Commit Graph
41 Commits
Author SHA1 Message Date
Nigel Tao aa2d41e0a0 Add a mimiclib scratch buffer 2020-12-29 21:38:52 +11:00
Nigel Tao 10e8ee5e79 Roll back 0c7a8cc0 re do_bench_image_decode
Commit 0c7a8cc029 is "Have
do_bench_image_decode pass a non-NULL dst". Adding a mandatory memcpy to
do_bench_image_decode noticably slowed down the bench numbers. Removing
the memcpy speeds it back up.

wuffs_gif_decode_1k_bw/clang9                278MB/s ± 0%   373MB/s ± 0%  +34.42%  (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/clang9  85.0MB/s ± 0%  91.1MB/s ± 0%   +7.27%  (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_part_init/clang9   104MB/s ± 0%   114MB/s ± 0%   +9.51%  (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/clang9             434MB/s ± 0%   449MB/s ± 0%   +3.59%  (p=0.008 n=5+5)
wuffs_gif_decode_10k_indexed/clang9          115MB/s ± 0%   120MB/s ± 0%   +4.63%  (p=0.008 n=5+5)
wuffs_gif_decode_20k/clang9                  140MB/s ± 1%   145MB/s ± 0%   +3.16%  (p=0.008 n=5+5)
wuffs_gif_decode_100k_artificial/clang9      301MB/s ± 0%   312MB/s ± 0%   +3.62%  (p=0.016 n=5+4)
wuffs_gif_decode_100k_realistic/clang9       125MB/s ± 0%   127MB/s ± 0%   +1.40%  (p=0.008 n=5+5)
wuffs_gif_decode_1000k_full_init/clang9      128MB/s ± 0%   129MB/s ± 0%   +0.78%  (p=0.008 n=5+5)
wuffs_gif_decode_1000k_part_init/clang9      128MB/s ± 0%   128MB/s ± 1%     ~     (p=0.151 n=5+5)
wuffs_gif_decode_anim_screencap/clang9       586MB/s ± 0%   671MB/s ± 0%  +14.60%  (p=0.016 n=5+4)

wuffs_gif_decode_1k_bw/gcc10                 271MB/s ± 0%   322MB/s ± 0%  +18.81%  (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/gcc10   94.8MB/s ± 0%  99.2MB/s ± 1%   +4.64%  (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_part_init/gcc10    116MB/s ± 0%   123MB/s ± 0%   +5.90%  (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/gcc10              374MB/s ± 0%   382MB/s ± 1%   +2.12%  (p=0.008 n=5+5)
wuffs_gif_decode_10k_indexed/gcc10           116MB/s ± 1%   119MB/s ± 0%   +3.09%  (p=0.008 n=5+5)
wuffs_gif_decode_20k/gcc10                   137MB/s ± 0%   139MB/s ± 0%   +1.46%  (p=0.008 n=5+5)
wuffs_gif_decode_100k_artificial/gcc10       286MB/s ± 0%   293MB/s ± 0%   +2.49%  (p=0.008 n=5+5)
wuffs_gif_decode_100k_realistic/gcc10        118MB/s ± 0%   119MB/s ± 0%   +0.80%  (p=0.016 n=5+4)
wuffs_gif_decode_1000k_full_init/gcc10       121MB/s ± 0%   121MB/s ± 0%   +0.33%  (p=0.008 n=5+5)
wuffs_gif_decode_1000k_part_init/gcc10       121MB/s ± 0%   121MB/s ± 0%   +0.28%  (p=0.016 n=5+5)
wuffs_gif_decode_anim_screencap/gcc10        582MB/s ± 0%   659MB/s ± 0%  +13.25%  (p=0.008 n=5+5)

