Nigel Tao
57bd11bf39
wuffs gen -version=0.3.2
2023-04-07 13:53:11 +10:00
Nigel Tao
17f7613262
std/{bmp,nie}: allow decode_frame to small pixbuf
2023-03-27 21:22:06 +11:00
Nigel Tao
000b0a3445
std/png: decode "truncated input" for short chunks
...
Updates #101
2023-03-12 19:23:41 +11:00
Nigel Tao
ef74175a20
wuffs gen -version=0.3.1
2023-03-04 09:54:01 +11:00
Nigel Tao
4d4c3c4c3c
floatconv: tweak Simple Decimal Conversion
...
This tweaks the code and comments added in commit 36d7748e "Merge pull
request #90 from sarastro-nl/improvement/optimize-SDC" and commit
d46220ca "optimize SDC". Both of those two commit messages are short but
see the discussion re algorithmic changes on PR 87 (yes, 87, not 90):
https://github.com/google/wuffs/pull/87
Also run clang-format.
Also update doc/changelog.md
Compared to before commit d46220ca "optimize SDC", when running
script/manual-test-parse-number-f64.cc and disabling both the
etc__parse_number_f64_eisel_lemire function and the "If both man and
(10 ** exp10) are exactly representable by a double" fast path, the
tests still pass but the number of etc__high_prec_dec__small_lshift and
etc__high_prec_dec__small_rshift calls drop:
Function Before After Ratio
lshift 31174584 25762258 82.64% = 100% - 17.36%
rshift 21592604 20982502 97.17% = 100% - 2.83%
The time taken drops from 15.984s to 13.710s (85.77% = 100% - 14.23%).
To repeat, these are the improvements after disabling the Eisel-Lemire
and other fast paths. Simple Decimal Conversion is the rarely invoked
fallback parse_number_f64 algorithm. The practical improvement (with
Eisel-Lemire etc enabled) is smaller.
2023-02-04 14:48:25 +11:00
Nigel Tao
36d7748ed5
Merge pull request #90 from sarastro-nl/improvement/optimize-SDC
...
optimize SDC
2023-02-04 10:30:29 +11:00
Nigel Tao
248bddcfd2
std/*image_decoder*: add "#truncated input"
...
name old speed new speed delta
wuffs_bmp_decode_40k/clang11 4.36GB/s ± 0% 4.48GB/s ± 0% +2.74% (p=0.008 n=5+5)
wuffs_bmp_decode_40k/gcc10 4.49GB/s ± 0% 4.50GB/s ± 0% +0.15% (p=0.008 n=5+5)
wuffs_gif_decode_1k_bw/clang11 723MB/s ± 0% 742MB/s ± 0% +2.64% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/clang11 177MB/s ± 0% 177MB/s ± 0% ~ (p=0.841 n=5+5)
wuffs_gif_decode_1k_color_part_init/clang11 216MB/s ± 0% 217MB/s ± 0% +0.66% (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/clang11 793MB/s ± 0% 785MB/s ± 0% -1.04% (p=0.016 n=4+5)
wuffs_gif_decode_10k_indexed/clang11 210MB/s ± 0% 209MB/s ± 0% -0.38% (p=0.008 n=5+5)
wuffs_gif_decode_20k/clang11 254MB/s ± 0% 255MB/s ± 0% +0.37% (p=0.008 n=5+5)
wuffs_gif_decode_100k_artificial/clang11 568MB/s ± 0% 569MB/s ± 0% +0.14% (p=0.008 n=5+5)
wuffs_gif_decode_100k_realistic/clang11 221MB/s ± 0% 221MB/s ± 0% ~ (p=0.222 n=5+5)
wuffs_gif_decode_1000k_full_init/clang11 224MB/s ± 0% 224MB/s ± 0% ~ (p=0.690 n=5+5)
