[llvm] 5b72d0e - [llvm-profdata] Add option to cap profile output size
William Huang via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 9 14:01:20 PST 2023
Author: William Huang
Date: 2023-01-09T22:01:10Z
New Revision: 5b72d0e4f5eeb8f90c744cac8e0728cffeca61a9
URL: https://github.com/llvm/llvm-project/commit/5b72d0e4f5eeb8f90c744cac8e0728cffeca61a9
DIFF: https://github.com/llvm/llvm-project/commit/5b72d0e4f5eeb8f90c744cac8e0728cffeca61a9.diff
LOG: [llvm-profdata] Add option to cap profile output size
Allow user to specify `--output-size-limit=n` to cap the size of generated profile to be strictly under n. Functions with the lowest total sample count are dropped first if necessary. Due to using a heuristic, excessive functions may be dropped to satisfy the size requirement
Reviewed By: snehasish
Differential Revision: https://reviews.llvm.org/D139603
Added:
llvm/test/tools/llvm-profdata/output-size-limit.test
Modified:
llvm/include/llvm/ProfileData/SampleProfWriter.h
llvm/lib/ProfileData/SampleProfWriter.cpp
llvm/tools/llvm-profdata/llvm-profdata.cpp
Removed:
################################################################################
diff --git a/llvm/include/llvm/ProfileData/SampleProfWriter.h b/llvm/include/llvm/ProfileData/SampleProfWriter.h
index b1ed0335e9c93..506c902f3d129 100644
--- a/llvm/include/llvm/ProfileData/SampleProfWriter.h
+++ b/llvm/include/llvm/ProfileData/SampleProfWriter.h
@@ -35,6 +35,56 @@ enum SectionLayout {
NumOfLayout,
};
+/// When writing a profile with size limit, user may want to use a
diff erent
+/// strategy to reduce function count other than dropping functions with fewest
+/// samples first. In this case a class implementing the same interfaces should
+/// be provided to SampleProfileWriter::writeWithSizeLimit().
+class FunctionPruningStrategy {
+protected:
+ SampleProfileMap &ProfileMap;
+ size_t OutputSizeLimit;
+
+public:
+ /// \p ProfileMap A reference to the original profile map. It will be modified
+ /// by Erase().
+ /// \p OutputSizeLimit Size limit in bytes of the output profile. This is
+ /// necessary to estimate how many functions to remove.
+ FunctionPruningStrategy(SampleProfileMap &ProfileMap, size_t OutputSizeLimit)
+ : ProfileMap(ProfileMap), OutputSizeLimit(OutputSizeLimit) {}
+
+ virtual ~FunctionPruningStrategy() = default;
+
+ /// SampleProfileWriter::writeWithSizeLimit() calls this after every write
+ /// iteration if the output size still exceeds the limit. This function
+ /// should erase some functions from the profile map so that the writer tries
+ /// to write the profile again with fewer functions. At least 1 entry from the
+ /// profile map must be erased.
+ ///
+ /// \p CurrentOutputSize Number of bytes in the output if current profile map
+ /// is written.
+ virtual void Erase(size_t CurrentOutputSize) = 0;
+};
+
+class DefaultFunctionPruningStrategy : public FunctionPruningStrategy {
+ std::vector<NameFunctionSamples> SortedFunctions;
+
+public:
+ DefaultFunctionPruningStrategy(SampleProfileMap &ProfileMap,
+ size_t OutputSizeLimit);
+
+ /// In this default implementation, functions with fewest samples are dropped
+ /// first. Since the exact size of the output cannot be easily calculated due
+ /// to compression, we use a heuristic to remove as many functions as
+ /// necessary but not too many, aiming to minimize the number of write
+ /// iterations.
+ /// Empirically, functions with larger total sample count contain linearly
+ /// more sample entries, meaning it takes linearly more space to write them.
+ /// The cumulative length is therefore quadratic if all functions are sorted
+ /// by total sample count.
+ /// TODO: Find better heuristic.
+ void Erase(size_t CurrentOutputSize) override;
+};
+
/// Sample-based profile writer. Base class.
class SampleProfileWriter {
public:
@@ -50,6 +100,17 @@ class SampleProfileWriter {
/// \returns status code of the file update operation.
virtual std::error_code write(const SampleProfileMap &ProfileMap);
+ /// Write sample profiles up to given size limit, using the pruning strategy
+ /// to drop some functions if necessary.
+ ///
+ /// \returns status code of the file update operation.
