Improving the performance of National Centre for Earth Observation (NCEO) code using GPUs

Martin, N, Clewley, D and Groom, SB 2023 Improving the performance of National Centre for Earth Observation (NCEO) code using GPUs. PML Publishing. (UNSPECIFIED)

[img]
Preview
Text
NCEO GPU_v5.pdf
Available under License Creative Commons Attribution.

Download (1MB) | Preview

Abstract/Summary

The aim of this study was to investigate the advantages of different tools designed for running code on Graphics Processing Units (GPUs) and specify the types of code best suited for GPU acceleration. • Three examples of code were obtained from NCEO scientists for three distinct applications and ported to GPUs on the Natural Environment Research Council (NERC) Earth Observation Data Acquisition and Analysis Service (NEODAAS) MAGEO computing cluster. • Comparisons were made between the time taken to run the code on the original Central Processing Unit (CPU) and the MAGEO CPU and GPU. • Accelerations of between x30 and x1800 were achieved: more details are provided below. • In terms of energy saving this relates to an estimated 93.9% to 99.8% reduction in electricity usage. • The study highlighted the value of expertise in GPUs and coding such as provided by NEODAAS

Item Type: Publication - Report (UNSPECIFIED)
Divisions: Plymouth Marine Laboratory > National Capability categories > NERC Earth Observation Data Acquisition & Analysis Service (NEODAAS)
Plymouth Marine Laboratory > National Capability categories > National Centre for Earth Observation
Plymouth Marine Laboratory > Science Areas > Earth Observation Science and Applications
Depositing User: Mrs Christina Devereux
Date made live: 21 Apr 2023 14:33
Last Modified: 21 Apr 2023 14:33
URI: https://plymsea.ac.uk/id/eprint/9911

Actions (login required)

View Item View Item