Performance-portable, length-agnostic SIMD with runtime dispatch
-
Updated
Jun 12, 2024 - C++
Performance-portable, length-agnostic SIMD with runtime dispatch
Parsing gigabytes of JSON per second : used by Facebook/Meta Velox, the Node.js runtime, ClickHouse, WatermelonDB, Apache Doris, Milvus, StarRocks
Expressive Vector Engine - SIMD in C++ Goes Brrrr
Fast inference engine for Transformer models
(REOS) Radar and Electro-Optical Simulation Framework written in C++.
a template based C++ short vector library with vectorized faithfully rounded elementary functions
SIMD Vector Classes for C++
RV: A Unified Region Vectorizer for LLVM
Mandelbrot visualization & AVX2 optimization.
C++ template library for high performance SIMD based sorting algorithms
This project Isn't a lot more than a simple experiment on C++ optimizations on a basic array. I'm publishing the code for anyone to check it out and try it out if they wish.
Matilda is a library to repeatedly multiply a constant matrix with a variable vector
Demo of a fast PNG encoder.
DR3 enables users to write vectorised code using generic lambdas and filters. Switch instruction set just by changing enclosing namespace
Add a description, image, and links to the avx2 topic page so that developers can more easily learn about it.
To associate your repository with the avx2 topic, visit your repo's landing page and select "manage topics."