kernel-tuner

Kernel Tuner

https://github.com/kerneltuner/kernel_tuner

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 2 DOI reference(s) in README
✓
Academic publication links
Links to: arxiv.org, sciencedirect.com, zenodo.org
✓
Committers with academic emails
3 of 31 committers (9.7%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (15.2%) to scientific vocabulary

Keywords

auto-tuning autotuning c cplusplus cuda cuda-kernels gpu gpu-computing kernel-tuner machine-learning opencl opencl-kernels optimization python software-development testing

Keywords from Contributors

copier copier-python copier-template python-template research-software fair web-app interaction bibliographics profiling

Last synced: 4 months ago · JSON representation ·

Repository

Kernel Tuner

Basic Info

Host: GitHub
Owner: KernelTuner
License: apache-2.0
Language: Python
Default Branch: master
Homepage: https://kerneltuner.github.io/kernel_tuner/
Size: 41.3 MB

Statistics

Stars: 357
Watchers: 9
Forks: 58
Open Issues: 19
Releases: 34

Topics

auto-tuning autotuning c cplusplus cuda cuda-kernels gpu gpu-computing kernel-tuner machine-learning opencl opencl-kernels optimization python software-development testing

Created over 9 years ago · Last pushed 4 months ago

Metadata Files

Readme Changelog Contributing License Citation Zenodo

README.md

Create optimized GPU applications in any mainstream GPU programming language (CUDA, HIP, OpenCL, OpenACC, OpenMP).

What Kernel Tuner does:

Works as an external tool to benchmark and optimize GPU kernels in isolation
Can be used directly on existing kernel code without extensive changes
Can be used with applications in any host programming language
Blazing fast search space construction
More than 20 optimization algorithms to speedup tuning
Energy measurements and optimizations (power capping, clock frequency tuning)
... and much more! For example, caching, output verification, tuning host and device code, user defined metrics, see the full documentation.

Installation

First, make sure you have your CUDA, OpenCL, or HIP compiler installed
Then type: pip install kernel_tuner[cuda], pip install kernel_tuner[opencl], or pip install kernel_tuner[hip]
or why not all of them: pip install kernel_tuner[cuda,opencl,hip]

More information on installation, also for other languages, in the installation guide.

