Title :
PSINS: An Open Source Event Tracer and Execution Simulator
Author :
Tikir, Mustafa M. ; Laurenzano, Michael A. ; Carrington, Laura ; Snavely, Allan
Author_Institution :
Performance Modeling & Characterization Lab., San Diego Supercomput. Center, La Jolla, CA, USA
Abstract :
As the size of today´s supercomputers grow exponentially in numbers of processors, the applications that run on these systems scale to larger processor counts. The majority of these applications commonly use Message Passing Interface (MPI); a trace of these MPI communication events is an important input to the tools that visualize, simulate for performance modeling, or enable tuning of parallel applications. We introduce an efficient, accurate and flexible trace-driven performance modeling and prediction tool, PMaC´s Open Source Interconnect and Network Simulator (PSINS), for MPI applications. A principal feature of PSINS is its usability for applications that scale up to large processor counts. PSINS generates compact and tractable event traces for fast and efficient simulations while producing accurate performance predictions. PSINS was incorporated into PMaC´s automated performance prediction framework and used to model three applications from the High Performance Computing Modernization Program´s (HPCMP) Technology Insertion 2009 (TI-09) application suite.
Keywords :
application program interfaces; message passing; parallel machines; performance evaluation; public domain software; MPI communication events; PMaC automated performance prediction framework; PSINS; execution simulator; message passing interface; network simulator; open source event tracer; open source interconnect; prediction tool; processor counts; supercomputers; trace-driven performance modeling; Accuracy; Computational modeling; High performance computing; Libraries; Predictive models; Program processors; Runtime;
Conference_Titel :
DoD High Performance Computing Modernization Program Users Group Conference (HPCMP-UGC), 2009
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-5768-7
DOI :
10.1109/HPCMP-UGC.2009.73