Commit Graph
3811 Commits
Author SHA1 Message Date
Nigel Tao e12f10eef0 std/jpeg: tweak ignore too-short marker code
name                                             old speed     new speed     delta

wuffs_jpeg_decode_19k_8bpp/clang14               317MB/s ± 0%  325MB/s ± 0%  +2.60%  (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/clang14  322MB/s ± 0%  325MB/s ± 0%  +0.94%  (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/clang14   864MB/s ± 0%  880MB/s ± 0%  +1.84%  (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/clang14              720MB/s ± 0%  730MB/s ± 0%  +1.39%  (p=0.016 n=4+5)
wuffs_jpeg_decode_552k_24bpp_420/clang14         783MB/s ± 0%  794MB/s ± 0%  +1.44%  (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/clang14         884MB/s ± 0%  914MB/s ± 0%  +3.39%  (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/clang14            781MB/s ± 0%  796MB/s ± 0%  +1.90%  (p=0.008 n=5+5)

wuffs_jpeg_decode_19k_8bpp/gcc12                 359MB/s ± 0%  360MB/s ± 0%  +0.12%  (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_progressive/gcc12    311MB/s ± 0%  310MB/s ± 0%  -0.30%  (p=0.008 n=5+5)
wuffs_jpeg_decode_30k_24bpp_sequential/gcc12     909MB/s ± 0%  915MB/s ± 0%  +0.66%  (p=0.008 n=5+5)
wuffs_jpeg_decode_77k_24bpp/gcc12                747MB/s ± 0%  750MB/s ± 0%  +0.34%  (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_420/gcc12           817MB/s ± 0%  819MB/s ± 0%  +0.30%  (p=0.008 n=5+5)
wuffs_jpeg_decode_552k_24bpp_444/gcc12           971MB/s ± 0%  972MB/s ± 0%  +0.11%  (p=0.008 n=5+5)
wuffs_jpeg_decode_4002k_24bpp/gcc12              819MB/s ± 0%  821MB/s ± 0%  +0.21%  (p=0.008 n=5+5)
2024-08-25 23:03:06 +10:00
Nigel Tao 6693250aa9 lang: add io_reader.peek_u8_at 2024-08-25 15:07:29 +10:00
Nigel Tao d4bab677b0 std/jpeg: skip 0xFF filler before restart search 2024-08-25 14:48:17 +10:00
Nigel Tao 6a9347843b std/jpeg: ignore too-short COM or APPn markers 2024-08-25 13:46:16 +10:00
Nigel Tao 408ab25f04 script: have confirm-matches-djpeg say "too large"
+Differ (large)
2024-08-25 13:05:59 +10:00
Nigel Tao 819742cfac std/jpeg: add "#short SOS bitstream" 2024-08-24 17:01:28 +10:00
Nigel Tao a824c55c3d std/jpeg: allow DHT markers before SOF 2024-08-24 16:13:31 +10:00
Nigel Tao 60e3b8cb1c test/data: add bricks-color.etc1s.pkm 2024-08-23 22:14:33 +10:00
Nigel Tao 96eda2ec0d std/etc2: support transparency 2024-08-18 15:09:51 +10:00
Nigel Tao 2d80615a08 std/etc2: refactor decoder.from_src_to_buffer 2024-08-18 10:07:58 +10:00
Nigel Tao 7637982814 std/etc2: support ETC2PACKAGE_RGB_NO_MIPMAPS 2024-08-18 09:42:22 +10:00
Nigel Tao 43df015669 std/etc2: add new package 2024-08-17 15:31:29 +10:00
Nigel Tao 5a8f636a66 base: add magic number for ETC2 2024-08-16 10:17:44 +10:00
Nigel Tao 4423a0cbbe test/data: add bricks-color.etc?.pkm 2024-08-16 09:21:12 +10:00
Nigel Tao beaf456500 release: wuffs gen -version=0.4.0-alpha.8 v0.4.0-alpha.8 2024-08-13 10:46:04 +10:00
Nigel Tao 5d69840f8e cgen: swap calloc args
For calloc(nmemb, size), multiplication is commutative, but this still
fixes a -Werror=calloc-transposed-args failure with coreboot's compiler.
2024-08-12 22:33:33 +10:00
Nigel Tao 721e574398 base: avoid "#if SIZE_MAX < UINT64_MAX"
This fixes a -Werror=undef failure with coreboot's compiler.
2024-08-12 22:29:40 +10:00
Nigel Tao c89b3bc6d8 release: wuffs gen -version=0.4.0-alpha.7 v0.4.0-alpha.7 2024-08-11 11:08:25 +10:00
Nigel Tao a07eb7704b std/jpeg: add QUIRK_REJECT_PROGRESSIVE_JPEGS 2024-08-11 10:15:13 +10:00
Nigel Tao bd27cc0d9b std/qoi: use PIXEL_FORMAT__BGRX 2024-08-09 13:48:34 +10:00
Nigel Tao d06700f00b std/qoi: add new package
Fixes #63
2024-08-08 23:49:17 +10:00
Nigel Tao 870cfd18a7 release: wuffs gen -version=0.4.0-alpha.6 v0.4.0-alpha.6 2024-08-05 00:14:21 +10:00
Nigel Tao ffb64df0a0 aux: add QuirkKeyValuePair type 2024-08-05 00:12:15 +10:00
Nigel Tao 3215f6afac fuzz: remove "not enough data" from pixel swizzler 2024-08-04 23:36:10 +10:00
Nigel Tao 8a722790af example/imageviewer: change screen_gamma flag 2024-08-04 23:25:07 +10:00
Nigel Tao d270839e3f std/jpeg: let use_lower_quality work with CMYK 2024-08-04 23:16:58 +10:00
Nigel Tao c9fff5b207 std/jpeg: add and use WUFFS_BASE__QUIRK_QUALITY 2024-08-04 23:15:58 +10:00
Nigel Tao fb769ff82f base: disable SIMD on MSVC x86_64 by default
This recreates the case as of commit f1698226 (tag v0.4.0-alpha.4), in
that, by default (without #define'ing a macro or passing an /arch:ETC
compiler flag), Wuffs does not use SIMD on MSVC x86_64.

