A Guide for Achieving High Performance with Very Small Matrices on GPUs: A Case Study of Batched LU and Cholesky Factorizations

TitleA Guide for Achieving High Performance with Very Small Matrices on GPUs: A Case Study of Batched LU and Cholesky Factorizations
Publication TypeJournal Article
Year of Publication2018
AuthorsHaidar, A., A. Abdelfattah, M. Zounon, S. Tomov, and J. Dongarra
JournalIEEE Transactions on Parallel and Distributed Systems
Volume29
Issue5
Pagination973–984
Date Published2018-05
Abstract

We present a high-performance GPU kernel with a substantial speedup over vendor libraries for very small matrix computations. In addition, we discuss most of the challenges that hinder the design of efficient GPU kernels for small matrix algorithms. We propose relevant algorithm analysis to harness the full power of a GPU, and strategies for predicting the performance, before introducing a proper implementation. We develop a theoretical analysis and a methodology for high-performance linear solvers for very small matrices. As test cases, we take the Cholesky and LU factorizations and show how the proposed methodology enables us to achieve a performance close to the theoretical upper bound of the hardware. This work investigates and proposes novel algorithms for designing highly optimized GPU kernels for solving batches of hundreds of thousands of small-size Cholesky and LU factorizations. Our focus on efficient batched Cholesky and batched LU kernels is motivated by the increasing need for these kernels in scientific simulations (e.g., astrophysics applications). Techniques for optimal memory traffic, register blocking, and tunable concurrency are incorporated in our proposed design. The proposed GPU kernels achieve performance speedups versus CUBLAS of up to 6x for the factorizations, using double precision arithmetic on an NVIDIA Pascal P100 GPU.

DOI10.1109/TPDS.2017.2783929
Project Tags: 
External Publication Flag: