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:20210402T160558Z
LOCATION:Track 2
DTSTART;TZID=America/New_York:20201113T175500
DTEND;TZID=America/New_York:20201113T182500
UID:submissions.supercomputing.org_SC20_sess221_ws_p3hpc109@linklings.com
SUMMARY:Evaluating the Performance and Portability of Contemporary SYCL Im
 plementations
DESCRIPTION:Workshop\n\nEvaluating the Performance and Portability of Cont
 emporary SYCL Implementations\n\nJohnston, Vetter, Milthorpe\n\nSYCL is a 
 single-source programming model for heterogeneous systems; it promises imp
 roved maintainability, productivity, and opportunity for compiler optimiza
 tion when compared to accelerator specific programming models.  Several im
 plementations of the SYCL standard have been developed over the past few y
 ears, including several backends using contemporary accelerator languages,
  like OpenCL, CUDA, and HIP.  These implementations vary widely in their s
 upport for specific features of the standard and in their performance.\n\n
 As SYCL grows in popularity, developers need to know how features are impl
 emented across popular implementations in order to make proper design choi
 ces.  In this paper, we evaluate the existing SYCL implementations for imp
 ortant SYCL features across a range of hardware in order to understand SYC
 L's performance and portability.  This work uses the newest SYCL benchmark
  suite (SYCL-Bench, 38 kernels) to evaluate these four existing implementa
 tions, comparing support of language features across backends and highligh
 ting feature completeness and performance.  For features, we focus on the 
 five major SYCL parallel constructs, using a motivating example of the mat
 rix multiplication benchmark.  Our results show that the basic data parall
 elism construct is the best choice for performance on current SYCL impleme
 ntations, and we identify opportunities for improvement in several of the 
 SYCL implementations.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR