Nigel Tao
4dfd70928b
std: add "get_quirk(key: u32) u64"
2023-07-16 12:04:09 +10:00
Nigel Tao
dd29401137
std/jpeg: re-format generated IDCT code
2023-06-28 13:49:55 +10:00
Nigel Tao
97c4e85e0e
std/jpeg: add more-SIMD-like IDCT algorithm
...
This adds commented-out code that is equivalent to the existing IDCT
algorithm. It's slower as is (and hence commented out) but it is closer
to a follow-up commit's SIMD-optimized algorithm.
2023-06-28 13:45:25 +10:00
Nigel Tao
49f50cca91
std/jpeg: cap the implicit-zero bitstream padding
...
Updates https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=59966
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 241MB/s ± 0% 237MB/s ± 0% -1.57% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 213MB/s ± 0% 212MB/s ± 0% -0.43% (p=0.016 n=5+4)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 387MB/s ± 0% 386MB/s ± 0% -0.08% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 341MB/s ± 0% 340MB/s ± 0% -0.50% (p=0.016 n=4+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 356MB/s ± 0% 353MB/s ± 0% -0.89% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 484MB/s ± 0% 480MB/s ± 0% -0.96% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 364MB/s ± 0% 360MB/s ± 0% -1.12% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 244MB/s ± 0% 247MB/s ± 0% +0.88% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 254MB/s ± 0% 254MB/s ± 0% -0.20% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 508MB/s ± 0% 512MB/s ± 0% +0.61% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 434MB/s ± 0% 436MB/s ± 0% +0.39% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 456MB/s ± 0% 458MB/s ± 0% +0.41% (p=0.016 n=4+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 481MB/s ± 0% 483MB/s ± 0% +0.49% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 463MB/s ± 0% 466MB/s ± 0% +0.57% (p=0.016 n=4+5)
2023-06-23 21:38:01 +10:00
Nigel Tao
8d9d6c1292
Performance mystery: load-bearing "no-op continue"
...
There is no semantic difference in this commit. There's no further code
after the if-else chain in the loop body. Nonetheless, adding a "no-op
continue" impacts performance: bad for clang and good for gcc.
Profiling suggests we spend less than 5% overall in
wuffs_jpeg__decoder__fill_bitstream.
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 241MB/s ± 0% 229MB/s ± 0% -5.02% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 213MB/s ± 0% 205MB/s ± 0% -4.13% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 386MB/s ± 0% 375MB/s ± 0% -2.88% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 341MB/s ± 0% 326MB/s ± 0% -4.58% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 356MB/s ± 0% 339MB/s ± 0% -4.90% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 484MB/s ± 0% 475MB/s ± 0% -1.96% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 364MB/s ± 0% 343MB/s ± 0% -5.83% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 234MB/s ± 0% 245MB/s ± 0% +4.68% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 245MB/s ± 0% 254MB/s ± 0% +3.35% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 500MB/s ± 0% 514MB/s ± 0% +2.81% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 417MB/s ± 0% 434MB/s ± 0% +4.18% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 442MB/s ± 0% 459MB/s ± 0% +3.76% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 477MB/s ± 0% 486MB/s ± 0% +1.99% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 450MB/s ± 0% 467MB/s ± 0% +3.70% (p=0.008 n=5+5)
It is a mystery why this happens. Note though that the "continue" in the
Wuffs code becomes a "goto" in the generated C code, because (in the
general case) Wuffs has "labeled continue/break", which can jump out of
a not-inner-most loop, and C99 does not. Wuffs' "generate C code" thus
uses a C "goto". A follow-up commit may try a C "continue" instead.
To reproduce:
----
$ git clone https://github.com/google/wuffs.git
$ cd wuffs
$ gcc --version | head -n 1
gcc (Debian 10.2.1-6) 10.2.1 20210110
$ # Check out this commit.