Example

```python import numpy as np from kerneltuner import tunekernel

kernelstring = """ _global__ void vectoradd(float *c, float *a, float *b, int n) { int i = blockIdx.x * blocksize_x + threadIdx.x; if (i<n) { c[i] = a[i] + b[i]; } } """

n = np.int32(10000000)

a = np.random.randn(n).astype(np.float32) b = np.random.randn(n).astype(np.float32) c = np.zeros_like(a)

args = [c, a, b, n]

tuneparams = {"blocksize_x": [32, 64, 128, 256, 512]}

tunekernel("vectoradd", kernelstring, n, args, tuneparams) ```

More examples here.

Resources

Full documentation
Guides:
Features & Use cases:
Kernel Tuner Tutorial slides [PDF], hands-on:
- Vector add example [.ipynb]
- Tuning thread block dimensions [.ipynb]
- Search space restrictions & output verification [.ipynb]
- Visualization & search space optimization [.ipynb]
Energy Efficient GPU Computing tutorial slides [PDF], hands-on:
- Kernel Tuner for GPU energy measurements [.ipynb]
- Code optimizations for energy [.ipynb]
- Mixed precision and accuracy tuning [.ipynb]
- Optimzing for time vs for energy [.ipynb]

Kernel Tuner ecosystem

C++ magic to integrate auto-tuned kernels into C++ applications

C++ data types for mixed-precision CUDA kernel programming

Monitor, analyze, and visualize auto-tuning runs

Communication & Contribution

GitHub Issues: Bug reports, install issues, feature requests, work in progress
GitHub Discussion group: General questions, Q&A, thoughts

Contributions are welcome! For feature requests, bug reports, or usage problems, please feel free to create an issue. For more extensive contributions, check the contribution guide.

Citation

If you use Kernel Tuner in research or research software, please cite the most relevant among the publications on Kernel Tuner. To refer to the project as a whole, please cite:

latex @article{kerneltuner, author = {Ben van Werkhoven}, title = {Kernel Tuner: A search-optimizing GPU code auto-tuner}, journal = {Future Generation Computer Systems}, year = {2019}, volume = {90}, pages = {347-358}, url = {https://www.sciencedirect.com/science/article/pii/S0167739X18313359}, doi = {https://doi.org/10.1016/j.future.2018.08.004} }

Owner

Name: Kernel Tuner
Login: KernelTuner
Kind: organization
Location: Netherlands

Website: https://kerneltuner.github.io/
Repositories: 6
Profile: https://github.com/KernelTuner

Kernel Tuner is a software ecosystem for the creation of highly-optimized GPU applications through auto-tuning.

Citation (CITATION.cff)

# YAML 1.2
---
cff-version: 1.2.0
authors:
  - affiliation: "Netherlands eScience Center"
    family-names: Werkhoven
    given-names: Ben
    name-particle: van
    orcid: "https://orcid.org/0000-0002-7508-3272"
    email: "b.vanwerkhoven@esciencecenter.nl"
date-released: 2019-12-20
doi: 10.5281/zenodo.1220113
keywords: 
  - "GPU Computing"
  - "Auto-Tuning"
  - "Performance Optimization"
  - "OpenCL"
  - "CUDA"
license: Apache-2.0
message: "If you use this software, please cite the following paper."
references:
  - type: article
    authors:
      - affiliation: "Netherlands eScience Center"
        family-names: Werkhoven
        given-names: Ben
        name-particle: van
        orcid: "https://orcid.org/0000-0002-7508-3272"
        email: "b.vanwerkhoven@esciencecenter.nl"
    title: "Kernel Tuner: A Search-Optimizing GPU Code Auto-Tuner"
    journal: "Future Generation Computer Systems"
    year: 2019
repository-code: "https://github.com/benvanwerkhoven/kernel_tuner"
title: Kernel Tuner
version: "0.3.0"

GitHub Events

Total

Create event: 29
Release event: 5
Issues event: 20
Watch event: 63
Delete event: 8
Issue comment event: 163
Push event: 211
