skia2/tools/bench_playback.cpp

141 lines
4.9 KiB
C++
Raw Normal View History

/*
* Copyright 2014 Google Inc.
*
* Use of this source code is governed by a BSD-style license that can be
* found in the LICENSE file.
*/
#include "SkCanvas.h"
#include "SkCommandLineFlags.h"
#include "SkForceLinking.h"
#include "SkGraphics.h"
#include "SkOSFile.h"
#include "SkPicture.h"
Use a tilegrid for bench_playback. Using --tile wasn't a fair comparison: SkPicture didn't get to optimize its playback, but SkRecord did. Numbers here are starting to agree with what I saw in telemetry: SkRecord with culling is on average at 0.8-0.9 of the speed of SkPicture (10-30% slower) than SkPicture SkPicture with a tile grid, but some in some cases it's down at 0.3, taking almost 4x as long to draw a 256x256 tile. 0.4x tabl_mercurynews.skp 0.109889 0.252483 0.5x tabl_cnet.skp 0.250367 0.527789 1.0x desk_mapsvg.skp 1.48698 1.49939 1.2x desk_yahoogames.skp 0.07745 0.065343 0.9x tabl_mlb.skp 0.294509 0.312505 0.8x tabl_hsfi.skp 0.250678 0.316337 0.6x tabl_worldjournal.skp 0.510204 0.828798 0.7x desk_facebook.skp 0.318981 0.483744 0.9x desk_googlehome.skp 0.06983 0.078964 0.9x desk_tigersvg.skp 0.019232 0.022611 1.0x desk_youtubetvvideo.skp 0.401614 0.401862 1.1x desk_amazon.skp 0.415552 0.362111 0.7x desk_yahooanswers.skp 0.237995 0.358659 0.7x desk_twitter.skp 0.323466 0.439772 1.2x desk_fontwipe.skp 0.121577 0.097845 1.1x desk_css3gradients.skp 0.395335 0.362087 0.9x desk_googlespreadsheet.skp 0.362056 0.406688 1.0x tabl_frantzen.skp 15.2475 14.8521 0.6x desk_forecastio.skp 0.154236 0.276881 0.7x desk_pinterest.skp 0.077433 0.11324 0.5x tabl_cuteoverload.skp 0.173014 0.361815 0.5x tabl_androidpolice.skp 0.225903 0.465608 0.6x tabl_vnexpress.skp 0.151075 0.241104 0.6x tabl_nytimes.skp 0.06515 0.117229 0.8x desk_ebay.skp 0.353437 0.422586 0.8x tabl_deviantart.skp 0.223103 0.295496 1.1x tabl_culturalsolutions.skp 0.551348 0.506104 0.9x mobi_wikipedia.skp 0.302603 0.337292 0.6x desk_linkedin.skp 0.165102 0.276149 0.6x tabl_digg.skp 0.159074 0.281529 1.2x desk_oldinboxapp.skp 0.019815 0.017146 1.0x tabl_nofolo.skp 5.18914 5.42784 0.6x desk_jsfiddlehumperclip.skp 0.076869 0.133665 1.0x desk_blogger.skp 0.206702 0.19688 0.8x desk_espn.skp 0.346386 0.451871 1.0x desk_samoasvg.skp 3.60037 3.43147 0.8x desk_booking.skp 0.338818 0.438267 1.3x desk_yahoosports.skp 0.603811 0.470052 0.6x tabl_engadget.skp 0.248995 0.404372 0.7x desk_wowwiki.skp 0.325801 0.479559 0.8x tabl_ukwsj.skp 0.326985 0.405971 0.9x tabl_gmail.skp 0.2604 0.276744 0.9x desk_googleplus.skp 8.08874 8.71105 1.1x tabl_slashdot.skp 0.559332 0.524313 0.9x desk_gmailthread.skp 0.671569 0.74134 0.8x desk_weather.skp 0.194162 0.247681 1.3x desk_rectangletransition.skp 0.218372 0.173685 0.6x tabl_gamedeksiam.skp 0.243374 0.4134 0.9x desk_jsfiddlebigcar.skp 0.162282 0.186035 0.3x desk_pokemonwiki.skp 0.202878 0.778934 0.7x tabl_googleblog.skp 0.141203 0.209971 0.8x desk_sfgate.skp 0.229078 0.275248 1.0x desk_chalkboard.skp 2.28916 2.20101 0.9x tabl_googlecalendar.skp 0.687155 0.75413 1.1x tabl_gspro.skp 0.186399 0.169522 0.5x desk_googlespreadsheetdashed.skp 0.512622 1.02815 0.6x desk_mobilenews.skp 0.183506 0.293929 0.8x tabl_techmeme.skp 0.193074 0.229106 1.2x desk_carsvg.skp 5.33047 4.34058 0.5x desk_youtube.skp 0.132663 0.248236 0.7x tabl_pravda.skp 0.21644 0.308788 1.1x desk_gws.skp 0.698107 0.625371 0.5x tabl_mozilla.skp 0.189638 0.386801 1.0x desk_baidu.skp 0.353438 0.355965 1.1x tabl_sahadan.skp 0.476226 0.416737 summary: ≥0.3x (A 0.9x, G 0.8x) ≤1.3x Whole SKP playback speed is fine of course. BUG=skia:2378 R=fmalita@chromium.org, mtklein@google.com Author: mtklein@chromium.org Review URL: https://codereview.chromium.org/277653002 git-svn-id: http://skia.googlecode.com/svn/trunk@14673 2bbb7eff-a529-9590-31e7-b0007b416f81
2014-05-09 15:00:10 +00:00
#include "SkPictureRecorder.h"
#include "SkStream.h"
