Performance-portable, length-agnostic SIMD with runtime dispatch

Roaring bitmaps in C (and C++), with SIMD (AVX2, AVX-512 and NEON) optimizations: used by Apache Doris, ClickHouse, and StarRocks

Unicode routines (UTF8, UTF16, UTF32) and Base64: billions of characters per second using SSE2, AVX2, NEON, AVX-512, RISC-V Vector Extension. Part of Node.js and Bun.

MIPP is a portable wrapper for SIMD instructions written in C++11. It supports NEON, SSE, AVX, AVX-512 and SVE (length specific).

Intel:registered: Homomorphic Encryption Acceleration Library accelerates modular arithmetic operations used in homomorphic encryption

A curated list of awesome SIMD frameworks, libraries and software

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

(REOS) Radar and ElectroOptical Simulation Framework written in Fortran.

Fast C++ function "is_utf8": checks if the input is valid UTF-8. Made of a single source file. Optimized for ARM NEON, x64 SSE, AVX2 and AVX-512.

AVX-512 documentation beyond what Intel provides

The fastest Run-Length-Encoding on the Planet (for x64)

AVX-Hole C++ SIMD Library

Masm compatible assembler

Algorithms for matrix matrix multiplication, dgemm, AVX-256, AVX-512

Benchmark to show which is the fastest memcpy.

Utility that was used to generate initial Go AVX-512 encoder test suite.

Running GPGPU-like kernels on CPU with auto-vectorization for SSE/AVX/AVX512 SIMD Architectures

Document Level Sentiment Analysis is an End-to-End deep learning workflow using Hugging Face transformers API to do a "classification" task at document level, to analyze the sentiment of input document containing English sentences or paragraphs.

high-speed math functions based on AVX-512 intrinsics

A generic and efficient SIMD implementation of MSB Radix Sort with separate key and payload datastreams that supports arbitrary key and payload data types written in C++ accompanied by a bachelor's thesis.