Towards GPU Acceleration of Phonon Computation with ShengBTE

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

Abstract

ShengBTE is one of the software packages that are commonly used in the field of phonon computation (e.g., to determine the lattice thermal conductivity). ShengBTE simulates the phonon diffusion by solving the Boltzmann transport equations, which take long execution time to derive the simulation results due to the high computation complexity. This paper mainly focuses on the performance optimization of ShengBTE on GPU. We identify the performance bottlenecks of ShengBTE and propose corresponding optimizations such as loop-carried dependency elimination, hotspot function acceleration on GPU and performance tuning on thread block. The experiment results show that the proposed optimizations significantly improve the performance of ShengBTE, which achieves an average speedup of 9.06x and 13.74x on discrete temperature simulation and continuous temperature simulation respectively without losing accuracy.

Original languageEnglish
Title of host publicationProceedings of International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2020
PublisherAssociation for Computing Machinery
Pages32-42
Number of pages11
ISBN (Electronic)9781450372367
DOIs
StatePublished - 15 Jan 2020
Event2020 International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2020 - Fukuoka, Japan
Duration: 15 Jan 202017 Jan 2020

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2020 International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2020
Country/TerritoryJapan
CityFukuoka
Period15/01/2017/01/20

Fingerprint

Dive into the research topics of 'Towards GPU Acceleration of Phonon Computation with ShengBTE'. Together they form a unique fingerprint.

Cite this