Implementations of SIMD instruction sets for systems which don't natively support them.

Math library using HLSL syntax with multiplatform SIMD support

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

SIMD-accelerated UTF-8 validation for Rust.

Boost SIMD

Node.js implementation of HighwayHash, Google's fast and strong hash function

A general purpose machine code manipulation library for x86-32 (IA-32) and x86-64 (AMD64) architectures (Assembler, Disassembler, Library).

High performance blur in pure Rust using SIMD

Software implementation of ARM and x86 SIMD intrinsics

Bilinear image filtering implemented with SSE4, AVX2 and AVX512.

Minify JSON files fast! Supports Comments. Uses D, C, and AVX2 and SSE4_1 SIMD.

Fast UTF-8 utility methods

A fast, specs-compliant WHATWG URL parser in pure Nim

IAA03_fast_math is a single-header math kernel(Atan2 only for now) designed to eliminate the "Trigonometry Tax" in high-throughput systems (Physics Engines, Audio DSP, and ML Pre-processing). Branchless ,ILP and SIMD (AVX2/SSE4.1), it achieves up to a ~186x per-element throughput speedup over std::atan2 while being IEEE 754 compliant

A small math library in SSE4 and upper written in C++

⚡ Accelerate your Go applications with a high-performance SIMD library for vectorized operations on various data types.

Tiny optimized math framework game oriented

Accelerated YaMaha Operators - Research Project

Implementation of GPU Gems 38 using OpenGL Compute Shaders