BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:2.0
BEGIN:VEVENT
DTSTART:20141118T231500Z
DTEND:20141119T010000Z
LOCATION:New Orleans Theater Lobby
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: We present a suite of directives, named pipelined accelerator (PACC),=0A and its implementation for accelerating large-scale computation on a=0A graphics processing unit (GPU). PACC extends OpenACC to achieve=0A division of large data that cannot be entirely stored in device=0A memory. Given a program with PACC directives, our PACC translator=0A rewrites the program into an OpenACC program such that data is=0A divided into multiple chunks for accelerated=0A execution. Furthermore, the generated program processes chunks in a=0A pipeline so that data transfer between the CPU and GPU can overlap=0A with computation on the GPU. Some preliminary results are also=0A presented to show the impact of PACC in terms of the program=0A execution time and the maximum data size that can be processed=0A successfully.
SUMMARY:PACC: An Extension of OpenACC for Pipelined Processing of Large Data on a GPU
PRIORITY:3
END:VEVENT
END:VCALENDAR