Adding Matching and Inference Functionality to Propeller-PR2: Compute basic block hash and emit to ELF.

wdx727 · lifengxiang1025 · zcfh · wdx727 · commit effb5747a37b · 2025-10-18T05:36:09.000+08:00
Co-authored-by: lifengxiang1025 &lt;lifengxiang@kuaishou.com&gt;
Co-authored-by: zcfh &lt;wuminghui03@kuaishou.com&gt;
diff --git a/llvm/include/llvm/CodeGen/MachineBlockHashInfo.h b/llvm/include/llvm/CodeGen/MachineBlockHashInfo.h
@@ -0,0 +1,118 @@
+//===- llvm/CodeGen/MachineBlockHashInfo.h ----------------------*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Compute the hashes of basic blocks.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CODEGEN_MACHINEBLOCKHASHINFO_H
+#define LLVM_CODEGEN_MACHINEBLOCKHASHINFO_H
+
+#include "llvm/CodeGen/MachineFunctionPass.h"
+
+namespace llvm {
+
+/// An object wrapping several components of a basic block hash. The combined
+/// (blended) hash is represented and stored as one uint64_t, while individual
+/// components are of smaller size (e.g., uint16_t or uint8_t).
+struct BlendedBlockHash {
+private:
+  static uint64_t combineHashes(uint16_t Hash1, uint16_t Hash2, uint16_t Hash3,
+                                uint16_t Hash4) {
+    uint64_t Hash = 0;
+
+    Hash |= uint64_t(Hash4);
+    Hash <<= 16;
+
+    Hash |= uint64_t(Hash3);
+    Hash <<= 16;
+
+    Hash |= uint64_t(Hash2);
+    Hash <<= 16;
+
+    Hash |= uint64_t(Hash1);
+
+    return Hash;
+  }
+
+  static void parseHashes(uint64_t Hash, uint16_t &Hash1, uint16_t &Hash2,
+                          uint16_t &Hash3, uint16_t &Hash4) {
+    Hash1 = Hash & 0xffff;
+    Hash >>= 16;
+
+    Hash2 = Hash & 0xffff;
+    Hash >>= 16;
+
+    Hash3 = Hash & 0xffff;
+    Hash >>= 16;
+
+    Hash4 = Hash & 0xffff;
+    Hash >>= 16;
+  }
+
+public:
+  explicit BlendedBlockHash() {}
+
+  explicit BlendedBlockHash(uint64_t CombinedHash) {
+    parseHashes(CombinedHash, Offset, OpcodeHash, InstrHash, NeighborHash);
+  }
+
+  /// Combine the blended hash into uint64_t.
+  uint64_t combine() const {
+    return combineHashes(Offset, OpcodeHash, InstrHash, NeighborHash);
+  }
+
+  /// Compute a distance between two given blended hashes. The smaller the
+  /// distance, the more similar two blocks are. For identical basic blocks,
+  /// the distance is zero.
+  uint64_t distance(const BlendedBlockHash &BBH) const {
+    assert(OpcodeHash == BBH.OpcodeHash &&
+           "incorrect blended hash distance computation");
+    uint64_t Dist = 0;
+    // Account for NeighborHash
+    Dist += NeighborHash == BBH.NeighborHash ? 0 : 1;
+    Dist <<= 16;
+    // Account for InstrHash
+    Dist += InstrHash == BBH.InstrHash ? 0 : 1;
+    Dist <<= 16;
+    // Account for Offset
+    Dist += (Offset >= BBH.Offset ? Offset - BBH.Offset : BBH.Offset - Offset);
+    return Dist;
+  }
+
+  /// The offset of the basic block from the function start.
+  uint16_t Offset{0};
+  /// (Loose) Hash of the basic block instructions, excluding operands.
+  uint16_t OpcodeHash{0};
+  /// (Strong) Hash of the basic block instructions, including opcodes and
+  /// operands.
+  uint16_t InstrHash{0};
+  /// Hash of the (loose) basic block together with (loose) hashes of its
+  /// successors and predecessors.
+  uint16_t NeighborHash{0};
+};
+
+class MachineBlockHashInfo : public MachineFunctionPass {
+  DenseMap<unsigned, uint64_t> MBBHashInfo;
+
+public:
+  static char ID;
+  MachineBlockHashInfo();
+
+  StringRef getPassName() const override { return "Basic Block Hash Compute"; }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override;
+
+  bool runOnMachineFunction(MachineFunction &F) override;
+
+  uint64_t getMBBHash(const MachineBasicBlock &MBB);
+};
+
+} // end namespace llvm
+
+#endif // LLVM_CODEGEN_MACHINEBLOCKHASHINFO_H
diff --git a/llvm/include/llvm/CodeGen/Passes.h b/llvm/include/llvm/CodeGen/Passes.h
@@ -69,6 +69,9 @@ LLVM_ABI MachineFunctionPass *createBasicBlockSectionsPass();
 
