CUDArray: CUDA-based NumPy

Anders Boesen Lindbo Larsen

Research output: Book/ReportReportResearch

532 Downloads (Pure)

Abstract

This technical report introduces CUDArray – a CUDA-accelerated subset of the NumPy library. The goal of CUDArray is to combine the ease of development from NumPy with the computational power of Nvidia GPUs in a lightweight and extensible framework. Since the motivation behind CUDArray is to facilitate neural network programming, CUDArray extends NumPy with a neural network submodule. This module has both a CPU and a GPU back-end to allow for experiments without requiring a GPU.
Original languageEnglish
Place of PublicationKgs. Lyngby
PublisherTechnical University of Denmark
Number of pages5
Publication statusPublished - 2014
SeriesDTU Compute-Technical Report-2014
Number21
ISSN1601-2321

Fingerprint

Dive into the research topics of 'CUDArray: CUDA-based NumPy'. Together they form a unique fingerprint.

Cite this