BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20141118T231500Z
DTEND:20141119T010000Z
LOCATION:New Orleans Theater Lobby
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: Modern HPC applications need to be run on many different platforms and performance portability has become a critical issue: parallel code needs to be executed correctly and performant despite variation in the architecture, operating system and software libraries. The numerical solution of partial differential equations using the finite element method is one of the key applications of high performance computing.  This poster presents a performance portable implementation of the  the finite element assembly in the Albany code. This implementation is based on the Kokkos programming model from Trilinos, which uses a library approach to provide performance portability across diverse devices with different memory models.=0AEvaluation experiments show good performance results for a single implementation across three multicore/many-core architectures: NVIDIA GPUs, Multicore CPUs, Intel Xeon Phi.
SUMMARY:Kokkos Implementation of Albany: a Performance-Portable Finite Element Application
PRIORITY:3
END:VEVENT
END:VCALENDAR