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:20260202T201258Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251121T080000
DTEND;TZID=America/Chicago:20251121T120000
UID:submissions.supercomputing.org_SC25_sess620_post275@linklings.com
SUMMARY:Sync-Free GPU Parallelization of Sparse Kernels from Sequential Py
 thon Code
DESCRIPTION:Malko-Bani Somo (McMaster University)\n\nSparse matrix kernels
  such as SpMV, SpTRSV, and Gauss-Seidel are critical in scientific computi
 ng, AI, and engineering, but they remain difficult to parallelize due to i
 rregular memory access patterns. Traditional compiler techniques assume af
 fine array accesses, which do not hold in sparse formats like CSR and CSC.
  As a result, existing compilers often leave sparse code under-optimized, 
 missing significant opportunities for parallelism.\n\nWe present a sync-fr
 ee, runtime-based transformation that automates loop parallelization for s
 parse kernels with loop-carried dependencies. Our approach traces memory r
 eads and writes to construct dependence sets, then generates Triton kernel
 s that use flag arrays to enforce correctness without global synchronizati
 on. This method generalizes across sparse kernels by leveraging properties
  such as associativity and affine simplifications, enabling efficient para
 llel execution.\n\nWe demonstrate our work with sparse triangular solves a
 nd related kernels, and will present performance results, methodology, and
  case studies in the poster session.\n\nTag: Research & ACM SRC Posters\n\
 nRegistration Category: Technical Program Reg Pass\n\nSession Chairs: Kent
 o Sato (RIKEN Center for Computational Science (R-CCS)); Anja Gerbes (Geor
 g-August-Universität Göttingen); and Chris Schlipalius (Pawsey Supercomput
 ing Research Centre; Commonwealth Scientific and Industrial Research Organ
 isation (CSIRO), Australia)\n\n
END:VEVENT
END:VCALENDAR