[BOLT] Match blocks with pseudo probes

bolt/include/bolt/Core/BinaryContext.h

@@ -722,12 +722,16 @@ class BinaryContext {
     /// Stats for stale profile matching:
     ///   the total number of basic blocks in the profile
     uint32_t NumStaleBlocks{0};
-    ///   the number of matched basic blocks
-    uint32_t NumMatchedBlocks{0};
+    ///   the number of exactly matched basic blocks
+    uint32_t NumExactMatchedBlocks{0};
+    ///   the number of pseudo probe matched basic blocks
+    uint32_t NumPseudoProbeMatchedBlocks{0};
     ///   the total count of samples in the profile
     uint64_t StaleSampleCount{0};
-    ///   the count of matched samples
-    uint64_t MatchedSampleCount{0};
+    ///   the count of exactly matched samples
+    uint64_t ExactMatchedSampleCount{0};
+    ///   the count of pseudo probe matched samples
+    uint64_t PseudoProbeMatchedSampleCount{0};
     ///   the number of stale functions that have matching number of blocks in
     ///   the profile
     uint64_t NumStaleFuncsWithEqualBlockCount{0};

bolt/lib/Passes/BinaryPasses.cpp

@@ -1519,10 +1519,20 @@ Error PrintProgramStats::runOnFunctions(BinaryContext &BC) {
         "BOLT-INFO: inference found an exact match for %.2f%% of basic blocks"
         " (%zu out of %zu stale) responsible for %.2f%% samples"
         " (%zu out of %zu stale)\n",
-        100.0 * BC.Stats.NumMatchedBlocks / BC.Stats.NumStaleBlocks,
-        BC.Stats.NumMatchedBlocks, BC.Stats.NumStaleBlocks,
-        100.0 * BC.Stats.MatchedSampleCount / BC.Stats.StaleSampleCount,
-        BC.Stats.MatchedSampleCount, BC.Stats.StaleSampleCount);
+        100.0 * BC.Stats.NumExactMatchedBlocks / BC.Stats.NumStaleBlocks,
+        BC.Stats.NumExactMatchedBlocks, BC.Stats.NumStaleBlocks,
+        100.0 * BC.Stats.ExactMatchedSampleCount / BC.Stats.StaleSampleCount,
+        BC.Stats.ExactMatchedSampleCount, BC.Stats.StaleSampleCount);
+    BC.outs() << format(
+        "BOLT-INFO: inference found a pseudo probe match for %.2f%% of basic "
+        "blocks"
+        " (%zu out of %zu stale) responsible for %.2f%% samples"
+        " (%zu out of %zu stale)\n",
+        100.0 * BC.Stats.NumPseudoProbeMatchedBlocks / BC.Stats.NumStaleBlocks,
+        BC.Stats.NumPseudoProbeMatchedBlocks, BC.Stats.NumStaleBlocks,
+        100.0 * BC.Stats.PseudoProbeMatchedSampleCount /
+            BC.Stats.StaleSampleCount,
+        BC.Stats.PseudoProbeMatchedSampleCount, BC.Stats.StaleSampleCount);
   }
 
   if (const uint64_t NumUnusedObjects = BC.getNumUnusedProfiledObjects()) {

bolt/lib/Profile/StaleProfileMatching.cpp

@@ -45,6 +45,8 @@ namespace opts {
 
 extern cl::opt<bool> TimeRewrite;
 extern cl::OptionCategory BoltOptCategory;
+extern cl::opt<unsigned> Verbosity;
+extern cl::opt<bool> ProfileUsePseudoProbes;
 
 cl::opt<bool>
     InferStaleProfile("infer-stale-profile",
@@ -191,6 +193,8 @@ struct BlendedBlockHash {
 /// release.
 class StaleMatcher {
 public:
+  StaleMatcher(const uint64_t YamlBFGUID) : YamlBFGUID(YamlBFGUID) {}
+
   /// Initialize stale matcher.
   void init(const std::vector<FlowBlock *> &Blocks,
             const std::vector<BlendedBlockHash> &Hashes,
@@ -208,11 +212,33 @@ class StaleMatcher {
     }
   }
 