wuffs_gif_decode_1000k_part_init/clang11 224MB/s ± 0% 224MB/s ± 0% ~ (p=0.841 n=5+5)
wuffs_gif_decode_anim_screencap/clang11 1.30GB/s ± 0% 1.30GB/s ± 0% ~ (p=0.111 n=5+5)
wuffs_gif_decode_1k_bw/gcc10 638MB/s ± 0% 672MB/s ± 0% +5.23% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/gcc10 175MB/s ± 0% 181MB/s ± 0% +3.03% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_part_init/gcc10 203MB/s ± 0% 209MB/s ± 0% +3.38% (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/gcc10 798MB/s ± 0% 804MB/s ± 0% +0.70% (p=0.008 n=5+5)
wuffs_gif_decode_10k_indexed/gcc10 210MB/s ± 0% 212MB/s ± 0% +0.84% (p=0.008 n=5+5)
wuffs_gif_decode_20k/gcc10 265MB/s ± 0% 265MB/s ± 0% ~ (p=0.222 n=5+5)
wuffs_gif_decode_100k_artificial/gcc10 576MB/s ± 0% 577MB/s ± 0% ~ (p=0.690 n=5+5)
wuffs_gif_decode_100k_realistic/gcc10 226MB/s ± 0% 227MB/s ± 0% +0.21% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_full_init/gcc10 230MB/s ± 0% 231MB/s ± 0% +0.32% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_part_init/gcc10 230MB/s ± 0% 231MB/s ± 0% +0.43% (p=0.008 n=5+5)
wuffs_gif_decode_anim_screencap/gcc10 1.32GB/s ± 0% 1.32GB/s ± 0% +0.18% (p=0.008 n=5+5)
wuffs_png_decode_image_19k_8bpp/clang11 267MB/s ± 0% 273MB/s ± 0% +2.47% (p=0.008 n=5+5)
wuffs_png_decode_image_40k_24bpp/clang11 326MB/s ± 0% 327MB/s ± 0% +0.51% (p=0.008 n=5+5)
wuffs_png_decode_image_77k_8bpp/clang11 954MB/s ± 0% 969MB/s ± 0% +1.58% (p=0.008 n=5+5)
wuffs_png_decode_image_552k_32bpp_ignore_checksum/clang11 865MB/s ± 0% 864MB/s ± 0% -0.18% (p=0.016 n=5+5)
wuffs_png_decode_image_552k_32bpp_verify_checksum/clang11 832MB/s ± 0% 831MB/s ± 0% -0.11% (p=0.016 n=5+5)
wuffs_png_decode_image_4002k_24bpp/clang11 331MB/s ± 0% 332MB/s ± 0% +0.18% (p=0.016 n=5+5)
wuffs_png_decode_image_19k_8bpp/gcc10 298MB/s ± 0% 292MB/s ± 0% -2.17% (p=0.008 n=5+5)
wuffs_png_decode_image_40k_24bpp/gcc10 352MB/s ± 0% 349MB/s ± 0% -0.75% (p=0.008 n=5+5)
wuffs_png_decode_image_77k_8bpp/gcc10 1.05GB/s ± 0% 1.03GB/s ± 0% -1.56% (p=0.008 n=5+5)
wuffs_png_decode_image_552k_32bpp_ignore_checksum/gcc10 950MB/s ± 0% 949MB/s ± 0% ~ (p=0.310 n=5+5)
wuffs_png_decode_image_552k_32bpp_verify_checksum/gcc10 905MB/s ± 0% 902MB/s ± 0% -0.35% (p=0.008 n=5+5)
wuffs_png_decode_image_4002k_24bpp/gcc10 360MB/s ± 0% 358MB/s ± 0% -0.40% (p=0.008 n=5+5)
wuffs_tga_decode_19k_8bpp/clang11 7.81GB/s ± 0% 7.90GB/s ± 0% +1.22% (p=0.008 n=5+5)
wuffs_tga_decode_77k_24bpp/clang11 4.34GB/s ± 0% 4.36GB/s ± 0% +0.59% (p=0.008 n=5+5)
wuffs_tga_decode_19k_8bpp/gcc10 7.10GB/s ± 0% 7.13GB/s ± 0% +0.33% (p=0.008 n=5+5)
wuffs_tga_decode_77k_24bpp/gcc10 4.61GB/s ± 0% 4.60GB/s ± 0% -0.35% (p=0.008 n=5+5)
Updates #96
2023-02-01 16:36:56 +11:00
Nigel Tao
3705e0d93a
cgen: io_reader.is_closed doesn't need derived var
2023-01-31 23:33:02 +11:00
Nigel Tao
f01f0859f0
std/*io_transformer*: add "#truncated input"
...
