic and Flow-aware.
+class Embeddings {
+protected:
+  const Function &F;
+  Vocab Vocabulary;
+
+  /// Weights for different entities (like opcode, arguments, types)
+  /// in the IR instructions to generate the vector representation.
+  // FIXME: Defaults to the values used in the original algorithm. Can be
+  // parameterized later.
+  float WO = 1.0, WT = 0.5, WA = 0.2;
----------------
svkeerthy wrote:

Renamed them to OpcWeight, TypeWeight, ArgWeight..

https://github.com/llvm/llvm-project/pull/134004