[lld] af5ca40 - temporary
Rui Ueyama via llvm-commits
llvm-commits at lists.llvm.org
Thu Dec 12 22:16:11 PST 2019
Author: Rui Ueyama
Date: 2019-12-13T14:35:03+09:00
New Revision: af5ca40b47b3e85c3add81ccdc0b787c4bc355ae
URL: https://github.com/llvm/llvm-project/commit/af5ca40b47b3e85c3add81ccdc0b787c4bc355ae
DIFF: https://github.com/llvm/llvm-project/commit/af5ca40b47b3e85c3add81ccdc0b787c4bc355ae.diff
LOG: temporary
Added:
lld/test/ELF/check-time-trace.s
lld/test/ELF/lto/thinlto-time-trace.ll
Modified:
lld/ELF/Config.h
lld/ELF/Driver.cpp
lld/ELF/ICF.cpp
lld/ELF/LTO.cpp
lld/ELF/MarkLive.cpp
lld/ELF/Options.td
lld/ELF/SyntheticSections.cpp
lld/ELF/Writer.cpp
llvm/include/llvm/LTO/Config.h
llvm/lib/LTO/LTO.cpp
Removed:
################################################################################
diff --git a/lld/ELF/Config.h b/lld/ELF/Config.h
index d7e715ebf357..6d804ee2bbe6 100644
--- a/lld/ELF/Config.h
+++ b/lld/ELF/Config.h
@@ -191,6 +191,7 @@ struct Configuration {
bool trace;
bool thinLTOEmitImportsFiles;
bool thinLTOIndexOnly;
+ bool timeTraceEnabled;
bool tocOptimize;
bool undefinedVersion;
bool useAndroidRelrTags = false;
@@ -240,6 +241,7 @@ struct Configuration {
unsigned ltoo;
unsigned optimize;
unsigned thinLTOJobs;
+ unsigned timeTraceGranularity;
int32_t splitStackAdjustSize;
// The following config options do not directly correspond to any
diff --git a/lld/ELF/Driver.cpp b/lld/ELF/Driver.cpp
index c721e872e12e..cc4cefc6ed97 100644
--- a/lld/ELF/Driver.cpp
+++ b/lld/ELF/Driver.cpp
@@ -56,6 +56,7 @@
#include "llvm/Support/Path.h"
#include "llvm/Support/TarWriter.h"
#include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/raw_ostream.h"
#include <cstdlib>
#include <utility>
@@ -490,6 +491,10 @@ void LinkerDriver::main(ArrayRef<const char *> argsArr) {
if (args.hasArg(OPT_version))
return;
+ // Initialize time trace.
+ if (config->timeTraceEnabled)
+ timeTraceProfilerInitialize(config->timeTraceGranularity, config->progName);
+
initLLVM();
createFiles(args);
if (errorCount())
@@ -509,19 +514,34 @@ void LinkerDriver::main(ArrayRef<const char *> argsArr) {
switch (config->ekind) {
case ELF32LEKind:
link<ELF32LE>(args);
- return;
+ break;
case ELF32BEKind:
link<ELF32BE>(args);
- return;
+ break;
case ELF64LEKind:
link<ELF64LE>(args);
- return;
+ break;
case ELF64BEKind:
link<ELF64BE>(args);
- return;
+ break;
default:
llvm_unreachable("unknown Config->EKind");
}
+
+ if (config->timeTraceEnabled) {
+ std::string path = args.getLastArgValue(OPT_time_trace_file_eq);
+ if (path.empty())
+ path = (config->outputFile + ".time-trace").str();
+
+ std::error_code ec;
+ raw_fd_ostream os(path, errorCode, sys::fs::F_Text);
+ if (ec) {
+ error("cannot open " + path + ": " + ec.message());
+ return;
+ }
+ timeTraceProfilerWrite(os);
+ timeTraceProfilerCleanup();
+ }
}
static std::string getRpath(opt::InputArgList &args) {
@@ -953,6 +973,9 @@ static void readConfigs(opt::InputArgList &args) {
getOldNewOptions(args, OPT_thinlto_object_suffix_replace_eq);
config->thinLTOPrefixReplace =
getOldNewOptions(args, OPT_thinlto_prefix_replace_eq);
+ config->timeTraceEnabled = args.hasArg(OPT_time_trace);
+ config->timeTraceGranularity =
+ args::getInteger(args, OPT_time_trace_granularity, 500);
config->trace = args.hasArg(OPT_trace);
config->undefined = args::getStrings(args, OPT_undefined);
config->undefinedVersion =
@@ -1597,6 +1620,7 @@ static Symbol *addUndefined(StringRef name) {
// Because all bitcode files that the program consists of are passed to
// the compiler at once, it can do a whole-program optimization.
