[SampleFDO] Add a new compact binary format for sample profile.
Name table occupies a big chunk of size in current binary format sample profile.
In order to reduce its size, the patch changes the sample writer/reader to
save/restore MD5Hash of names in the name table. Sample annotation phase will
also use MD5Hash of name to query samples accordingly.
Experiment shows compact binary format can reduce the size of sample profile by
2/3 compared with binary format generally.
Differential Revision: https://reviews.llvm.org/D47955
llvm-svn: 334447
diff --git a/llvm/lib/ProfileData/SampleProfWriter.cpp b/llvm/lib/ProfileData/SampleProfWriter.cpp
index 45c8178..092139d 100644
--- a/llvm/lib/ProfileData/SampleProfWriter.cpp
+++ b/llvm/lib/ProfileData/SampleProfWriter.cpp
@@ -25,6 +25,7 @@
#include "llvm/Support/ErrorOr.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/LEB128.h"
+#include "llvm/Support/MD5.h"
#include "llvm/Support/raw_ostream.h"
#include <algorithm>
#include <cstdint>
@@ -144,13 +145,61 @@
}
}
-std::error_code SampleProfileWriterBinary::writeHeader(
- const StringMap<FunctionSamples> &ProfileMap) {
- auto &OS = *OutputStream;
+void SampleProfileWriterBinary::stablizeNameTable(std::set<StringRef> &V) {
+ // Sort the names to make NameTable deterministic.
+ for (const auto &I : NameTable)
+ V.insert(I.first);
+ int i = 0;
+ for (const StringRef &N : V)
+ NameTable[N] = i++;
+}
+std::error_code SampleProfileWriterRawBinary::writeNameTable() {
+ auto &OS = *OutputStream;
+ std::set<StringRef> V;
+ stablizeNameTable(V);
+
+ // Write out the name table.
+ encodeULEB128(NameTable.size(), OS);
+ for (auto N : V) {
+ OS << N;
+ encodeULEB128(0, OS);
+ }
+ return sampleprof_error::success;
+}
+
+std::error_code SampleProfileWriterCompactBinary::writeNameTable() {
+ auto &OS = *OutputStream;
+ std::set<StringRef> V;
+ stablizeNameTable(V);
+
+ // Write out the name table.
+ encodeULEB128(NameTable.size(), OS);
+ for (auto N : V) {
+ encodeULEB128(MD5Hash(N), OS);
+ }
+ return sampleprof_error::success;
+}
+
+std::error_code SampleProfileWriterRawBinary::writeMagicIdent() {
+ auto &OS = *OutputStream;
// Write file magic identifier.
encodeULEB128(SPMagic(), OS);
encodeULEB128(SPVersion(), OS);
+ return sampleprof_error::success;
+}
+
+std::error_code SampleProfileWriterCompactBinary::writeMagicIdent() {
+ auto &OS = *OutputStream;
+ // Write file magic identifier.
+ encodeULEB128(SPMagic(SPF_Compact_Binary), OS);
+ encodeULEB128(SPVersion(), OS);
+ return sampleprof_error::success;
+}
+
+std::error_code SampleProfileWriterBinary::writeHeader(
+ const StringMap<FunctionSamples> &ProfileMap) {
+ writeMagicIdent();
computeSummary(ProfileMap);
if (auto EC = writeSummary())
@@ -162,20 +211,7 @@
addNames(I.second);
}
- // Sort the names to make NameTable is deterministic.
- std::set<StringRef> V;
- for (const auto &I : NameTable)
- V.insert(I.first);
- int i = 0;
- for (const StringRef &N : V)
- NameTable[N] = i++;
-
- // Write out the name table.
- encodeULEB128(NameTable.size(), OS);
- for (auto N : V) {
- OS << N;
- encodeULEB128(0, OS);
- }
+ writeNameTable();
return sampleprof_error::success;
}
@@ -258,7 +294,7 @@
SampleProfileWriter::create(StringRef Filename, SampleProfileFormat Format) {
std::error_code EC;
std::unique_ptr<raw_ostream> OS;
- if (Format == SPF_Binary)
+ if (Format == SPF_Raw_Binary || Format == SPF_Compact_Binary)
OS.reset(new raw_fd_ostream(Filename, EC, sys::fs::F_None));
else
OS.reset(new raw_fd_ostream(Filename, EC, sys::fs::F_Text));
@@ -281,8 +317,10 @@
std::error_code EC;
std::unique_ptr<SampleProfileWriter> Writer;
- if (Format == SPF_Binary)
- Writer.reset(new SampleProfileWriterBinary(OS));
+ if (Format == SPF_Raw_Binary)
+ Writer.reset(new SampleProfileWriterRawBinary(OS));
+ else if (Format == SPF_Compact_Binary)
+ Writer.reset(new SampleProfileWriterCompactBinary(OS));
else if (Format == SPF_Text)
Writer.reset(new SampleProfileWriterText(OS));
else if (Format == SPF_GCC)