artv3

mlpack

mlpack: a fast, header-only C++ machine learning library

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

compute-runtime

Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver

OpenCL-SDK

OpenCL SDK

Trixi.jl

Trixi.jl: Adaptive high-order numerical simulations of conservation laws in Julia

easy-just-in-time

LLVM Optimization to extract a function, embedded in its intermediate representation in the binary, and execute it using the LLVM Just-In-Time compiler.

RAJA

RAJA Performance Portability Layer (C++)

KernelAbstractions.jl

Heterogeneous programming in Julia

alpaka

Abstraction Library for Parallel Kernel Acceleration :llama:

riemann_book

An interactive book about the Riemann problem for hyperbolic PDEs, using Jupyter notebooks.

level-zero

oneAPI Level Zero Specification Headers and Loader

clSPARSE

a software library containing Sparse functions written in OpenCL

HIP-CPU

An implementation of HIP that works on CPUs, across OSes.

raptor

General, high performance algebraic multigrid solver

Element-based-Galerkin-Methods

This directory contains the Lecture files and Project codes in both Julia and Matlab for a course based on the Springer textbook "An Introduction to Element-based Galerkin Methods on Tensor-Product Bases" by F.X. Giraldo

portage

Tribol

Modular interface physics library featuring state-of-the-art contact physics methods.

ELEMENTS

The C++ ELEMENTS library contains a suite of sub-libraries to support mathematical functions (elements), data representations (MATAR), and novel mesh classes (geometry and SWAGE) to support a very broad range of element types, numerical methods, and mesh connectivity data structures useful for computational physics and engineering.

occa

JIT Compilation for Multiple Architectures: C++, OpenMP, CUDA, HIP, OpenCL, Metal

hiCL

A high level OpenCL abstraction layer for C/C++ and Fortran scientific computing.

fast-alg-ie-notes

Lecture notes for "Fast Algorithms and Integral Equations"

numCL

Finite volume and difference methods for conservation laws

hip-training

copper-multigrid-tutorial

2021-tutorials

occa-taf

Shaping the future of the OCCA portability framework together.

p4est_occa_tutorial

dense_qr

Householder dense QR - testing

dissectionqr

Nested Dissection based sparse QR Factorization using Rust

splitting_method_limits

Randomly sampling matrix splittings and finding distribution of preconditioner quality (EXPERIMENTAL)