Early experiences with KTAU on the IBM BG/L

Abstract

The influences of OS and system-specific effects on application performance are increasingly important in high performance computing. In this regard, OS kernel measurement is necessary to understand the interrelationship of system and application behavior. This can be viewed from two perspectives: kernel-wide and process-centric. An integrated methodology and framework to observe both views in HPC systems using OS kernel measurement has remained elusive. We demonstrate a new tool called KTAU (Kernel TAU) that aims to provide parallel kernel performance measurement from both perspectives. KTAU extends the TAU performance system with kernel-level monitoring, while leveraging TAU's measurement and analysis capabilities. As part of the ZeptoOS scalable operating systems project, we report early experiences using KTAU in ZeptoOS on the IBM BG/L system. © Springer-Verlag Berlin Heidelberg 2006.