template <class ELFT> void LinkerDriver::compileBitcodeFiles() {
+ llvm::TimeTraceScope timeScope("LTO");
// Compile bitcode files and replace bitcode symbols.
lto.reset(new BitcodeCompiler);
for (BitcodeFile *file : bitcodeFiles)
@@ -1723,6 +1747,8 @@ template <class ELFT> static uint32_t getAndFeatures() {
// Do actual linking. Note that when this function is called,
// all linker scripts have already been parsed.
template <class ELFT> void LinkerDriver::link(opt::InputArgList &args) {
+ llvm::TimeTraceScope timeScope("ExecuteLinker");
+
// If a -hash-style option was not given, set to a default value,
// which varies depending on the target.
if (!args.hasArg(OPT_hash_style)) {
@@ -1762,8 +1788,11 @@ template <class ELFT> void LinkerDriver::link(opt::InputArgList &args) {
// symbols that we need to the symbol table. This process might
// add files to the link, via autolinking, these files are always
// appended to the Files vector.
- for (size_t i = 0; i < files.size(); ++i)
- parseFile(files[i]);
+ {
+ llvm::TimeTraceScope timeScope("Parse input files");
+ for (size_t i = 0; i < files.size(); ++i)
+ parseFile(files[i]);
+ }
// Now that we have every file, we can decide if we will need a
// dynamic symbol table.
@@ -1981,11 +2010,15 @@ template <class ELFT> void LinkerDriver::link(opt::InputArgList &args) {
// merging MergeInputSections into a single MergeSyntheticSection. From this
// point onwards InputSectionDescription::sections should be used instead of
// sectionBases.
- for (BaseCommand *base : script->sectionCommands)
- if (auto *sec = dyn_cast<OutputSection>(base))
- sec->finalizeInputSections();
- llvm::erase_if(inputSections,
- [](InputSectionBase *s) { return isa<MergeInputSection>(s); });
+ {
+ llvm::TimeTraceScope timeScope("Merge input sections");
+ for (BaseCommand *base : script->sectionCommands)
+ if (auto *sec = dyn_cast<OutputSection>(base))
+ sec->finalizeInputSections();
+ llvm::erase_if(inputSections, [](InputSectionBase *s) {
+ return isa<MergeInputSection>(s);
+ });
+ }
// Two input sections with
diff erent output sections should not be folded.
// ICF runs after processSectionCommands() so that we know the output sections.
diff --git a/lld/ELF/ICF.cpp b/lld/ELF/ICF.cpp
index 5e38066f45ba..7838a45557cc 100644
--- a/lld/ELF/ICF.cpp
+++ b/lld/ELF/ICF.cpp
@@ -84,6 +84,7 @@
#include "llvm/ADT/StringExtras.h"
#include "llvm/BinaryFormat/ELF.h"
#include "llvm/Object/ELF.h"
+#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/xxhash.h"
#include <algorithm>
#include <atomic>
@@ -452,6 +453,7 @@ static void print(const Twine &s) {
// The main function of ICF.
template <class ELFT> void ICF<ELFT>::run() {
+ llvm::TimeTraceScope timeScope("ICF");
// Compute isPreemptible early. We may add more symbols later, so this loop
// cannot be merged with the later computeIsPreemptible() pass which is used
// by scanRelocations().
diff --git a/lld/ELF/LTO.cpp b/lld/ELF/LTO.cpp
index 524d552b0b84..3f677d86f13a 100644
--- a/lld/ELF/LTO.cpp
+++ b/lld/ELF/LTO.cpp
@@ -108,6 +108,9 @@ static lto::Config createConfig() {
c.DebugPassManager = config->ltoDebugPassManager;
c.DwoDir = config->dwoDir;
+ c.TimeTraceEnabled = config->timeTraceEnabled;
+ c.TimeTraceGranularity = config->timeTraceGranularity;
+
c.CSIRProfile = config->ltoCSProfileFile;
c.RunCSIRInstr = config->ltoCSProfileGenerate;
diff --git a/lld/ELF/MarkLive.cpp b/lld/ELF/MarkLive.cpp
index bb0105c28928..b77fab9abb62 100644
--- a/lld/ELF/MarkLive.cpp
+++ b/lld/ELF/MarkLive.cpp
@@ -31,6 +31,7 @@
#include "lld/Common/Strings.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/Object/ELF.h"
+#include "llvm/Support/TimeProfiler.h"
#include <functional>
#include <vector>
@@ -323,6 +324,7 @@ template <class ELFT> void MarkLive<ELFT>::moveToMain() {
// input sections. This function make some or all of them on
// so that they are emitted to the output file.