+ template <typename FunctionPruningStrategy = DefaultFunctionPruningStrategy>
+ std::error_code writeWithSizeLimit(SampleProfileMap &ProfileMap,
+ size_t OutputSizeLimit) {
+ FunctionPruningStrategy Strategy(ProfileMap, OutputSizeLimit);
+ return writeWithSizeLimitInternal(ProfileMap, OutputSizeLimit, &Strategy);
+ }
+
raw_ostream &getOutputStream() { return *OutputStream; }
/// Profile writer factory.
@@ -79,6 +140,10 @@ class SampleProfileWriter {
// Write function profiles to the profile file.
virtual std::error_code writeFuncProfiles(const SampleProfileMap &ProfileMap);
+ std::error_code writeWithSizeLimitInternal(SampleProfileMap &ProfileMap,
+ size_t OutputSizeLimit,
+ FunctionPruningStrategy *Strategy);
+
/// Output stream where to emit the profile to.
std::unique_ptr<raw_ostream> OutputStream;
diff --git a/llvm/lib/ProfileData/SampleProfWriter.cpp b/llvm/lib/ProfileData/SampleProfWriter.cpp
index 093790afe2d66..e52c7bac70311 100644
--- a/llvm/lib/ProfileData/SampleProfWriter.cpp
+++ b/llvm/lib/ProfileData/SampleProfWriter.cpp
@@ -30,6 +30,7 @@
#include "llvm/Support/MD5.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
+#include <cmath>
#include <cstdint>
#include <memory>
#include <set>
@@ -37,9 +38,96 @@
#include <utility>
#include <vector>
+#define DEBUG_TYPE "llvm-profdata"
+
using namespace llvm;
using namespace sampleprof;
+namespace llvm {
+namespace support {
+namespace endian {
+namespace {
+
+// Adapter class to llvm::support::endian::Writer for pwrite().
+struct SeekableWriter {
+ raw_pwrite_stream &OS;
+ endianness Endian;
+ SeekableWriter(raw_pwrite_stream &OS, endianness Endian)
+ : OS(OS), Endian(Endian) {}
+
+ template <typename ValueType>
+ void pwrite(ValueType Val, size_t Offset) {
+ std::string StringBuf;
+ raw_string_ostream SStream(StringBuf);
+ Writer(SStream, Endian).write(Val);
+ OS.pwrite(StringBuf.data(), StringBuf.size(), Offset);
+ }
+};
+
+} // namespace
+} // namespace endian
+} // namespace support
+} // namespace llvm
+
+DefaultFunctionPruningStrategy::DefaultFunctionPruningStrategy(
+ SampleProfileMap &ProfileMap, size_t OutputSizeLimit)
+ : FunctionPruningStrategy(ProfileMap, OutputSizeLimit) {
+ sortFuncProfiles(ProfileMap, SortedFunctions);
+}
+
+void DefaultFunctionPruningStrategy::Erase(size_t CurrentOutputSize) {
+ double D = (double)OutputSizeLimit / CurrentOutputSize;
+ size_t NewSize = (size_t)round(ProfileMap.size() * D * D);
+ size_t NumToRemove = ProfileMap.size() - NewSize;
+ if (NumToRemove < 1)
+ NumToRemove = 1;
+
+ assert(NumToRemove <= SortedFunctions.size());
+ llvm::for_each(
+ llvm::make_range(SortedFunctions.begin() + SortedFunctions.size() -
+ NumToRemove,
+ SortedFunctions.end()),
+ [&](const NameFunctionSamples &E) { ProfileMap.erase(E.first); });
+ SortedFunctions.resize(SortedFunctions.size() - NumToRemove);
+}
+
+std::error_code SampleProfileWriter::writeWithSizeLimitInternal(
+ SampleProfileMap &ProfileMap, size_t OutputSizeLimit,
+ FunctionPruningStrategy *Strategy) {
+ if (OutputSizeLimit == 0)
+ return write(ProfileMap);
+
+ size_t OriginalFunctionCount = ProfileMap.size();
+
+ SmallVector<char> StringBuffer;
+ std::unique_ptr<raw_ostream> BufferStream(
+ new raw_svector_ostream(StringBuffer));
+ OutputStream.swap(BufferStream);
+
+ if (std::error_code EC = write(ProfileMap))
+ return EC;
+ size_t IterationCount = 0;
+ while (StringBuffer.size() > OutputSizeLimit) {
+ Strategy->Erase(StringBuffer.size());
+
+ if (ProfileMap.size() == 0)
+ return sampleprof_error::too_large;
+
+ StringBuffer.clear();
+ OutputStream.reset(new raw_svector_ostream(StringBuffer));
+ if (std::error_code EC = write(ProfileMap))
+ return EC;
+ IterationCount++;
+ }
+
+ OutputStream.swap(BufferStream);
+ OutputStream->write(StringBuffer.data(), StringBuffer.size());
+ LLVM_DEBUG(dbgs() << "Profile originally has " << OriginalFunctionCount
+ << " functions, reduced to " << ProfileMap.size() << " in "
+ << IterationCount << " iterations\n");
+ return sampleprof_error::success;
+}
+
std::error_code
SampleProfileWriter::writeFuncProfiles(const SampleProfileMap &ProfileMap) {
std::vector<NameFunctionSamples> V;
@@ -116,6 +204,12 @@ std::error_code SampleProfileWriterExtBinaryBase::addNewSection(
std::error_code
SampleProfileWriterExtBinaryBase::write(const SampleProfileMap &ProfileMap) {
+ // When calling write on a
diff erent profile map, existing states should be
+ // cleared.
