BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121113T203000Z
DTEND:20121113T210000Z
LOCATION:155-E
DESCRIPTION;ENCODING=QUOTED-PRINTABLE: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.=0A =0AWe 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.=0A =0AOn 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.
SUMMARY:Billion-Particle SIMD-Friendly Two-Point Correlation on Large-Scale HPC Cluster Systems
PRIORITY:3
END:VEVENT
END:VCALENDAR
BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121113T203000Z
DTEND:20121113T210000Z
LOCATION:155-E
DESCRIPTION;ENCODING=QUOTED-PRINTABLE: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.=0A =0AWe 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.=0A =0AOn 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.
SUMMARY:Billion-Particle SIMD-Friendly Two-Point Correlation on Large-Scale HPC Cluster Systems
PRIORITY:3
END:VEVENT
END:VCALENDAR