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 58.5MB/s ± 0% 59.9MB/s ± 0% +2.50% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/clang11 45.7MB/s ± 0% 50.5MB/s ± 0% +10.66% (p=0.008 n=5+5)
wuffs_bzip2_decode_10k/gcc10 56.2MB/s ± 0% 61.9MB/s ± 0% +10.01% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/gcc10 46.5MB/s ± 0% 50.4MB/s ± 0% +8.41% (p=0.016 n=4+5)
wuffs_deflate_decode_1k_full_init/clang11 195MB/s ± 0% 191MB/s ± 0% -1.71% (p=0.008 n=5+5)
wuffs_deflate_decode_1k_part_init/clang11 224MB/s ± 0% 225MB/s ± 0% +0.87% (p=0.008 n=5+5)
wuffs_deflate_decode_10k_full_init/clang11 421MB/s ± 0% 401MB/s ± 0% -4.59% (p=0.008 n=5+5)
wuffs_deflate_decode_10k_part_init/clang11 432MB/s ± 0% 413MB/s ± 0% -4.49% (p=0.008 n=5+5)
wuffs_deflate_decode_100k_just_one_read/clang11 542MB/s ± 0% 518MB/s ± 0% -4.43% (p=0.008 n=5+5)
wuffs_deflate_decode_100k_many_big_reads/clang11 338MB/s ± 0% 325MB/s ± 0% -3.81% (p=0.008 n=5+5)
wuffs_deflate_decode_1k_full_init/gcc10 181MB/s ± 0% 185MB/s ± 0% +1.76% (p=0.008 n=5+5)
wuffs_deflate_decode_1k_part_init/gcc10 209MB/s ± 0% 212MB/s ± 0% +1.79% (p=0.008 n=5+5)
wuffs_deflate_decode_10k_full_init/gcc10 410MB/s ± 0% 407MB/s ± 0% -0.93% (p=0.008 n=5+5)
wuffs_deflate_decode_10k_part_init/gcc10 421MB/s ± 0% 418MB/s ± 0% -0.87% (p=0.008 n=5+5)
wuffs_deflate_decode_100k_just_one_read/gcc10 533MB/s ± 0% 533MB/s ± 0% ~ (p=0.548 n=5+5)
wuffs_deflate_decode_100k_many_big_reads/gcc10 336MB/s ± 0% 334MB/s ± 1% -0.67% (p=0.008 n=5+5)
wuffs_gzip_decode_10k/clang11 401MB/s ± 0% 398MB/s ± 0% -0.77% (p=0.008 n=5+5)
wuffs_gzip_decode_100k/clang11 505MB/s ± 0% 503MB/s ± 0% -0.46% (p=0.008 n=5+5)
wuffs_gzip_decode_10k/gcc10 403MB/s ± 0% 410MB/s ± 0% +1.90% (p=0.008 n=5+5)
wuffs_gzip_decode_100k/gcc10 522MB/s ± 0% 523MB/s ± 0% +0.10% (p=0.032 n=5+5)
wuffs_zlib_decode_10k/clang11 418MB/s ± 0% 417MB/s ± 1% ~ (p=0.310 n=5+5)
wuffs_zlib_decode_100k/clang11 530MB/s ± 0% 529MB/s ± 0% ~ (p=0.421 n=5+5)
wuffs_zlib_decode_10k/gcc10 428MB/s ± 0% 434MB/s ± 0% +1.50% (p=0.008 n=5+5)
wuffs_zlib_decode_100k/gcc10 551MB/s ± 0% 551MB/s ± 0% ~ (p=0.690 n=5+5)
Fixes #96
2023-01-31 23:09:37 +11:00
Nigel Tao
d7c48ae76b
cgen: have io_limit update meta.closed
2023-01-31 22:05:20 +11:00
Nigel Tao
48e69da5af
std/lzw: add "#truncated input" error
...