 LLVM_ABI MachineFunctionPass *createBasicBlockPathCloningPass();
 
+/// createMachineBlockHashInfoPass - This pass computes basic block hashes.
+LLVM_ABI MachineFunctionPass *createMachineBlockHashInfoPass();
+
 /// createMachineFunctionSplitterPass - This pass splits machine functions
 /// using profile information.
 LLVM_ABI MachineFunctionPass *createMachineFunctionSplitterPass();
diff --git a/llvm/include/llvm/InitializePasses.h b/llvm/include/llvm/InitializePasses.h
@@ -62,6 +62,7 @@ LLVM_ABI void initializeBasicBlockSectionsPass(PassRegistry &);
 LLVM_ABI void initializeBarrierNoopPass(PassRegistry &);
 LLVM_ABI void initializeBasicAAWrapperPassPass(PassRegistry &);
 LLVM_ABI void initializeBlockFrequencyInfoWrapperPassPass(PassRegistry &);
+LLVM_ABI void initializeMachineBlockHashInfoPass(PassRegistry &);
 LLVM_ABI void initializeBranchFolderLegacyPass(PassRegistry &);
 LLVM_ABI void initializeBranchProbabilityInfoWrapperPassPass(PassRegistry &);
 LLVM_ABI void initializeBranchRelaxationLegacyPass(PassRegistry &);
diff --git a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -41,6 +41,7 @@
 #include "llvm/CodeGen/GCMetadataPrinter.h"
 #include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineBlockHashInfo.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
 #include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/CodeGen/MachineDominators.h"
@@ -184,6 +185,8 @@ static cl::opt<bool> PrintLatency(
     cl::desc("Print instruction latencies as verbose asm comments"), cl::Hidden,
     cl::init(false));
 
+extern cl::opt<bool> EmitBBHash;
+
 STATISTIC(EmittedInsts, "Number of machine instrs printed");
 
 char AsmPrinter::ID = 0;
@@ -474,6 +477,8 @@ void AsmPrinter::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.addRequired<GCModuleInfo>();
   AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
   AU.addRequired<MachineBranchProbabilityInfoWrapperPass>();
+  if (EmitBBHash)
+    AU.addRequired<MachineBlockHashInfo>();
 }
 
 bool AsmPrinter::doInitialization(Module &M) {
@@ -1440,7 +1445,7 @@ getBBAddrMapFeature(const MachineFunction &MF, int NumMBBSectionRanges,
           MF.hasBBSections() && NumMBBSectionRanges > 1,
           static_cast<bool>(BBAddrMapSkipEmitBBEntries),
           HasCalls,
-          false};
+          static_cast<bool>(EmitBBHash)};
 }
 
 void AsmPrinter::emitBBAddrMapSection(const MachineFunction &MF) {
@@ -1499,6 +1504,9 @@ void AsmPrinter::emitBBAddrMapSection(const MachineFunction &MF) {
       PrevMBBEndSymbol = MBBSymbol;
     }
 
