CUDA

CUDA programming in Julia.

https://github.com/juliagpu/cuda.jl

Science Score: 77.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 1 DOI reference(s) in README
  • Academic publication links
    Links to: ieee.org, zenodo.org
  • Committers with academic emails
    18 of 218 committers (8.3%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (15.4%) to scientific vocabulary

Keywords

cuda gpu hacktoberfest julia

Keywords from Contributors

julialang numerical programming-language flux automatic-differentiation the-human-brain sciml gradient control-flow julia-compiler
Last synced: 6 months ago · JSON representation ·

Repository

CUDA programming in Julia.

Basic Info
Statistics
  • Stars: 1,309
  • Watchers: 19
  • Forks: 248
  • Open Issues: 324
  • Releases: 110
Topics
cuda gpu hacktoberfest julia
Created over 6 years ago · Last pushed 6 months ago
Metadata Files
Readme Changelog Funding License Citation

README.md

CUDA.jl

CUDA programming in Julia

The CUDA.jl package is the main programming interface for working with NVIDIA CUDA GPUs using Julia. It features a user-friendly array abstraction, a compiler for writing CUDA kernels in Julia, and wrappers for various CUDA libraries.

Quick start

Before all, make sure you have a recent NVIDIA driver. On Windows, also make sure you have the Visual C++ redistributable installed. You do not need to install the CUDA Toolkit.

CUDA.jl can be installed with the Julia package manager. From the Julia REPL, type ] to enter the Pkg REPL mode and run:

pkg> add CUDA

Or, equivalently, via the Pkg API:

julia julia> import Pkg; Pkg.add("CUDA")