wuffs_png_decode_19k_8bpp/clang9            88.7MB/s ± 0%  94.2MB/s ± 0%   +6.28%  (p=0.008 n=5+5)
wuffs_png_decode_40k_24bpp/clang9            104MB/s ± 0%   108MB/s ± 0%   +3.96%  (p=0.008 n=5+5)
wuffs_png_decode_77k_8bpp/clang9             335MB/s ± 0%   352MB/s ± 0%   +5.29%  (p=0.008 n=5+5)
wuffs_png_decode_552k_32bpp/clang9           118MB/s ± 0%   119MB/s ± 0%   +0.54%  (p=0.008 n=5+5)
wuffs_png_decode_4002k_24bpp/clang9          109MB/s ± 0%   112MB/s ± 0%   +2.36%  (p=0.008 n=5+5)

wuffs_png_decode_19k_8bpp/gcc10             96.7MB/s ± 0%  98.0MB/s ± 0%   +1.36%  (p=0.029 n=4+4)
wuffs_png_decode_40k_24bpp/gcc10             114MB/s ± 0%   115MB/s ± 0%   +0.79%  (p=0.008 n=5+5)
wuffs_png_decode_77k_8bpp/gcc10              316MB/s ± 0%   320MB/s ± 0%   +1.18%  (p=0.016 n=5+4)
wuffs_png_decode_552k_32bpp/gcc10            149MB/s ± 0%   149MB/s ± 0%   +0.17%  (p=0.016 n=5+4)
wuffs_png_decode_4002k_24bpp/gcc10           116MB/s ± 0%   116MB/s ± 0%   +0.09%  (p=0.032 n=5+5)
2020-12-29 21:29:32 +11:00
Nigel Tao 0c7a8cc029 Have do_bench_image_decode pass a non-NULL dst 2020-12-28 15:54:15 +11:00
Nigel Tao 88616cc969 Add std/png mimic benches
Wuffs' std/png and std/zlib implementations have not been optimized yet,
but even at this early stage, they are roughly on par with their
"mimics": equivalent production-quality C libraries (libpng and zlib).

On a mid-range x86_64 laptop:

wuffs_png_decode_19k_8bpp/clang9     95.8MB/s ± 0%
wuffs_png_decode_40k_24bpp/clang9     100MB/s ± 1%
wuffs_png_decode_77k_8bpp/clang9      359MB/s ± 0%
wuffs_png_decode_552k_32bpp/clang9    119MB/s ± 0%
wuffs_png_decode_4002k_24bpp/clang9   101MB/s ± 0%

wuffs_png_decode_19k_8bpp/gcc10      97.2MB/s ± 0%
wuffs_png_decode_40k_24bpp/gcc10      111MB/s ± 0%
wuffs_png_decode_77k_8bpp/gcc10       316MB/s ± 0%
wuffs_png_decode_552k_32bpp/gcc10     132MB/s ± 0%
wuffs_png_decode_4002k_24bpp/gcc10    116MB/s ± 0%

mimic_png_decode_19k_8bpp            58.1MB/s ± 0%
mimic_png_decode_40k_24bpp           73.3MB/s ± 0%
mimic_png_decode_77k_8bpp             177MB/s ± 0%
mimic_png_decode_552k_32bpp           147MB/s ± 0%
mimic_png_decode_4002k_24bpp          104MB/s ± 0%

wuffs_zlib_decode_10k/clang9   126MB/s ± 0%
wuffs_zlib_decode_100k/clang9  136MB/s ± 0%

wuffs_zlib_decode_10k/gcc10    131MB/s ± 0%
wuffs_zlib_decode_100k/gcc10   159MB/s ± 0%