Pull request review comment event: 3
Pull request review event: 17
Pull request event: 57
Fork event: 11

Last Year

Create event: 29
Release event: 5
Issues event: 20
Watch event: 63
Delete event: 8
Issue comment event: 163
Push event: 211
Pull request review comment event: 3
Pull request review event: 17
Pull request event: 57
Fork event: 11

Committers

Last synced: 7 months ago

All Time

Total Commits: 1,883
Total Committers: 31
Avg Commits per committer: 60.742
Development Distribution Score (DDS): 0.449

Past Year

Commits: 118
Committers: 11
Avg Commits per committer: 10.727
Development Distribution Score (DDS): 0.432

Top Committers

Name	Email	Commits
Ben van Werkhoven	b**n@e**l	1,038
Alessio Sclocco	a**o@e**l	410
fjwillemsen	f**n@i**m	135
stijn	s**s@e**l	58
MiloLurati	l**o@g**m	39
Bram Veenboer	b**r@g**m	35
E. G. Patrick Bos	e**s@g**m	31
Willem Jan Palenstijn	W**n@c**l	29
Milo Lurati	m**0@f**l	28
Leon Oostrum	l**m@e**l	13
ipelupessy	i**y@e**l	9
Felipe Zapata	f**a@f**r	7
dependabot[bot]	4****]	7
felipeZ	t**l@g**m	6
schoonhovenrichard	r**n@h**m	5
Johan Hidding	j**g@g**m	5
Bouwe Andela	b**a@e**l	4
Hanno Spreeuw	h**w@e**l	3
Jisk Attema	j**a@e**l	3
Martijn	m**1@g**m	3
Ben van Werkhoven	b**0@f**l	2
Abel Soares Siqueira	a**a@g**m	2
Jeff(Yujie) Liu	y**e@g**m	2
Nicolas Renaud	n**d@t**l	2
Anant Gupta	a****d	1
Emmanuel Ferdman	e**n@g**m	1
Lars	l**k@g**m	1
Leon Oostrum	l**m@c**l	1
Ben van Werkhoven	e**n@w**l	1
Wiebe van Breukelen	b**n@a**l	1
and 1 more...

Committer Domains (Top 20 + Academic)

esciencecenter.nl: 8 fs0.das6.cs.vu.nl: 2 astron.nl: 1 wn-gp-01.novalocal: 1 cn7.esc.surfsara.nl: 1 tudelft.nl: 1 fs0.cm.cluster: 1 cwi.nl: 1

Issues and Pull Requests

Last synced: 4 months ago

All Time

Total issues: 65
Total pull requests: 214
Average time to close issues: 9 months
Average time to close pull requests: 27 days
Total issue authors: 13
Total pull request authors: 21
Average comments per issue: 1.66
Average comments per pull request: 1.87
Merged pull requests: 160
Bot issues: 0
Bot pull requests: 24

Past Year

Issues: 11
Pull requests: 72
Average time to close issues: about 14 hours
Average time to close pull requests: 21 days
Issue authors: 4
Pull request authors: 11
Average comments per issue: 0.64
Average comments per pull request: 1.19
Merged pull requests: 42
Bot issues: 0
Bot pull requests: 6

View more stats

Top Authors

Issue Authors

benvanwerkhoven (33)
isazi (8)
stijnh (8)
fjwillemsen (3)
loostrum (3)
bouweandela (2)
LiuLiujie (2)
sjsprecious (1)
neworderofjamie (1)
jinghere11 (1)
srflp (1)
vesuppi (1)
jiskattema (1)

Pull Request Authors

benvanwerkhoven (63)
fjwillemsen (25)
dependabot[bot] (24)
isazi (23)
stijnh (20)
csbnw (15)
MiloLurati (9)
loostrum (7)
emmanuel-ferdman (6)
kentr0w (3)
jiskattema (3)
tdejong00 (2)
wvbbreu (2)
cesarg1337 (2)
MartijnFr (2)

Top Labels

Issue Labels

bug (12) enhancement (10) help wanted (4) documentation (2) tests (2) idea (2) wontfix (1)

Pull Request Labels

dependencies (28) enhancement (17) python (6) bug (5)

Packages

Total packages: 2
Total downloads:
- pypi 185 last-month

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 1
(may contain duplicates)
Total versions: 35
Total maintainers: 3

proxy.golang.org: github.com/kerneltuner/kernel_tuner

Documentation: https://pkg.go.dev/github.com/kerneltuner/kernel_tuner#section-documentation
License: apache-2.0
Latest release: v0.0.1-beta
published over 9 years ago

Versions: 1
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 5.4%

Average: 5.5%

Dependent repos count: 5.7%

Last synced: 4 months ago

pypi.org: kernel-tuner

An easy to use CUDA/OpenCL kernel tuner in Python

Homepage: https://KernelTuner.github.io/kernel_tuner/