$ git checkout --quiet THE_HASH_OF_THIS_COMMIT
$ gcc -O3 -Wall -std=c99 test/c/std/jpeg.c -DWUFFS_MIMIC -ljpeg
$ ./a.out -bench -focus=wuffs_jpeg_decode_77k_24bpp | grep MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 176988 ns/op 433.927 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 176849 ns/op 434.268 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 176800 ns/op 434.389 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 176844 ns/op 434.279 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 176869 ns/op 434.218 MB/s
$ # Check out the parent commit.
$ git checkout --quiet THE_HASH_OF_THIS_COMMIT^
$ gcc -O3 -Wall -std=c99 test/c/std/jpeg.c -DWUFFS_MIMIC -ljpeg
$ ./a.out -bench -focus=wuffs_jpeg_decode_77k_24bpp | grep MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 183848 ns/op 417.734 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 183870 ns/op 417.684 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 183833 ns/op 417.770 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 183873 ns/op 417.679 MB/s
Benchmarkwuffs_jpeg_decode_77k_24bpp/gcc10 3000 183843 ns/op 417.746 MB/s
----
2023-06-23 17:02:14 +10:00
Nigel Tao
40fca0f03d
std/jpeg: roll back fill_bitstream inner loop
...
Commit 723c604a "std/jpeg: tweak decoder.fill_bitstream inner loop"
inadvertently changed "increment wi" behavior in the rare code paths.
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 237MB/s ± 0% 241MB/s ± 0% +1.79% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 213MB/s ± 0% 213MB/s ± 0% +0.36% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 384MB/s ± 0% 386MB/s ± 0% +0.50% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 338MB/s ± 0% 341MB/s ± 0% +0.95% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 353MB/s ± 0% 356MB/s ± 0% +0.99% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 481MB/s ± 0% 484MB/s ± 0% +0.61% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 359MB/s ± 0% 364MB/s ± 0% +1.40% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 245MB/s ± 0% 234MB/s ± 0% -4.45% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 247MB/s ± 0% 245MB/s ± 0% -0.59% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 510MB/s ± 0% 500MB/s ± 0% -1.94% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 432MB/s ± 0% 417MB/s ± 0% -3.62% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 456MB/s ± 0% 442MB/s ± 0% -3.14% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 484MB/s ± 0% 477MB/s ± 0% -1.49% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 465MB/s ± 0% 450MB/s ± 0% -3.28% (p=0.008 n=5+5)
2023-06-23 16:29:16 +10:00
Nigel Tao
a00150f62f
std/jpeg: tweak decode_mcu up-front r.length check
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 236MB/s ± 0% 237MB/s ± 0% +0.11% (p=0.032 n=4+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 210MB/s ± 0% 213MB/s ± 0% +1.20% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 385MB/s ± 0% 384MB/s ± 0% ~ (p=0.095 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 338MB/s ± 0% 338MB/s ± 0% ~ (p=0.151 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 353MB/s ± 0% 353MB/s ± 0% ~ (p=0.548 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 481MB/s ± 0% 481MB/s ± 0% ~ (p=0.690 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 360MB/s ± 0% 359MB/s ± 0% -0.35% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 244MB/s ± 0% 245MB/s ± 0% +0.44% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 251MB/s ± 0% 247MB/s ± 0% -1.46% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 509MB/s ± 0% 510MB/s ± 0% +0.13% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 431MB/s ± 0% 432MB/s ± 0% +0.24% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 455MB/s ± 0% 456MB/s ± 0% +0.26% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 481MB/s ± 0% 484MB/s ± 0% +0.56% (p=0.016 n=4+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 463MB/s ± 0% 465MB/s ± 0% +0.36% (p=0.008 n=5+5)
2023-06-22 11:37:40 +10:00
Nigel Tao
255516bc21
std/jpeg: comments for "read Huffman LUT earlier"
...
This commit is the second of two. It just adds comments to the code
added by the previous commit.
2023-06-21 22:51:22 +10:00
Nigel Tao
d9c7740ea6
std/jpeg: read Huffman look-up table earlier
...
This commit is the first of two. It just changes code, and is the
minimal code change that leads to these performance improvements. The
follow-up commit will add comments that will also include a reference to
this one's commit hash. Even later commits may do some more refactoring.
