Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/hshindo/libcuda.jl

CUDA GPU array for Julia
https://github.com/hshindo/libcuda.jl

cuda gpu julia

Last synced: about 1 month ago
JSON representation

CUDA GPU array for Julia

Host: GitHub
URL: https://github.com/hshindo/libcuda.jl
Owner: hshindo
License: mit
Created: 2017-12-27T20:03:00.000Z (about 7 years ago)
Default Branch: master
Last Pushed: 2018-04-20T21:47:59.000Z (almost 7 years ago)
Last Synced: 2024-11-11T08:50:39.986Z (3 months ago)
Topics: cuda, gpu, julia
Language: Julia
Homepage:
Size: 1.39 MB
Stars: 0
Watchers: 3
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        # LibCUDA.jl

[![Build Status](https://travis-ci.org/hshindo/LibCUDA.jl.svg?branch=master)](https://travis-ci.org/hshindo/LibCUDA.jl)

`LibCUDA.jl` provides a basic GPU array for [Julia](https://julialang.org/), which has been developed for deep learning library: [Merlin.jl](https://github.com/hshindo/Merlin.jl).  

For more general implementation, take a look at [JuliaGPU](https://github.com/JuliaGPU).

`LibCUDA.jl` internally loads the following libraries.

* CUBLAS

* CURAND

* NVML

* NVRTC

* CUDNN

* NCCL

## Installation

First, install `CUDA`, `CUDNN`, and `NCCL`.  

Then,

```

julia> Pkg.add("LibCUDA")

```

## Usage

```julia

T = Float32

d_x = curand(T, 10, 5)

println(Array(d_x))

fill!(d_x, 2)

println(Array(d_x))

```