BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20111116T213000Z
DTEND:20111116T220000Z
LOCATION:TCC 303
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: Hashing is a fundamental technique in computer science to allow O(1) insert and lookups of items in an associative array. Here we present several thread coordination and hashing strategies and compare their performance on large shared memory symmetric multiprocessor machines.  We show how our approach can be used as a key kernel for fundamental paradigms such as dynamic programming and MapReduce. We further show that a set of approaches yields close to linear speedup for both uniform random and more difficult power law distributions. This scalable performance is in spite of the fact that our set of=0Aapproaches is not completely lock-free. Our experimental results utilize and compare an SGI Altix UV with 4 Xeon processors (32 cores) and a Cray XMT with 128 processors.=0AWe show that the Altix UV far exceeds performance of the Cray XMT for power law distributions. However, the Cray XMT exhibits greater scalability.
SUMMARY:Scalable Hashing for Shared Memory Supercomputers
PRIORITY:3
END:VEVENT
END:VCALENDAR