template <class ELFT> void markLive() {
+ llvm::TimeTraceScope timeScope("GC");
// If -gc-sections is not given, no sections are removed.
if (!config->gcSections) {
for (InputSectionBase *sec : inputSections)
diff --git a/lld/ELF/Options.td b/lld/ELF/Options.td
index b86a670915c1..3ee1d17b31df 100644
--- a/lld/ELF/Options.td
+++ b/lld/ELF/Options.td
@@ -358,6 +358,12 @@ defm threads: B<"threads",
"Run the linker multi-threaded (default)",
"Do not run the linker multi-threaded">;
+def time_trace: F<"time-trace">, HelpText<"Record time trace">;
+def time_trace_file_eq: J<"time-trace-file=">, HelpText<"Specify time trace output file">;
+
+defm time_trace_granularity: Eq<"time-trace-granularity",
+ "Minimum time granularity (in microseconds) traced by time profiler">;
+
defm toc_optimize : B<"toc-optimize",
"(PowerPC64) Enable TOC related optimizations (default)",
"(PowerPC64) Disable TOC related optimizations">;
diff --git a/lld/ELF/SyntheticSections.cpp b/lld/ELF/SyntheticSections.cpp
index d014da220817..e765d2a9465b 100644
--- a/lld/ELF/SyntheticSections.cpp
+++ b/lld/ELF/SyntheticSections.cpp
@@ -36,6 +36,7 @@
#include "llvm/Support/Endian.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/MD5.h"
+#include "llvm/Support/TimeProfiler.h"
#include <cstdlib>
#include <thread>
@@ -3132,6 +3133,7 @@ MergeSyntheticSection *createMergeSynthetic(StringRef name, uint32_t type,
}
template <class ELFT> void splitSections() {
+ llvm::TimeTraceScope timeScope("Split sections");
// splitIntoPieces needs to be called on each MergeInputSection
// before calling finalizeContents().
parallelForEach(inputSections, [](InputSectionBase *sec) {
diff --git a/lld/ELF/Writer.cpp b/lld/ELF/Writer.cpp
index 38009bdd9aa3..67fd2b9a8c53 100644
--- a/lld/ELF/Writer.cpp
+++ b/lld/ELF/Writer.cpp
@@ -27,6 +27,7 @@
#include "llvm/ADT/StringSwitch.h"
#include "llvm/Support/RandomNumberGenerator.h"
#include "llvm/Support/SHA1.h"
+#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/xxhash.h"
#include <climits>
@@ -139,7 +140,10 @@ static bool needsInterpSection() {
script->needsInterpSection();
}
-template <class ELFT> void writeResult() { Writer<ELFT>().run(); }
+template <class ELFT> void writeResult() {
+ llvm::TimeTraceScope timeScope("Write output file");
+ Writer<ELFT>().run();
+}
static void removeEmptyPTLoad(std::vector<PhdrEntry *> &phdrs) {
llvm::erase_if(phdrs, [&](const PhdrEntry *p) {
diff --git a/lld/test/ELF/check-time-trace.s b/lld/test/ELF/check-time-trace.s
new file mode 100644
index 000000000000..8144b2abefb5
--- /dev/null
+++ b/lld/test/ELF/check-time-trace.s
@@ -0,0 +1,39 @@
+# REQUIRES: x86
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t.o
+
+# Test implicit trace file name
+# RUN: ld.lld -time-trace -time-trace-granularity=0 -o %t1.elf %t.o
+# RUN: cat %t1.elf.time-trace \
+# RUN: | %python -c 'import json, sys; json.dump(json.loads(sys.stdin.read()), sys.stdout, sort_keys=True, indent=2)' \
+# RUN: | FileCheck %s
+
+# Test specified trace file name
+# RUN: ld.lld -time-trace -time-trace-file=%t2.json -time-trace-granularity=0 -o %t2.elf %t.o
+# RUN: cat %t2.json \
+# RUN: | %python -c 'import json, sys; json.dump(json.loads(sys.stdin.read()), sys.stdout, sort_keys=True, indent=2)' \
+# RUN: | FileCheck %s
+
+# Test trace requested to stdout
+# RUN: ld.lld -time-trace -time-trace-file=- -time-trace-granularity=0 -o %t3.elf %t.o \
+# RUN: | %python -c 'import json, sys; json.dump(json.loads(sys.stdin.read()), sys.stdout, sort_keys=True, indent=2)' \
+# RUN: | FileCheck %s
