PAGANI: A Parallel Adaptive GPU Algorithm for Numerical Integration

Authors

Ioannis Sakiotis, Old Dominion UniversityFollow
Kamesh Arumugam
Marc Paterno
Desh Ranjan, Old Dominion UniversityFollow
Balša Terzić, Old Dominion UniversityFollow
Mohammad Zubair, Old Dominion UniversityFollow

Document Type

Conference Paper

Publication Date

2021

DOI

10.1145/3458817.3476198

Publication Title

SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis

Pages

83 (1-13)

Conference Name

SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, November 14-19, 2021, St. Louis, Missouri

Abstract

We present a new adaptive parallel algorithm for the challenging problem of multi-dimensional numerical integration on massively parallel architectures. Adaptive algorithms have demonstrated the best performance, but efficient many-core utilization is difficult to achieve because the adaptive work-load can vary greatly across the integration space and is impossible to predict a priori. Existing parallel algorithms utilize sequential computations on independent processors, which results in bottlenecks due to the need for data redistribution and processor synchronization. Our algorithm employs a high-throughput approach in which all existing sub-regions are processed and sub-divided in parallel. Repeated sub-region classification and filtering improves upon a brute-force approach and allows the algorithm to make efficient use of computation and memory resources. A CUDA implementation shows orders of magnitude speedup over the fastest open-source CPU method and extends the achievable accuracy for difficult integrands. Our algorithm typically outperforms other existing deterministic parallel methods.

Comments

© 2021 Association for Computing Machinery.

Original Publication Citation

Sakiotis, I., Arumugam, K., Paterno, M., Ranjan, D., Terzić, B., & Zubair, M. (2021). PAGANI: A parallel adaptive GPU algorithm for numerical integration. In SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (83). Association for Computing Machinery. https://doi.org/10.1145/3458817.3476198

Repository Citation

Sakiotis, I., Arumugam, K., Paterno, M., Ranjan, D., Terzić, B., & Zubair, M. (2021). PAGANI: A parallel adaptive GPU algorithm for numerical integration. In SC '21: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis (83). Association for Computing Machinery. https://doi.org/10.1145/3458817.3476198

ORCID

0000-0002-1988-0314 (Sakiotis), 0000-0002-9646-815D5 (Terzić), 0000-0002-5449-1779 (Zubair)