SC12 Home > SC12 Schedule > SC12 Presentation - Comparing GPU and Increment-Based Checkpoint Compression

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.

Comparing GPU and Increment-Based Checkpoint Compression

SESSION: Research Poster Reception

EVENT TYPE: Posters and Electronic Posters

TIME: 5:15PM - 7:00PM

SESSION CHAIR: Torsten Hoefler

AUTHOR(S):Dewan Ibtesham, Dorian Arnold, Kurt B. Ferreira, Ronald Brightwell

ROOM:East Entrance

ABSTRACT:
The increasing size and complexity of HPC systems have led to major concerns over fault frequencies and the mechanisms necessary to tolerate these faults. Previous studies have shown that state-of-the-field checkpoint/restart mechanisms will not scale sufficiently for future generation systems. Therefore, Checkpoint/restart overheads must be improved to maintain feasibility for future HPC systems. Previously, we showed the effectiveness of checkpoint data compression for reducing checkpoint/restart latencies and storage overheads. In this work we (1)compare CPU-based and GPU-based checkpoint compression, (2)compare to increment-based checkpoint optimization, (3) evaluate the combination of checkpoint compression with incremental checkpointing and (4) motivate future GPU-based compression work by exploring various hypothetical scenarios.

Chair/Author Details:

Torsten Hoefler (Chair) - ETH Zurich

Dewan Ibtesham - University of New Mexico

Dorian Arnold - University of New Mexico

Kurt B. Ferreira - Sandia National Laboratories

Ronald Brightwell - Sandia National Laboratories

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

Comparing GPU and Increment-Based Checkpoint Compression

SESSION: Research Poster Reception

EVENT TYPE:

TIME: 5:15PM - 7:00PM

SESSION CHAIR: Torsten Hoefler

AUTHOR(S):Dewan Ibtesham, Dorian Arnold, Kurt B. Ferreira, Ronald Brightwell

ROOM:East Entrance

ABSTRACT:
The increasing size and complexity of HPC systems have led to major concerns over fault frequencies and the mechanisms necessary to tolerate these faults. Previous studies have shown that state-of-the-field checkpoint/restart mechanisms will not scale sufficiently for future generation systems. Therefore, Checkpoint/restart overheads must be improved to maintain feasibility for future HPC systems. Previously, we showed the effectiveness of checkpoint data compression for reducing checkpoint/restart latencies and storage overheads. In this work we (1)compare CPU-based and GPU-based checkpoint compression, (2)compare to increment-based checkpoint optimization, (3) evaluate the combination of checkpoint compression with incremental checkpointing and (4) motivate future GPU-based compression work by exploring various hypothetical scenarios.

Chair/Author Details:

Torsten Hoefler (Chair) - ETH Zurich

Dewan Ibtesham - University of New Mexico

Dorian Arnold - University of New Mexico

Kurt B. Ferreira - Sandia National Laboratories

Ronald Brightwell - Sandia National Laboratories

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