+ NameTable.clear();
+ CSNameTable.clear();
+ SecHdrTable.clear();
+
if (std::error_code EC = writeHeader(ProfileMap))
return EC;
@@ -605,14 +699,10 @@ std::error_code SampleProfileWriterCompactBinary::writeFuncOffsetTable() {
auto &OS = *OutputStream;
// Fill the slot remembered by TableOffset with the offset of FuncOffsetTable.
- auto &OFS = static_cast<raw_fd_ostream &>(OS);
uint64_t FuncOffsetTableStart = OS.tell();
- if (OFS.seek(TableOffset) == (uint64_t)-1)
- return sampleprof_error::ostream_seek_unsupported;
- support::endian::Writer Writer(*OutputStream, support::little);
- Writer.write(FuncOffsetTableStart);
- if (OFS.seek(FuncOffsetTableStart) == (uint64_t)-1)
- return sampleprof_error::ostream_seek_unsupported;
+ support::endian::SeekableWriter Writer(static_cast<raw_pwrite_stream &>(OS),
+ support::little);
+ Writer.pwrite(FuncOffsetTableStart, TableOffset);
// Write out the table size.
encodeULEB128(FuncOffsetTable.size(), OS);
@@ -650,6 +740,10 @@ SampleProfileWriterBinary::writeMagicIdent(SampleProfileFormat Format) {
std::error_code
SampleProfileWriterBinary::writeHeader(const SampleProfileMap &ProfileMap) {
+ // When calling write on a
diff erent profile map, existing names should be
+ // cleared.
+ NameTable.clear();
+
writeMagicIdent(Format);
computeSummary(ProfileMap);
@@ -690,14 +784,6 @@ void SampleProfileWriterExtBinaryBase::allocSecHdrTable() {
}
std::error_code SampleProfileWriterExtBinaryBase::writeSecHdrTable() {
- auto &OFS = static_cast<raw_fd_ostream &>(*OutputStream);
- uint64_t Saved = OutputStream->tell();
-
- // Set OutputStream to the location saved in SecHdrTableOffset.
- if (OFS.seek(SecHdrTableOffset) == (uint64_t)-1)
- return sampleprof_error::ostream_seek_unsupported;
- support::endian::Writer Writer(*OutputStream, support::little);
-
assert(SecHdrTable.size() == SectionHdrLayout.size() &&
"SecHdrTable entries doesn't match SectionHdrLayout");
SmallVector<uint32_t, 16> IndexMap(SecHdrTable.size(), -1);
@@ -714,21 +800,23 @@ std::error_code SampleProfileWriterExtBinaryBase::writeSecHdrTable() {
// needs to be computed after SecLBRProfile (the order in SecHdrTable),
// but it needs to be read before SecLBRProfile (the order in
// SectionHdrLayout). So we use IndexMap above to switch the order.
