PyCUDA

From UFRC
Revision as of 23:20, 10 October 2024 by Omkar.bhabad (talk | contribs) (Created page with "Category:Software {|<!--CONFIGURATION: REQUIRED--> |{{#vardefine:app|PyCUDA}} |{{#vardefine:url|https://documen.tician.de/pycuda/}} <!--CONFIGURATION: OPTIONAL (|1}} means...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Description

PyCUDA website  


PyCUDA is a Python library that allows easy access to Nvidia's CUDA parallel computation API from Python. It provides the ability to write GPU code in Python and offers a variety of features for efficient GPU programming.


Environment Modules

Run module spider pycuda to find out what environment modules are available for this application.
Run module load pycuda/version to load the required module.

System Variables

  • HPC_PYCUDA_DIR - installation directory
  • HPC_PYCUDA_BIN - executable directory