-  /// Find the most similar block for a given hash.
-  const FlowBlock *matchBlock(BlendedBlockHash BlendedHash,
-                              uint64_t CallHash) const {
+  /// Creates a mapping from a pseudo probe index to pseudo probe.
+  void mapIndexToProbe(uint64_t Index, const MCDecodedPseudoProbe *Probe) {
+    IndexToBBPseudoProbes[Index].push_back(Probe);
+  }
+
+  /// Creates a mapping from a pseudo probe to a flow block.
+  void mapProbeToBB(const MCDecodedPseudoProbe *Probe, FlowBlock *Block) {
+    BBPseudoProbeToBlock[Probe] = Block;
+  }
+
+  /// Find the most similar flow block for a profile block given its hashes and
+  /// pseudo probe information.
+  const FlowBlock *
+  matchBlock(BlendedBlockHash BlendedHash, uint64_t CallHash,
+             const std::vector<yaml::bolt::PseudoProbeInfo> &PseudoProbes) {
     const FlowBlock *BestBlock = matchWithOpcodes(BlendedHash);
-    return BestBlock ? BestBlock : matchWithCalls(BlendedHash, CallHash);
+    if (BestBlock) {
+      ++MatchedWithOpcodes;
+      return BestBlock;
+    }
+    BestBlock = matchWithCalls(BlendedHash, CallHash);
+    if (BestBlock)
+      return BestBlock;
+    BestBlock = matchWithPseudoProbes(BlendedHash, PseudoProbes);
+    if (BestBlock)
+      MatchedWithPseudoProbes.insert(BlendedHash.combine());
+    return BestBlock;
   }
 
   /// Returns true if the two basic blocks (in the binary and in the profile)
@@ -223,10 +249,31 @@ class StaleMatcher {
     return Hash1.InstrHash == Hash2.InstrHash;
   }
 
+  /// Returns true if a profiled block was matched with its pseudo probe.
+  bool isPseudoProbeMatch(BlendedBlockHash YamlBBHash) {
+    return MatchedWithPseudoProbes.find(YamlBBHash.combine()) !=
+           MatchedWithPseudoProbes.end();
+  }
+
+  /// Returns the number of blocks matched with opcodes.
+  size_t getNumBlocksMatchedWithOpcodes() const { return MatchedWithOpcodes; }
+
+  /// Returns the number of blocks matched with pseudo probes.
+  size_t getNumBlocksMatchedWithPseudoProbes() const {
+    return MatchedWithPseudoProbes.size();
+  }
+
 private:
   using HashBlockPairType = std::pair<BlendedBlockHash, FlowBlock *>;
   std::unordered_map<uint16_t, std::vector<HashBlockPairType>> OpHashToBlocks;
   std::unordered_map<uint64_t, std::vector<HashBlockPairType>> CallHashToBlocks;
+  std::unordered_map<uint64_t, std::vector<const MCDecodedPseudoProbe *>>
+      IndexToBBPseudoProbes;
+  std::unordered_map<const MCDecodedPseudoProbe *, FlowBlock *>
+      BBPseudoProbeToBlock;
+  std::unordered_set<uint64_t> MatchedWithPseudoProbes;
+  const uint64_t YamlBFGUID{0};
+  uint64_t MatchedWithOpcodes{0};
 
