# OrchesPy: Device-independent library for NumPy program on heterogeneous system
OrchesPy is a library for NumPy programs to execute part of the program
on accelerators by decorating functions.
## Prerequisites
Using OrchesPy requires the following packages.
- Python 3: tested with Python 3.8.
- NumPy 1.23.2: since CuPy and NLCPy require numpy>=1.17 and NLCPy requires
numpy<=1.23.2.
- To run programs on VE, install NLCPy = 2.2.0 and its dependencies
such as veoffload.
- To run programs on CUDA GPU, install CuPy = 11.0.0 and its dependencies such
as CUDA toolkit working with your GPU.
- Install Inter-Device Copy Library = 0.1.0b1 for GPU-VE transfer.
To build OrchesPy, see also the section "Install from source".
## Installation
You can install OrchesPy from PyPI or from source.
### Install from PyPI
Execute the following command.
```
$ pip install orchespy
```
### Install from source
To build OrchesPy, install CUDA toolkit and veoffload (VEO) for CuPy and NLCPy.
Download the source tree from GitHub.
```
$ git clone https://github.com/SX-Aurora/orchespy.git
```
Execute the following command.
```
$ cd orchespy
$ pip install .
```
PIP will install dependencies automatically, and build and install OrchesPy on
your environment.
## Documentation
- [OrchesPy User's Guide](https://sxauroratsubasa.sakura.ne.jp/documents/orchespy/en/index.html)
## License
The BSD-3-Clause license (see `LICENSE` file).
Raw data
{
"_id": null,
"home_page": "https://github.com/SX-Aurora/orchespy/",
"name": "orchespy",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "NEC",
"author_email": "dev-nlcpy@sxarr.jp.nec.com",
"download_url": "",
"platform": null,
"description": "# OrchesPy: Device-independent library for NumPy program on heterogeneous system\nOrchesPy is a library for NumPy programs to execute part of the program\non accelerators by decorating functions.\n\n## Prerequisites\nUsing OrchesPy requires the following packages.\n\n- Python 3: tested with Python 3.8.\n- NumPy 1.23.2: since CuPy and NLCPy require numpy>=1.17 and NLCPy requires\n numpy<=1.23.2.\n- To run programs on VE, install NLCPy = 2.2.0 and its dependencies\n such as veoffload.\n- To run programs on CUDA GPU, install CuPy = 11.0.0 and its dependencies such\n as CUDA toolkit working with your GPU.\n- Install Inter-Device Copy Library = 0.1.0b1 for GPU-VE transfer.\n\nTo build OrchesPy, see also the section \"Install from source\".\n\n## Installation\nYou can install OrchesPy from PyPI or from source.\n\n### Install from PyPI\nExecute the following command.\n\n```\n$ pip install orchespy\n```\n\n### Install from source\nTo build OrchesPy, install CUDA toolkit and veoffload (VEO) for CuPy and NLCPy.\nDownload the source tree from GitHub.\n\n```\n$ git clone https://github.com/SX-Aurora/orchespy.git\n```\nExecute the following command.\n\n```\n$ cd orchespy\n$ pip install .\n```\n\nPIP will install dependencies automatically, and build and install OrchesPy on\nyour environment.\n\n## Documentation\n- [OrchesPy User's Guide](https://sxauroratsubasa.sakura.ne.jp/documents/orchespy/en/index.html)\n\n## License\n\nThe BSD-3-Clause license (see `LICENSE` file).\n\n",
"bugtrack_url": null,
"license": "BSD 3-Clause",
"summary": "Device-independent library for NumPy programs",
"version": "0.2.0b2",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "798c9afc253b9098d30e5a66bded9151218553917eee5c3ef3d3a8c781211e39",
"md5": "772e28e95cf816e547d4abcfe7390500",
"sha256": "1758b3d8adb44c89d56973aed473495bcd55b69049c5870175cfaac3a73853f9"
},
"downloads": -1,
"filename": "orchespy-0.2.0b2-cp38-cp38-manylinux1_x86_64.whl",
"has_sig": false,
"md5_digest": "772e28e95cf816e547d4abcfe7390500",
"packagetype": "bdist_wheel",
"python_version": "cp38",
"requires_python": null,
"size": 59499,
"upload_time": "2023-03-30T05:36:29",
"upload_time_iso_8601": "2023-03-30T05:36:29.062421Z",
"url": "https://files.pythonhosted.org/packages/79/8c/9afc253b9098d30e5a66bded9151218553917eee5c3ef3d3a8c781211e39/orchespy-0.2.0b2-cp38-cp38-manylinux1_x86_64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-03-30 05:36:29",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "SX-Aurora",
"github_project": "orchespy",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "orchespy"
}
JSON