mimic_zlib_decode_10k          133MB/s ± 0%
mimic_zlib_decode_100k         160MB/s ± 0%
2020-12-28 15:52:46 +11:00
Nigel Tao 2784613b49 Add n_bytes_out arg to gif bench functions 2020-06-01 13:14:14 +10:00
Nigel Tao 2914bae3b2 Re-format C function signatures 2020-02-26 09:40:30 +11:00
Nigel Tao 7b199116b0 Rename s/got/have/ in test/c 2020-02-24 21:23:58 +11:00
Nigel Tao b92ea03889 Fix mimiclib/deflate-gzip-zlib.c build with miniz 2019-10-20 20:47:18 +11:00
Nigel Tao c36b4d79c4 Add a mimic test for zlib dictionaries 2019-08-11 20:06:29 +10:00
Nigel Tao 881474be5a Remove "0 means no I/O limit" in tests 2019-07-06 08:41:46 +10:00
Nigel Tao ffeb2bff63 Split benchmarks for full / partial initialization 2019-02-24 16:54:19 +11:00
Nigel Tao 11a6819be9 Add a deflate distance-code-31 test 2019-02-02 13:04:09 +11:00
Nigel Tao 670b45be53 Add some "horizontal rule" comment lines 2019-02-02 08:10:08 +11:00
Nigel Tao 109d6f04bc Add std/deflate many_big_read benchmarks 2019-01-13 10:08:40 +11:00
Nigel Tao f1c5bb6cb7 Add BGRA GIF benchmark, not just indexed color 2018-12-08 21:24:26 +11:00
Nigel Tao 6fed251b40 Split an io_buffer's fields into data and meta 2018-09-15 08:45:50 +10:00
Nigel Tao 76c6af4ff4 Use some more animated GIF test data 2018-05-10 10:14:07 +10:00
Nigel Tao 97aab37462 Rename buf1, reader1, etc to io_buffer, io_reader
Also remove the unused Buf1, Buf2 and Usize tokens.
2018-04-05 20:49:48 +10:00
Nigel Tao a2949fe28d Add Adler32 and CRC32/IEEE tests for pi's digits 2018-03-25 21:54:07 +11:00
Nigel Tao 372618c817 Use the faster mimic_deflate API
name                             old speed     new speed     delta
mimic_deflate_decode_1k/gcc      217MB/s ± 1%  217MB/s ± 1%     ~     (p=1.000 n=5+5)
mimic_deflate_decode_10k/gcc     260MB/s ± 2%  263MB/s ± 1%     ~     (p=0.421 n=5+5)
mimic_deflate_decode_100k/gcc    277MB/s ± 1%  316MB/s ± 1%  +13.95%  (p=0.008 n=5+5)

Note that these numbers are for the C zlib library (these are "mimic"
numbers), not for the Wuffs code.
2018-01-05 18:22:25 +11:00
Nigel Tao 4877279ee7 Be able to test and bench the miniz library
For the record, benchstat numbers for 'old' being zlib-the-library and
'new' being miniz are below. Neither 'old' or 'new' is Wuffs code.

name                             old speed     new speed     delta
mimic_deflate_decode_1k/clang    217MB/s ± 1%  175MB/s ± 1%  -19.54%  (p=0.008 n=5+5)
mimic_deflate_decode_10k/clang   262MB/s ± 2%  222MB/s ± 0%  -15.34%  (p=0.008 n=5+5)
mimic_deflate_decode_100k/clang  281MB/s ± 1%  262MB/s ± 0%   -6.86%  (p=0.008 n=5+5)
mimic_deflate_decode_1k/gcc      220MB/s ± 1%  169MB/s ± 0%  -23.12%  (p=0.008 n=5+5)
mimic_deflate_decode_10k/gcc     267MB/s ± 0%  266MB/s ± 0%     ~     (p=0.222 n=5+5)
mimic_deflate_decode_100k/gcc    283MB/s ± 0%  282MB/s ± 1%     ~     (p=0.690 n=5+5)
mimic_zlib_decode_10k/clang      243MB/s ± 1%  197MB/s ± 1%  -18.68%  (p=0.008 n=5+5)
mimic_zlib_decode_100k/clang     287MB/s ± 1%  229MB/s ± 1%  -20.13%  (p=0.008 n=5+5)
mimic_zlib_decode_10k/gcc        243MB/s ± 0%  240MB/s ± 6%     ~     (p=0.730 n=5+5)
mimic_zlib_decode_100k/gcc       288MB/s ± 1%  260MB/s ± 0%   -9.51%  (p=0.008 n=5+5)
2017-12-15 11:33:35 +11:00
Nigel Tao 1388f84e5c Rename std/flate to std/deflate 2017-12-04 10:27:48 +11:00
Nigel Tao d168e6977b Rename test/c/mimiclib/flate.c 2017-12-03 14:34:41 +11:00
Nigel Tao dd3f0b9ed4 Add a placeholder std/zlib package 2017-12-02 11:21:30 +11:00
Nigel Tao 3c708dfe59 Rename PUFFS to WUFFS, part 7 of N 2017-11-30 18:02:59 +11:00
Nigel Tao 79a94558be Rename PUFFS to WUFFS, part 5 of N 2017-11-30 16:37:20 +11:00
Nigel Tao 94eba81892 Have mimiclib accept both giflib v4 and v5. 2017-11-03 11:35:16 +11:00
Nigel Tao f29c4e278f Follow the pkg__type__method convention for base. 2017-10-21 15:59:08 +11:00
Nigel Tao f9cea5c17c Fix the adler.update implementation. 2017-10-19 20:45:43 +11:00
Nigel Tao fca0cab724 Add write and read limits to some tests. 2017-10-14 14:52:54 +11:00
Nigel Tao d4372cb5b8 Change license to Apache 2.
Also remove explicit PATENTS file. The new LICENSE file already
discusses patents.

