题目: Framework for Automatic Extraction of Parallel Benchmarks from HPC Applications
Parallel application benchmarks are indispensable for evaluating/optimizing HPC software and hardware. However, it is very challenging and costly to obtain high-fidelity benchmarks reflecting the scale and complexity of state-of-the-art parallel applications. Hand-extracted synthetic benchmarks are time- and labor-intensive to create. Real applications themselves, while offering most accurate performance evaluation, are expensive to compile, port, reconfigure, and often plainly inaccessible due to security or ownership concerns.
In this talk, I will present our group's recent work on workload characterization, tracing, and automatic benchmark generation. In particular, we introduce APPrime, a novel tool for trace-based automatic parallel benchmark generation. Taking as input standard communication-I/O traces of an application’s execution, it couples accurate automatic phase identification with statistical regeneration of event parameters to create compact, portable, and to some degree reconfigurable parallel application benchmarks. Experiments with four NAS Parallel Benchmarks (NPB) and three real scientific simulation codes confirm the fidelity of APPrime benchmarks. They retain the original applications’ performance characteristics, in particular the relative performance across platforms. Also, the result benchmarks, already released online, are much more compact and easy-to-port compared to the original applications.
Xiaosong Ma is currently a Senior Scientist at Qatar Computing Research Institute. Previously, she was Associate Professor in the Department of Computer Science at North Carolina State University, as well as a Joint Faculty Member at Oak Ridge National Laboratory. Her research interests are in the areas of storage systems, parallel I/O, high-performance parallel applications, cloud computing, and workload characterization. She received the DOE Early Career Principal Investigator Award in 2005, the NSF CAREER Award in 2006, an IBM Faculty Award in 2009, and a NetApp Faculty Fellowship, an HPDC 20-Year Best Paper Award, as well as a University of Illinois Department of Computer Science Alumni Distinguished Educator Award in 2012. Xiaosong received her Ph.D. in computer science from the University of Illinois at Urbana-Champaign in 2003, and her B.S. in computer science from Peking University, China in 1997.