Feature-based SpMV Performance Analysis on Contemporary Devices

Mpakos, P., Galanopoulos, D., Anastasiadis, P., Papadopoulou, N. , Koziris, N. and Goumas, G. (2023) Feature-based SpMV Performance Analysis on Contemporary Devices. In: 2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS), St. Petersburg, FL, USA, 15-19 May 2023, ISBN 9798350337662 (doi: 10.1109/ipdps54959.2023.00072)

Abstract

The SpMV kernel is characterized by high performance variation per input matrix and computing platform. While GPUs were considered State-of-the-Art for SpMV, with the emergence of advanced multicore CPUs and low-power FPGA accelerators, we need to revisit its performance and energy efficiency. This paper provides a high-level SpMV performance analysis based on structural features of matrices related to common bottlenecks of memory-bandwidth intensity, low ILP, load imbalance and memory latency overheads. Towards this, we create a wide artificial matrix dataset that spans these features and study the performance of different storage formats in nine modern HPC platforms; five CPUs, three GPUs and an FPGA. After validating our proposed methodology using real-world matrices, we analyze our extensive experimental results and draw key insights on the competitiveness of different target architectures for SpMV and the impact of each feature/bottleneck on its performance.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Papadopoulou, Dr Nikela
• Authors: Mpakos, P., Galanopoulos, D., Anastasiadis, P., Papadopoulou, N., Koziris, N., and Goumas, G.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: 2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
• ISSN: 1530-2075
• ISBN: 9798350337662