+
+# CHECK: "traceEvents": [
+# Check one event has correct fields
+# CHECK: "dur":
+# CHECK-NEXT: "name":
+# CHECK-NEXT: "ph":
+# CHECK-NEXT: "pid":
+# CHECK-NEXT: "tid":
+# CHECK-NEXT: "ts":
+
+# Check there is an ExecuteLinker event
+# CHECK: "name": "ExecuteLinker"
+
+# Check process_name entry field
+# CHECK: "name": "ld.lld{{(.exe)?}}"
+# CHECK: "name": "process_name"
+
+.globl _start
+_start:
+ ret
diff --git a/lld/test/ELF/lto/thinlto-time-trace.ll b/lld/test/ELF/lto/thinlto-time-trace.ll
new file mode 100644
index 000000000000..1b8335cbb9a9
--- /dev/null
+++ b/lld/test/ELF/lto/thinlto-time-trace.ll
@@ -0,0 +1,43 @@
+; REQUIRES: x86
+
+; Test ThinLTO with time trace
+; RUN: opt -module-summary %s -o %t1.o
+; RUN: opt -module-summary %p/Inputs/thinlto.ll -o %t2.o
+
+; Test single-threaded
+; RUN: ld.lld --thinlto-jobs=1 -time-trace -time-trace-granularity=0 -shared %t1.o %t2.o -o %t3.so
+; RUN: cat %t3.so.time-trace \
+; RUN: | %python -c 'import json, sys; json.dump(json.loads(sys.stdin.read()), sys.stdout, sort_keys=True, indent=2)' \
+; RUN: | FileCheck %s
+
+; Test multi-threaded
+; RUN: ld.lld -time-trace -time-trace-granularity=0 -shared %t1.o %t2.o -o %t4.so
+; RUN: cat %t4.so.time-trace \
+; RUN: | %python -c 'import json, sys; json.dump(json.loads(sys.stdin.read()), sys.stdout, sort_keys=True, indent=2)' \
+; RUN: | FileCheck %s
+
+; CHECK: "traceEvents": [
+; Check fields for an event are present
+; CHECK: "args":
+; CHECK-NEXT: "detail":
+; CHECK: "dur":
+; CHECK-NEXT: "name":
+; CHECK-NEXT: "ph":
+; CHECK-NEXT: "pid":
+; CHECK-NEXT: "tid":
+; CHECK-NEXT: "ts":
+
+; Check that an optimisation event is present
+; CHECK: "name": "OptModule"
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+declare void @g(...)
+
+define void @f() {
+entry:
+ call void (...) @g()
+ ret void
+}
+
diff --git a/llvm/include/llvm/LTO/Config.h b/llvm/include/llvm/LTO/Config.h
index 754e3126f8a9..6db1235a692c 100644
--- a/llvm/include/llvm/LTO/Config.h
+++ b/llvm/include/llvm/LTO/Config.h
@@ -117,6 +117,12 @@ struct Config {
/// Statistics output file path.
std::string StatsFile;
+ /// Time trace enabled
+ bool TimeTraceEnabled = false;
+
+ /// Time trace granularity
+ unsigned TimeTraceGranularity = 500;
+
bool ShouldDiscardValueNames = true;
DiagnosticHandlerFunction DiagHandler;
diff --git a/llvm/lib/LTO/LTO.cpp b/llvm/lib/LTO/LTO.cpp
index 0d48090e4268..e2c8aa159896 100644
--- a/llvm/lib/LTO/LTO.cpp
+++ b/llvm/lib/LTO/LTO.cpp
@@ -39,6 +39,7 @@
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/ThreadPool.h"
#include "llvm/Support/Threading.h"
+#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/VCSRevision.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
@@ -1133,6 +1134,9 @@ class InProcessThinBackend : public ThinBackendProc {
&ResolvedODR,
const GVSummaryMapTy &DefinedGlobals,
MapVector<StringRef, BitcodeModule> &ModuleMap) {
+ if (Conf.TimeTraceEnabled)
+ timeTraceProfilerInitialize(Conf.TimeTraceGranularity,
+ "thin backend");
Error E = runThinLTOBackendThread(
AddStream, Cache, Task, BM, CombinedIndex, ImportList, ExportList,
ResolvedODR, DefinedGlobals, ModuleMap);
@@ -1143,6 +1147,8 @@ class InProcessThinBackend : public ThinBackendProc {
else
Err = std::move(E);
}
+ if (timeTraceProfilerEnabled())
+ timeTraceProfilerFinishThread();
},
BM, std::ref(CombinedIndex), std::ref(ImportList), std::ref(ExportList),
std::ref(ResolvedODR), std::ref(DefinedGlobals), std::ref(ModuleMap));
More information about the llvm-commits
mailing list