   // Uses OpcodeHash to find the most similar block for a given hash.
   const FlowBlock *matchWithOpcodes(BlendedBlockHash BlendedHash) const {
@@ -266,6 +313,65 @@ class StaleMatcher {
     }
     return BestBlock;
   }
+  // Uses pseudo probe information to attach the profile to the appropriate
+  // block.
+  const FlowBlock *matchWithPseudoProbes(
+      BlendedBlockHash BlendedHash,
+      const std::vector<yaml::bolt::PseudoProbeInfo> &PseudoProbes) const {
+    if (!YamlBFGUID)
+      return nullptr;
+
+    if (opts::Verbosity >= 3)
+      outs() << "BOLT-INFO: attempting to match block with pseudo probes\n";
+
+    // Searches for the pseudo probe attached to the matched function's block,
+    // ignoring pseudo probes attached to function calls and inlined functions'
+    // blocks.
+    std::vector<const yaml::bolt::PseudoProbeInfo *> BlockPseudoProbes;
+    for (const auto &PseudoProbe : PseudoProbes) {
+      // Ensures that pseudo probe information belongs to the appropriate
+      // function and not an inlined function.
+      if (PseudoProbe.GUID != YamlBFGUID)
+        continue;
+      // Skips pseudo probes attached to function calls.
+      if (PseudoProbe.Type != static_cast<uint8_t>(PseudoProbeType::Block))
+        continue;
+
+      BlockPseudoProbes.push_back(&PseudoProbe);
+    }
+    // Returns nullptr if there is not a 1:1 mapping of the yaml block pseudo
+    // probe and binary pseudo probe.
+    if (BlockPseudoProbes.size() == 0) {
+      if (opts::Verbosity >= 3)
+        errs() << "BOLT-WARNING: no pseudo probes in profile block\n";
+      return nullptr;
+    }
+    if (BlockPseudoProbes.size() > 1) {
+      if (opts::Verbosity >= 3)
+        errs() << "BOLT-WARNING: more than 1 pseudo probes in profile block\n";
+      return nullptr;
+    }
+    uint64_t Index = BlockPseudoProbes[0]->Index;
+    auto It = IndexToBBPseudoProbes.find(Index);
+    if (It == IndexToBBPseudoProbes.end()) {
+      if (opts::Verbosity >= 3)
+        errs() << "BOLT-WARNING: no block pseudo probes found within binary "
+                  "block at index\n";
+      return nullptr;
+    }
+    if (It->second.size() > 1) {
+      if (opts::Verbosity >= 3)
+        errs() << "BOLT-WARNING: more than 1 block pseudo probes in binary "
+                  "block at index\n";
+      return nullptr;
+    }
+    const MCDecodedPseudoProbe *BinaryPseudoProbe = It->second[0];
+    auto BinaryPseudoProbeIt = BBPseudoProbeToBlock.find(BinaryPseudoProbe);
+    assert(BinaryPseudoProbeIt != BBPseudoProbeToBlock.end() &&
+           "All binary pseudo probes should belong a binary basic block");
+
+    return BinaryPseudoProbeIt->second;
+  }
 };
 
 void BinaryFunction::computeBlockHashes(HashFunction HashFunction) const {
@@ -447,15 +553,36 @@ createFlowFunction(const BinaryFunction::BasicBlockOrderType &BlockOrder) {
 /// of the basic blocks in the binary, the count is "matched" to the block.
 /// Similarly, if both the source and the target of a count in the profile are
 /// 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, HashFunction HashFunction,
-                     YAMLProfileReader::ProfileLookupMap &IdToYamlBF) {
+size_t matchWeightsByHashes(
+    BinaryContext &BC, const BinaryFunction::BasicBlockOrderType &BlockOrder,
+    const yaml::bolt::BinaryFunctionProfile &YamlBF, FlowFunction &Func,
+    HashFunction HashFunction, YAMLProfileReader::ProfileLookupMap &IdToYamlBF,
+    const BinaryFunction &BF) {
 
   assert(Func.Blocks.size() == BlockOrder.size() + 2);
 