For an overview of the CUDA toolchain in use, you can run the following command after importing the package:

```julia julia> using CUDA

julia> CUDA.versioninfo() ```

This may take a while, as it will precompile the package and download a suitable version of the CUDA toolkit. If your GPU is not fully supported, the above command (or any other command that initializes the toolkit) will issue a warning.

For quick testing, you can also use the juliagpu/cuda.jl container image from the GitHub Container Registry, which provides Julia, a precompiled version of CUDA.jl, and a matching CUDA toolkit:

sh docker run -it --rm --gpus=all ghcr.io/juliagpu/cuda.jl:latest # other tags available too

For more usage instructions and other information, please refer to the documentation.

Requirements

The latest development version of CUDA.jl requires Julia 1.10 or higher. If you are using an older version of Julia, you need to use a previous version of CUDA.jl. This will happen automatically when you install the package using Julia's package manager.

Note that CUDA.jl may not work with a custom build of Julia; it is recommended that you install Julia using the official binaries or juliaup.

The latest version of CUDA.jl also has certain requirements that cannot be enforced by the package manager:

  • Host platform: only 64-bit Linux and Windows are supported;
  • Device hardware: only NVIDIA GPUs with compute capability 3.5 (Kepler) or higher are supported;
  • NVIDIA driver: a driver for CUDA 11.0 or newer is required;
  • CUDA toolkit (in case you need to use your own): only CUDA toolkit 11.4 or newer are supported.

If you cannot meet these requirements, you may need to install an older version of CUDA.jl:

  • CUDA.jl v5.8 is the last version with support for CUDA 11, and consequently Kepler GPUs (removed in v5.9)
  • CUDA.jl v5.3 is the last version with support for PowerPC (removed in v5.4)
  • CUDA.jl v4.4 is the last version with support for CUDA 11.0-11.3 (deprecated in v5.0)
  • CUDA.jl v4.0 is the last version to work with CUDA 10.2 (removed in v4.1)
  • CUDA.jl v3.8 is the last version to work with CUDA 10.1 (removed in v3.9)
  • CUDA.jl v1.3 is the last version to work with CUDA 9-10.0 (removed in v2.0)

Supporting and Citing

Much of the software in this ecosystem was developed as part of academic research. If you would like to help support it, please star the repository as such metrics may help us secure funding in the future. If you use our software as part of your research, teaching, or other activities, we would be grateful if you could cite our work. The CITATION.bib file in the root of this repository lists the relevant papers.

Project Status

The package is tested against, and being developed for, Julia 1.10 and above. Main development and testing happens on x86 Linux, but the package is expected to work on Windows and ARM and as well.

Questions and Contributions

Usage questions can be posted on the Julia Discourse forum under the GPU domain and/or in the #gpu channel of the Julia Slack.

Contributions are very welcome, as are feature requests and suggestions. Please open an issue if you encounter any problems.

Owner

  • Name: JuliaGPU
  • Login: JuliaGPU
  • Kind: organization

GPU Computing in Julia

Citation (CITATION.bib)

% primary paper, detailing the GPU compiler and relevant aspects
@article{besard2018juliagpu,
  author        = {Besard, Tim and Foket, Christophe and De Sutter, Bjorn},
  title         = {Effective Extensible Programming: Unleashing {Julia} on {GPUs}},
  journal       = {IEEE Transactions on Parallel and Distributed Systems},
  year          = {2018},
  doi           = {10.1109/TPDS.2018.2872064},
  ISSN          = {1045-9219},
  archivePrefix = {arXiv},
  eprint        = {1712.03112},
  primaryClass  = {cs.PL},
}

% specific paper on array programming for heterogeneous systems
@article{besard2019prototyping,
  title         = {Rapid software prototyping for heterogeneous and distributed platforms},
  author        = {Besard, Tim and Churavy, Valentin and Edelman, Alan and De Sutter, Bjorn},
  journal       = {Advances in Engineering Software},
  volume        = {132},
  pages         = {29--46},
  year          = {2019},
  publisher     = {Elsevier}
}

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 6,640
  • Total Committers: 218
  • Avg Commits per committer: 30.459
  • Development Distribution Score (DDS): 0.216
Past Year
  • Commits: 295
  • Committers: 37
  • Avg Commits per committer: 7.973
  • Development Distribution Score (DDS): 0.532
Top Committers
Name Email Commits
Tim Besard t****d@g****m 5,207
Mike J Innes m****s@g****m 180
Katharine Hyatt k****t@f****g 163
github-actions[bot] 4****] 162
Valentin Churavy v****y@g****m 108
Alexis Montoison 3****n 89
Andreas Noack a****n@g****m 34
Tim Besard t****d@e****e 30
Pieter Verstraete p****r@p****e 25
SimonDanisch s****h@g****m 21
William Moses gh@w****m 19
Dahua Lin l****a@g****m 18
