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:20260202T201248Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251120T080000
DTEND;TZID=America/Chicago:20251120T170000
UID:submissions.supercomputing.org_SC25_sess533_post147@linklings.com
SUMMARY:Exploring Fine-Grained Parallelism in Data-Flow Runtime Systems on
  Many-Core Systems
DESCRIPTION:Wenyi Wang and Maxime Gonthier (University of Chicago), Haibin
  Lai (Southern University of Science and Technology), Poornima Nookala (In
 tel Corporation), Haochen Pan and Ian Foster (University of Chicago), Ioan
  Raicu (Illinois Institute of Technology), and Kyle Chard (University of C
 hicago)\n\nHigh synchronization overhead in frameworks like GNU OpenMP imp
 edes fine-grained task parallelism on many-core architectures. We introduc
 e three advances to GNU OpenMP: a lock-less concurrent queue (XQueue), a s
 calable distributed tree barrier, and two NUMA-aware, lock-less load-balan
 cing strategies.\n\nEvaluated with Barcelona OpenMP Task Suite (BOTS) benc
 hmarks, our XQueue and tree barrier improve performance by up to 1522.8× o
 ver the original GNU OpenMP. The load-balancing strategies provide an addi
 tional performance improvement of up to 4×. \n\nWe further apply these tec
 hniques to the TaskFlow runtime, demonstrating performance and scalability
  gains in selected applications while also analyzing the inherent limitati
 ons of the lock-less approach on x86 architectures.\n\nTag: Research & ACM
  SRC Posters\n\nRegistration Category: Technical Program Reg Pass\n\nSessi
 on Chairs: Kento Sato (RIKEN Center for Computational Science (R-CCS)); Ch
 ris Schlipalius (Pawsey Supercomputing Research Centre; Commonwealth Scien
 tific and Industrial Research Organisation (CSIRO), Australia); and Anja G
 erbes (Georg-August-Universität Göttingen)\n\n
END:VEVENT
END:VCALENDAR