+  // Sets the YamlBFGUID in the StaleMatcher such that if either the profiled or
+  // binary function dne or they are not equal, to zero, as not to perform
+  // pseudo probe block matching. Otherwise, the YamlBF's GUID is used for
+  // pseudo probe block matching.
+  const MCPseudoProbeDecoder *PseudoProbeDecoder =
+      opts::ProfileUsePseudoProbes ? BC.getPseudoProbeDecoder() : nullptr;
+  uint64_t BFPseudoProbeDescHash = 0;
+  if (opts::ProfileUsePseudoProbes && BF.getGUID() != 0) {
+    assert(PseudoProbeDecoder &&
+           "If BF has pseudo probe, BC should have a pseudo probe decoder");
+    auto &GUID2FuncDescMap = PseudoProbeDecoder->getGUID2FuncDescMap();
+    auto It = GUID2FuncDescMap.find(BF.getGUID());
+    if (It != GUID2FuncDescMap.end())
+      BFPseudoProbeDescHash = It->second.FuncHash;
+  }
+  uint64_t YamlBFGUID =
+      BFPseudoProbeDescHash && YamlBF.PseudoProbeDescHash &&
+              BFPseudoProbeDescHash == YamlBF.PseudoProbeDescHash
+          ? static_cast<uint64_t>(YamlBF.GUID)
+          : 0;
+
+  StaleMatcher Matcher(YamlBFGUID);
   std::vector<uint64_t> CallHashes;
   std::vector<FlowBlock *> Blocks;
   std::vector<BlendedBlockHash> BlendedHashes;
@@ -478,10 +605,31 @@ matchWeightsByHashes(BinaryContext &BC,
     Blocks.push_back(&Func.Blocks[I + 1]);
     BlendedBlockHash BlendedHash(BB->getHash());
     BlendedHashes.push_back(BlendedHash);
+    // Collects pseudo probes attached to the BB for use in the StaleMatcher.
+    if (opts::ProfileUsePseudoProbes && PseudoProbeDecoder) {
+      const AddressProbesMap &ProbeMap =
+          PseudoProbeDecoder->getAddress2ProbesMap();
+      const uint64_t FuncAddr = BF.getAddress();
+      const std::pair<uint64_t, uint64_t> &BlockRange =
+          BB->getInputAddressRange();
+      const auto &BlockProbes =
+          llvm::make_range(ProbeMap.lower_bound(FuncAddr + BlockRange.first),
+                           ProbeMap.lower_bound(FuncAddr + BlockRange.second));
+      for (const auto &[_, Probes] : BlockProbes) {
+        for (const MCDecodedPseudoProbe &Probe : Probes) {
+          if (Probe.getInlineTreeNode()->hasInlineSite())
+            continue;
+          if (Probe.getType() != static_cast<uint8_t>(PseudoProbeType::Block))
+            continue;
+          Matcher.mapIndexToProbe(Probe.getIndex(), &Probe);
+          Matcher.mapProbeToBB(&Probe, Blocks[I]);
+        }
+      }
+    }
+
     LLVM_DEBUG(dbgs() << "BB with index " << I << " has hash = "
                       << Twine::utohexstr(BB->getHash()) << "\n");
   }
-  StaleMatcher Matcher;
   Matcher.init(Blocks, BlendedHashes, CallHashes);
 
   // Index in yaml profile => corresponding (matched) block
@@ -502,7 +650,7 @@ matchWeightsByHashes(BinaryContext &BC,
       else
         llvm_unreachable("Unhandled HashFunction");
     }
-    MatchedBlock = Matcher.matchBlock(YamlHash, CallHash);
+    MatchedBlock = Matcher.matchBlock(YamlHash, CallHash, YamlBB.PseudoProbes);
     if (MatchedBlock == nullptr && YamlBB.Index == 0)
       MatchedBlock = Blocks[0];
     if (MatchedBlock != nullptr) {
@@ -516,9 +664,13 @@ matchWeightsByHashes(BinaryContext &BC,
                         << "\n");
       // Update matching stats accounting for the matched block.
       if (Matcher.isHighConfidenceMatch(BinHash, YamlHash)) {
-        ++BC.Stats.NumMatchedBlocks;
-        BC.Stats.MatchedSampleCount += YamlBB.ExecCount;
+        ++BC.Stats.NumExactMatchedBlocks;
+        BC.Stats.ExactMatchedSampleCount += YamlBB.ExecCount;
         LLVM_DEBUG(dbgs() << "  exact match\n");
+      } else if (Matcher.isPseudoProbeMatch(YamlHash)) {
+        ++BC.Stats.NumPseudoProbeMatchedBlocks;
+        BC.Stats.PseudoProbeMatchedSampleCount += YamlBB.ExecCount;
+        LLVM_DEBUG(dbgs() << "  pseudo probe match\n");
       } else {
         LLVM_DEBUG(dbgs() << "  loose match\n");
       }
@@ -535,6 +687,13 @@ matchWeightsByHashes(BinaryContext &BC,
     BC.Stats.StaleSampleCount += YamlBB.ExecCount;
   }
 