name old speed new speed delta
wuffs_gif_decode_1k_bw/clang11 659MB/s ± 0% 748MB/s ± 0% +13.43% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/clang11 182MB/s ± 0% 178MB/s ± 0% -2.17% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_part_init/clang11 223MB/s ± 0% 219MB/s ± 0% -2.00% (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/clang11 799MB/s ± 0% 795MB/s ± 0% -0.52% (p=0.008 n=5+5)
wuffs_gif_decode_10k_indexed/clang11 211MB/s ± 0% 210MB/s ± 0% -0.47% (p=0.008 n=5+5)
wuffs_gif_decode_20k/clang11 250MB/s ± 1% 254MB/s ± 0% +1.75% (p=0.008 n=5+5)
wuffs_gif_decode_100k_artificial/clang11 581MB/s ± 0% 568MB/s ± 0% -2.09% (p=0.008 n=5+5)
wuffs_gif_decode_100k_realistic/clang11 221MB/s ± 0% 221MB/s ± 0% ~ (p=0.690 n=5+5)
wuffs_gif_decode_1000k_full_init/clang11 222MB/s ± 0% 224MB/s ± 0% +0.65% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_part_init/clang11 223MB/s ± 0% 224MB/s ± 0% +0.58% (p=0.008 n=5+5)
wuffs_gif_decode_anim_screencap/clang11 1.28GB/s ± 0% 1.30GB/s ± 0% +1.45% (p=0.008 n=5+5)
wuffs_gif_decode_1k_bw/gcc10 595MB/s ± 0% 642MB/s ± 0% +7.91% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/gcc10 168MB/s ± 0% 169MB/s ± 0% +0.36% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_part_init/gcc10 202MB/s ± 0% 203MB/s ± 0% +0.46% (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/gcc10 790MB/s ± 0% 798MB/s ± 0% +1.04% (p=0.008 n=5+5)
wuffs_gif_decode_10k_indexed/gcc10 208MB/s ± 0% 210MB/s ± 0% +1.00% (p=0.008 n=5+5)
wuffs_gif_decode_20k/gcc10 258MB/s ± 0% 266MB/s ± 0% +3.08% (p=0.008 n=5+5)
wuffs_gif_decode_100k_artificial/gcc10 566MB/s ± 0% 577MB/s ± 0% +1.83% (p=0.008 n=5+5)
wuffs_gif_decode_100k_realistic/gcc10 220MB/s ± 0% 227MB/s ± 0% +3.03% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_full_init/gcc10 223MB/s ± 0% 231MB/s ± 0% +3.23% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_part_init/gcc10 224MB/s ± 0% 231MB/s ± 0% +3.14% (p=0.008 n=5+5)
wuffs_gif_decode_anim_screencap/gcc10 1.30GB/s ± 0% 1.32GB/s ± 0% +1.70% (p=0.008 n=5+5)
wuffs_lzw_decode_20k/clang11 294MB/s ± 0% 321MB/s ± 0% +9.11% (p=0.008 n=5+5)
wuffs_lzw_decode_100k/clang11 533MB/s ± 0% 560MB/s ± 0% +5.13% (p=0.008 n=5+5)
wuffs_lzw_decode_20k/gcc10 271MB/s ± 0% 272MB/s ± 0% +0.55% (p=0.008 n=5+5)
wuffs_lzw_decode_100k/gcc10 527MB/s ± 0% 521MB/s ± 0% -1.31% (p=0.008 n=5+5)
Updates #96
2023-01-31 20:18:53 +11:00
Nigel Tao
1e03a0c84f
wuffs gen -version=0.3.0
2023-01-26 17:18:14 +11:00
sarastro-nl
d46220ca00
optimize SDC
2022-11-21 22:10:19 +01:00
Nigel Tao
dee65c0e61
wuffs gen -version=0.3.0-rc.3
2022-10-28 17:29:05 +11:00
Nigel Tao
9445c8b9d0
Guard header declarations on the MODULE_ETC macros
2022-10-28 17:11:14 +11:00
Nigel Tao
b5ccd9e8e7
wuffs gen -version=0.3.0-rc.2
2022-10-20 11:23:06 +11:00
Nigel Tao
b0e9efff3f
Avoid (NULL + 0) in derived io_buffer variables
...
