CUDA.jl 5.4: Memory management mayhem  ↗

oneAPI.jl 1.5: Ponte Vecchio support and oneMKL improvements  ↗

CUDA.jl 5.2 and 5.3: Maintenance releases  ↗

CUDA.jl 5.1: Unified memory and cooperative groups  ↗

CUDA.jl 5.0: Integrated profiler and task synchronization changes  ↗

Profiling oneAPI.jl applications with VTune

Metal.jl 0.2: Metal Performance Shaders

oneAPI.jl 1.0: oneMKL, Intel Arc and Julia 1.9

CUDA.jl 4.0

Technical preview: Programming Apple M1 GPUs in Julia with Metal.jl

oneAPI.jl status update

CUDA.jl 3.5-3.8

CUDA.jl 3.4

CUDA.jl 3.3

CUDA.jl 3.0

CUDA.jl 2.4 and 2.5

Introducing: oneAPI.jl

CUDA.jl 2.1

CUDA.jl 2.0

Paper: Flexible Performant GEMM Kernels on GPUs

CUDA.jl 1.3 - Multi-device programming

CUDA.jl 1.1

CUDAnative.jl 3.0 and CuArrays.jl 2.0

Julia's Dramatic Rise in HPC and Elsewhere  ↗

Accelerating Tensor Computations in Julia with the GPU  ↗

New website for JuliaGPU

Julia Computing Brings Support for NVIDIA GPU Computing on Arm Powered Servers  ↗

DifferentialEquations.jl v6.9.0 released with automatic Multi-GPU support  ↗

An Introduction to GPU Programming in Julia  ↗

Next Generation Climate Models leverage Julia and GPUs  ↗

New Climate Model to be Built from the Ground Up  ↗

Solving Systems of Stochastic PDEs and using GPUs in Julia  ↗

High-Performance GPU Computing in the Julia Programming Language  ↗