+ support::endian::SeekableWriter Writer(
+ static_cast<raw_pwrite_stream &>(*OutputStream), support::little);
for (uint32_t LayoutIdx = 0; LayoutIdx < SectionHdrLayout.size();
LayoutIdx++) {
assert(IndexMap[LayoutIdx] < SecHdrTable.size() &&
"Incorrect LayoutIdx in SecHdrTable");
auto Entry = SecHdrTable[IndexMap[LayoutIdx]];
- Writer.write(static_cast<uint64_t>(Entry.Type));
- Writer.write(static_cast<uint64_t>(Entry.Flags));
- Writer.write(static_cast<uint64_t>(Entry.Offset));
- Writer.write(static_cast<uint64_t>(Entry.Size));
+ Writer.pwrite(static_cast<uint64_t>(Entry.Type),
+ SecHdrTableOffset + 4 * LayoutIdx * sizeof(uint64_t));
+ Writer.pwrite(static_cast<uint64_t>(Entry.Flags),
+ SecHdrTableOffset + (4 * LayoutIdx + 1) * sizeof(uint64_t));
+ Writer.pwrite(static_cast<uint64_t>(Entry.Offset),
+ SecHdrTableOffset + (4 * LayoutIdx + 2) * sizeof(uint64_t));
+ Writer.pwrite(static_cast<uint64_t>(Entry.Size),
+ SecHdrTableOffset + (4 * LayoutIdx + 3) * sizeof(uint64_t));
}
- // Reset OutputStream.
- if (OFS.seek(Saved) == (uint64_t)-1)
- return sampleprof_error::ostream_seek_unsupported;
-
return sampleprof_error::success;
}
diff --git a/llvm/test/tools/llvm-profdata/output-size-limit.test b/llvm/test/tools/llvm-profdata/output-size-limit.test
new file mode 100644
index 0000000000000..bdecae0149c29
--- /dev/null
+++ b/llvm/test/tools/llvm-profdata/output-size-limit.test
@@ -0,0 +1,119 @@
+Tests for output-size-limit option. Functions with least sample count are dropped.
+
+1- No effect if output size limit >= original size
+RUN: llvm-profdata merge --sample --text --output-size-limit=212 %p/Inputs/sample-profile.proftext | FileCheck %s --check-prefix=TEST_TEXT1
+TEST_TEXT1: main:184019:0
+TEST_TEXT1-NEXT: 4: 534
+TEST_TEXT1-NEXT: 4.2: 534
+TEST_TEXT1-NEXT: 5: 1075
+TEST_TEXT1-NEXT: 5.1: 1075
+TEST_TEXT1-NEXT: 6: 2080
+TEST_TEXT1-NEXT: 7: 534
+TEST_TEXT1-NEXT: 9: 2064 _Z3bari:1471 _Z3fooi:631
+TEST_TEXT1-NEXT: 10: inline1:1000
+TEST_TEXT1-NEXT: 1: 1000
+TEST_TEXT1-NEXT: 10: inline2:2000
+TEST_TEXT1-NEXT: 1: 2000
+TEST_TEXT1-NEXT: _Z3bari:20301:1437
+TEST_TEXT1-NEXT: 1: 1437
+TEST_TEXT1-NEXT: _Z3fooi:7711:610
+TEST_TEXT1-NEXT: 1: 610
+
+2- 1 function dropped
+RUN: llvm-profdata merge --sample --text --output-size-limit=211 %p/Inputs/sample-profile.proftext | FileCheck %s --check-prefix=TEST_TEXT2
+RUN: llvm-profdata merge --sample --text --output-size-limit=187 %p/Inputs/sample-profile.proftext | FileCheck %s --check-prefix=TEST_TEXT2
+TEST_TEXT2: main:184019:0
+TEST_TEXT2-NEXT: 4: 534
+TEST_TEXT2-NEXT: 4.2: 534
+TEST_TEXT2-NEXT: 5: 1075
+TEST_TEXT2-NEXT: 5.1: 1075
+TEST_TEXT2-NEXT: 6: 2080
+TEST_TEXT2-NEXT: 7: 534
+TEST_TEXT2-NEXT: 9: 2064 _Z3bari:1471 _Z3fooi:631
+TEST_TEXT2-NEXT: 10: inline1:1000
+TEST_TEXT2-NEXT: 1: 1000
+TEST_TEXT2-NEXT: 10: inline2:2000
+TEST_TEXT2-NEXT: 1: 2000
+TEST_TEXT2-NEXT: _Z3bari:20301:1437
+TEST_TEXT2-NEXT: 1: 1437
+
+3- 2 functions dropped
+RUN: llvm-profdata merge --sample --text --output-size-limit=170 %p/Inputs/sample-profile.proftext | FileCheck %s --check-prefix=TEST_TEXT3
+TEST_TEXT3: main:184019:0