Commit b64a7610 (after tag v0.4.0-alpha.4, before tag v0.4.0-alpha.5)
changed the default so that x86_64_v2 (roughly equivalent to SSE4.2) was
enabled by default, since the user from issue #148 was enabling that
anyway (in an unsupported way, by #define'ing a macro that was a private
implementation detail) with no problems (and better performance).

However, another user later reported (in issue #151) that enabling SIMD
on MSVC x86_64 somehow lead to ICEs (Internal Compiler Errors).

This commit restores the default to "no SIMD" and it is up to the MSVC
user to opt in to the SIMD code paths. Clang and GCC are unaffected:
SIMD remains enabled by default.

Updates #148
Updates #151
2024-07-31 17:12:55 +10:00
Nigel Tao 5e0b2ae0d5 script: add print-json-token-etc usage comments 2024-07-27 09:41:00 +10:00
Nigel Tao a7fb1e8d69 script: avoid gcc -Wstringop-overread for strnlen 2024-07-27 09:33:39 +10:00
Nigel Tao ce1f59e9ce base: format token-public.h constants 2024-07-27 09:11:53 +10:00
Nigel Tao 42b070e487 std/jpeg: halve maximum scan count from 64 to 32
cjpeg defaults to using 1 (sequential) or 10 (progressive) scans. 32 is
still easily more than what's seen in practice.

The previous commit (f9c384d6 std/jpeg: add "expect multiple scans"
check) makes Wuffs more closely match libjpeg. Without that commit,
though, this commit halves the time taken to decode the oss-fuzz test
case (linked below) from 6 to 3 seconds, in an optimized build. For the
debug-sanitizer fuzzer build, without this commit, that test case times
out after 60 seconds but this commit should halve the time taken.

