Write GPU kernels using pure Julia

Fast `StatsBase.countmap` for small types on the GPU via CUDA.jl

Julia Bindings for the HSA Runtime

Concept for a fast event system, using JIT and GPU acceleration

Julia interface to CUBLAS

Julia wrapper for the NVIDIA cuDNN GPU deep learning library

Julia wrapper for CUDA runtime API

OpenCL Julia bindings

MXNet Julia Package - flexible and efficient deep learning in Julia

CUDA programming in Julia.