Tile primitives for speedy kernels

Apple G13 GPU architecture docs and tools

A modern supercompiler for call-by-value functional languages

A minimal GPU design in Verilog to learn how GPUs work from the ground up

OCANNL: OCaml Compiles Algorithms for Neural Networks Learning

Apple AMX Instruction Set

Implementation of a Tensor Processing Unit for embedded systems and the IoT.

Tensor library for machine learning

Fearless hardware design

A polyhedral compiler for expressing fast and portable data parallel algorithms

High-performance automatic differentiation of LLVM and MLIR.

Hardcaml_zprize implements high performance, open source cryptographic solutions for large scale number theoretic transforms (NTT) and multi-scalar multiplications (MSM) in Hardcaml. Originally dev…

Fast CUDA matrix multiplication from scratch

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

You like pytorch? You like micrograd? You love tinygrad! ❤️

Triton is a virtual machine that comes with Algebraic Execution Tables (AET) and Arithmetic Intermediate Representations (AIR) for use in combination with a STARK proof system.

Nova: High-speed recursive zero-knowledge arguments from folding schemes

Middleware to compile Circom circuits to Nova prover

Library of basic circuits for circom

Spartan: High-speed zkSNARKs without trusted setup

A modern, lightweight, descriptor-based wallet library written in Rust!

The fastest in-browser verification of ECDSA signatures in ZK, using Spartan on the secq256k1 curve

A programming language and model of computation that matches the optimal λ-calculus reduction algorithm perfectly.

A massively parallel, optimal functional runtime in Rust

A maliciously secure two-party computation engine which is embeddable and accessible

A cross-platform, safe, pure-Rust graphics API.

Curve ecGFp5

A library for fast NTTs over the Goldilocks prime field

An arbitrary-precision arithmetic library for Rust.