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 224MB/s ± 0% 236MB/s ± 0% +5.38% (p=0.016 n=5+4)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 211MB/s ± 0% 210MB/s ± 0% -0.55% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 377MB/s ± 0% 385MB/s ± 0% +1.91% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 328MB/s ± 0% 338MB/s ± 0% +3.23% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 341MB/s ± 0% 353MB/s ± 0% +3.47% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 472MB/s ± 0% 481MB/s ± 0% +1.93% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 347MB/s ± 0% 360MB/s ± 0% +3.70% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 225MB/s ± 0% 244MB/s ± 0% +8.27% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 246MB/s ± 0% 251MB/s ± 0% +1.67% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 498MB/s ± 0% 509MB/s ± 0% +2.18% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 408MB/s ± 0% 431MB/s ± 0% +5.86% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 428MB/s ± 0% 455MB/s ± 0% +6.38% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 470MB/s ± 0% 481MB/s ± 0% +2.46% (p=0.016 n=5+4)
wuffs_jpeg_decode_4002k_24bpp/gcc10 433MB/s ± 0% 463MB/s ± 0% +7.03% (p=0.008 n=5+5)
2023-06-21 21:56:54 +10:00
Nigel Tao
bedf2bd7c3
lang: let skip_u32_fast imply can_undo_byte
2023-06-20 23:02:01 +10:00
Nigel Tao
723c604a5b
std/jpeg: tweak decoder.fill_bitstream inner loop
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 229MB/s ± 0% 225MB/s ± 0% -1.78% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 212MB/s ± 0% 212MB/s ± 0% ~ (p=0.421 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 380MB/s ± 0% 377MB/s ± 0% -0.56% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 331MB/s ± 0% 328MB/s ± 0% -1.00% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 344MB/s ± 0% 341MB/s ± 0% -0.97% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 476MB/s ± 0% 473MB/s ± 0% -0.66% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 350MB/s ± 0% 348MB/s ± 0% -0.64% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 215MB/s ± 0% 225MB/s ± 0% +4.62% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 246MB/s ± 0% 247MB/s ± 0% +0.35% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 485MB/s ± 0% 499MB/s ± 0% +2.84% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 394MB/s ± 0% 408MB/s ± 0% +3.63% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 414MB/s ± 0% 428MB/s ± 0% +3.30% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 462MB/s ± 0% 470MB/s ± 0% +1.81% (p=0.016 n=4+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 420MB/s ± 0% 433MB/s ± 0% +3.13% (p=0.008 n=5+5)
2023-06-20 22:21:10 +10:00
Nigel Tao
1acd74482a
std/jpeg: add more EXTEND comments
2023-06-20 17:33:08 +10:00
Nigel Tao
6eb92544bd
std/jpeg: tweak decode_mcu z variable assignment
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 227MB/s ± 0% 229MB/s ± 0% +0.93% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 213MB/s ± 0% 212MB/s ± 0% -0.50% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 380MB/s ± 0% 380MB/s ± 0% ~ (p=1.000 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 329MB/s ± 0% 331MB/s ± 0% +0.73% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 342MB/s ± 0% 344MB/s ± 0% +0.72% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 469MB/s ± 0% 476MB/s ± 0% +1.46% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 348MB/s ± 0% 350MB/s ± 0% +0.51% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 213MB/s ± 0% 215MB/s ± 0% +0.70% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 246MB/s ± 0% 246MB/s ± 0% ~ (p=0.095 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 482MB/s ± 0% 485MB/s ± 0% +0.61% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 392MB/s ± 0% 394MB/s ± 0% +0.53% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 412MB/s ± 0% 414MB/s ± 0% +0.45% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 460MB/s ± 0% 462MB/s ± 0% +0.43% (p=0.016 n=5+4)
wuffs_jpeg_decode_4002k_24bpp/gcc10 419MB/s ± 0% 420MB/s ± 0% +0.32% (p=0.008 n=5+5)
2023-06-19 20:13:01 +10:00
Nigel Tao
48fa7182f4
std/jpeg: tweak UNZIG comments
2023-06-19 13:19:24 +10:00
Nigel Tao
36323abf87
std/jpeg: tighten EXTEND element type s/u32/u16/
...
