highwayhash VS SimSIMD

highwayhash (alt) provides 256 bits. Fast mainly for larger inputs and supports seeds.

HighwayHash can produce 256 bit output, if you really need a hash that long.

It’s a nice post, but “using array methods” probably shouldn’t be placed in the “Efficient Implementation” section. As it often happens with high-level languages, a single plain old loop is faster that three array methods.

Similarly, if you plan to query those vectors in search, you should consider continuous `TypedArray` types, and smaller scalars, than the double precision `number`.

I know very little about JS, but some of the amazing HackerNews community members have previously helped port SimSIMD to JavaScript (https://github.com/ashvardanian/SimSIMD), and I wrote a blogpost covering some of those JS/TS-specifics, NumJS, and MathJS in 2023 (https://ashvardanian.com/posts/javascript-ai-vector-search/).

Hopefully it should help unlock another 10-100x in performance

Arch specific similarity functions in SIMD, with bindings in Python and other languages:

https://github.com/ashvardanian/SimSIMD

SciPy distances module has its own problems. It's pretty slow, and constantly overflows in mixed precision scenarios. It also raises the wrong type of errors when it overflows, and uses general purpose `math` package instead of `numpy` for square roots. So use it with caution.

I've outlined some of the related issues here: https://github.com/ashvardanian/SimSIMD#cosine-similarity-re...

SimSIMD https://github.com/ashvardanian/SimSIMD :

> Up to 200x Faster Inner Products and Vector Similarity — for Python, JavaScript, Rust, C, and Swift, supporting f64, f32, f16 real & complex, i8, and binary vectors using SIMD for both x86 AVX2 & AVX-512 and Arm NEON & SVE

https://news.ycombinator.com/item?id=37808036

For other languages (including nodejs/bun/rust/python etc) you can have a look at SimSIMD which I have contributed to this year (made recompiled binaries for nodejs/bun part of the build process for x86_64 and arm64 on Mac and Linux, x86 and x86_64 on windows).

[0] https://github.com/ashvardanian/SimSIMD

Kahan floats are also commonly used in such cases, but I believe there is room for improvement without hitting those extremes. First of all, we should tune the epsilon here: https://github.com/ashvardanian/SimSIMD/blob/f8ff727dcddcd14...

As for the 64-bit version, its harder, as the higher-precision `rsqrt` approximations are only available with "AVX512ER". I'm not sure which CPUs support that, but its not available on Sapphire Rapids.