This addresses a "runtime error: applying zero offset to null pointer"
UBSAN (Undefined Behavior Sanitizer) warning using clang 15.0.1:
https://logs.chromium.org/logs/skia/5e005cc1b1981011/+/steps/dm/0/stdout
The offending line of code was "io1_a_dst = io0_a_dst + a_dst->meta.wi"
in wuffs_lzw__decoder__write_to and "io1_a_dst = NULL + 0" was Undefined
Behavior even though io1_a_dst was never dereferenced.
This commit avoids initializing io1_a_dst to (NULL + 0) when io0_a_dst
is NULL, falling back to initializing it with just NULL.
As discussed in https://reviews.llvm.org/D67122 while (nullptr + 0) is
Defined Behavior according to the C++ spec, (NULL + 0) is Undefined
Behavior (by omission) in C11 6.5.6/8: "If both the pointer operand and
the result point to elements of the same array object, or one past the
last element of the array object, the evaluation shall not produce an
overflow; otherwise, the behavior is undefined."
The benchmarks (an excerpt of the full suite is below) seem quite
sensitive to this simple change that's outside of hot loops, sometimes
much better and sometimes much worse. I don't know why.
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 63.1MB/s ± 0% 58.4MB/s ± 0% -7.43% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/clang11 49.4MB/s ± 0% 46.2MB/s ± 0% -6.35% (p=0.008 n=5+5)
wuffs_bzip2_decode_10k/gcc10 60.9MB/s ± 0% 56.3MB/s ± 0% -7.59% (p=0.016 n=5+4)
wuffs_bzip2_decode_100k/gcc10 49.6MB/s ± 0% 47.0MB/s ± 0% -5.15% (p=0.008 n=5+5)
wuffs_deflate_decode_1k_full_init/clang11 196MB/s ± 0% 195MB/s ± 1% -0.63% (p=0.008 n=5+5)
wuffs_deflate_decode_1k_part_init/clang11 226MB/s ± 0% 224MB/s ± 0% -0.95% (p=0.008 n=5+5)
wuffs_deflate_decode_10k_full_init/clang11 409MB/s ± 0% 420MB/s ± 0% +2.84% (p=0.008 n=5+5)
wuffs_deflate_decode_10k_part_init/clang11 418MB/s ± 0% 431MB/s ± 0% +2.97% (p=0.008 n=5+5)
wuffs_deflate_decode_100k_just_one_read/clang11 517MB/s ± 1% 542MB/s ± 0% +4.78% (p=0.008 n=5+5)
wuffs_deflate_decode_100k_many_big_reads/clang11 330MB/s ± 0% 338MB/s ± 0% +2.45% (p=0.008 n=5+5)
wuffs_deflate_decode_1k_full_init/gcc10 188MB/s ± 0% 177MB/s ± 0% -5.38% (p=0.008 n=5+5)
wuffs_deflate_decode_1k_part_init/gcc10 218MB/s ± 0% 209MB/s ± 0% -4.11% (p=0.016 n=4+5)
wuffs_deflate_decode_10k_full_init/gcc10 402MB/s ± 0% 407MB/s ± 1% +1.19% (p=0.008 n=5+5)
wuffs_deflate_decode_10k_part_init/gcc10 413MB/s ± 0% 419MB/s ± 1% +1.64% (p=0.008 n=5+5)
wuffs_deflate_decode_100k_just_one_read/gcc10 520MB/s ± 0% 532MB/s ± 0% +2.25% (p=0.008 n=5+5)
