Scalable Control and Monitoring of Supercomputer Applications Using an Integrated Tool Framework

Abstract

Recently, a new generation of significantly more powerful petascale systems has become available to the scientific computing community. The vast power of these systems, coupled with a corresponding increase in application code complexity, is now making the limitations of existing programming and performance tools ever more apparent. If developers are going to be able to effectively utilize these systems, then a new generation of exemplary tools will be required. The Parallel Tools Platform (PTP) Project was established in 2005 to create a best-practice integrated tool workbench designed to increase the productivity of parallel application development. PTP has increased in popularity over the years, and is now used by a growing community of developers in scientific and engineering fields, however, PTP also faces some challenges in adapting to the new petascale environments. In this paper we describe some of the recent changes to PTP core infrastructure that will enable it to work effectively with these and future generations of high performance computing systems.