PAGANI: A Parallel Adaptive GPU Algorithm for Numerical Integration

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

ORCID

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

Share

COinS