wuffs_deflate_decode_100k_many_big_reads/gcc10 330MB/s ± 0% 335MB/s ± 0% +1.56% (p=0.008 n=5+5)
wuffs_gif_decode_1k_bw/clang11 781MB/s ± 0% 645MB/s ± 0% -17.46% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/clang11 176MB/s ± 0% 181MB/s ± 0% +3.11% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_part_init/clang11 215MB/s ± 0% 223MB/s ± 0% +3.46% (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/clang11 786MB/s ± 0% 801MB/s ± 0% +1.94% (p=0.008 n=5+5)
wuffs_gif_decode_10k_indexed/clang11 208MB/s ± 0% 211MB/s ± 0% +1.44% (p=0.008 n=5+5)
wuffs_gif_decode_20k/clang11 261MB/s ± 0% 252MB/s ± 0% -3.43% (p=0.008 n=5+5)
wuffs_gif_decode_100k_artificial/clang11 578MB/s ± 0% 583MB/s ± 0% +0.86% (p=0.008 n=5+5)
wuffs_gif_decode_100k_realistic/clang11 224MB/s ± 0% 223MB/s ± 0% -0.79% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_full_init/clang11 229MB/s ± 0% 225MB/s ± 0% -1.73% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_part_init/clang11 229MB/s ± 0% 225MB/s ± 0% -1.69% (p=0.008 n=5+5)
wuffs_gif_decode_anim_screencap/clang11 1.31GB/s ± 0% 1.29GB/s ± 0% -1.06% (p=0.008 n=5+5)
wuffs_gif_decode_1k_bw/gcc10 650MB/s ± 0% 631MB/s ± 0% -3.03% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_full_init/gcc10 169MB/s ± 0% 168MB/s ± 0% -0.51% (p=0.008 n=5+5)
wuffs_gif_decode_1k_color_part_init/gcc10 202MB/s ± 0% 202MB/s ± 0% -0.18% (p=0.008 n=5+5)
wuffs_gif_decode_10k_bgra/gcc10 766MB/s ± 0% 790MB/s ± 0% +3.08% (p=0.008 n=5+5)
wuffs_gif_decode_10k_indexed/gcc10 202MB/s ± 0% 208MB/s ± 0% +3.16% (p=0.008 n=5+5)
wuffs_gif_decode_20k/gcc10 250MB/s ± 0% 258MB/s ± 0% +3.20% (p=0.008 n=5+5)
wuffs_gif_decode_100k_artificial/gcc10 563MB/s ± 0% 566MB/s ± 0% +0.57% (p=0.008 n=5+5)
wuffs_gif_decode_100k_realistic/gcc10 217MB/s ± 0% 220MB/s ± 0% +1.49% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_full_init/gcc10 220MB/s ± 0% 224MB/s ± 0% +1.49% (p=0.008 n=5+5)
wuffs_gif_decode_1000k_part_init/gcc10 220MB/s ± 0% 224MB/s ± 0% +1.43% (p=0.008 n=5+5)
wuffs_gif_decode_anim_screencap/gcc10 1.30GB/s ± 0% 1.30GB/s ± 0% +0.34% (p=0.008 n=5+5)
wuffs_lzw_decode_20k/clang11 293MB/s ± 0% 292MB/s ± 0% -0.41% (p=0.008 n=5+5)
wuffs_lzw_decode_100k/clang11 486MB/s ± 0% 537MB/s ± 0% +10.49% (p=0.008 n=5+5)
wuffs_lzw_decode_20k/gcc10 258MB/s ± 0% 276MB/s ± 0% +7.19% (p=0.016 n=4+5)
wuffs_lzw_decode_100k/gcc10 512MB/s ± 0% 527MB/s ± 0% +3.08% (p=0.016 n=4+5)
2022-10-20 11:18:09 +11:00
Nigel Tao
315b2e5262
wuffs gen -version=0.3.0-rc.1
2022-07-10 10:30:15 +10:00
Nigel Tao
c226ed60f5
Use memcpy-based peeks and pokes on Microsoft C
...
