2013-06-05 10:32:26 +08:00
|
|
|
//===- YAML.cpp - YAMLIO utilities for object files -----------------------===//
|
|
|
|
//
|
2019-01-19 16:50:56 +08:00
|
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
2013-06-05 10:32:26 +08:00
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file defines utility classes for handling the YAML representation of
|
|
|
|
// object files.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2016-03-02 03:15:06 +08:00
|
|
|
#include "llvm/ObjectYAML/YAML.h"
|
2013-08-07 13:51:27 +08:00
|
|
|
#include "llvm/ADT/StringExtras.h"
|
2013-06-06 06:59:00 +08:00
|
|
|
#include "llvm/Support/raw_ostream.h"
|
2013-10-12 08:55:57 +08:00
|
|
|
#include <cctype>
|
2017-07-01 09:35:55 +08:00
|
|
|
#include <cstdint>
|
2013-06-05 10:32:26 +08:00
|
|
|
|
|
|
|
using namespace llvm;
|
|
|
|
|
2014-07-03 10:01:39 +08:00
|
|
|
void yaml::ScalarTraits<yaml::BinaryRef>::output(
|
2017-07-01 09:35:55 +08:00
|
|
|
const yaml::BinaryRef &Val, void *, raw_ostream &Out) {
|
2013-06-06 07:47:23 +08:00
|
|
|
Val.writeAsHex(Out);
|
2013-06-05 10:32:26 +08:00
|
|
|
}
|
|
|
|
|
2014-07-03 10:01:39 +08:00
|
|
|
StringRef yaml::ScalarTraits<yaml::BinaryRef>::input(StringRef Scalar, void *,
|
|
|
|
yaml::BinaryRef &Val) {
|
2013-06-06 06:59:00 +08:00
|
|
|
if (Scalar.size() % 2 != 0)
|
|
|
|
return "BinaryRef hex string must contain an even number of nybbles.";
|
|
|
|
// TODO: Can we improve YAMLIO to permit a more accurate diagnostic here?
|
|
|
|
// (e.g. a caret pointing to the offending character).
|
|
|
|
for (unsigned I = 0, N = Scalar.size(); I != N; ++I)
|
[yaml::BinaryRef] Slight perf tuning (for llvm-exegesis analysis mode)
Summary:
llvm-exegesis uses this functionality to read it's benchmark dumps.
This reading of `.yaml`s takes ~60% of runtime for 14656 benchmark points (i.e. one sweep over all x86 instructions),
but only 30% of time for 3x as much benchmark points.
In particular, this `BinaryRef` appears to be an obvious pain point.
Without patch:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file="" -analysis-inconsistencies-output-file=/tmp/clusters-orig.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-orig.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-orig.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file= -analysis-inconsistencies-output-file=/tmp/clusters-orig.html' (25 runs):
972.86 msec task-clock # 0.994 CPUs utilized ( +- 0.25% )
30 context-switches # 30.774 M/sec ( +- 21.74% )
0 cpu-migrations # 0.370 M/sec ( +- 67.81% )
11873 page-faults # 12211.512 M/sec ( +- 0.00% )
3898373408 cycles # 4009682.186 GHz ( +- 0.25% ) (83.12%)
360399748 stalled-cycles-frontend # 9.24% frontend cycles idle ( +- 0.54% ) (83.24%)
1099450483 stalled-cycles-backend # 28.20% backend cycles idle ( +- 0.59% ) (33.63%)
4910528820 instructions # 1.26 insn per cycle
# 0.22 stalled cycles per insn ( +- 0.13% ) (50.21%)
1111976775 branches # 1143726625.854 M/sec ( +- 0.10% ) (66.77%)
23248474 branch-misses # 2.09% of all branches ( +- 0.19% ) (83.29%)
0.97850 +- 0.00647 seconds time elapsed ( +- 0.66% )
```
With the patch:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file="" -analysis-inconsistencies-output-file=/tmp/clusters-new.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file= -analysis-inconsistencies-output-file=/tmp/clusters-new.html' (25 runs):
905.29 msec task-clock # 0.999 CPUs utilized ( +- 0.11% )
15 context-switches # 16.533 M/sec ( +- 32.27% )
0 cpu-migrations # 0.000 K/sec
11873 page-faults # 13121.789 M/sec ( +- 0.00% )
3627759720 cycles # 4009283.100 GHz ( +- 0.11% ) (83.19%)
370401480 stalled-cycles-frontend # 10.21% frontend cycles idle ( +- 0.22% ) (83.19%)
1007114438 stalled-cycles-backend # 27.76% backend cycles idle ( +- 0.34% ) (33.62%)
4414014304 instructions # 1.22 insn per cycle
# 0.23 stalled cycles per insn ( +- 0.08% ) (50.36%)
1003751700 branches # 1109314021.971 M/sec ( +- 0.07% ) (66.97%)
24611010 branch-misses # 2.45% of all branches ( +- 0.10% ) (83.41%)
0.90593 +- 0.00105 seconds time elapsed ( +- 0.12% )
```
So this decreases the overall run time of llvm-exegesis analysis mode (on one sweep) by roughly -7%.