+TEST_TEXT3-NEXT: 4: 534
+TEST_TEXT3-NEXT: 4.2: 534
+TEST_TEXT3-NEXT: 5: 1075
+TEST_TEXT3-NEXT: 5.1: 1075
+TEST_TEXT3-NEXT: 6: 2080
+TEST_TEXT3-NEXT: 7: 534
+TEST_TEXT3-NEXT: 9: 2064 _Z3bari:1471 _Z3fooi:631
+TEST_TEXT3-NEXT: 10: inline1:1000
+TEST_TEXT3-NEXT: 1: 1000
+TEST_TEXT3-NEXT: 10: inline2:2000
+TEST_TEXT3-NEXT: 1: 2000
+
+4- All functions dropped, should report an error
+RUN: not llvm-profdata merge --sample --text --output-size-limit=158 %p/Inputs/sample-profile.proftext 2>&1 | FileCheck %s --check-prefix=INVALID1
+INVALID1: error: Too much profile data
+
+5- ExtBinary form, no function dropped. Check output size and file content converted back to text
+RUN: llvm-profdata merge --sample --extbinary --output-size-limit=489 %p/Inputs/sample-profile.proftext -o %t.output
+RUN: test $(stat -c %%s %t.output) -le 489
+RUN: llvm-profdata merge --sample --text %t.output | FileCheck %s --check-prefix=TEST_EXTBINARY1
+TEST_EXTBINARY1: main:184019:0
+TEST_EXTBINARY1-NEXT: 4: 534
+TEST_EXTBINARY1-NEXT: 4.2: 534
+TEST_EXTBINARY1-NEXT: 5: 1075
+TEST_EXTBINARY1-NEXT: 5.1: 1075
+TEST_EXTBINARY1-NEXT: 6: 2080
+TEST_EXTBINARY1-NEXT: 7: 534
+TEST_EXTBINARY1-NEXT: 9: 2064 _Z3bari:1471 _Z3fooi:631
+TEST_EXTBINARY1-NEXT: 10: inline1:1000
+TEST_EXTBINARY1-NEXT: 1: 1000
+TEST_EXTBINARY1-NEXT: 10: inline2:2000
+TEST_EXTBINARY1-NEXT: 1: 2000
+TEST_EXTBINARY1-NEXT: _Z3bari:20301:1437
+TEST_EXTBINARY1-NEXT: 1: 1437
+TEST_EXTBINARY1-NEXT: _Z3fooi:7711:610
+TEST_EXTBINARY1-NEXT: 1: 610
+
+6- ExtBinary form, 1 function dropped
+RUN: llvm-profdata merge --sample --extbinary --output-size-limit=488 %p/Inputs/sample-profile.proftext -o %t.output
+RUN: test $(stat -c %%s %t.output) -le 488
+RUN: llvm-profdata merge --sample --text %t.output | FileCheck %s --check-prefix=TEST_EXTBINARY2
+TEST_EXTBINARY2: main:184019:0
+TEST_EXTBINARY2-NEXT: 4: 534
+TEST_EXTBINARY2-NEXT: 4.2: 534
+TEST_EXTBINARY2-NEXT: 5: 1075
+TEST_EXTBINARY2-NEXT: 5.1: 1075
+TEST_EXTBINARY2-NEXT: 6: 2080
+TEST_EXTBINARY2-NEXT: 7: 534
+TEST_EXTBINARY2-NEXT: 9: 2064 _Z3bari:1471 _Z3fooi:631
+TEST_EXTBINARY2-NEXT: 10: inline1:1000
+TEST_EXTBINARY2-NEXT: 1: 1000
+TEST_EXTBINARY2-NEXT: 10: inline2:2000
+TEST_EXTBINARY2-NEXT: 1: 2000
+TEST_EXTBINARY2-NEXT: _Z3bari:20301:1437
+TEST_EXTBINARY2-NEXT: 1: 1437
+
+7- ExtBinary form, 2 functions dropped
+RUN: llvm-profdata merge --sample --extbinary --output-size-limit=474 %p/Inputs/sample-profile.proftext -o %t.output
+RUN: test $(stat -c %%s %t.output) -le 474
+RUN: llvm-profdata merge --sample --text %t.output | FileCheck %s --check-prefix=TEST_EXTBINARY3
+TEST_EXTBINARY3: main:184019:0
+TEST_EXTBINARY3-NEXT: 4: 534
+TEST_EXTBINARY3-NEXT: 4.2: 534
+TEST_EXTBINARY3-NEXT: 5: 1075
+TEST_EXTBINARY3-NEXT: 5.1: 1075
+TEST_EXTBINARY3-NEXT: 6: 2080
+TEST_EXTBINARY3-NEXT: 7: 534
+TEST_EXTBINARY3-NEXT: 9: 2064 _Z3bari:1471 _Z3fooi:631
+TEST_EXTBINARY3-NEXT: 10: inline1:1000
+TEST_EXTBINARY3-NEXT: 1: 1000
+TEST_EXTBINARY3-NEXT: 10: inline2:2000
+TEST_EXTBINARY3-NEXT: 1: 2000
+
+8- ExtBinary form, all functions dropped