I don't have a Windows machine readily available, but according to
https://godbolt.org/z/q4MfjzTPh and the https://imgur.com/UD5a7MF
profile mentioned in #72 , this could improve inner loop performance.
Updates #72
2022-06-12 17:18:49 +10:00
Nigel Tao
45a79923e6
Tighten std/bzip2 Huffman leaf node bit packing
2022-06-10 14:31:53 +10:00
Nigel Tao
67aa63297c
Rename std/bzip2 num_nodes variable
2022-06-10 14:06:27 +10:00
Nigel Tao
8c33dd503b
Tighten std/bzip2 huffman_trees array size
2022-06-10 14:02:17 +10:00
Nigel Tao
9256fe5e54
Have std/bzip2 check the number of sections
...
Updates #79
2022-06-08 16:41:46 +10:00
Nigel Tao
5392d503e3
wuffs gen -version=0.3.0-beta.15
2022-06-03 14:16:18 +10:00
Nigel Tao
ebe080c9ec
Fix gif metadata when skipping decode_image_config
2022-06-03 11:43:05 +10:00
Nigel Tao
65afe919b5
Fix std/gif "@end of data" for 0-frame GIFs
...
This fixes a regression introduced by 8d03a67e "Re-do image decoders'
call sequence state machine".
build-all.sh's script/print-nia-checksums.sh test once again matches
test/nia-checksums-of-data.txt:
-4c6d02c3 test/data/artificial-gif/no-frames.gif
+ba6e48f8 test/data/artificial-gif/no-frames.gif
2022-06-02 16:48:06 +10:00
Nigel Tao
c5e41f0e65
Let std/png report metadata after the first frame
...
Fixes #58
2022-06-02 16:05:24 +10:00
Nigel Tao
8d03a67e6e
Re-do image decoders' call sequence state machine
2022-05-28 15:06:56 +10:00
Nigel Tao
f55274aaa7
Fix -Werror=conversion in decode_bzip2.wuffs
2022-05-24 13:58:48 +10:00
Nigel Tao
e6793fc501
Have std/bzip2 support QUIRK_IGNORE_CHECKSUM
2022-05-24 12:31:43 +10:00
Nigel Tao
09102fb1e8
Tweak std/bzip2 decoder.flush_fast applicability
2022-05-24 12:25:47 +10:00
Nigel Tao
6a3e43f495
Tweak std/bzip2 flush_* basic blocks
...
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 65.2MB/s ± 0% 65.2MB/s ± 0% ~ (p=0.056 n=5+5)
wuffs_bzip2_decode_100k/clang11 52.4MB/s ± 0% 51.5MB/s ± 0% -1.67% (p=0.016 n=5+4)
wuffs_bzip2_decode_10k/gcc10 60.6MB/s ± 0% 61.7MB/s ± 0% +1.81% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/gcc10 49.2MB/s ± 0% 49.6MB/s ± 0% +0.86% (p=0.008 n=5+5)
2022-05-24 12:01:30 +10:00
Nigel Tao
bed155bd6f
Optimize std/bzip2 flush_repeat_count checks
...
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 60.5MB/s ± 0% 65.2MB/s ± 0% +7.85% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/clang11 45.7MB/s ± 1% 52.4MB/s ± 0% +14.68% (p=0.008 n=5+5)
wuffs_bzip2_decode_10k/gcc10 58.5MB/s ± 0% 60.6MB/s ± 0% +3.67% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/gcc10 46.3MB/s ± 0% 49.2MB/s ± 0% +6.31% (p=0.008 n=5+5)
2022-05-24 11:56:23 +10:00
Nigel Tao
66f194f7e0
Introduce std/bzip2 decoder.flush_fast method
...
