Submitted by claxton on
Title | Design, Optimization, and Benchmarking of Dense Linear Algebra Algorithms on AMD GPUs |
Publication Type | Tech Report |
Year of Publication | 2020 |
Authors | Brown, C., A. Abdelfattah, S. Tomov, and J. Dongarra |
Technical Report Series Title | Innovative Computing Laboratory Technical Report |
Number | ICL-UT-20-12 |
Date Published | 2020-08 |
Institution | University of Tennessee |
Keywords | AMD GPUs, GPU computing, HIP Runtime, HPC, numerical linear algebra, Portability |
Abstract | Dense linear algebra (DLA) has historically been in the vanguard of software that must be adapted first to hardware changes. This is because DLA is both critical to the accuracy and performance of so many different types of applications, and because they have proved to be outstanding vehicles for finding and implementing solutions to the problems that novel architectures pose. Therefore, in this paper we investigate the portability of the MAGMA DLA library to the latest AMD GPUs. We use auto tools to convert the CUDA code in MAGMA to the HeterogeneousComputing Interface for Portability (HIP) language. MAGMA provides LAPACK for GPUs and benchmarks for fundamental DLA routines ranging from BLAS to dense factorizations, linear systems and eigen-problem solvers. We port these routines to HIP and quantify currently achievable performance through the MAGMA benchmarks for the main workload algorithms on MI25 and MI50 AMD GPUs. Comparison with performance roofline models and theoretical expectations are used to identify current limitations and directions for future improvements. |