Performance Analysis of GPU-Accelerated Filter-Based Source Finding for HI Spectral Line Image Data

TL;DR

This paper evaluates GPU acceleration for source finding in spectral-line radio astronomy data, demonstrating significant speedups in processing time through optimized memory management and parallel algorithms.

Contribution

It introduces GPU-based acceleration techniques for source finding algorithms and quantifies performance improvements over CPU-only implementations.

Findings

GPU acceleration achieved a 3.2x speedup in specific algorithms

Overall program speedup of 2.0x with GPU use

Memory management techniques are crucial for performance gains

Abstract

Searching for sources of electromagnetic emission in spectral-line radio astronomy interferometric data is a computationally intensive process. Parallel programming techniques and High Performance Computing hardware may be used to improve the computational performance of a source finding program. However, it is desirable to further reduce the processing time of source finding in order to decrease the computational resources required for the task. GPU acceleration is a method that may achieve significant increases in performance for some source finding algorithms, particularly for filtering image data. This work considers the application of GPU acceleration to the task of source finding and the techniques used to achieve the best performance, such as memory management. We also examine the changes in performance, where the algorithms that were GPU accelerated achieved a speedup of around 3.2 times the 12 core per node CPU-only performance, while the program as a whole experienced a speedup of 2.0 times.