[llvm-branch-commits] [llvm] [BOLT] Match blocks with calls as anchors (PR #96596)

[Davide Italiano via llvm-branch-commits]

================
@@ -414,31 +449,59 @@ createFlowFunction(const BinaryFunction::BasicBlockOrderType &BlockOrder) {
 /// matched to a jump in the binary, the count is recorded in CFG.
 size_t matchWeightsByHashes(
     BinaryContext &BC, const BinaryFunction::BasicBlockOrderType &BlockOrder,
-    const yaml::bolt::BinaryFunctionProfile &YamlBF, FlowFunction &Func) {
+    const yaml::bolt::BinaryFunctionProfile &YamlBF, FlowFunction &Func,
+    HashFunction HashFunction,
+    const DenseMap<uint32_t, std::string *> &IdToFunctionName) {
+
   assert(Func.Blocks.size() == BlockOrder.size() + 2);
 
+  std::vector<uint64_t> CallHashes;
   std::vector<FlowBlock *> Blocks;
   std::vector<BlendedBlockHash> BlendedHashes;
   for (uint64_t I = 0; I < BlockOrder.size(); I++) {
     const BinaryBasicBlock *BB = BlockOrder[I];
     assert(BB->getHash() != 0 && "empty hash of BinaryBasicBlock");
+
+    std::string CallHashStr = hashBlockCalls(BC, *BB);
+    if (CallHashStr.empty()) {
+      CallHashes.push_back(0);
+    } else if (HashFunction == HashFunction::StdHash) {
+      CallHashes.push_back(std::hash<std::string>{}(CallHashStr));
+    } else if (HashFunction == HashFunction::XXH3) {
+      CallHashes.push_back(llvm::xxh3_64bits(CallHashStr));
+    } else {
+      llvm_unreachable("Unhandled HashFunction");
+    }
+
     Blocks.push_back(&Func.Blocks[I + 1]);
     BlendedBlockHash BlendedHash(BB->getHash());
     BlendedHashes.push_back(BlendedHash);
     LLVM_DEBUG(dbgs() << "BB with index " << I << " has hash = "
                       << Twine::utohexstr(BB->getHash()) << "\n");
   }
   StaleMatcher Matcher;
-  Matcher.init(Blocks, BlendedHashes);
+  Matcher.init(Blocks, BlendedHashes, CallHashes);
 
   // Index in yaml profile => corresponding (matched) block
   DenseMap<uint64_t, const FlowBlock *> MatchedBlocks;
   // Match blocks from the profile to the blocks in CFG
   for (const yaml::bolt::BinaryBasicBlockProfile &YamlBB : YamlBF.Blocks) {
     assert(YamlBB.Hash != 0 && "empty hash of BinaryBasicBlockProfile");
     BlendedBlockHash YamlHash(YamlBB.Hash);
-    const FlowBlock *MatchedBlock = Matcher.matchBlock(YamlHash);
-    // Always match the entry block.
+
+    const FlowBlock *MatchedBlock = nullptr;
+    std::string CallHashStr = hashBlockCalls(IdToFunctionName, YamlBB);
+    uint64_t CallHash = 0;
+    if (CallHashStr.empty()) { // Noop
+    } else if (HashFunction == HashFunction::StdHash) {
+      CallHash = std::hash<std::string>{}(CallHashStr);
+    } else if (HashFunction == HashFunction::XXH3) {
+      CallHash = llvm::xxh3_64bits(CallHashStr);
+    } else {
+      llvm_unreachable("Unhandled HashFunction");
----------------
dcci wrote:

you might want to add a more informative message.

https://github.com/llvm/llvm-project/pull/96596