+RUN: not llvm-profdata merge --sample --extbinary --output-size-limit=400 %p/Inputs/sample-profile.proftext 2>&1 | FileCheck %s --check-prefix=INVALID2
+INVALID2: error: Too much profile data
+
diff --git a/llvm/tools/llvm-profdata/llvm-profdata.cpp b/llvm/tools/llvm-profdata/llvm-profdata.cpp
index 90c9e560d47c7..0b7d9341b611c 100644
--- a/llvm/tools/llvm-profdata/llvm-profdata.cpp
+++ b/llvm/tools/llvm-profdata/llvm-profdata.cpp
@@ -967,7 +967,7 @@ mergeSampleProfile(const WeightedFileVector &Inputs, SymbolRemapper *Remapper,
bool UseMD5, bool GenPartialProfile, bool GenCSNestedProfile,
bool SampleMergeColdContext, bool SampleTrimColdContext,
bool SampleColdContextFrameDepth, FailureMode FailMode,
- bool DropProfileSymbolList) {
+ bool DropProfileSymbolList, size_t OutputSizeLimit) {
using namespace sampleprof;
SampleProfileMap ProfileMap;
SmallVector<std::unique_ptr<sampleprof::SampleProfileReader>, 5> Readers;
@@ -1049,6 +1049,13 @@ mergeSampleProfile(const WeightedFileVector &Inputs, SymbolRemapper *Remapper,
ProfileIsCS = FunctionSamples::ProfileIsCS = false;
}
+ // If limiting the output size, write to a string buffer first, and drop
+ // functions if the output size exceeds limit. This iterates multiple times
+ // until the limit is satisfied.
+ SmallVector<char> StringBuffer;
+ std::unique_ptr<raw_ostream> BufferStream(
+ new raw_svector_ostream(StringBuffer));
+
auto WriterOrErr =
SampleProfileWriter::create(OutputFilename, FormatMap[OutputFormat]);
if (std::error_code EC = WriterOrErr.getError())
@@ -1060,7 +1067,9 @@ mergeSampleProfile(const WeightedFileVector &Inputs, SymbolRemapper *Remapper,
auto Buffer = getInputFileBuf(ProfileSymbolListFile);
handleExtBinaryWriter(*Writer, OutputFormat, Buffer.get(), WriterList,
CompressAllSections, UseMD5, GenPartialProfile);
- if (std::error_code EC = Writer->write(ProfileMap))
+
+ if (std::error_code EC =
+ Writer->writeWithSizeLimit(ProfileMap, OutputSizeLimit))
exitWithErrorCode(std::move(EC));
}
@@ -1203,6 +1212,11 @@ static int merge_main(int argc, const char *argv[]) {
"sample-frame-depth-for-cold-context", cl::init(1),
cl::desc("Keep the last K frames while merging cold profile. 1 means the "
"context-less base profile"));
+ cl::opt<size_t> OutputSizeLimit(
+ "output-size-limit", cl::init(0), cl::Hidden,
+ cl::desc("Trim cold functions until profile size is below specified "
+ "limit in bytes. This uses a heursitic and functions may be "
+ "excessively trimmed"));
cl::opt<bool> GenPartialProfile(
"gen-partial-profile", cl::init(false), cl::Hidden,
cl::desc("Generate a partial profile (only meaningful for -extbinary)"));
@@ -1289,7 +1303,8 @@ static int merge_main(int argc, const char *argv[]) {
WeightedInputs, Remapper.get(), OutputFilename, OutputFormat,
ProfileSymbolListFile, CompressAllSections, UseMD5, GenPartialProfile,
GenCSNestedProfile, SampleMergeColdContext, SampleTrimColdContext,
- SampleColdContextFrameDepth, FailureMode, DropProfileSymbolList);
+ SampleColdContextFrameDepth, FailureMode, DropProfileSymbolList,
+ OutputSizeLimit);
return 0;
}
More information about the llvm-commits
mailing list