highway
libjxl
highway | libjxl | |
---|---|---|
66 | 84 | |
3,645 | 2,209 | |
1.8% | 28.2% | |
9.8 | 9.8 | |
6 days ago | 7 days ago | |
C++ | C++ | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
highway
-
Llamafile 0.7 Brings AVX-512 Support: 10x Faster Prompt Eval Times for AMD Zen 4
The bf16 dot instruction replaces 6 instructions: https://github.com/google/highway/blob/master/hwy/ops/x86_12...
-
JPEG XL and the Pareto Front
[0] for those interested in Highway.
It's also mentioned in [1], which starts off
> Today we're sharing open source code that can sort arrays of numbers about ten times as fast as the C++ std::sort, and outperforms state of the art architecture-specific algorithms, while being portable across all modern CPU architectures. Below we discuss how we achieved this.
[0] https://github.com/google/highway
[1] https://opensource.googleblog.com/2022/06/Vectorized%20and%2..., which has an associated paper at https://arxiv.org/pdf/2205.05982.pdf.
-
Gemma.cpp: lightweight, standalone C++ inference engine for Gemma models
Thanks so much!
Everyone working on this self-selected into contributing, so I think of it less as my team than ... a team?
Specifically want to call out: Jan Wassenberg (author of https://github.com/google/highway) and I started gemma.cpp as a small project just a few months ago + Phil Culliton, Dan Zheng, and Paul Chang + of course the GDM Gemma team.
-
From slow to SIMD: A Go optimization story
C++ users can enjoy Highway [1].
[1] https://github.com/google/highway/
- GDlog: A GPU-Accelerated Deductive Engine
-
Designing a SIMD Algorithm from Scratch
At that point it is better to have some kind of DSL that should not be in the main language, because it would target a much lower level than a typical program. The best effort I've seen in this scene was Google's Highway [1] (not to be confused with HighwayHash) and I even once attempted to recreate it in Rust, but it is still distanced from my ideal.
[1] https://github.com/google/highway
-
SIMD Everywhere Optimization from ARM Neon to RISC-V Vector Extensions
Interesting, thanks for sharing :)
At the time we open-sourced Highway, the standardization process had already started and there were some discussions.
I'm curious why stdlib is the only path you see to default? Compare the activity level of https://github.com/VcDevel/std-simd vs https://github.com/google/highway. As to open-source usage, after years of std::experimental, I see <200 search hits [1], vs >400 for Highway [2], even after excluding several library users.
But that aside, I'm not convinced standardization is the best path for a SIMD library. We and external users extend Highway on a weekly basis as new use cases arise. What if we deferred those changes to 3-monthly meetings, or had to wait for one meeting per WD, CD, (FCD), DIS, (FDIS) stage before it's standardized? Standardization seems more useful for rarely-changing things.
1: https://sourcegraph.com/search?q=context:global+std::experim...
2: https://sourcegraph.com/search?q=context:global+HWY_NAMESPAC...
-
Permuting Bits with GF2P8AFFINEQB
Thanks for the link. We were previously using GFNI for bit reversal and 8-bit shifts, and I just extended that to our 8-bit BroadcastSignBit (https://github.com/google/highway/pull/1784).
-
Six times faster than C
You could study Google's Highway library [1].
[1] https://github.com/google/highway
-
AMD EPYC 97x4 “Bergamo” CPUs: 128 Zen 4c CPU Cores for Servers, Shipping Now
Runtime feature detection need not be rare nor hard, it's a few dozen lines of boilerplate. You can even write your code just once: see https://github.com/google/highway#examples.
libjxl
- JPEG XL Reference Implementation
-
JPEG XL and the Pareto Front
https://github.com/libjxl/libjxl/blob/main/doc/format_overvi... is a pretty detailed but good overview. The highlights are variable size DCT (up to 128x128), ANS entropy prediction, and chroma from luminance prediction. https://github.com/libjxl/libjxl/blob/main/doc/encode_effort... also gives a good breakdown of features by effort level.
-
Compressing Text into Images
For JPEG XL, refer to its format overview [1]. In short its lossless mode uses a combination of multiple techniques: the rANS coding with an alias table, LZ77, reversible color transforms, a general vector quantization that subsumes palettes, a modified Haar transform and a learnable meta-adaptive decision tree for context modelling.
One good thing about JPEG XL is that its lossy mode also largely uses the same tool, with a major addition of specialized quantization and context modelling for low- and high-frequenty components.
[1] https://github.com/libjxl/libjxl/blob/main/doc/format_overvi...
- JPEG XL v0.9.0 Released
-
Stripping Metadata
The cjxl source is here. If you spot any reason why -x strip=exif may not work, tell me.
-
Www Which WASM Works
The problem is that the instructions for actually running the WASM file are not that clear... the docs the author mentions shows how to compile to WASM, which is easy enough, but then here's the instructions to make that actually work in the browser:
https://github.com/libjxl/libjxl/blob/main/tools/wasm_demo/R...
Yeah, you need some mysterious Python script, a JS service worker at runtime, choose whether you want the WASM or WASM_SIMD target, use a browser that supports Threads and SIMD if you chose that, make sure to serve everything with the appropriate custom HTTP headers... just reading that, I can see that to get this stuff working on non-browser WASM targets would likely require expertise in WASM, which is the point of the OP. WASM's UX is just not there yet.
-
First automatic JPEG-XL cloud service
https://github.com/libjxl/libjxl#usage
> Specifically for JPEG files, the default cjxl behavior is to apply lossless recompression and the default djxl behavior is to reconstruct the original JPEG file (when the extension of the output file is .jpg).
-
Why "sudo make install"?
I mean compiling a bleeding edge kicad, inkscape or jpeg-xl is easy. But will probably trash your system if you already have an older version installed.
-
XYB JPEG: Perceptual Color Encoding Tested
But you look at your image viewer that could have the lossless indicator? (and there is an issue open to add this indicator to the jxl files)
https://github.com/libjxl/libjxl/issues/432
-
Heyo Everyone! - is there a win or mac software to batch convert imgs to avif?
You might want to use libjxl directly, e.g. for visually lossless images: cjxl --effort 9 --brotli_effort 11 --distance 1.0 --num_threads (nproc) --lossless_jpeg 0 input.png output.jxl on linux (if you're on windows/mac, just replace the (nproc) with the number of cpu threads you have, e.g. --num_threads 16).
What are some alternatives?
xsimd - C++ wrappers for SIMD intrinsics and parallelized, optimized mathematical functions (SSE, AVX, AVX512, NEON, SVE))
qoi - The “Quite OK Image Format” for fast, lossless image compression
Vc - SIMD Vector Classes for C++
Android-Image-Filter - some android image filters
swup - Versatile and extensible page transition library for server-rendered websites 🎉
DirectXMath - DirectXMath is an all inline SIMD C++ linear algebra library for use in games and graphics apps
libavif - libavif - Library for encoding and decoding .avif files
riscv-v-spec - Working draft of the proposed RISC-V V vector extension
jxl-migrate - A simple Python script to migrate images to the JPEG XL (JXL) format
jpeg-xl
squoosh - Make images smaller using best-in-class codecs, right in the browser.