To be noted, `BinaryRef::writeAsBinary()` change is the reason for the perf changes,
usage of `llvm::isHexDigit()` instead of `isxdigit()` does not appear to have any perf impact,
i have only changed it "for symmetry".
`writeAsBinary()` change is correct, it produces identical de-hex-ified buffer, and the final output is thus identical:
```
$ sha512sum /tmp/clusters-*
db4bbd904fe8840853b589b032c5041bc060b91bcd9c27b914b56581fbc473550eea74b852238c79963b5adf2419f379e9f5db76784048b48e3937f9f3e732bf /tmp/clusters-new.html
db4bbd904fe8840853b589b032c5041bc060b91bcd9c27b914b56581fbc473550eea74b852238c79963b5adf2419f379e9f5db76784048b48e3937f9f3e732bf /tmp/clusters-orig.html
```
Reviewers: silvas, espindola, sbc100, zturner, courbet, gchatelet
Reviewed By: gchatelet
Subscribers: tschuett, RKSimon, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D57699
llvm-svn: 353282
2019-02-06 16:57:01 +08:00
|
|
|
if (!llvm::isHexDigit(Scalar[I]))
|
2013-06-06 06:59:00 +08:00
|
|
|
return "BinaryRef hex string must contain only hex digits.";
|
2014-07-03 10:01:39 +08:00
|
|
|
Val = yaml::BinaryRef(Scalar);
|
2017-07-01 09:35:55 +08:00
|
|
|
return {};
|
2013-06-05 10:32:26 +08:00
|
|
|
}
|
2013-06-06 06:59:00 +08:00
|
|
|
|
2019-11-01 20:24:58 +08:00
|
|
|
void yaml::BinaryRef::writeAsBinary(raw_ostream &OS, uint64_t N) const {
|
2013-06-06 07:32:31 +08:00
|
|
|
if (!DataIsHexString) {
|
2019-11-11 17:11:54 +08:00
|
|
|
OS.write((const char *)Data.data(), std::min<uint64_t>(N, Data.size()));
|
2013-06-06 06:59:00 +08:00
|
|
|
return;
|
|
|
|
}
|
2019-11-01 20:24:58 +08:00
|
|
|
|
[FixBB] - An attemp to fix clang-armv7-linux-build-cache builder.