+    auto MBHI =
+        Features.BBHash ? &getAnalysis<MachineBlockHashInfo>() : nullptr;
+
     if (!Features.OmitBBEntries) {
       OutStreamer->AddComment("BB id");
       // Emit the BB ID for this basic block.
@@ -1526,6 +1534,10 @@ void AsmPrinter::emitBBAddrMapSection(const MachineFunction &MF) {
       emitLabelDifferenceAsULEB128(MBB.getEndSymbol(), CurrentLabel);
       // Emit the Metadata.
       OutStreamer->emitULEB128IntValue(getBBAddrMapMetadata(MBB));
+      // Emit the Hash.
+      if (MBHI) {
+        OutStreamer->emitInt64(MBHI->getMBBHash(MBB));
+      }
     }
     PrevMBBEndSymbol = MBB.getEndSymbol();
   }
diff --git a/llvm/lib/CodeGen/CMakeLists.txt b/llvm/lib/CodeGen/CMakeLists.txt
@@ -108,6 +108,7 @@ add_llvm_component_library(LLVMCodeGen
   LowerEmuTLS.cpp
   MachineBasicBlock.cpp
   MachineBlockFrequencyInfo.cpp
+  MachineBlockHashInfo.cpp
   MachineBlockPlacement.cpp
   MachineBranchProbabilityInfo.cpp
   MachineCFGPrinter.cpp
diff --git a/llvm/lib/CodeGen/MachineBlockHashInfo.cpp b/llvm/lib/CodeGen/MachineBlockHashInfo.cpp
@@ -0,0 +1,123 @@
+//===- llvm/CodeGen/MachineBlockHashInfo.cpp---------------------*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Compute the hashes of basic blocks.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/CodeGen/MachineBlockHashInfo.h"
+#include "llvm/CodeGen/Passes.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Target/TargetMachine.h"
+
+using namespace llvm;
+
+using OperandHashFuncTy =
+    function_ref<uint64_t(uint64_t &, const MachineOperand &)>;
+
+uint64_t hashBlock(const MachineBasicBlock &MBB,
+                   OperandHashFuncTy OperandHashFunc) {
+  uint64_t Hash = 0;
+  for (const MachineInstr &MI : MBB) {
+    if (MI.isMetaInstruction())
+      continue;
+    // Ignore terminator instruction
+    if (MI.isTerminator())
+      continue;
+    Hash = hashing::detail::hash_16_bytes(Hash, MI.getOpcode());
+    for (unsigned i = 0; i < MI.getNumOperands(); i++) {
+      Hash = OperandHashFunc(Hash, MI.getOperand(i));
+    }
+  }
+  return Hash;
+}
+
+/// Hashing a 64-bit integer to a 16-bit one.
+uint16_t hash_64_to_16(const uint64_t Hash) {
+  uint16_t Res = (uint16_t)(Hash & 0xFFFF);
+  Res ^= (uint16_t)((Hash >> 16) & 0xFFFF);
+  Res ^= (uint16_t)((Hash >> 32) & 0xFFFF);
+  Res ^= (uint16_t)((Hash >> 48) & 0xFFFF);
+  return Res;
+}
+
+uint64_t hashInstOperand(uint64_t &Hash, const MachineOperand &Operand) {
+  return hashing::detail::hash_16_bytes(Hash, hash_value(Operand));
+}
+
+INITIALIZE_PASS(MachineBlockHashInfo, "machine-block-hash",
+                "Machine Block Hash Analysis", true, true)
+
+char MachineBlockHashInfo::ID = 0;
+
+MachineBlockHashInfo::MachineBlockHashInfo() : MachineFunctionPass(ID) {
+  initializeMachineBlockHashInfoPass(*PassRegistry::getPassRegistry());
+}
+
+void MachineBlockHashInfo::getAnalysisUsage(AnalysisUsage &AU) const {
+  AU.setPreservesAll();
+  MachineFunctionPass::getAnalysisUsage(AU);
+}
+
+bool MachineBlockHashInfo::runOnMachineFunction(MachineFunction &F) {
+  DenseMap<MachineBasicBlock *, BlendedBlockHash> BlendedHashes;