Documentation: https://KernelTuner.github.io/kernel_tuner/
License: Apache-2.0
Latest release: 1.3.0
published 4 months ago

Versions: 34
Dependent Packages: 0
Dependent Repositories: 1
Downloads: 185 Last month

Rankings

Stargazers count: 5.1%

Forks count: 6.4%

Dependent packages count: 10.1%

Average: 11.2%

Downloads: 12.9%

Dependent repos count: 21.6%

Maintainers (3)

benvanwerkhoven isazi fjwillemsen

Last synced: 4 months ago

Dependencies

.github/workflows/cffconvert.yml actions

actions/checkout v2 composite
citation-file-format/cffconvert-github-action 2.0.0 composite

.github/workflows/docs-on-release.yml actions

actions/checkout master composite
ad-m/github-push-action master composite
sphinx-notes/pages v2 composite

.github/workflows/docs.yml actions

actions/checkout master composite
ad-m/github-push-action master composite
sphinx-notes/pages v2 composite

.github/workflows/update-fair-software-badge.yml actions

EndBug/add-and-commit v9 composite
actions/checkout v2 composite
benvanwerkhoven/howfairis-github-action main composite

.github/workflows/publish-python-package.yml actions

Gr1N/setup-poetry v8 composite
actions/checkout v4 composite
actions/setup-python v4 composite
pypa/gh-action-pypi-publish release/v1 composite

.github/workflows/test-python-package.yml actions

Gr1N/setup-poetry v8 composite
actions/checkout v4 composite
fjwillemsen/setup-nox2 v3.0.0 composite

doc/requirements.txt pypi

alabaster ==0.7.13
appnope ==0.1.3
asttokens ==2.4.1
attrs ==23.1.0
babel ==2.13.1
backcall ==0.2.0
beautifulsoup4 ==4.12.2
bleach ==6.1.0
certifi ==2023.7.22
cffi ==1.16.0
charset-normalizer ==3.3.2
colorama ==0.4.6
decorator ==5.1.1
defusedxml ==0.7.1
docutils ==0.18.1
dom-toml ==0.6.1
domdf-python-tools ==3.7.0
exceptiongroup ==1.1.3
executing ==2.0.1
fastjsonschema ==2.18.1
idna ==3.4
imagesize ==1.4.1
importlib-metadata ==6.8.0
importlib-resources ==6.1.1
iniconfig ==2.0.0
ipython ==8.12.3
jedi ==0.19.1
jinja2 ==3.1.2
joblib ==1.3.2
jsonschema ==4.19.2
jsonschema-specifications ==2023.7.1
jupyter-client ==8.6.0
jupyter-core ==5.5.0
jupyterlab-pygments ==0.2.2
markupsafe ==2.1.3
matplotlib-inline ==0.1.6
mistune ==3.0.2
natsort ==8.4.0
nbclient ==0.9.0
nbconvert ==7.11.0
nbformat ==5.9.2
nbsphinx ==0.9.3
numpy ==1.24.4
packaging ==23.2
pandas ==2.0.3
pandocfilters ==1.5.0
parso ==0.8.3
pexpect ==4.8.0
pickleshare ==0.7.5
pkgutil-resolve-name ==1.3.10
platformdirs ==3.11.0
pluggy ==1.3.0
prompt-toolkit ==3.0.39
ptyprocess ==0.7.0
pure-eval ==0.2.2
pycparser ==2.21
pygments ==2.16.1
pytest ==7.4.3
python-constraint2 ==2.0.0b3
python-dateutil ==2.8.2
pytz ==2023.3.post1
pywin32 ==306
pyzmq ==25.1.1
referencing ==0.30.2
requests ==2.31.0
rpds-py ==0.12.0
scikit-learn ==1.3.2
scipy ==1.10.1
six ==1.16.0
snowballstemmer ==2.2.0
soupsieve ==2.5
sphinx ==7.1.2
sphinx-pyproject ==0.3.0
sphinx-rtd-theme ==1.3.0
sphinxcontrib-applehelp ==1.0.4
sphinxcontrib-devhelp ==1.0.2
sphinxcontrib-htmlhelp ==2.0.1
sphinxcontrib-jquery ==4.1
sphinxcontrib-jsmath ==1.0.1
sphinxcontrib-qthelp ==1.0.3
sphinxcontrib-serializinghtml ==1.1.5
stack-data ==0.6.3
threadpoolctl ==3.2.0
tinycss2 ==1.2.1
toml ==0.10.2
tomli ==2.0.1
tornado ==6.3.3
traitlets ==5.13.0
typing-extensions ==4.8.0
tzdata ==2023.3
urllib3 ==2.0.7
wcwidth ==0.2.9
webencodings ==0.5.1
xmltodict ==0.13.0
zipp ==3.17.0

poetry.lock pypi

168 dependencies

pyproject.toml pypi

jsonschema *
jupyter ^1.0.0
matplotlib ^3.5.0
numpy ^1.22.2
nvidia-ml-py ^12.535.108
pandas ^2.0.0
pycuda ^2022.1
pyhip-interface *
pynvml ^11.4.1
pyopencl *
python >=3.8,<3.12
python-constraint2 ^2.0.0b3
scikit-learn ^1.0.2
scipy ^1.10.1
xmltodict *