[Profiling] Add a -sparse mode to llvm-profdata merge

Add an option to llvm-profdata merge for writing out sparse indexed
profiles. These profiles omit InstrProfRecords for functions which are
never executed.

Differential Revision: http://reviews.llvm.org/D16727

llvm-svn: 259258

llvm/docs/CommandGuide/llvm-profdata.rst

@@ -90,6 +90,12 @@ OPTIONS
 
  Emit the profile using GCC's gcov format (Not yet supported).
 
+ .. option:: -sparse[=true|false]
+
+ Do not emit function records with 0 execution count. Can only be used in
+ conjunction with -instr. Defaults to false, since it can inhibit compiler
+ optimization during PGO.
+
 EXAMPLES
 ^^^^^^^^
 Basic Usage

llvm/include/llvm/ProfileData/InstrProfWriter.h

@@ -32,13 +32,14 @@ class InstrProfWriter {
   typedef SmallDenseMap<uint64_t, InstrProfRecord, 1> ProfilingData;
 
 private:
+  bool Sparse;
   StringMap<ProfilingData> FunctionData;
   uint64_t MaxFunctionCount;
   // Use raw pointer here for the incomplete type object.
   InstrProfRecordWriterTrait *InfoObj;
 
 public:
-  InstrProfWriter();
+  InstrProfWriter(bool Sparse = false);
   ~InstrProfWriter();
 
   /// Add function counts for the given function. If there are already counts
@@ -57,8 +58,10 @@ class InstrProfWriter {
 
   // Internal interface for testing purpose only.
   void setValueProfDataEndianness(support::endianness Endianness);
+  void setOutputSparse(bool Sparse);
 
 private:
+  bool shouldEncodeData(const ProfilingData &PD);
   void writeImpl(ProfOStream &OS);
 };
 

llvm/lib/ProfileData/InstrProfWriter.cpp

@@ -139,8 +139,8 @@ class InstrProfRecordWriterTrait {
 };
 }
 
-InstrProfWriter::InstrProfWriter()
-    : FunctionData(), MaxFunctionCount(0),
+InstrProfWriter::InstrProfWriter(bool Sparse)
+    : Sparse(Sparse), FunctionData(), MaxFunctionCount(0),
       InfoObj(new InstrProfRecordWriterTrait()) {}
 
 InstrProfWriter::~InstrProfWriter() { delete InfoObj; }
@@ -150,6 +150,9 @@ void InstrProfWriter::setValueProfDataEndianness(
     support::endianness Endianness) {
   InfoObj->ValueProfDataEndianness = Endianness;
 }
+void InstrProfWriter::setOutputSparse(bool Sparse) {
+  this->Sparse = Sparse;
+}
 
 std::error_code InstrProfWriter::addRecord(InstrProfRecord &&I,
                                            uint64_t Weight) {
@@ -184,11 +187,24 @@ std::error_code InstrProfWriter::addRecord(InstrProfRecord &&I,
   return Result;
 }
 
+bool InstrProfWriter::shouldEncodeData(const ProfilingData &PD) {
+  if (!Sparse)
+    return true;
+  for (const auto &Func : PD) {
+    const InstrProfRecord &IPR = Func.second;
+    if (std::any_of(IPR.Counts.begin(), IPR.Counts.end(),
+                    [](uint64_t Count) { return Count > 0; }))
+      return true;
+  }
+  return false;
+}
+
 void InstrProfWriter::writeImpl(ProfOStream &OS) {
   OnDiskChainedHashTableGenerator<InstrProfRecordWriterTrait> Generator;
   // Populate the hash table generator.
   for (const auto &I : FunctionData)
-    Generator.insert(I.getKey(), &I.getValue());
+    if (shouldEncodeData(I.getValue()))
+      Generator.insert(I.getKey(), &I.getValue());
   // Write the header.
   IndexedInstrProf::Header Header;
   Header.Magic = IndexedInstrProf::Magic;
@@ -279,10 +295,12 @@ void InstrProfWriter::writeRecordInText(const InstrProfRecord &Func,
 void InstrProfWriter::writeText(raw_fd_ostream &OS) {
   InstrProfSymtab Symtab;
   for (const auto &I : FunctionData)
-    Symtab.addFuncName(I.getKey());
+    if (shouldEncodeData(I.getValue()))
+      Symtab.addFuncName(I.getKey());
   Symtab.finalizeSymtab();
 
   for (const auto &I : FunctionData)
-    for (const auto &Func : I.getValue())
-      writeRecordInText(Func.second, Symtab, OS);
+    if (shouldEncodeData(I.getValue()))
+      for (const auto &Func : I.getValue())
+        writeRecordInText(Func.second, Symtab, OS);
 }

llvm/test/tools/llvm-profdata/general.proftext

@@ -1,6 +1,6 @@
+# RUN: llvm-profdata merge -sparse=true %s -o %t.profdata
 
-
-# RUN: llvm-profdata merge %s -o %t.profdata
+# RUN: llvm-profdata merge -sparse=false %s -o %t.profdata.dense
 
 # RUN: llvm-profdata show %t.profdata --function function_count_only --counts | FileCheck %s -check-prefix=FUNC_COUNT_ONLY
 function_count_only
@@ -12,7 +12,8 @@ function_count_only
 # FUNC_COUNT_ONLY-NEXT: Function count: 97531
 # FUNC_COUNT_ONLY-NEXT: Block counts: []
 
-# RUN: llvm-profdata show %t.profdata --function "name with spaces" --counts | FileCheck %s -check-prefix=SPACES
+# RUN: llvm-profdata show %t.profdata.dense --function "name with spaces" --counts | FileCheck %s -check-prefix=SPACES
+# RUN: llvm-profdata show %t.profdata --function "name with spaces" --counts | FileCheck %s --check-prefix=SPARSE_SPACES
 name with spaces
 1024
 2
@@ -22,6 +23,7 @@ name with spaces
 # SPACES-NEXT: Counters: 2
 # SPACES-NEXT: Function count: 0
 # SPACES-NEXT: Block counts: [0]
+# SPARSE_SPACES-NOT: Function count: 0
 
 # RUN: llvm-profdata show %t.profdata --function large_numbers --counts | FileCheck %s -check-prefix=LARGENUM
 large_numbers
@@ -38,7 +40,7 @@ large_numbers
 # LARGENUM-NEXT: Function count: 2305843009213693952
 # LARGENUM-NEXT: Block counts: [1152921504606846976, 576460752303423488, 288230376151711744, 144115188075855872, 72057594037927936]
 
-# RUN: llvm-profdata show %t.profdata --function hex_hash | FileCheck %s -check-prefix=HEX-HASH
+# RUN: llvm-profdata show %t.profdata.dense --function hex_hash | FileCheck %s -check-prefix=HEX-HASH
 hex_hash
 0x1234
 1
@@ -51,19 +53,21 @@ hex_hash
 # NOSUCHFUNC: Functions shown: 0
 
 # RUN: llvm-profdata show %t.profdata --function _ | FileCheck %s -check-prefix=SOMEFUNCS
+# RUN: llvm-profdata show %t.profdata.dense --function _ | FileCheck %s -check-prefix=SOMEFUNCS_DENSE
 # SOMEFUNCS: Counters:
 # SOMEFUNCS: function_count_only:
 # SOMEFUNCS: large_numbers:
-# SOMEFUNCS: Functions shown: 3
+# SOMEFUNCS: Functions shown: 2
+# SOMEFUNCS_DENSE: Functions shown: 3
 
-# RUN: llvm-profdata show %t.profdata | FileCheck %s -check-prefix=SUMMARY
+# RUN: llvm-profdata show %t.profdata.dense | FileCheck %s -check-prefix=SUMMARY
 # SUMMARY-NOT: Counters:
 # SUMMARY-NOT: Functions shown:
 # SUMMARY: Total functions: 4
 # SUMMARY: Maximum function count: 2305843009213693952
 # SUMMARY: Maximum internal block count: 1152921504606846976
 
