BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160554Z
LOCATION:Track 4
DTSTART;TZID=America/New_York:20201111T120000
DTEND;TZID=America/New_York:20201111T121000
UID:submissions.supercomputing.org_SC20_sess201_ws_ia112@linklings.com
SUMMARY:Supporting Irregularity in Throughput-Oriented Computing by SIMT-S
 IMD Integration
DESCRIPTION:Workshop\n\nSupporting Irregularity in Throughput-Oriented Com
 puting by SIMT-SIMD Integration\n\nThuerck\n\nThe last two decades have se
 en continued exponential performance increases in HPC systems, well after 
 the predicted end of Moore's Law for CPUs, largely due to the widespread a
 doption of throughput-oriented compute accelerators such as GPUs. When fac
 ed with irregular yet throughput-oriented applications, their simple, grid
 -based computing model turns into a serious limitation. Instead of repeate
 dly tackling the issues of irregularity on the application layer, we argue
  that a generalization of the CUDA model to irregular grids can be support
 ed through minor modifications to already established throughput-oriented 
 architectures.\n\nTo that end, we propose a unifying approach that combine
 s techniques from both SIMD and MIMD approaches, but adheres to the SIMT p
 rinciples -- based on an unlikely ally: a wide-SIMD vector architecture. W
 e extend CUDA's familiar programming model and implement SIMT-inspired str
 ategies for dealing with data and control flow irregularities. Our approac
 h requires only minimal hardware changes and an additional compiler phase.
   Using a model-based software simulation, we demonstrate that the propose
 d system can be a first step towards native support for irregularity on th
 roughput-oriented processors while greatly simplifying the development of 
 irregular applications.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR