Adding Matching and Inference Functionality to Propeller-PR2

llvm/include/llvm/CodeGen/BasicBlockMatchingAndInference.h

@@ -0,0 +1,50 @@
+#ifndef LLVM_CODEGEN_BASIC_BLOCK_AND_INFERENCE_H
+#define LLVM_CODEGEN_BASIC_BLOCK_AND_INFERENCE_H
+
+#include "llvm/CodeGen/BasicBlockSectionsProfileReader.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/Transforms/Utils/SampleProfileInference.h"
+
+namespace llvm {
+
+class BasicBlockMatchingAndInference : public MachineFunctionPass {
+private:
+  using Edge = std::pair<const MachineBasicBlock *, const MachineBasicBlock *>;
+  using BlockWeightMap = DenseMap<const MachineBasicBlock *, uint64_t>;
+  using EdgeWeightMap = DenseMap<Edge, uint64_t>;
+  using BlockEdgeMap = DenseMap<const MachineBasicBlock *,
+                                SmallVector<const MachineBasicBlock *, 8>>;
+
+  struct WeightInfo {
+    // Weight of basic blocks.
+    BlockWeightMap BlockWeights;
+    // Weight of edges.
+    EdgeWeightMap EdgeWeights;
+  };
+
+public:
+  static char ID;
+  BasicBlockMatchingAndInference();
+
+  StringRef getPassName() const override {
+    return "Basic Block Matching and Inference";
+  }
+
+  void getAnalysisUsage(AnalysisUsage &AU) const override;
+
+  bool runOnMachineFunction(MachineFunction &F) override;
+
+  std::optional<WeightInfo> getWeightInfo(StringRef FuncName) const;
+
+private:
+  StringMap<WeightInfo> ProgramWeightInfo;
+
+  WeightInfo initWeightInfoByMatching(MachineFunction &MF);
+
+  void generateWeightInfoByInference(MachineFunction &MF,
+                                     WeightInfo &MatchWeight);
+};
+
+} // end namespace llvm
+
+#endif // LLVM_CODEGEN_BASIC_BLOCK_AND_INFERENCE_H

llvm/include/llvm/CodeGen/BasicBlockSectionsProfileReader.h

@@ -54,6 +54,8 @@ struct FunctionPathAndClusterInfo {
   DenseMap<UniqueBBID, uint64_t> NodeCounts;
   // Edge counts for each edge, stored as a nested map.
   DenseMap<UniqueBBID, DenseMap<UniqueBBID, uint64_t>> EdgeCounts;
+  // Hash for each basic block.
+  DenseMap<unsigned, uint64_t> BBHashes;
 };
 
 class BasicBlockSectionsProfileReader {
@@ -86,6 +88,10 @@ class BasicBlockSectionsProfileReader {
   uint64_t getEdgeCount(StringRef FuncName, const UniqueBBID &SrcBBID,
                         const UniqueBBID &SinkBBID) const;
 
+  // Return the complete function path and cluster info for the given function.
+  std::pair<bool, FunctionPathAndClusterInfo>
+  getFunctionPathAndClusterInfo(StringRef FuncName) const;
+
 private:
   StringRef getAliasName(StringRef FuncName) const {
     auto R = FuncAliasMap.find(FuncName);
@@ -195,6 +201,9 @@ class BasicBlockSectionsProfileReaderWrapperPass : public ImmutablePass {
   uint64_t getEdgeCount(StringRef FuncName, const UniqueBBID &SrcBBID,
                         const UniqueBBID &DestBBID) const;
 
+  std::pair<bool, FunctionPathAndClusterInfo>
+  getFunctionPathAndClusterInfo(StringRef FuncName) const;
+
   // Initializes the FunctionNameToDIFilename map for the current module and
   // then reads the profile for the matching functions.
   bool doInitialization(Module &M) override;

llvm/include/llvm/CodeGen/MachineBlockHashInfo.h

@@ -0,0 +1,106 @@
+#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

llvm/include/llvm/CodeGen/Passes.h

@@ -69,6 +69,13 @@ LLVM_ABI MachineFunctionPass *createBasicBlockSectionsPass();
 
 LLVM_ABI MachineFunctionPass *createBasicBlockPathCloningPass();
 
+/// createBasicBlockMatchingAndInferencePass - This pass enables matching
+/// and inference when using propeller.
+MachineFunctionPass *createBasicBlockMatchingAndInferencePass();
+
+/// createMachineBlockHashInfoPass - This pass computes basic block hashes.
+MachineFunctionPass *createMachineBlockHashInfoPass();
+
 /// createMachineFunctionSplitterPass - This pass splits machine functions
 /// using profile information.
 LLVM_ABI MachineFunctionPass *createMachineFunctionSplitterPass();

llvm/include/llvm/InitializePasses.h

@@ -55,13 +55,15 @@ LLVM_ABI void initializeAlwaysInlinerLegacyPassPass(PassRegistry &);
 LLVM_ABI void initializeAssignmentTrackingAnalysisPass(PassRegistry &);
 LLVM_ABI void initializeAssumptionCacheTrackerPass(PassRegistry &);
 LLVM_ABI void initializeAtomicExpandLegacyPass(PassRegistry &);
+LLVM_ABI void initializeBasicBlockMatchingAndInferencePass(PassRegistry &);
 LLVM_ABI void initializeBasicBlockPathCloningPass(PassRegistry &);
 LLVM_ABI void
 initializeBasicBlockSectionsProfileReaderWrapperPassPass(PassRegistry &);
 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 &);

llvm/include/llvm/MC/MCContext.h

@@ -175,7 +175,7 @@ class MCContext {
   unsigned GetInstance(unsigned LocalLabelVal);
 
   /// SHT_LLVM_BB_ADDR_MAP version to emit.
-  uint8_t BBAddrMapVersion = 3;
+  uint8_t BBAddrMapVersion = 4;
 
   /// The file name of the log file from the environment variable
   /// AS_SECURE_LOG_FILE.  Which must be set before the .secure_log_unique

llvm/include/llvm/Transforms/Utils/SampleProfileInference.h

@@ -130,6 +130,11 @@ template <typename FT> class SampleProfileInference {
   SampleProfileInference(FunctionT &F, BlockEdgeMap &Successors,
                          BlockWeightMap &SampleBlockWeights)
       : F(F), Successors(Successors), SampleBlockWeights(SampleBlockWeights) {}
+  SampleProfileInference(FunctionT &F, BlockEdgeMap &Successors,
+                         BlockWeightMap &SampleBlockWeights,
+                         EdgeWeightMap &SampleEdgeWeights)
+      : F(F), Successors(Successors), SampleBlockWeights(SampleBlockWeights), 
+        SampleEdgeWeights(SampleEdgeWeights) {}
 
   /// Apply the profile inference algorithm for a given function
   void apply(BlockWeightMap &BlockWeights, EdgeWeightMap &EdgeWeights);
@@ -157,6 +162,9 @@ template <typename FT> class SampleProfileInference {
 
   /// Map basic blocks to their sampled weights.
   BlockWeightMap &SampleBlockWeights;
+
+  /// Map edges to their sampled weights.
+  EdgeWeightMap SampleEdgeWeights;
 };
 
 template <typename BT>
@@ -266,6 +274,14 @@ FlowFunction SampleProfileInference<BT>::createFlowFunction(
       FlowJump Jump;
       Jump.Source = BlockIndex[BB];
       Jump.Target = BlockIndex[Succ];
+      auto It = SampleEdgeWeights.find(std::make_pair(BB, Succ));
+      if (It != SampleEdgeWeights.end()) {
+        Jump.HasUnknownWeight = false;
+        Jump.Weight = It->second;
+      } else {
+        Jump.HasUnknownWeight = true;
+        Jump.Weight = 0;
+      }
       Func.Jumps.push_back(Jump);
     }
   }

llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp

@@ -40,6 +40,7 @@
 #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"
@@ -182,6 +183,8 @@ 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;
@@ -461,6 +464,8 @@ 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) {
@@ -1427,7 +1432,8 @@ getBBAddrMapFeature(const MachineFunction &MF, int NumMBBSectionRanges,
           BrProbEnabled,
           MF.hasBBSections() && NumMBBSectionRanges > 1,
           static_cast<bool>(BBAddrMapSkipEmitBBEntries),
-          HasCalls};
+          HasCalls,
+          static_cast<bool>(EmitBBHash)};
 }
 
 void AsmPrinter::emitBBAddrMapSection(const MachineFunction &MF) {
@@ -1486,6 +1492,8 @@ 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.
@@ -1513,6 +1521,10 @@ void AsmPrinter::emitBBAddrMapSection(const MachineFunction &MF) {
       emitLabelDifferenceAsULEB128(MBB.getEndSymbol(), CurrentLabel);
       // Emit the Metadata.
       OutStreamer->emitULEB128IntValue(getBBAddrMapMetadata(MBB));
+      // Emit the Hash.
+      if (MBHI) {
+        OutStreamer->emitULEB128IntValue(MBHI->getMBBHash(MBB));
+      }
     }
     PrevMBBEndSymbol = MBB.getEndSymbol();
   }