-# RUN: llvm-profdata show --detailed-summary %t.profdata | FileCheck %s -check-prefix=DETAILED-SUMMARY
+# RUN: llvm-profdata show --detailed-summary %t.profdata.dense | FileCheck %s -check-prefix=DETAILED-SUMMARY
 # DETAILED-SUMMARY: Detailed summary:
 # DETAILED-SUMMARY: Total number of blocks: 10
 # DETAILED-SUMMARY: Total count: 4539628424389557499

llvm/tools/llvm-profdata/llvm-profdata.cpp

@@ -107,7 +107,7 @@ typedef SmallVector<WeightedFile, 5> WeightedFileVector;
 
 static void mergeInstrProfile(const WeightedFileVector &Inputs,
                               StringRef OutputFilename,
-                              ProfileFormat OutputFormat) {
+                              ProfileFormat OutputFormat, bool OutputSparse) {
   if (OutputFilename.compare("-") == 0)
     exitWithError("Cannot write indexed profdata format to stdout.");
 
@@ -119,7 +119,7 @@ static void mergeInstrProfile(const WeightedFileVector &Inputs,
   if (EC)
     exitWithErrorCode(EC, OutputFilename);
 
-  InstrProfWriter Writer;
+  InstrProfWriter Writer(OutputSparse);
   SmallSet<std::error_code, 4> WriterErrorCodes;
   for (const auto &Input : Inputs) {
     auto ReaderOrErr = InstrProfReader::create(Input.Filename);
@@ -228,6 +228,9 @@ static int merge_main(int argc, const char *argv[]) {
                             "GCC encoding (only meaningful for -sample)"),
                  clEnumValEnd));
 
+  cl::opt<bool> OutputSparse("sparse", cl::init(false),
+      cl::desc("Generate a sparse profile (only meaningful for -instr)"));
+
   cl::ParseCommandLineOptions(argc, argv, "LLVM profile data merger\n");
 
   if (InputFilenames.empty() && WeightedInputFilenames.empty())
@@ -241,7 +244,8 @@ static int merge_main(int argc, const char *argv[]) {
     WeightedInputs.push_back(parseWeightedFile(WeightedFilename));
 
   if (ProfileKind == instr)
-    mergeInstrProfile(WeightedInputs, OutputFilename, OutputFormat);
+    mergeInstrProfile(WeightedInputs, OutputFilename, OutputFormat,
+                      OutputSparse);
   else
     mergeSampleProfile(WeightedInputs, OutputFilename, OutputFormat);
 

llvm/unittests/ProfileData/CoverageMappingTest.cpp

@@ -92,6 +92,7 @@ struct CoverageMappingTest : ::testing::Test {
 
   void SetUp() override {
     NextFile = 0;
+    ProfileWriter.setOutputSparse(false);
   }
 
   unsigned getFile(StringRef Name) {
@@ -154,7 +155,16 @@ struct CoverageMappingTest : ::testing::Test {
   }
 };
 
-TEST_F(CoverageMappingTest, basic_write_read) {
+struct MaybeSparseCoverageMappingTest
+    : public CoverageMappingTest,
+      public ::testing::WithParamInterface<bool> {
+  void SetUp() {
+    CoverageMappingTest::SetUp();
+    ProfileWriter.setOutputSparse(GetParam());
+  }
+};
+
+TEST_P(MaybeSparseCoverageMappingTest, basic_write_read) {
   addCMR(Counter::getCounter(0), "foo", 1, 1, 1, 1);
   addCMR(Counter::getCounter(1), "foo", 2, 1, 2, 2);
   addCMR(Counter::getZero(),     "foo", 3, 1, 3, 4);
@@ -174,7 +184,7 @@ TEST_F(CoverageMappingTest, basic_write_read) {
   }
 }
 
