This release is a pre-release and may not be stable for production use.
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
License
The BSD-3-Clause license (see LICENSE file).
1 maintainer
Metadata
1 maintainer
Release files for orchespy 0.2.0b2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| orchespy-0.2.0b2-cp38-cp38-manylinux1_x86_64.whl | CPython 3.8 | CPython 3.8 | Linux glibc 2.5+ x86-64 | Details for orchespy-0.2.0b2-cp38-cp38-manylinux1_x86_64.whl |
Release files / orchespy-0.2.0b2-cp38-cp38-manylinux1_x86_64.whl
| Download URL | orchespy-0.2.0b2-cp38-cp38-manylinux1_x86_64.whl |
|---|---|
| Size | 59.5 kB |
| Tags | CPython 3.8 Linux glibc 2.5+ x86-64 |
|
SHA-256 checksum How to use checksums |
1758b3d8adb44c89d56973aed473495bcd55b69049c5870175cfaac3a73853f9
|
|
BLAKE2b-256 checksum How to use checksums |
798c9afc253b9098d30e5a66bded9151218553917eee5c3ef3d3a8c781211e39
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.8.16
|
Security for orchespy 0.2.0b2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
