BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20111117T013000Z
DTEND:20111117T030000Z
LOCATION:TCC LL2
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: Hardware is evolving to make efficient use of multi-core CPUs. For example, the K Computer features technologies to allow fast inter-core communication, sharing of the programmable L2 cache, and so on. The advent of multi-core computers has led to a re-evaluation of the programming model. The flat MPI approach is sub-optimal, and while PGAS models might offer a solution in the longer term, the best compromise at present is a hybrid model where thread parallelism is used within a node and MPI is used for communication between nodes.=0A=0AUse of numerical libraries that support this model presents a practical way to extract high performance from application codes. Open Petascale Libraries is a global collaboration that aims to promote the development of open-source thread-parallel and hybrid numerical libraries. This session introduces the project, provides an update on progress, and seeks to obtain feedback from the wider community on future directions.
SUMMARY:Open Petascale Libraries
PRIORITY:3
END:VEVENT
END:VCALENDAR