Note that the Puffs project has not yet been publicly released.
2017-10-12 11:17:41 +11:00
Nigel Tao 8be6dc3394 Add adler32 and crc32 benchmarks. 2017-07-14 13:01:08 +10:00
Nigel Tao 03572374dd Add zlib (not just raw flate) benchmark. 2017-07-14 12:00:00 +10:00
Nigel Tao 6c8414099a Add gzip (not just raw flate) benchmark. 2017-07-14 10:53:33 +10:00
Nigel Tao fe96654119 Rename some tests and benches for consistency. 2017-07-07 12:37:15 +10:00
Nigel Tao 0b9f9162a5 Add std/flate tests. 2017-07-07 12:06:54 +10:00
Nigel Tao 004a583aaf Add a comment about gif_mimic_DGifSlurp. 2017-07-02 13:26:42 +10:00
Nigel Tao 30f9c947f5 Roll back the custom gif_mimic_DGifSlurp function.
See the previous commit for the rationale.
2017-07-02 13:17:36 +10:00
Nigel Tao ab7e0ae795 Add a custom gif_mimic_DGifSlurp function.
This avoids some malloc's of intermediate buffers when using giflib,
i.e. for mimic benchmarks. The numbers don't show a huge difference:

name                          old speed      new speed      delta
gif_mimic_decode_1k/clang      158MB/s ± 0%   158MB/s ± 2%    ~     (p=0.421 n=5+5)
gif_mimic_decode_10k/clang    94.5MB/s ± 0%  93.8MB/s ± 1%  -0.70%  (p=0.016 n=5+5)
gif_mimic_decode_100k/clang    100MB/s ± 0%   100MB/s ± 0%  -0.42%  (p=0.008 n=5+5)
gif_mimic_decode_1000k/clang   102MB/s ± 0%   102MB/s ± 0%  -0.29%  (p=0.016 n=5+5)
gif_mimic_decode_1k/gcc        158MB/s ± 1%   160MB/s ± 0%  +1.34%  (p=0.008 n=5+5)
gif_mimic_decode_10k/gcc      94.3MB/s ± 0%  94.6MB/s ± 0%  +0.36%  (p=0.008 n=5+5)
gif_mimic_decode_100k/gcc      100MB/s ± 0%   101MB/s ± 0%  +0.46%  (p=0.008 n=5+5)
gif_mimic_decode_1000k/gcc     102MB/s ± 0%   103MB/s ± 0%  +0.70%  (p=0.008 n=5+5)

This commit will immediately be followed by a rollback, but it is
committed anyway so that we can refer to these numbers in the git log.
2017-07-02 13:12:45 +10:00
Nigel Tao c06580a4f9 Fix a typo. 2017-07-02 12:53:56 +10:00
Nigel Tao a65e2bacf0 Add mimic tests. 2017-07-02 11:19:23 +10:00