SC13 Home > SC13 Schedule > SC13 Presentation - Characterization and Modeling of PIDX Parallel I/O for Performance Optimization

SCHEDULE: NOV 16-22, 2013

When viewing the Technical Program schedule, on the far righthand side is a column labeled "PLANNER." Use this planner to build your own schedule. Once you select an event and want to add it to your personal schedule, just click on the calendar icon of your choice (outlook calendar, ical calendar or google calendar) and that event will be stored there. As you select events in this manner, you will have your own schedule to guide you through the week.

Characterization and Modeling of PIDX Parallel I/O for Performance Optimization



TIME: 3:30PM - 4:00PM

SESSION CHAIR: André Brinkmann

AUTHOR(S):Sidharth Kumar, Avishek Saha, Venkatram Vishwanath, Philip Carns, John A. Schmidt, Robert Latham, Giorgio Scorzelli, Hemanth Kolla, Robert Ross, Jackie Chen, Michael E. Papka, Ray Grout, Valerio Pascucci


Parallel I/O library performance can vary greatly in response to user-tunable parameter values such as aggregator count, file count, and aggregation strategy. Unfortunately, manual selection of these values is time consuming and dependent on characteristics of the target machine, the underlying file system, and the dataset itself. Some characteristics, such as the amount of memory per core, can also impose hard constraints on the range of viable parameter values. In this work we address these problems by using machine learning techniques to model the performance of the PIDX parallel I/O library and select appropriate tunable parameter values. We characterize both the network and I/O phases of PIDX on a Cray XE6 as well as an IBM Blue Gene/P system. We use the results of this study to develop a machine learning model for parameter space exploration and performance prediction.

Chair/Author Details:

André Brinkmann (Chair) - Johannes Gutenberg-University Mainz

Sidharth Kumar - University of Utah

Avishek Saha - University of Utah

Venkatram Vishwanath - Argonne National Laboratory

Philip Carns - Argonne National Laboratory

John A. Schmidt - University of Utah

Robert Latham - Argonne National Laboratory

Giorgio Scorzelli - University of Utah

Hemanth Kolla - Sandia National Laboratories

Robert Ross - Argonne National Laboratory

Jackie Chen - Sandia National Laboratories

Michael E. Papka - Argonne National Laboratory

Ray Grout - National Renewable Energy Laboratory

Valerio Pascucci - University of Utah

Add to iCal  Click here to download .ics calendar file

Add to Outlook  Click here to download .vcs calendar file

Add to Google Calendarss  Click here to add event to your Google Calendar

The full paper can be found in the ACM Digital Library