A Prototype Implementation of NNEF Execution Framework with CUDA Acceleration

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recently, we have many research works on the neural networks and their related issues. For exchangeability of neural network frameworks, the Neural Network Exchange Format (NNEF) specification is now widely used. Due to very large size of these neural networks, their accelerations are actively explored, and can be achieved through parallel processing techniques. In this paper, we present a prototype implementation of NNEF execution system with parallel-processing accelerations based on CUDA (compute unified device architecture). We will tune the prototype acceleration to achieve more remark-able speed ups.

Original languageEnglish
Title of host publicationInformation Science and Applications - Proceedings of ICISA 2020
EditorsHyuncheol Kim, Kuinam J. Kim, Suhyun Park
PublisherSpringer Science and Business Media Deutschland GmbH
Pages129-132
Number of pages4
ISBN (Print)9789813363847
DOIs
StatePublished - 2021
EventiCatse International Conference on Information Science and Applications, ICISA 2020 - Busan, Korea, Republic of
Duration: 16 Dec 202018 Dec 2020

Publication series

NameLecture Notes in Electrical Engineering
Volume739 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceiCatse International Conference on Information Science and Applications, ICISA 2020
Country/TerritoryKorea, Republic of
CityBusan
Period16/12/2018/12/20

Keywords

  • Acceleration
  • CUDA
  • Neural network
  • NNEF
  • Parallel processing

Fingerprint

Dive into the research topics of 'A Prototype Implementation of NNEF Execution Framework with CUDA Acceleration'. Together they form a unique fingerprint.

Cite this