+  DenseMap<MachineBasicBlock *, uint64_t> OpcodeHashes;
+  uint16_t Offset = 0;
+  // Initialize hash components
+  for (MachineBasicBlock &MBB : F) {
+    BlendedBlockHash BlendedHash;
+    // offset of the machine basic block
+    BlendedHash.Offset = Offset;
+    Offset += MBB.size();
+    // Hashing opcodes
+    uint64_t OpcodeHash = hashBlock(
+        MBB, [](uint64_t &Hash, const MachineOperand &Op) { return Hash; });
+    OpcodeHashes[&MBB] = OpcodeHash;
+    BlendedHash.OpcodeHash = hash_64_to_16(OpcodeHash);
+    // Hash complete instructions
+    uint64_t InstrHash = hashBlock(MBB, hashInstOperand);
+    BlendedHash.InstrHash = hash_64_to_16(InstrHash);
+    BlendedHashes[&MBB] = BlendedHash;
+  }
+
+  // Initialize neighbor hash
+  for (MachineBasicBlock &MBB : F) {
+    uint64_t Hash = OpcodeHashes[&MBB];
+    // Append hashes of successors
+    for (MachineBasicBlock *SuccMBB : MBB.successors()) {
+      uint64_t SuccHash = OpcodeHashes[SuccMBB];
+      Hash = hashing::detail::hash_16_bytes(Hash, SuccHash);
+    }
+    // Append hashes of predecessors
+    for (MachineBasicBlock *PredMBB : MBB.predecessors()) {
+      uint64_t PredHash = OpcodeHashes[PredMBB];
+      Hash = hashing::detail::hash_16_bytes(Hash, PredHash);
+    }
+    BlendedHashes[&MBB].NeighborHash = hash_64_to_16(Hash);
+  }
+
+  // Assign hashes
+  for (MachineBasicBlock &MBB : F) {
+    if (MBB.getBBID()) {
+      MBBHashInfo[MBB.getBBID()->BaseID] = BlendedHashes[&MBB].combine();
+    }
+  }
+
+  return false;
+}
+
+uint64_t MachineBlockHashInfo::getMBBHash(const MachineBasicBlock &MBB) {
+  if (MBB.getBBID()) {
+    return MBBHashInfo[MBB.getBBID()->BaseID];
+  }
+  return 0;
+}
+
+MachineFunctionPass *llvm::createMachineBlockHashInfoPass() {
+  return new MachineBlockHashInfo();
+}
diff --git a/llvm/lib/CodeGen/TargetPassConfig.cpp b/llvm/lib/CodeGen/TargetPassConfig.cpp
@@ -272,6 +272,12 @@ static cl::opt<bool>
                     cl::desc("Split static data sections into hot and cold "
                              "sections using profile information"));
 
+cl::opt<bool> EmitBBHash(
+    "emit-bb-hash",
+    cl::desc(
+        "Emit the hash of basic block in the SHT_LLVM_BB_ADDR_MAP section."),
+    cl::init(false), cl::Optional);
+
 /// Allow standard passes to be disabled by command line options. This supports
 /// simple binary flags that either suppress the pass or do nothing.
 /// i.e. -disable-mypass=false has no effect.
@@ -1281,6 +1287,8 @@ void TargetPassConfig::addMachinePasses() {
   // address map (or both).
   if (TM->getBBSectionsType() != llvm::BasicBlockSection::None ||
       TM->Options.BBAddrMap) {
+    if (EmitBBHash)
+      addPass(llvm::createMachineBlockHashInfoPass());
     if (TM->getBBSectionsType() == llvm::BasicBlockSection::List) {
       addPass(llvm::createBasicBlockSectionsProfileReaderWrapperPass(
           TM->getBBSectionsFuncListBuf()));
diff --git a/llvm/test/CodeGen/X86/basic-block-address-map-with-emit-bb-hash.ll b/llvm/test/CodeGen/X86/basic-block-address-map-with-emit-bb-hash.ll