I'm not sure of the underlying reason for the gcc benchmark anomaly (the
clang numbers don't change).
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 227MB/s ± 0% 227MB/s ± 0% ~ (p=0.151 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 209MB/s ± 0% 213MB/s ± 0% +1.62% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 379MB/s ± 0% 380MB/s ± 0% +0.13% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 329MB/s ± 0% 329MB/s ± 0% +0.06% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 342MB/s ± 0% 342MB/s ± 0% ~ (p=0.690 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 468MB/s ± 0% 469MB/s ± 0% +0.10% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 348MB/s ± 0% 348MB/s ± 0% +0.08% (p=0.016 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 213MB/s ± 0% 213MB/s ± 0% ~ (p=0.151 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 221MB/s ± 0% 246MB/s ± 0% +11.51% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 487MB/s ± 0% 482MB/s ± 0% -0.98% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 392MB/s ± 0% 392MB/s ± 0% ~ (p=1.000 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 413MB/s ± 0% 412MB/s ± 0% ~ (p=0.190 n=4+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 459MB/s ± 0% 460MB/s ± 0% +0.09% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 419MB/s ± 0% 419MB/s ± 0% +0.04% (p=0.008 n=5+5)
2023-06-18 21:35:49 +10:00
Nigel Tao
e4902dbd45
std/jpeg: tweak "this.mcu_zig_index" vs "var z"
2023-06-18 21:18:41 +10:00
Nigel Tao
9b97c27ec6
std/jpeg: tweak UNZIG array
...
We'll hopefully claw back the performance in a follow-up commit.
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 222MB/s ± 0% 224MB/s ± 0% +1.11% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 213MB/s ± 0% 210MB/s ± 0% -1.53% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 376MB/s ± 0% 378MB/s ± 0% +0.37% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 325MB/s ± 0% 328MB/s ± 0% +0.66% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 339MB/s ± 0% 340MB/s ± 0% +0.46% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 468MB/s ± 0% 469MB/s ± 0% +0.27% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 344MB/s ± 0% 346MB/s ± 0% +0.37% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 212MB/s ± 0% 213MB/s ± 0% +0.46% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 246MB/s ± 0% 221MB/s ± 0% -9.98% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 484MB/s ± 0% 484MB/s ± 0% ~ (p=0.056 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 390MB/s ± 0% 392MB/s ± 0% +0.47% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 415MB/s ± 0% 414MB/s ± 0% -0.17% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 463MB/s ± 0% 459MB/s ± 0% -0.78% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 420MB/s ± 0% 419MB/s ± 0% -0.19% (p=0.008 n=5+5)
2023-06-18 20:57:50 +10:00
Nigel Tao
19e5cccee3
std/jpeg: add an EXTEND look-up table
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 223MB/s ± 0% 222MB/s ± 0% -0.81% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 208MB/s ± 0% 213MB/s ± 0% +2.32% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 375MB/s ± 0% 376MB/s ± 0% +0.34% (p=0.016 n=4+5)
wuffs_jpeg_decode_77k_24bpp/clang11 319MB/s ± 0% 325MB/s ± 0% +1.92% (p=0.016 n=4+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 329MB/s ± 0% 339MB/s ± 0% +3.00% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 465MB/s ± 0% 468MB/s ± 0% +0.65% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 331MB/s ± 0% 344MB/s ± 0% +4.02% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 208MB/s ± 0% 212MB/s ± 0% +1.76% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 243MB/s ± 0% 246MB/s ± 0% +1.09% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 479MB/s ± 0% 484MB/s ± 0% +1.17% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 385MB/s ± 0% 390MB/s ± 0% +1.40% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 407MB/s ± 0% 415MB/s ± 0% +1.98% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 457MB/s ± 0% 463MB/s ± 0% +1.29% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 411MB/s ± 0% 420MB/s ± 0% +2.06% (p=0.008 n=5+5)
