BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T055412Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211114T120000
DTEND;TZID=America/Chicago:20211114T123000
UID:submissions.supercomputing.org_SC21_sess429_ws_p3hpc107@linklings.com
SUMMARY:Analyzing Reduction Abstractions Capabilities
DESCRIPTION:Workshop\n\nAnalyzing Reduction Abstractions Capabilities\n\nD
 eakin, McIntosh-Smith, Pennycook, Sewall\n\nReductions are a common patter
 n in parallel programming, and every parallel programming language or fram
 ework has its own reduction abstraction with its own idiosyncrasies.  Thes
 e abstractions differ not only in their syntax, but also in their semantic
 s and their ability to express certain types of reduction.  Such differenc
 es may prevent specific combinations of abstraction and hardware platform 
 from reaching high levels of performance, with consequences for portabilit
 y and programmer productivity.\n\nIn this paper, we present a set of repre
 sentative reduction benchmarks to explore the capabilities of five contemp
 orary programming languages and frameworks - OpenMP, Kokkos, RAJA, SYCL, a
 nd the oneAPI DPC++ Library (oneDPL) - across a variety of hardware platfo
 rms, including CPUs and GPUs from multiple vendors.  We discuss the advant
 ages and disadvantages of each reduction abstraction, and conclude with re
 commendations to improve their design and implementation.\n\nTag: Online O
 nly, Heterogeneous Systems, Parallel Programming Languages and Models, Per
 formance, Productivity Tools, Software Engineering\n\nRegistration Categor
 y: Workshop Reg Pass
END:VEVENT
END:VCALENDAR