#include "SkString.h"
#include "Stats.h"
#include "Timer.h"
__SK_FORCE_IMAGE_DECODER_LINKING;
DEFINE_string2(skps, r, "skps", "Directory containing SKPs to playback.");
DEFINE_int32(samples, 10, "Gather this many samples of each picture playback.");
DEFINE_bool(skr, false, "Play via SkRecord instead of SkPicture.");
DEFINE_int32(tile, 1000000000, "Simulated tile size.");
DEFINE_string(match, "", "The usual filters on file names of SKPs to bench.");
DEFINE_string(timescale, "ms", "Print times in ms, us, or ns");
DEFINE_int32(verbose, 0, "0: print min sample; "
"1: print min, mean, max and noise indication "
"2: print all samples");
static double timescale() {
if (FLAGS_timescale.contains("us")) return 1000;
if (FLAGS_timescale.contains("ns")) return 1000000;
return 1;
}
static SkPicture* rerecord(const SkPicture& src, bool skr) {
SkTileGridFactory::TileGridInfo info;
info.fTileInterval.set(FLAGS_tile, FLAGS_tile);
info.fMargin.setEmpty();
info.fOffset.setZero();
SkTileGridFactory factory(info);
SkPictureRecorder recorder;
src.draw(skr ? recorder.EXPERIMENTAL_beginRecording(src.width(), src.height(), &factory)
: recorder. beginRecording(src.width(), src.height(), &factory));
return recorder.endRecording();
}
static void bench(SkPMColor* scratch, const SkPicture& src, const char* name) {
SkAutoTUnref<const SkPicture> picture(rerecord(src, FLAGS_skr));
SkAutoTDelete<SkCanvas> canvas(SkCanvas::NewRasterDirectN32(src.width(),
src.height(),
scratch,
src.width() * sizeof(SkPMColor)));
canvas->clipRect(SkRect::MakeWH(SkIntToScalar(FLAGS_tile), SkIntToScalar(FLAGS_tile)));
// Draw once to warm any caches. The first sample otherwise can be very noisy.
picture->draw(canvas.get());
WallTimer timer;
const double scale = timescale();
SkAutoTMalloc<double> samples(FLAGS_samples);
for (int i = 0; i < FLAGS_samples; i++) {
// We assume timer overhead (typically, ~30ns) is insignificant
// compared to draw runtime (at least ~100us, usually several ms).
timer.start();
picture->draw(canvas.get());
timer.end();
samples[i] = timer.fWall * scale;
}
Stats stats(samples.get(), FLAGS_samples);
if (FLAGS_verbose == 0) {
printf("%g\t%s\n", stats.min, name);
} else if (FLAGS_verbose == 1) {
// Get a rough idea of how noisy the measurements were.
const double noisePercent = 100 * sqrt(stats.var) / stats.mean;
printf("%g\t%g\t%g\t±%.0f%%\t%s\n", stats.min, stats.mean, stats.max, noisePercent, name);
} else if (FLAGS_verbose == 2) {
printf("%s", name);
for (int i = 0; i < FLAGS_samples; i++) {
printf("\t%g", samples[i]);
}
printf("\n");
}
}
int tool_main(int argc, char** argv);
int tool_main(int argc, char** argv) {
SkCommandLineFlags::Parse(argc, argv);
SkAutoGraphics autoGraphics;
// We share a single scratch bitmap among benches to reduce the profile noise from allocation.
static const int kMaxArea = 209825221; // tabl_mozilla is this big.
SkAutoTMalloc<SkPMColor> scratch(kMaxArea);
SkOSFile::Iter it(FLAGS_skps[0], ".skp");
SkString filename;
bool failed = false;
while (it.next(&filename)) {
if (SkCommandLineFlags::ShouldSkip(FLAGS_match, filename.c_str())) {
continue;
}
const SkString path = SkOSPath::SkPathJoin(FLAGS_skps[0], filename.c_str());
SkAutoTUnref<SkStream> stream(SkStream::NewFromFile(path.c_str()));
if (!stream) {
SkDebugf("Could not read %s.\n", path.c_str());
failed = true;
continue;
}
SkAutoTUnref<const SkPicture> src(SkPicture::CreateFromStream(stream));
if (!src) {
SkDebugf("Could not read %s as an SkPicture.\n", path.c_str());
failed = true;
continue;
}
if (src->width() * src->height() > kMaxArea) {
SkDebugf("%s (%dx%d) is larger than hardcoded scratch bitmap (%dpx).\n",
path.c_str(), src->width(), src->height(), kMaxArea);
failed = true;
continue;
}
bench(scratch.get(), *src, filename.c_str());
}
return failed ? 1 : 0;
}
#if !defined SK_BUILD_FOR_IOS
int main(int argc, char * const argv[]) {
return tool_main(argc, (char**) argv);
}
#endif