Compared to the recent commit 623290ef "Cache std/bzip2 Huffman tree
lookup":
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 60.5MB/s ± 0% 60.5MB/s ± 0% ~ (p=1.000 n=5+5)
wuffs_bzip2_decode_100k/clang11 46.7MB/s ± 1% 45.7MB/s ± 1% -2.05% (p=0.008 n=5+5)
wuffs_bzip2_decode_10k/gcc10 58.7MB/s ± 0% 58.5MB/s ± 0% ~ (p=0.222 n=5+5)
wuffs_bzip2_decode_100k/gcc10 46.9MB/s ± 0% 46.3MB/s ± 0% -1.46% (p=0.008 n=5+5)
2022-05-24 11:50:48 +10:00
Nigel Tao
ae1e075401
Rename std/bzip2 decode_block_* functions
2022-05-24 11:24:57 +10:00
Nigel Tao
fc0c5e465b
Rename std/bzip2/decode_block_*.wuffs
2022-05-24 11:24:15 +10:00
Nigel Tao
623290ef87
Cache std/bzip2 Huffman tree lookup
...
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 46.5MB/s ± 0% 60.5MB/s ± 0% +30.16% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/clang11 39.4MB/s ± 1% 46.7MB/s ± 1% +18.43% (p=0.008 n=5+5)
wuffs_bzip2_decode_10k/gcc10 43.8MB/s ± 0% 58.7MB/s ± 0% +34.07% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/gcc10 35.9MB/s ± 0% 46.9MB/s ± 0% +30.92% (p=0.008 n=5+5)
2022-05-23 15:51:51 +10:00
Nigel Tao
fdad12d59f
Have std/bzip2 read 4 (not 1) bytes per inner loop
...
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 42.9MB/s ± 0% 46.5MB/s ± 0% +8.38% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/clang11 36.9MB/s ± 0% 39.4MB/s ± 1% +6.75% (p=0.008 n=5+5)
wuffs_bzip2_decode_10k/gcc10 36.5MB/s ± 0% 43.8MB/s ± 0% +19.73% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/gcc10 30.8MB/s ± 0% 35.9MB/s ± 0% +16.37% (p=0.008 n=5+5)
2022-05-23 15:22:31 +10:00
Nigel Tao
94a2c704d4
Factor out std/bzip2/decode_block_slow.wuffs
2022-05-23 13:54:50 +10:00
Nigel Tao
27e9b81588
Optimize bzip2 invert_bwt letter counting
...
name old speed new speed delta
wuffs_bzip2_decode_10k/clang11 42.2MB/s ± 0% 42.9MB/s ± 0% +1.63% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/clang11 36.2MB/s ± 1% 36.9MB/s ± 0% +2.07% (p=0.008 n=5+5)
wuffs_bzip2_decode_10k/gcc10 35.3MB/s ± 0% 36.5MB/s ± 0% +3.62% (p=0.008 n=5+5)
wuffs_bzip2_decode_100k/gcc10 29.5MB/s ± 0% 30.8MB/s ± 0% +4.59% (p=0.008 n=5+5)
2022-05-23 13:36:55 +10:00
Nigel Tao
be047533e1
Add bounds check to wuffs_base__make_slice_uNN_ij
2022-05-23 11:07:31 +10:00
Nigel Tao
84ef91dda8
Tweak cgen for an_array[i .. j]
2022-05-17 00:00:25 +10:00
Nigel Tao
f1350825cc
Fix cgen for an_array[i .. j]
2022-05-16 23:39:44 +10:00
Nigel Tao
68b76a8a56
Implement std/bzip2
2022-05-16 23:35:32 +10:00
Nigel Tao
787ff21cc7
Let magic_number_guess_fourcc sniff compression
2022-05-13 11:01:28 +10:00
Nigel Tao
ce8d08598d
Add std/bzip2 package
...
This is just a placeholder decoder implementation.
2022-05-12 23:52:12 +10:00
Nigel Tao
4c56f5bdb2
Fix png.DECODER_WORKBUF_LEN_MAX_INCL_WORST_CASE
2022-05-12 22:30:28 +10:00
Nigel Tao
03fd43cfcc
Add "#png: unsupported CgBI extension" status
2022-03-21 14:12:25 +11:00
Nigel Tao
dd9679b56e
Remove some redundant assignments after yields
2022-01-25 21:33:19 +11:00
Nigel Tao
7b51266642
Remove redundant json decode_comment "while true"
2022-01-25 21:26:27 +11:00