BEGIN:VCALENDAR PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN VERSION:1.0 BEGIN:VEVENT DTSTART:20111115T233000Z DTEND:20111116T010000Z LOCATION:WSCC 2A/2B DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: Building on CUDA Programming Part I, this session focuses on performance considerations in CUDA programs. Topics include: organizing data into effective block arrangements (matrix multiplication); basic performance tuning; more in-depth GPU architecture features such as block-shared memory; hands-on examples of using fast memories to increase performance (tiled matrix multiplication and n-body); an overview of other performance factors to consider in optimization.=0A=0APrerequisite: "CUDA Programming Part I" session or equivalent. SUMMARY: PRIORITY:3 END:VEVENT END:VCALENDAR