2023-06-18 18:44:41 +10:00
Nigel Tao
44e745dd0e
std/jpeg: optimize EXTEND'ing MCU bits
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 224MB/s ± 1% 223MB/s ± 0% ~ (p=0.190 n=4+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 206MB/s ± 0% 208MB/s ± 0% +0.86% (p=0.016 n=4+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 374MB/s ± 0% 375MB/s ± 0% +0.26% (p=0.016 n=5+4)
wuffs_jpeg_decode_77k_24bpp/clang11 319MB/s ± 0% 319MB/s ± 0% +0.16% (p=0.029 n=4+4)
wuffs_jpeg_decode_552k_24bpp_420/clang11 329MB/s ± 0% 329MB/s ± 0% -0.06% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 465MB/s ± 0% 465MB/s ± 0% -0.12% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 332MB/s ± 0% 331MB/s ± 0% -0.15% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 176MB/s ± 0% 208MB/s ± 0% +18.26% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 246MB/s ± 0% 243MB/s ± 0% -1.03% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 472MB/s ± 0% 479MB/s ± 0% +1.33% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 334MB/s ± 0% 385MB/s ± 0% +15.33% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 351MB/s ± 0% 407MB/s ± 0% +15.74% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 425MB/s ± 0% 457MB/s ± 0% +7.38% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 349MB/s ± 0% 411MB/s ± 0% +17.74% (p=0.008 n=5+5)
2023-06-18 17:37:23 +10:00
Nigel Tao
143991a301
std/jpeg: check up-front for sufficient AC bits
...
The micro-benchmarks are mixed for now, but this sets us up to remove an
inner-loop bounds check in a future commit.
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 226MB/s ± 0% 224MB/s ± 1% -1.03% (p=0.029 n=4+4)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 210MB/s ± 0% 206MB/s ± 0% -1.59% (p=0.029 n=4+4)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 379MB/s ± 0% 374MB/s ± 0% -1.25% (p=0.016 n=4+5)
wuffs_jpeg_decode_77k_24bpp/clang11 326MB/s ± 0% 319MB/s ± 0% -2.35% (p=0.029 n=4+4)
wuffs_jpeg_decode_552k_24bpp_420/clang11 338MB/s ± 0% 329MB/s ± 0% -2.53% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 468MB/s ± 0% 465MB/s ± 0% -0.58% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 347MB/s ± 0% 332MB/s ± 0% -4.41% (p=0.016 n=4+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 174MB/s ± 0% 176MB/s ± 0% +1.18% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 247MB/s ± 0% 246MB/s ± 0% -0.55% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 477MB/s ± 0% 472MB/s ± 0% -0.90% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 328MB/s ± 0% 334MB/s ± 0% +1.69% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 346MB/s ± 0% 351MB/s ± 0% +1.57% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 424MB/s ± 0% 425MB/s ± 0% +0.39% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 350MB/s ± 0% 349MB/s ± 0% -0.23% (p=0.008 n=5+5)
2023-06-18 17:37:12 +10:00
Nigel Tao
43beae1d3d
lang: make "return a slice" return a slice of this
2023-06-13 22:38:29 +10:00
Nigel Tao
dd6a5d5435
std/jpeg: memoize ac_huff_table_fast
