[llvm-branch-commits] [llvm] [IR2Vec] Consider only reachable BBs and non-debug instructions (PR #143476)

[S. VenkataKeerthy via llvm-branch-commits]

https://github.com/svkeerthy updated https://github.com/llvm/llvm-project/pull/143476

>From 6e44bb095fa214a5146af383de0ffeb89606607b Mon Sep 17 00:00:00 2001
From: svkeerthy <venkatakeerthy at google.com>
Date: Tue, 10 Jun 2025 04:49:59 +0000
Subject: [PATCH] reachable BB

---
 llvm/lib/Analysis/IR2Vec.cpp | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/Analysis/IR2Vec.cpp b/llvm/lib/Analysis/IR2Vec.cpp
index 0f7303c1b0917..fa38c35796a0e 100644
--- a/llvm/lib/Analysis/IR2Vec.cpp
+++ b/llvm/lib/Analysis/IR2Vec.cpp
@@ -13,7 +13,9 @@
 
 #include "llvm/Analysis/IR2Vec.h"
 
+#include "llvm/ADT/DepthFirstIterator.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/IR/CFG.h"
 #include "llvm/IR/Module.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Support/Debug.h"
@@ -190,7 +192,8 @@ Embedding SymbolicEmbedder::getOperandEmbedding(const Value *Op) const {
 void SymbolicEmbedder::computeEmbeddings(const BasicBlock &BB) const {
   Embedding BBVector(Dimension, 0);
 
-  for (const auto &I : BB) {
+  // We consider only the non-debug and non-pseudo instructions
+  for (const auto &I : BB.instructionsWithoutDebug()) {
     Embedding InstVector(Dimension, 0);
 
     const auto OpcVec = lookupVocab(I.getOpcodeName());
@@ -215,9 +218,11 @@ void SymbolicEmbedder::computeEmbeddings(const BasicBlock &BB) const {
 void SymbolicEmbedder::computeEmbeddings() const {
   if (F.isDeclaration())
     return;
-  for (const auto &BB : F) {
-    computeEmbeddings(BB);
-    FuncVector += BBVecMap[&BB];
+
+  // Consider only the basic blocks that are reachable from entry
+  for (const BasicBlock *BB : depth_first(&F)) {
+    computeEmbeddings(*BB);
+    FuncVector += BBVecMap[BB];
   }
 }