Updates https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=70340
2024-07-24 22:09:25 +10:00
Nigel Tao f9c384d6b2 std/jpeg: add "expect multiple scans" check
Updates https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=70340
2024-07-23 21:53:32 +10:00
Nigel Tao d0603f3b94 test/3pdata: add webpsuite 2024-07-09 21:43:24 +10:00
Nigel Tao c6aebf819f std/webp: re-implement 8-bit color indexing 2024-07-09 16:50:58 +10:00
Nigel Tao 8fe987e0b2 base: add sign_extend_convert_u8_u32 2024-07-09 16:31:58 +10:00
Nigel Tao d1a9749571 check: drop pointer-typed facts on suspension 2024-07-09 16:21:47 +10:00
Nigel Tao f37cfcf554 check: drop more facts when calling coroutines 2024-07-09 14:11:31 +10:00
Nigel Tao cc9ee184d0 cgen: omit consecutive Wconversion gcc pragmas 2024-07-09 12:39:16 +10:00
Nigel Tao fab0dd534a release: wuffs gen -version=0.4.0-alpha.5 v0.4.0-alpha.5 2024-07-09 12:08:25 +10:00
Nigel Tao 3be81643cc hello-wuffs-c: update endwhile syntax
Also fix lang/check
2024-07-09 10:39:24 +10:00
Nigel Tao 495f0280a8 base: add ETC__I_KNOW_THAT_ETC_BEST_WITH_ARCH_AVX2
Updates #148
2024-07-09 10:34:35 +10:00
Nigel Tao b64a761067 base: enable ETC__CPU_ARCH__X86_64_V2 on MSVC
If I understand the https://github.com/google/wuffs/issues/148
discussion correctly, a user overrode WUFFS_BASE__CPU_ARCH__X86_FAMILY
(without also providing /arch:AVX) to enable SSE4.2 code (even though,
technically, x86_64 doesn't guarantee SSE4.2, only SSE2). This seemed to
work fine in practice, but was unsupported by Wuffs and 'broke' by
fixing #145, now looking for WUFFS_BASE__CPU_ARCH__X86_64 instead of
WUFFS_BASE__CPU_ARCH__X86_FAMILY.

WUFFS_BASE__CPU_ARCH__X86_FAMILY has since been renamed to
WUFFS_PRIVATE_IMPL__CPU_ARCH__X86_FAMILY and then removed entirely.

As SSE4.2 (roughly equivalent to x86-64-v2) seems to work fine at
compile time (with the existing cpuid detection at runtime), enable it
by default for MSVC, without need /arch.

Enabling x86-64-v3 too, by default, is held back for now, pending
further confirmation from MSVC users. The #148 user was exercising
Wuffs' PNG codec, which uses SSE4.2 but not AVX or AVX2. Currently, only
Wuffs' JPEG codec (and YCbCr conversion) uses AVX or AVX2.

GCC and Clang don't need this fiddliness, because they support
"__attribute__((target(arg)))".

Updates #148
2024-07-09 10:25:42 +10:00
Nigel Tao 7a57e2b600 base: remove ETC__CPU_ARCH__X86_FAMILY
Updates #148
2024-07-09 09:33:34 +10:00
Nigel Tao 4111785304 base: have MSVC detect AVX2 not AVX
The x86-64-v3 micro-architecture level requires AVX2.

Updates #148
2024-07-09 09:22:23 +10:00
Nigel Tao affa1e02d4 base: add WUFFS_PRIVATE_IMPL__CPU_ARCH__X86_64_V2
Updates #148
2024-07-09 09:17:09 +10:00
Nigel Tao 97b727a1ae base: warn defining private implementation macros
Updates #148
2024-07-08 21:08:05 +10:00
Nigel Tao 37a3c3ce9b base: rename WUFFS_BASE__CPU_ARCH__ETC
See
https://github.com/google/wuffs/issues/148#issuecomment-2130535812

Updates #148
2024-07-08 18:14:59 +10:00
Nigel Tao 5d4bb4c6e4 std/bmp: remove superfluous "while.goto_suspend" 2024-07-08 17:23:25 +10:00
Nigel Tao aae5997e12 lang: remove endwhile keyword 2024-07-08 17:15:48 +10:00