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 215MB/s ± 0% 226MB/s ± 0% +5.17% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 209MB/s ± 0% 210MB/s ± 0% +0.50% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 368MB/s ± 0% 380MB/s ± 1% +3.11% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 313MB/s ± 0% 327MB/s ± 0% +4.27% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 326MB/s ± 0% 338MB/s ± 0% +3.50% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 462MB/s ± 0% 468MB/s ± 0% +1.14% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 329MB/s ± 1% 346MB/s ± 0% +5.39% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 174MB/s ± 0% 175MB/s ± 0% +0.55% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 228MB/s ± 0% 248MB/s ± 0% +8.49% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 472MB/s ± 0% 478MB/s ± 0% +1.20% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 327MB/s ± 0% 328MB/s ± 0% +0.47% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 344MB/s ± 0% 346MB/s ± 0% +0.46% (p=0.016 n=4+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 422MB/s ± 0% 424MB/s ± 0% +0.49% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 349MB/s ± 0% 348MB/s ± 0% -0.24% (p=0.008 n=5+5)
2023-06-13 22:38:29 +10:00
Nigel Tao
1f0f323414
std/jpeg: memoize Huffman table selectors
2023-06-12 16:23:53 +10:00
Nigel Tao
c0d7d7d046
std/jpeg: remove decode_idct block-selector arg
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 210MB/s ± 0% 213MB/s ± 0% +1.54% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 200MB/s ± 0% 197MB/s ± 0% -1.31% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 362MB/s ± 0% 373MB/s ± 0% +3.04% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 307MB/s ± 0% 318MB/s ± 0% +3.82% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 318MB/s ± 0% 331MB/s ± 0% +4.09% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 434MB/s ± 0% 440MB/s ± 0% +1.34% (p=0.016 n=4+5)
wuffs_jpeg_decode_4002k_24bpp/clang11 320MB/s ± 0% 340MB/s ± 0% +6.29% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 165MB/s ± 0% 172MB/s ± 0% +4.32% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 224MB/s ± 0% 227MB/s ± 0% +1.30% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 454MB/s ± 0% 465MB/s ± 0% +2.40% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 311MB/s ± 0% 324MB/s ± 0% +4.38% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 327MB/s ± 0% 342MB/s ± 0% +4.52% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 384MB/s ± 0% 393MB/s ± 0% +2.34% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 324MB/s ± 0% 345MB/s ± 1% +6.26% (p=0.008 n=5+5)
2023-06-10 14:12:08 +10:00
Nigel Tao
f43246e3bb
std/cbor: fix BEGIN/END comment typo
2023-06-08 22:47:22 +10:00
Nigel Tao
d6cc525059
std/jpeg: optimize IDCT when AC terms are zero
...
name old speed new speed delta
wuffs_jpeg_decode_19k_8bpp/clang11 199MB/s ± 0% 211MB/s ± 0% +5.69% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 169MB/s ± 1% 176MB/s ± 0% +4.32% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang11 269MB/s ± 0% 291MB/s ± 0% +7.89% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang11 250MB/s ± 0% 254MB/s ± 0% +1.90% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/clang11 258MB/s ± 0% 262MB/s ± 0% +1.51% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang11 275MB/s ± 0% 356MB/s ± 0% +29.59% (p=0.016 n=5+4)
wuffs_jpeg_decode_4002k_24bpp/clang11 261MB/s ± 0% 263MB/s ± 1% +0.61% (p=0.008 n=5+5)
wuffs_jpeg_decode_19k_8bpp/gcc10 153MB/s ± 0% 165MB/s ± 0% +8.09% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 180MB/s ± 0% 197MB/s ± 0% +9.56% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc10 288MB/s ± 0% 337MB/s ± 0% +16.81% (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc10 237MB/s ± 0% 245MB/s ± 0% +3.47% (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc10 247MB/s ± 0% 256MB/s ± 0% +3.71% (p=0.016 n=4+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc10 249MB/s ± 0% 348MB/s ± 0% +39.88% (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc10 247MB/s ± 0% 254MB/s ± 0% +2.81% (p=0.008 n=5+5)
2023-06-08 22:03:46 +10:00
Nigel Tao
a3e8531ecb
std/jpeg: add swizzle_ycck_scratch_buffer_2k
2023-06-06 22:25:30 +10:00
Nigel Tao
2865c5bfbd
std/jpeg: call slice.bulk_{load,save}_host_endian
...
