SC12 Home > SC12 Schedule > SC12 Presentation - Billion-Particle SIMD-Friendly Two-Point Correlation on Large-Scale HPC Cluster Systems

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.

Billion-Particle SIMD-Friendly Two-Point Correlation on Large-Scale HPC Cluster Systems

SESSION: ACM Gordon Bell Prize I

EVENT TYPE: ACM Gordon Bell Finalists

TIME: 1:30PM - 2:00PM

SESSION CHAIR: Michael Norman

AUTHOR(S):Jatin Chhugani, Changkyu Kim, Hemant Shukla, Jongsoo Park, Pradeep Dubey, John Shalf, Horst D. Simon

ROOM:155-E

ABSTRACT:
Correlation analysis is a widely used tool in a range of scientific fields, ranging from geology to genetics and astronomy. In astronomy, Two-point Correlation Function (TPCF) is commonly used to characterize the distribution of matter/energy in the Universe. Due to the large amount of computation with massive data, TPCF is a compelling benchmark for future exa-scale architectures. We propose a novel algorithm that significantly reduces the computation and communication requirement of TPCF. We exploit the locality of histogram values and thus achieve near-linear scaling with respect to number of cores and SIMD-width. On a 1600-node Zin supercomputer at Lawrence Livermore National Laboratory (1.06 Petaflops), we achieve 90% parallel efficiency and 96% SIMD efficiency, and perform computation on a 1.7 billion particle dataset in 5.3 hours (3537X faster than previous approaches). Consequently, we now have line-of-sight to achieving the processing power for correlation computation to process billion+ particles telescopic data.

Chair/Author Details:

Michael Norman (Chair) - University of California, San Diego

Jatin Chhugani - Intel Corporation

Changkyu Kim - Intel Corporation

Hemant Shukla - Lawrence Berkeley National Laboratory

Jongsoo Park - Intel Corporation

Pradeep Dubey - Intel Corporation

John Shalf - Lawrence Berkeley National Laboratory

Horst D. Simon - Lawrence Berkeley National Laboratory

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

Billion-Particle SIMD-Friendly Two-Point Correlation on Large-Scale HPC Cluster Systems

SESSION: ACM Gordon Bell Prize I

EVENT TYPE:

TIME: 1:30PM - 2:00PM

SESSION CHAIR: Michael Norman

AUTHOR(S):Jatin Chhugani, Changkyu Kim, Hemant Shukla, Jongsoo Park, Pradeep Dubey, John Shalf, Horst D. Simon

ROOM:155-E

ABSTRACT:
Correlation analysis is a widely used tool in a range of scientific fields, ranging from geology to genetics and astronomy. In astronomy, Two-point Correlation Function (TPCF) is commonly used to characterize the distribution of matter/energy in the Universe. Due to the large amount of computation with massive data, TPCF is a compelling benchmark for future exa-scale architectures. We propose a novel algorithm that significantly reduces the computation and communication requirement of TPCF. We exploit the locality of histogram values and thus achieve near-linear scaling with respect to number of cores and SIMD-width. On a 1600-node Zin supercomputer at Lawrence Livermore National Laboratory (1.06 Petaflops), we achieve 90% parallel efficiency and 96% SIMD efficiency, and perform computation on a 1.7 billion particle dataset in 5.3 hours (3537X faster than previous approaches). Consequently, we now have line-of-sight to achieving the processing power for correlation computation to process billion+ particles telescopic data.

Chair/Author Details:

Michael Norman (Chair) - University of California, San Diego

Jatin Chhugani - Intel Corporation

Changkyu Kim - Intel Corporation

Hemant Shukla - Lawrence Berkeley National Laboratory

Jongsoo Park - Intel Corporation

Pradeep Dubey - Intel Corporation

John Shalf - Lawrence Berkeley National Laboratory

Horst D. Simon - Lawrence Berkeley National Laboratory

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