+  if (opts::Verbosity >= 2) {
+    outs() << "BOLT-INFO: " << Matcher.getNumBlocksMatchedWithPseudoProbes()
+           << " blocks matched with pseudo probes\n"
+           << "BOLT-INFO: " << Matcher.getNumBlocksMatchedWithOpcodes()
+           << " blocks matched with opcodes\n";
+  }
+
   // Match jumps from the profile to the jumps from CFG
   std::vector<uint64_t> OutWeight(Func.Blocks.size(), 0);
   std::vector<uint64_t> InWeight(Func.Blocks.size(), 0);
@@ -828,7 +987,7 @@ bool YAMLProfileReader::inferStaleProfile(
   // Match as many block/jump counts from the stale profile as possible
   size_t MatchedBlocks =
       matchWeightsByHashes(BF.getBinaryContext(), BlockOrder, YamlBF, Func,
-                           YamlBP.Header.HashFunction, IdToYamLBF);
+                           YamlBP.Header.HashFunction, IdToYamLBF, BF);
 
   // Adjust the flow function by marking unreachable blocks Unlikely so that
   // they don't get any counts assigned.

bolt/test/X86/match-blocks-with-pseudo-probes.test

@@ -0,0 +1,62 @@
+## Tests stale block matching with pseudo probes.
+
+# REQUIRES: system-linux
+# RUN: split-file %s %t
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %t/main.s -o %t.o
+# RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib
+# RUN: llvm-bolt %t.exe -o %t.out --data %t/yaml -v=2 \
+# RUN:   --print-cfg --funcs=main --profile-ignore-hash=0 --infer-stale-profile --profile-use-pseudo-probes 2>&1 | FileCheck %s
+
+# CHECK: BOLT-INFO: inference found a pseudo probe match for 100.00% of basic blocks (1 out of 1 stale) responsible for -nan% samples (0 out of 0 stale)
+
+#--- main.s
+ .text
+  .globl  main                            # -- Begin function main
+  .p2align        4, 0x90
+  .type   main,@function
+main:                                   # @main
+# %bb.0:
+  pushq   %rbp
+  movq    %rsp, %rbp
+  movl    $0, -4(%rbp)
+  .pseudoprobe    15822663052811949562 1 0 0 main
+  xorl    %eax, %eax
+  popq    %rbp
+  retq
+.Lfunc_end0:
+  .size   main, .Lfunc_end0-main
+                                  # -- End function
+  .section        .pseudo_probe_desc,"",@progbits
+  .quad   -2624081020897602054
+  .quad   4294967295
+  .byte   4
+  .ascii  "main"
+  .ident  "clang version 17.0.6 (CentOS 17.0.6-5.el9)"
+  .section        ".note.GNU-stack","",@progbits
+  .addrsig
+
+#--- yaml
+---
+header:
+  profile-version: 1
+  binary-name:     'match-blocks-with-pseudo-probes.s.tmp.exe'
+  binary-build-id: '<unknown>'
+  profile-flags:   [ lbr ]
+  profile-origin:  branch profile reader
+  profile-events:  ''
+  dfs-order:       false
+  hash-func:       xxh3
+functions:
+  - name:                   main
+    fid:                    0
+    hash:                   0x0000000000000001
+    exec:                   1
+    nblocks:                6
+    guid:                   0xDB956436E78DD5FA
+    pseudo_probe_desc_hash: 4294967295
+    blocks:
+      - bid:             1
+        hash:            0x0000000000000001
+        insns:           1
+        succ:            [ { bid: 3, cnt: 1} ]
+        pseudo_probes: [ { guid: 0xDB956436E78DD5FA, id: 1, type: 0 } ]

clang/include/clang/Driver/Options.td

@@ -5566,6 +5566,10 @@ def pg : Flag<["-"], "pg">, HelpText<"Enable mcount instrumentation">,
   MarshallingInfoFlag<CodeGenOpts<"InstrumentForProfiling">>;
 def pipe : Flag<["-", "--"], "pipe">,
   HelpText<"Use pipes between commands, when possible">;
+// Facebook T92898286
+def post_link_optimize : Flag<["--"], "post-link-optimize">,
+  HelpText<"Apply post-link optimizations using BOLT">;
+// End Facebook T92898286
 def prebind__all__twolevel__modules : Flag<["-"], "prebind_all_twolevel_modules">;
 def prebind : Flag<["-"], "prebind">;
 def preload : Flag<["-"], "preload">;