Updates https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=59540
name old speed new speed delta
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 131MB/s ± 0% 168MB/s ± 0% +28.44% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 167MB/s ± 0% 175MB/s ± 0% +4.80% (p=0.008 n=5+5)
2023-06-05 12:51:50 +10:00
Nigel Tao
4a164cda64
std/jpeg: tweak apply_progressive_idct
2023-06-05 09:29:30 +10:00
Nigel Tao
238aadd8eb
std/jpeg: factor out calculate_multiple_competc
2023-06-04 21:27:23 +10:00
Nigel Tao
2f18dc61d0
std/jpeg: call slice.bulk_memset
2023-06-04 21:22:14 +10:00
Nigel Tao
5edfe45e15
std/jpeg: add "#unsupported scan count"
...
Updates https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=59540
2023-06-04 15:46:18 +10:00
Nigel Tao
0b18d43e4f
std/jpeg: avoid unnecessary IDCT applications
...
Updates https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=59540
name old speed new speed delta
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 84.6MB/s ± 0% 136.4MB/s ± 0% +61.33% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 93.8MB/s ± 0% 166.5MB/s ± 0% +77.49% (p=0.008 n=5+5)
2023-06-04 15:30:20 +10:00
Nigel Tao
442533f08c
std/jpeg: avoid unnecessary swizzles
...
Updates https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=59540
name old speed new speed delta
wuffs_jpeg_decode_30k_24bpp_progressive/clang11 32.4MB/s ± 0% 84.6MB/s ± 0% +160.78% (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc10 38.6MB/s ± 0% 93.8MB/s ± 0% +142.75% (p=0.008 n=5+5)
2023-06-04 13:24:39 +10:00
Nigel Tao
27a3197727
script: add truncate-progressive-jpeg.go
...
"script/confirm-matches-djpeg.sh test/data/*.jpeg" shows differences on
"test/data/peacock.progressive.scan00[0-8].jpeg".
2023-06-01 22:32:37 +10:00
Nigel Tao
d7ddc153ba
std/jpeg: decode progressive JPEGs
...
"script/confirm-matches-djpeg.sh test/data/*.jpeg" is now all matches.
2023-06-01 12:16:14 +10:00
Nigel Tao
1cd3604351
std/jpeg: prepare to decode progressive JPEGs
2023-05-30 15:36:50 +10:00
Nigel Tao
145ff0ce64
std/jpeg: have fill_bitstream call copy_from_slice
2023-05-22 14:23:16 +10:00
Nigel Tao
ac3bd9cdba
std/jpeg: reject 2 (not 1, 3 or 4) components
2023-05-22 14:11:46 +10:00
Nigel Tao
06ffee27a2
std/jpeg: allow DQT markers after SOF marker
...
Fixes #120
2023-05-21 22:28:59 +10:00
Nigel Tao
94df43c530
std/jpeg: prepare for triangle-filter upsampling
2023-05-21 22:04:45 +10:00
Nigel Tao
9ffc41d16d
std/jpeg: tighten decoder workbuf_len worst case
2023-05-17 22:45:23 +10:00
Nigel Tao
de5dc68b40
std/jpeg: remove components_{w,h}_in_blocks fields
2023-05-17 22:10:42 +10:00
Nigel Tao
85b244aa49
std/netpbm: add new package
2023-05-16 16:29:58 +10:00
Nigel Tao
7514dede23
std/jpeg: decode color images, not just gray
...
Updates #42
2023-05-14 23:03:33 +10:00
Nigel Tao
3bd83e3ebb
std/jpeg: apply Inverse DCT
...
Updates #42
2023-05-11 21:29:07 +10:00
Nigel Tao
8cfe304f3c
std/jpeg: implement Inverse DCT
...
Updates #42
2023-05-08 21:51:47 +10:00
Nigel Tao
cac4df3bde
std/tga: re-type a field from slice to roslice
2023-05-06 10:03:15 +10:00
Nigel Tao
65924cd44d
std/lzw: have flush return a roslice
2023-05-06 10:00:02 +10:00
Nigel Tao
c914f66a6c
std/jpeg: decode Huffman entropy coded data
...
Updates #42
2023-05-06 09:47:10 +10:00