SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems
This work addresses the need for scalable evaluation tools to understand AI performance trends on HPC systems, particularly for scientific applications, but it is incremental as it builds on existing benchmarking approaches.
The authors tackled the problem of static AI benchmarks being insufficient for understanding performance trends of evolving AI applications on HPC systems, by proposing SAIH, a scalable evaluation methodology that augments problem sizes to analyze AI performance trends and diagnose bottlenecks, as demonstrated in a case study with a cosmological AI application on a GPU-equipped HPC system.
Novel artificial intelligence (AI) technology has expedited various scientific research, e.g., cosmology, physics and bioinformatics, inevitably becoming a significant category of workload on high performance computing (HPC) systems. Existing AI benchmarks tend to customize well-recognized AI applications, so as to evaluate the AI performance of HPC systems under predefined problem size, in terms of datasets and AI models. Due to lack of scalability on the problem size, static AI benchmarks might be under competent to help understand the performance trend of evolving AI applications on HPC systems, in particular, the scientific AI applications on large-scale systems. In this paper, we propose a scalable evaluation methodology (SAIH) for analyzing the AI performance trend of HPC systems with scaling the problem sizes of customized AI applications. To enable scalability, SAIH builds a set of novel mechanisms for augmenting problem sizes. As the data and model constantly scale, we can investigate the trend and range of AI performance on HPC systems, and further diagnose system bottlenecks. To verify our methodology, we augment a cosmological AI application to evaluate a real HPC system equipped with GPUs as a case study of SAIH.