Auto‐Tuning Mixed‐Precision Computation by Specifying Multiple Regions
Concurrency and Computation: Practice and Experience · 25.01.2025 · 37 (2)
DOI: 10.1002/cpe.8326 ↗Kurz gefasst
Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 07.11.2024. Verfasst von Xuanzhengbo Ren und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Mixed‐precision computation is a promising method for substantially improving high‐performance computing applications. However, using mixed‐precision data is a double‐edged sword. While it can improve computational performance, the reduction in precision introduces more uncertainties and errors. As a result, precision tuning is necessary to determine the optimal mixed‐precision configurations. Much effort is therefore spent on selecting appropriate variables while balancing execution time and numerical accuracy. Auto‐tuning (AT) is one of the technologies that can assist in alleviating this intensive task. In recent years, ppOpen‐AT, an AT language, introduced a directive for mixed‐precision tuning called “Blocks.” In this study, we investigated an AT strategy for the “Blocks” directive for multi‐region tuning of a program. The non‐hydrostatic icosahedral atmospheric model (NICAM), a global cloud‐resolving model, was used as a benchmark program to evaluate the effectiveness of the AT strategy. Experimental results indicated that when a single region of the program performed well in mixed‐precision computation, combining these regions resulted in better performance. When tested on the supercomputer “Flow” Type I (Fujitsu PRIMEHPC FX1000) and Type II (Fujitsu PRIMEHPC CX1000) subsystems, the mixed‐precision NICAM benchmark program tuned by the AT strategy achieved a speedup of nearly 1.31× on the Type I subsystem compared to the original double‐precision program, and a 1.12× speedup on the Type II subsystem.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Ren, X., Kawai, M., Hoshino, T., Katagiri, T., & Nagai, T. (2025). Auto‐Tuning Mixed‐Precision Computation by Specifying Multiple Regions. Concurrency and Computation: Practice and Experience, 37(2). https://doi.org/10.1002/cpe.8326
Vancouver
Ren X, Kawai M, Hoshino T, Katagiri T, Nagai T. Auto‐Tuning Mixed‐Precision Computation by Specifying Multiple Regions. Concurrency and Computation: Practice and Experience. 2025;37(2). doi:10.1002/cpe.8326
BibTeX
@article{Ren2025,
author = {Ren, Xuanzhengbo and Kawai, Masatoshi and Hoshino, Tetsuya and Katagiri, Takahiro and Nagai, Toru},
title = {Auto‐Tuning Mixed‐Precision Computation by Specifying Multiple Regions},
journal = {Concurrency and Computation: Practice and Experience},
year = {2025},
volume = {37},
number = {2},
doi = {10.1002/cpe.8326}
}
EUVIMED