Computing Prestack Kirchhoff time migration algorithm on OpenCL and GPGPU

In seismic data processing, Prestack Kirchhoff time migration is a forming method, and widely used. In this paper, we introduced how to port the original CUDA program to OpenCL, and how to implement and optimize Prestack Kirchhoff Time Migration algorithm on OpenCL and General Purpose GPU, and how t...

Full description

Saved in:
Bibliographic Details
Published in2014 International Conference on Mechatronics and Control (ICMC) pp. 1416 - 1419
Main Authors Zhanlin Yu, Xiaohua Shi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2014
Subjects
Computer architecture
General Purpose GPU
Graphics processing units
Instruction sets
Kernel
Kirchhoff Migration
OpenCL
Parallel processing
Performance evaluation
Programming
Online AccessGet full text

Cover

More Information
Summary:In seismic data processing, Prestack Kirchhoff time migration is a forming method, and widely used. In this paper, we introduced how to port the original CUDA program to OpenCL, and how to implement and optimize Prestack Kirchhoff Time Migration algorithm on OpenCL and General Purpose GPU, and how to optimize the OpenCL program to get the competitive performance comparing with the original CUDA version. Our OpenCL version of Kirchhoff Migration algorithm on NVidia 8800GT almost as fast as its CUDA version, its 8.9 times faster than original CPU version on AMD245 2.9HGZ.
DOI:10.1109/ICMC.2014.7231787