SC12 Home > SC12 Schedule > SC12 Presentation - Statistical Power and Energy Modeling of Multi-GPU kernels

SCHEDULE: NOV 10-16, 2012

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.

Statistical Power and Energy Modeling of Multi-GPU kernels

SESSION: Research Poster Reception

EVENT TYPE: Posters and Electronic Posters

TIME: 5:15PM - 7:00PM

SESSION CHAIR: Torsten Hoefler

AUTHOR(S):Sayan Ghosh, Sunita Chandrasekaran, Barbara Chapman

ROOM:East Entrance

ABSTRACT:
Current high performance computing systems consume a lot of energy. Although there have been substantial increase in computation performance, the same is not reflected in case of energy efficiency. To have an exascale computer by end of this decade, tremendous improvements in energy efficiency is mandatory. It is not possible to have sophisticated instruments to measure energy or power at such a large scale, but estimation could be useful. In this work, we have developed a statistical model using limited performance counters providing an estimation of power/energy components. The data collected range from different types of application kernel such asFFT, DGEMM, Stencils and Pseudo-Random-Number-Generators; widely used in various disciplines of high performance computing. A power analyzer has been used to analyze/extract the electrical power usage information of the multi-GPU node under inspection. An API was also written to remotely interface with the analyzer and get the instantaneous power readings.

Chair/Author Details:

Torsten Hoefler (Chair) - ETH Zurich

Sayan Ghosh - University of Houston

Sunita Chandrasekaran - University of Houston

Barbara Chapman - University of Houston

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

Statistical Power and Energy Modeling of Multi-GPU kernels

SESSION: Research Poster Reception

EVENT TYPE:

TIME: 5:15PM - 7:00PM

SESSION CHAIR: Torsten Hoefler

AUTHOR(S):Sayan Ghosh, Sunita Chandrasekaran, Barbara Chapman

ROOM:East Entrance

ABSTRACT:
Current high performance computing systems consume a lot of energy. Although there have been substantial increase in computation performance, the same is not reflected in case of energy efficiency. To have an exascale computer by end of this decade, tremendous improvements in energy efficiency is mandatory. It is not possible to have sophisticated instruments to measure energy or power at such a large scale, but estimation could be useful. In this work, we have developed a statistical model using limited performance counters providing an estimation of power/energy components. The data collected range from different types of application kernel such asFFT, DGEMM, Stencils and Pseudo-Random-Number-Generators; widely used in various disciplines of high performance computing. A power analyzer has been used to analyze/extract the electrical power usage information of the multi-GPU node under inspection. An API was also written to remotely interface with the analyzer and get the instantaneous power readings.

Chair/Author Details:

Torsten Hoefler (Chair) - ETH Zurich

Sayan Ghosh - University of Houston

Sunita Chandrasekaran - University of Houston

Barbara Chapman - University of Houston

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