Retry: [llvm-profdata] Speed up merging by using a thread pool

Add a "-j" option to llvm-profdata to control the number of threads used.
Auto-detect NumThreads when it isn't specified, and avoid spawning threads when
they wouldn't be beneficial.

I tested this patch using a raw profile produced by clang (147MB). Here is the
time taken to merge 4 copies together on my laptop:

  No thread pool: 112.87s user 5.92s system 97% cpu 2:01.08 total
  With 2 threads: 134.99s user 26.54s system 164% cpu 1:33.31 total

Changes since the initial commit:

  - When handling odd-length inputs, call ThreadPool::wait() before merging the
    last profile. Should fix a race/off-by-one (see r275937).

Differential Revision: https://reviews.llvm.org/D22438

llvm-svn: 275938

docs/CommandGuide/llvm-profdata.rst

@@ -106,6 +106,11 @@ OPTIONS
  conjunction with -instr. Defaults to false, since it can inhibit compiler
  optimization during PGO.
 
+.. option:: -num-threads=N, -j=N
+
+ Use N threads to perform profile merging. When N=0, llvm-profdata auto-detects
+ an appropriate number of threads to use. This is the default.
+
 EXAMPLES
 ^^^^^^^^
 Basic Usage

include/llvm/ProfileData/InstrProfWriter.h

@@ -47,6 +47,8 @@ public:
   /// for this function and the hash and number of counts match, each counter is
   /// summed. Optionally scale counts by \p Weight.
   Error addRecord(InstrProfRecord &&I, uint64_t Weight = 1);
+  /// Merge existing function counts from the given writer.
+  Error mergeRecordsFromWriter(InstrProfWriter &&IPW);
   /// Write the profile to \c OS
   void write(raw_fd_ostream &OS);
   /// Write the profile in text format to \c OS

lib/ProfileData/InstrProfWriter.cpp

@@ -182,6 +182,14 @@ Error InstrProfWriter::addRecord(InstrProfRecord &&I, uint64_t Weight) {
   return Dest.takeError();
 }
 
+Error InstrProfWriter::mergeRecordsFromWriter(InstrProfWriter &&IPW) {
+  for (auto &I : IPW.FunctionData)
+    for (auto &Func : I.getValue())
+      if (Error E = addRecord(std::move(Func.second), 1))
+        return E;
+  return Error::success();
+}
+
 bool InstrProfWriter::shouldEncodeData(const ProfilingData &PD) {
   if (!Sparse)
     return true;

test/tools/llvm-profdata/multiple-inputs.test

@@ -51,3 +51,43 @@ DISJOINT-2: Block counts: [2, 3]
 DISJOINT: Total functions: 2
 DISJOINT: Maximum function count: 1
 DISJOINT: Maximum internal block count: 3
+
+RUN: llvm-profdata merge %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     -num-threads 2 -o %t
+RUN: llvm-profdata show %t -all-functions -counts | FileCheck %s --check-prefix=FOO4
+RUN: llvm-profdata merge %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     -j 3 -o %t
+RUN: llvm-profdata show %t -all-functions -counts | FileCheck %s --check-prefix=FOO4
+FOO4: foo:
+FOO4: Counters: 3
+FOO4: Function count: 4
+FOO4: Block counts: [8, 12]
+FOO4: Total functions: 1
+FOO4: Maximum function count: 4
+FOO4: Maximum internal block count: 12
+
+RUN: llvm-profdata merge %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext -j 2 -o %t
+RUN: llvm-profdata show %t -all-functions -counts | FileCheck %s --check-prefix=FOO5
+RUN: llvm-profdata merge %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext -j 3 -o %t
+RUN: llvm-profdata show %t -all-functions -counts | FileCheck %s --check-prefix=FOO5
+RUN: llvm-profdata merge %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext -o %t
+RUN: llvm-profdata show %t -all-functions -counts | FileCheck %s --check-prefix=FOO5
+RUN: llvm-profdata merge %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext %p/Inputs/foo3-1.proftext \
+RUN:                     %p/Inputs/foo3-1.proftext -j 1 -o %t
+RUN: llvm-profdata show %t -all-functions -counts | FileCheck %s --check-prefix=FOO5
+FOO5: foo:
+FOO5: Counters: 3
+FOO5: Function count: 5
+FOO5: Block counts: [10, 15]
+FOO5: Total functions: 1
+FOO5: Maximum function count: 5
+FOO5: Maximum internal block count: 15

tools/llvm-profdata/llvm-profdata.cpp

@@ -29,6 +29,7 @@
 #include "llvm/Support/Path.h"
 #include "llvm/Support/PrettyStackTrace.h"
 #include "llvm/Support/Signals.h"
+#include "llvm/Support/ThreadPool.h"
 #include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 
@@ -117,9 +118,68 @@ struct WeightedFile {
 };
 typedef SmallVector<WeightedFile, 5> WeightedFileVector;
 
+/// Keep track of merged data and reported errors.
+struct WriterContext {
+  std::mutex Lock;
+  InstrProfWriter Writer;
+  Error Err;
+  StringRef ErrWhence;
+  std::mutex &ErrLock;
+  SmallSet<instrprof_error, 4> &WriterErrorCodes;
+
+  WriterContext(bool IsSparse, std::mutex &ErrLock,
+                SmallSet<instrprof_error, 4> &WriterErrorCodes)
+      : Lock(), Writer(IsSparse), Err(Error::success()), ErrWhence(""),
+        ErrLock(ErrLock), WriterErrorCodes(WriterErrorCodes) {}
+};
+
+/// Load an input into a writer context.
+static void loadInput(const WeightedFile &Input, WriterContext *WC) {
+  std::unique_lock<std::mutex> CtxGuard{WC->Lock};
+
+  // If there's a pending hard error, don't do more work.
+  if (WC->Err)
+    return;
+
+  WC->ErrWhence = Input.Filename;
+
+  auto ReaderOrErr = InstrProfReader::create(Input.Filename);
+  if ((WC->Err = ReaderOrErr.takeError()))
+    return;
+
+  auto Reader = std::move(ReaderOrErr.get());
+  bool IsIRProfile = Reader->isIRLevelProfile();
+  if (WC->Writer.setIsIRLevelProfile(IsIRProfile)) {
+    WC->Err = make_error<StringError>(
+        "Merge IR generated profile with Clang generated profile.",
+        std::error_code());
+    return;
+  }
+
+  for (auto &I : *Reader) {
+    if (Error E = WC->Writer.addRecord(std::move(I), Input.Weight)) {
+      // Only show hint the first time an error occurs.
+      instrprof_error IPE = InstrProfError::take(std::move(E));
+      std::unique_lock<std::mutex> ErrGuard{WC->ErrLock};
+      bool firstTime = WC->WriterErrorCodes.insert(IPE).second;
+      handleMergeWriterError(make_error<InstrProfError>(IPE), Input.Filename,
+                             I.Name, firstTime);
+    }
+  }
+  if (Reader->hasError())
+    WC->Err = Reader->getError();
+}
+
+/// Merge the \p Src writer context into \p Dst.
+static void mergeWriterContexts(WriterContext *Dst, WriterContext *Src) {
+  if (Error E = Dst->Writer.mergeRecordsFromWriter(std::move(Src->Writer)))
+    Dst->Err = std::move(E);
+}
+
 static void mergeInstrProfile(const WeightedFileVector &Inputs,
                               StringRef OutputFilename,
-                              ProfileFormat OutputFormat, bool OutputSparse) {
+                              ProfileFormat OutputFormat, bool OutputSparse,
+                              unsigned NumThreads) {
   if (OutputFilename.compare("-") == 0)
     exitWithError("Cannot write indexed profdata format to stdout.");
 
@@ -131,30 +191,59 @@ static void mergeInstrProfile(const WeightedFileVector &Inputs,
   if (EC)
     exitWithErrorCode(EC, OutputFilename);
 
-  InstrProfWriter Writer(OutputSparse);
+  std::mutex ErrorLock;
   SmallSet<instrprof_error, 4> WriterErrorCodes;
-  for (const auto &Input : Inputs) {
-    auto ReaderOrErr = InstrProfReader::create(Input.Filename);
-    if (Error E = ReaderOrErr.takeError())
-      exitWithError(std::move(E), Input.Filename);
 
-    auto Reader = std::move(ReaderOrErr.get());
-    bool IsIRProfile = Reader->isIRLevelProfile();
-    if (Writer.setIsIRLevelProfile(IsIRProfile))
-      exitWithError("Merge IR generated profile with Clang generated profile.");
+  // If NumThreads is not specified, auto-detect a good default.
+  if (NumThreads == 0)
+    NumThreads = std::max(1U, std::min(std::thread::hardware_concurrency(),
+                                       unsigned(Inputs.size() / 2)));
 
-    for (auto &I : *Reader) {
-      if (Error E = Writer.addRecord(std::move(I), Input.Weight)) {
-        // Only show hint the first time an error occurs.
-        instrprof_error IPE = InstrProfError::take(std::move(E));
-        bool firstTime = WriterErrorCodes.insert(IPE).second;
-        handleMergeWriterError(make_error<InstrProfError>(IPE), Input.Filename,
-                               I.Name, firstTime);
-      }
+  // Initialize the writer contexts.
+  SmallVector<std::unique_ptr<WriterContext>, 4> Contexts;
+  for (unsigned I = 0; I < NumThreads; ++I)
+    Contexts.emplace_back(llvm::make_unique<WriterContext>(
+        OutputSparse, ErrorLock, WriterErrorCodes));
+
+  if (NumThreads == 1) {
+    for (const auto &Input : Inputs)
+      loadInput(Input, Contexts[0].get());
+  } else {
+    ThreadPool Pool(NumThreads);
+
+    // Load the inputs in parallel (N/NumThreads serial steps).
+    unsigned Ctx = 0;
+    for (const auto &Input : Inputs) {
+      Pool.async(loadInput, Input, Contexts[Ctx].get());
+      Ctx = (Ctx + 1) % NumThreads;
     }
-    if (Reader->hasError())
-      exitWithError(Reader->getError(), Input.Filename);
+    Pool.wait();
+
+    // Merge the writer contexts together (~ lg(NumThreads) serial steps).
+    unsigned Mid = Contexts.size() / 2;
+    unsigned End = Contexts.size();
+    assert(Mid > 0 && "Expected more than one context");
+    do {
+      for (unsigned I = 0; I < Mid; ++I)
+        Pool.async(mergeWriterContexts, Contexts[I].get(),
+                   Contexts[I + Mid].get());
+      Pool.wait();
+      if (End & 1) {
+        Pool.async(mergeWriterContexts, Contexts[0].get(),
+                   Contexts[End - 1].get());
+        Pool.wait();
+      }
+      End = Mid;
+      Mid /= 2;
+    } while (Mid > 0);
   }
+
+  // Handle deferred hard errors encountered during merging.
+  for (std::unique_ptr<WriterContext> &WC : Contexts)
+    if (WC->Err)
+      exitWithError(std::move(WC->Err), WC->ErrWhence);
+
+  InstrProfWriter &Writer = Contexts[0]->Writer;
   if (OutputFormat == PF_Text)
     Writer.writeText(Output);
   else
@@ -288,6 +377,11 @@ static int merge_main(int argc, const char *argv[]) {
                  clEnumValEnd));
   cl::opt<bool> OutputSparse("sparse", cl::init(false),
       cl::desc("Generate a sparse profile (only meaningful for -instr)"));
+  cl::opt<unsigned> NumThreads(
+      "num-threads", cl::init(0),
+      cl::desc("Number of merge threads to use (default: autodetect)"));
+  cl::alias NumThreadsA("j", cl::desc("Alias for --num-threads"),
+                        cl::aliasopt(NumThreads));
 
   cl::ParseCommandLineOptions(argc, argv, "LLVM profile data merger\n");
 
@@ -314,7 +408,7 @@ static int merge_main(int argc, const char *argv[]) {
 
   if (ProfileKind == instr)
     mergeInstrProfile(WeightedInputs, OutputFilename, OutputFormat,
-                      OutputSparse);
+                      OutputSparse, NumThreads);
   else
     mergeSampleProfile(WeightedInputs, OutputFilename, OutputFormat);
 

unittests/ProfileData/InstrProfTest.cpp

@@ -204,6 +204,31 @@ TEST_F(InstrProfTest, get_profile_summary) {
   delete PSFromMD;
 }
 
+TEST_F(InstrProfTest, test_writer_merge) {
+  InstrProfRecord Record1("func1", 0x1234, {42});
+  NoError(Writer.addRecord(std::move(Record1)));
+
+  InstrProfWriter Writer2;
+  InstrProfRecord Record2("func2", 0x1234, {0, 0});
+  NoError(Writer2.addRecord(std::move(Record2)));
+
+  NoError(Writer.mergeRecordsFromWriter(std::move(Writer2)));
+
+  auto Profile = Writer.writeBuffer();
+  readProfile(std::move(Profile));
+
+  Expected<InstrProfRecord> R = Reader->getInstrProfRecord("func1", 0x1234);
+  ASSERT_TRUE(NoError(R.takeError()));
+  ASSERT_EQ(1U, R->Counts.size());
+  ASSERT_EQ(42U, R->Counts[0]);
+
+  R = Reader->getInstrProfRecord("func2", 0x1234);
+  ASSERT_TRUE(NoError(R.takeError()));
+  ASSERT_EQ(2U, R->Counts.size());
+  ASSERT_EQ(0U, R->Counts[0]);
+  ASSERT_EQ(0U, R->Counts[1]);
+}
+
 static const char callee1[] = "callee1";
 static const char callee2[] = "callee2";
 static const char callee3[] = "callee3";