A Comparative Performance Analysis of Convolution W/O OpenCL on a Standalone System

Title

A Comparative Performance Analysis of Convolution W/O OpenCL on a Standalone System

Creator

Keswani B.; Venugopalan J.

Description

Initial approach of this paper is to provide a deep understanding of OpenCL architecture. Secondly, it proposes an implementation of a matrix and image convolution implemented in C (Serial Programming) and OpenCL (Parallel Programming), to describe detailed OpenCL programming flow and to provide a comparative performance analysis. The implementation is being carried on AMD A10 APU and various algebraic scenarios are created, to observe the performance improvement achieved on a single system when using Parallel Programming. In the related works authors have worked on AMDAPPSDK samples such as N-body & SimpleGL to understand the concept of vector data types in OpenCL and OpenCL-GL interoperability, have also implemented 3-D particle bouncing concept in OpenCL & 3D-Mesh rendering using OpenCL. Lastly, authors have also illuminated about their future work, where they intend to implement a novel algorithm for mesh segmentation using OpenCL, for which they have tried to form a strong knowledge base through this work. 2015 IEEE.

Source

Proceedings - 2015 2nd IEEE International Conference on Advances in Computing and Communication Engineering, ICACCE 2015, pp. 378-383.

Date

2015-01-01

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

Convolution; float4; GPGPU; Mesh Segmentation; Vertex Buffer Objects

Coverage

Keswani B., Computer Science Engineering Department, Christ University, Bangalore, India; Venugopalan J., Christ University, Bangalore, India

Rights

Restricted Access

Relation

ISBN: 978-147991734-1

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICACCE.2015.108

https://www.scopus.com/inward/record.uri?eid=2-s2.0-84959058047&doi=10.1109%2fICACCE.2015.108&partnerID=40&md5=ab28c9a112e7b72cf1df7f20033e22f3