libjpeg-turbo VS rav1e

> all decoders will render the same pixels

Not true. Even just within libjpeg, there are three different IDCT implementations (jidctflt.c, jidctfst.c, jidctint.c) and they produce different pixels (it's a classic speed vs quality trade-off). It's spec-compliant to choose any of those.

A few years ago, in libjpeg-turbo, they changed the smoothing kernel used for decoding (incomplete) progressive JPEGs, from a 3x3 window to 5x5. This meant the decoder produced different pixels, but again, that's still valid:

https://github.com/libjpeg-turbo/libjpeg-turbo/commit/6d91e9...

Last vestiges of this fact AFAIK were libjpeg, which had a macro NEED_SHORT_EXTERNAL_NAMES that shortens all public identifiers to have unique 6-letter-long prefixes. Libjpeg-turbo nowadays has removed them though [1].

[1] https://github.com/libjpeg-turbo/libjpeg-turbo/commit/52ded8...

While I think the move to safer code through Rust and other alternatives is a nice breath of fresh air, I doubt you can get these kinds of optimization without using unsafe code in Rust. These optimized implementations often require some kind of safety-bypassing memory modifications to work as efficiently ad they do.

There's a reason https://github.com/libjpeg-turbo/libjpeg-turbo/tree/main/sim... is filled with assembly files with conditional loading.

Sure. You'll see it very often in codec implementations. From rav1e, a fast AV1 encoder mostly written in Rust: https://github.com/xiph/rav1e/tree/master/src/x86

Large portions of the algorithm have been translated into assembly for ARM and x86. Shaving even a couple percent off something like motion compensation search will add up to meaningful gains.

Or the current reference implementation of JPEG: https://github.com/libjpeg-turbo/libjpeg-turbo/tree/main/sim...

zune-jpeg is 1.5x to 2x faster than jpeg-decoder and is on par with libjpeg-turbo.

This is interesting from the standpoint of how new JVM features can be used to improve performance (what I presume the article's main purpose to have been), but the image processing improvement itself isn't head-turning. Also, we've found that libjpeg-turbo (https://libjpeg-turbo.org/) is ~5x (IIRC, can re-run my JMH benchmark if anyone wants me to) as fast for decoding JPEGs as ImageIO, so we wouldn't even benefit from this change in 21 much.

libjpeg-turbo: https://github.com/libjpeg-turbo/libjpeg-turbo/blob/main/simd/x86_64/jsimdcpu.asm

libjpeg-turbo

For all but the simplest formats (basically BMP), the difficulty of implementing encoding/decoding from scratch is significant - well beyond a beginner's ability, and challenging/time-consuming even for senior developers. So, libraries are used in practice - e.g. libpng and libjpeg-turbo.

Sure. You'll see it very often in codec implementations. From rav1e, a fast AV1 encoder mostly written in Rust: https://github.com/xiph/rav1e/tree/master/src/x86

Large portions of the algorithm have been translated into assembly for ARM and x86. Shaving even a couple percent off something like motion compensation search will add up to meaningful gains.

Or the current reference implementation of JPEG: https://github.com/libjpeg-turbo/libjpeg-turbo/tree/main/sim...

Again, if anything AOM would be the one restricting licenses to AV1 (if they chose to) except AOM has stated and also published AV1 in a way to allow license free access to development (which allows people to make forks of the official build like it's open source) and usage. (1)(2) I don't see why they would suddenly change this.

You can speed up the sampling process with --vmaf n_subsample=5, which in my experience works more accurately than either 2 or 4, possibly due to this bug/feature present in multiple encoders. You might also need to manually set the number of threads used for VMAF calculation with --vmaf n_threads=16, but YMMV.

That remember me of https://github.com/xiph/rav1e which is an AV1 encoder

I put in the request for ffmpeg passthrough mastering-display data a few years ago and haven't heard of any support yet.

It's getting there.. Initial steps for FFmepg: https://patchwork.ffmpeg.org/project/ffmpeg/list/?series=8444 rav1e: https://github.com/xiph/rav1e/pull/3000

It's entirely possible to re-use bits of other HW encoders for the first pass (motion estimation, etc).