http://lab.llvm.org:8011/builders/clang-armv7-linux-build-cache/builds/22130/steps/build%20stage%201/logs/stdio
/usr/bin/c++ -DGTEST_HAS_RTTI=0 -D_DEBUG -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE -D_LARGEFILE_SOURCE -D__STDC_CONSTANT_MACROS -D__STDC_FORMAT_MACROS -D__STDC_LIMIT_MACROS -Ilib/ObjectYAML -I/home/buildslave/buildslave/clang-armv7-linux-build-cache/llvm/llvm/lib/ObjectYAML -I/usr/include/libxml2 -Iinclude -I/home/buildslave/buildslave/clang-armv7-linux-build-cache/llvm/llvm/include -mthumb -fPIC -fvisibility-inlines-hidden -Werror=date-time -Werror=unguarded-availability-new -Wall -Wextra -Wno-unused-parameter -Wwrite-strings -Wcast-qual -Wmissing-field-initializers -pedantic -Wno-long-long -Wimplicit-fallthrough -Wcovered-switch-default -Wno-noexcept-type -Wnon-virtual-dtor -Wdelete-non-virtual-dtor -Wstring-conversion -fdiagnostics-color -ffunction-sections -fdata-sections -O3 -UNDEBUG -fno-exceptions -fno-rtti -std=c++14 -MMD -MT lib/ObjectYAML/CMakeFiles/LLVMObjectYAML.dir/YAML.cpp.o -MF lib/ObjectYAML/CMakeFiles/LLVMObjectYAML.dir/YAML.cpp.o.d -o lib/ObjectYAML/CMakeFiles/LLVMObjectYAML.dir/YAML.cpp.o -c /home/buildslave/buildslave/clang-armv7-linux-build-cache/llvm/llvm/lib/ObjectYAML/YAML.cpp
/home/buildslave/buildslave/clang-armv7-linux-build-cache/llvm/llvm/lib/ObjectYAML/YAML.cpp:42:41: error: no matching function for call to 'min'
OS.write((const char *)Data.data(), std::min(N, Data.size()));
^~~~~~~~
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/algorithmfwd.h:370:5: note: candidate template ignored: deduced conflicting types for parameter '_Tp' ('unsigned long long' vs. 'unsigned int')
min(const _Tp&, const _Tp&);
^
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/stl_algo.h:3451:5: note: candidate template ignored: could not match 'initializer_list<type-parameter-0-0>' against 'unsigned long long'
min(initializer_list<_Tp> __l, _Compare __comp)
^
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/algorithmfwd.h:375:5: note: candidate function template not viable: requires 3 arguments, but 2 were provided
min(const _Tp&, const _Tp&, _Compare);
^
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/stl_algo.h:3445:5: note: candidate function template not viable: requires single argument '__l', but 2 arguments were provided
min(initializer_list<_Tp> __l)
^
/home/buildslave/buildslave/clang-armv7-linux-build-cache/llvm/llvm/lib/ObjectYAML/YAML.cpp:46:28: error: no matching function for call to 'min'
for (uint64_t I = 0, E = std::min(N, Data.size() / 2); I != E; ++I) {
^~~~~~~~
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/algorithmfwd.h:370:5: note: candidate template ignored: deduced conflicting types for parameter '_Tp' ('unsigned long long' vs. 'unsigned int')
min(const _Tp&, const _Tp&);
^
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/stl_algo.h:3451:5: note: candidate template ignored: could not match 'initializer_list<type-parameter-0-0>' against 'unsigned long long'
min(initializer_list<_Tp> __l, _Compare __comp)
^
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/algorithmfwd.h:375:5: note: candidate function template not viable: requires 3 arguments, but 2 were provided
min(const _Tp&, const _Tp&, _Compare);
^
/usr/bin/../lib/gcc/arm-linux-gnueabihf/5.4.0/../../../../include/c++/5.4.0/bits/stl_algo.h:3445:5: note: candidate function template not viable: requires single argument '__l', but 2 arguments were provided
min(initializer_list<_Tp> __l)
Fix: specify the type for std::min call.
2019-11-11 16:59:38 +08:00
|
|
|
for (uint64_t I = 0, E = std::min<uint64_t>(N, Data.size() / 2); I != E;
|
|
|
|
++I) {
|
2019-11-01 20:24:58 +08:00
|
|
|
uint8_t Byte = llvm::hexDigitValue(Data[I * 2]);
|
[yaml::BinaryRef] Slight perf tuning (for llvm-exegesis analysis mode)
Summary:
llvm-exegesis uses this functionality to read it's benchmark dumps.
This reading of `.yaml`s takes ~60% of runtime for 14656 benchmark points (i.e. one sweep over all x86 instructions),
but only 30% of time for 3x as much benchmark points.
In particular, this `BinaryRef` appears to be an obvious pain point.