-TEST_F(CoverageMappingTest, expansion_gets_first_counter) {
+TEST_P(MaybeSparseCoverageMappingTest, expansion_gets_first_counter) {
   addCMR(Counter::getCounter(1), "foo", 10, 1, 10, 2);
   // This starts earlier in "foo", so the expansion should get its counter.
   addCMR(Counter::getCounter(2), "foo", 1, 1, 20, 1);
@@ -187,7 +197,7 @@ TEST_F(CoverageMappingTest, expansion_gets_first_counter) {
   ASSERT_EQ(3U, OutputCMRs[2].LineStart);
 }
 
-TEST_F(CoverageMappingTest, basic_coverage_iteration) {
+TEST_P(MaybeSparseCoverageMappingTest, basic_coverage_iteration) {
   InstrProfRecord Record("func", 0x1234, {30, 20, 10, 0});
   ProfileWriter.addRecord(std::move(Record));
   readProfCounts();
@@ -210,7 +220,7 @@ TEST_F(CoverageMappingTest, basic_coverage_iteration) {
   ASSERT_EQ(CoverageSegment(11, 11, false),   Segments[6]);
 }
 
-TEST_F(CoverageMappingTest, uncovered_function) {
+TEST_P(MaybeSparseCoverageMappingTest, uncovered_function) {
   readProfCounts();
 
   addCMR(Counter::getZero(), "file1", 1, 2, 3, 4);
@@ -223,7 +233,7 @@ TEST_F(CoverageMappingTest, uncovered_function) {
   ASSERT_EQ(CoverageSegment(3, 4, false),   Segments[1]);
 }
 
-TEST_F(CoverageMappingTest, uncovered_function_with_mapping) {
+TEST_P(MaybeSparseCoverageMappingTest, uncovered_function_with_mapping) {
   readProfCounts();
 
   addCMR(Counter::getCounter(0), "file1", 1, 1, 9, 9);
@@ -238,7 +248,7 @@ TEST_F(CoverageMappingTest, uncovered_function_with_mapping) {
   ASSERT_EQ(CoverageSegment(9, 9, false),    Segments[2]);
 }
 
-TEST_F(CoverageMappingTest, combine_regions) {
+TEST_P(MaybeSparseCoverageMappingTest, combine_regions) {
   InstrProfRecord Record("func", 0x1234, {10, 20, 30});
   ProfileWriter.addRecord(std::move(Record));
   readProfCounts();
@@ -257,9 +267,11 @@ TEST_F(CoverageMappingTest, combine_regions) {
   ASSERT_EQ(CoverageSegment(9, 9, false), Segments[3]);
 }
 
-TEST_F(CoverageMappingTest, dont_combine_expansions) {
-  InstrProfRecord Record("func", 0x1234, {10, 20});
-  ProfileWriter.addRecord(std::move(Record));
+TEST_P(MaybeSparseCoverageMappingTest, dont_combine_expansions) {
+  InstrProfRecord Record1("func", 0x1234, {10, 20});
+  InstrProfRecord Record2("func", 0x1234, {0, 0});
+  ProfileWriter.addRecord(std::move(Record1));
+  ProfileWriter.addRecord(std::move(Record2));
   readProfCounts();
 
   addCMR(Counter::getCounter(0), "file1", 1, 1, 9, 9);
@@ -277,8 +289,8 @@ TEST_F(CoverageMappingTest, dont_combine_expansions) {
   ASSERT_EQ(CoverageSegment(9, 9, false), Segments[3]);
 }
 
-TEST_F(CoverageMappingTest, strip_filename_prefix) {
-  InstrProfRecord Record("file1:func", 0x1234, {10});
+TEST_P(MaybeSparseCoverageMappingTest, strip_filename_prefix) {
+  InstrProfRecord Record("file1:func", 0x1234, {0});
   ProfileWriter.addRecord(std::move(Record));
   readProfCounts();
 
@@ -292,4 +304,7 @@ TEST_F(CoverageMappingTest, strip_filename_prefix) {
   ASSERT_EQ("func", Names[0]);
 }
 
+INSTANTIATE_TEST_CASE_P(MaybeSparse, MaybeSparseCoverageMappingTest,
+                        ::testing::Bool());
+
 } // end anonymous namespace