Rogerluo r****8@g****m 17
chengchingwen a****5@h****m 17
Mus m****m@o****m 15
Yasser Deceukelier y****r@u****e 15
Harmen Stoppels h****s@g****m 14
Jutho Haegeman j****n@u****e 14
Qin Yu q****5@o****m 12
James Douglas 6****z 11
Zentrik Z****k 11
Jarrett Revels j****s@g****m 10
Yueh-Hua Tu a****2@g****m 9
Lucas C Wilcox l****s@s****m 9
femtocleaner[bot] f****] 9
Andrei Zhabinski f****d@g****m 9
David Sanders d****s@g****m 9
xaellison x****n@g****m 9
marius m****a@g****m 8
Daniel Wennberg d****g@g****m 8
and 188 more...

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 472
  • Total pull requests: 938
  • Average time to close issues: 11 months
  • Average time to close pull requests: 15 days
  • Total issue authors: 250
  • Total pull request authors: 94
  • Average comments per issue: 3.23
  • Average comments per pull request: 2.11
  • Merged pull requests: 699
  • Bot issues: 0
  • Bot pull requests: 61
Past Year
  • Issues: 131
  • Pull requests: 410
  • Average time to close issues: 8 days
  • Average time to close pull requests: 3 days
  • Issue authors: 88
  • Pull request authors: 38
  • Average comments per issue: 1.61
  • Average comments per pull request: 2.17
  • Merged pull requests: 304
  • Bot issues: 0
  • Bot pull requests: 14
Top Authors
Issue Authors
  • maleadt (105)
  • lpawela (8)
  • simonbyrne (7)
  • huiyuxie (6)
  • ChrisRackauckas (6)
  • kmp5VT (6)
  • albertomercurio (5)
  • vpuri3 (5)
  • vchuravy (5)
  • RainerHeintzmann (4)
  • CarloLucibello (4)
  • avik-pal (4)
  • amontoison (4)
  • kshyatt (4)
  • wsmoses (3)
Pull Request Authors
  • maleadt (310)
  • kshyatt (157)
  • amontoison (76)
  • github-actions[bot] (55)
  • wsmoses (45)
  • vchuravy (39)
  • christiangnrd (19)
  • Zentrik (12)
  • bjarthur (8)
  • lpawela (8)
  • dkarrasch (7)
  • nikopj (7)
  • xaellison (6)
  • dependabot[bot] (6)
  • albertomercurio (6)
Top Labels
Issue Labels
bug (270) enhancement (100) good first issue (44) cuda array (39) needs information (31) cuda libraries (30) upstream (25) cuda kernels (20) performance (20) help wanted (15) installation (13) speculative (8) regression (6) tests (4) documentation (4) extensions (2) hard (2) needs tests (2) needs decision (1) important (1) ci (1) bugfix (1) enzyme (1)
Pull Request Labels
cuda libraries (173) enhancement (141) tests (110) cuda array (77) bugfix (58) documentation (30) cuda kernels (24) performance (21) needs changes (21) extensions (13) dependencies (11) speculative (11) ci (10) needs tests (9) installation (8) upstream (5) help wanted (2) bug (1) good first issue (1) github_actions (1)

Packages

  • Total packages: 7
  • Total downloads:
    • julia 3,961 total
  • Total dependent packages: 267
    (may contain duplicates)
  • Total dependent repositories: 0
    (may contain duplicates)
  • Total versions: 380
juliahub.com: CUDA

CUDA programming in Julia.

  • Versions: 110
  • Dependent Packages: 241
  • Dependent Repositories: 0
  • Downloads: 3,399 Total
Rankings
Stargazers count: 0.3%
Forks count: 0.3%
Dependent packages count: 0.4%
Average: 2.7%
Dependent repos count: 9.9%
Last synced: 6 months ago
proxy.golang.org: github.com/juliagpu/cuda.jl
  • Versions: 100
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 6.5%
Average: 6.7%
Dependent repos count: 7.0%
Last synced: about 1 year ago
proxy.golang.org: github.com/JuliaGPU/CUDA.jl
  • Versions: 110
  • Dependent Packages: 0
  • Dependent Repositories: 0
Rankings
Dependent packages count: 6.5%
Average: 6.7%
Dependent repos count: 7.0%
Last synced: 6 months ago
juliahub.com: cuTENSOR

CUDA programming in Julia.

  • Versions: 15
  • Dependent Packages: 4
  • Dependent Repositories: 0
  • Downloads: 32 Total
Rankings
Stargazers count: 0.3%
Forks count: 0.3%
Average: 6.8%
Dependent repos count: 9.9%
Dependent packages count: 16.6%
Last synced: 6 months ago
juliahub.com: cuDNN

CUDA programming in Julia.

  • Versions: 17
  • Dependent Packages: 22
  • Dependent Repositories: 0
  • Downloads: 521 Total
Rankings
Stargazers count: 0.3%
Forks count: 0.3%
Average: 6.8%
Dependent repos count: 9.9%
Dependent packages count: 16.6%
Last synced: 6 months ago
juliahub.com: cuStateVec

CUDA programming in Julia.

  • Versions: 14
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 7 Total
Rankings
Stargazers count: 0.3%
Forks count: 0.3%
Dependent repos count: 9.9%
Average: 12.4%
Dependent packages count: 38.9%
Last synced: 6 months ago
juliahub.com: cuTensorNet

CUDA programming in Julia.

  • Versions: 14
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 2 Total
Rankings
Stargazers count: 0.3%
Forks count: 0.3%
Dependent repos count: 9.9%
Average: 12.4%
Dependent packages count: 38.9%
Last synced: 6 months ago

Dependencies

.github/workflows/CompatHelper.yml actions
  • actions/checkout v3 composite
  • julia-actions/setup-julia v1 composite
.github/workflows/TagBot.yml actions
  • JuliaRegistries/TagBot v1 composite
Dockerfile docker
  • julia 1.8-bullseye build