Without patch:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file="" -analysis-inconsistencies-output-file=/tmp/clusters-orig.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-orig.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-orig.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file= -analysis-inconsistencies-output-file=/tmp/clusters-orig.html' (25 runs):
972.86 msec task-clock # 0.994 CPUs utilized ( +- 0.25% )
30 context-switches # 30.774 M/sec ( +- 21.74% )
0 cpu-migrations # 0.370 M/sec ( +- 67.81% )
11873 page-faults # 12211.512 M/sec ( +- 0.00% )
3898373408 cycles # 4009682.186 GHz ( +- 0.25% ) (83.12%)
360399748 stalled-cycles-frontend # 9.24% frontend cycles idle ( +- 0.54% ) (83.24%)
1099450483 stalled-cycles-backend # 28.20% backend cycles idle ( +- 0.59% ) (33.63%)
4910528820 instructions # 1.26 insn per cycle
# 0.22 stalled cycles per insn ( +- 0.13% ) (50.21%)
1111976775 branches # 1143726625.854 M/sec ( +- 0.10% ) (66.77%)
23248474 branch-misses # 2.09% of all branches ( +- 0.19% ) (83.29%)
0.97850 +- 0.00647 seconds time elapsed ( +- 0.66% )
```
With the patch:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file="" -analysis-inconsistencies-output-file=/tmp/clusters-new.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file= -analysis-inconsistencies-output-file=/tmp/clusters-new.html' (25 runs):
905.29 msec task-clock # 0.999 CPUs utilized ( +- 0.11% )
15 context-switches # 16.533 M/sec ( +- 32.27% )
0 cpu-migrations # 0.000 K/sec
11873 page-faults # 13121.789 M/sec ( +- 0.00% )
3627759720 cycles # 4009283.100 GHz ( +- 0.11% ) (83.19%)
370401480 stalled-cycles-frontend # 10.21% frontend cycles idle ( +- 0.22% ) (83.19%)
1007114438 stalled-cycles-backend # 27.76% backend cycles idle ( +- 0.34% ) (33.62%)
4414014304 instructions # 1.22 insn per cycle
# 0.23 stalled cycles per insn ( +- 0.08% ) (50.36%)
1003751700 branches # 1109314021.971 M/sec ( +- 0.07% ) (66.97%)
24611010 branch-misses # 2.45% of all branches ( +- 0.10% ) (83.41%)
0.90593 +- 0.00105 seconds time elapsed ( +- 0.12% )
```
So this decreases the overall run time of llvm-exegesis analysis mode (on one sweep) by roughly -7%.
To be noted, `BinaryRef::writeAsBinary()` change is the reason for the perf changes,
usage of `llvm::isHexDigit()` instead of `isxdigit()` does not appear to have any perf impact,
i have only changed it "for symmetry".
`writeAsBinary()` change is correct, it produces identical de-hex-ified buffer, and the final output is thus identical:
```
$ sha512sum /tmp/clusters-*
db4bbd904fe8840853b589b032c5041bc060b91bcd9c27b914b56581fbc473550eea74b852238c79963b5adf2419f379e9f5db76784048b48e3937f9f3e732bf /tmp/clusters-new.html
db4bbd904fe8840853b589b032c5041bc060b91bcd9c27b914b56581fbc473550eea74b852238c79963b5adf2419f379e9f5db76784048b48e3937f9f3e732bf /tmp/clusters-orig.html
```
Reviewers: silvas, espindola, sbc100, zturner, courbet, gchatelet
Reviewed By: gchatelet
Subscribers: tschuett, RKSimon, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D57699
llvm-svn: 353282
2019-02-06 16:57:01 +08:00
|
|
|
Byte <<= 4;
|
2019-11-01 20:24:58 +08:00
|
|
|
Byte |= llvm::hexDigitValue(Data[I * 2 + 1]);
|
2013-06-06 06:59:00 +08:00
|
|
|
OS.write(Byte);
|
|
|
|
}
|
|
|
|
}
|
2013-06-06 07:47:23 +08:00
|
|
|
|
2014-07-03 10:01:39 +08:00
|
|
|
void yaml::BinaryRef::writeAsHex(raw_ostream &OS) const {
|
2014-03-20 14:28:52 +08:00
|
|
|
if (binary_size() == 0)
|
2013-07-09 08:54:46 +08:00
|
|
|
return;
|
2013-06-06 07:47:23 +08:00
|
|
|
if (DataIsHexString) {
|
|
|
|
OS.write((const char *)Data.data(), Data.size());
|
|
|
|
return;
|
|
|
|
}
|
2016-03-01 18:11:27 +08:00
|
|
|
for (uint8_t Byte : Data)
|
|
|
|
OS << hexdigit(Byte >> 4) << hexdigit(Byte & 0xf);
|
2013-06-06 07:47:23 +08:00
|
|
|
}
|