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:20260202T201250Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251120T080000
DTEND;TZID=America/Chicago:20251120T170000
UID:submissions.supercomputing.org_SC25_sess533_post205@linklings.com
SUMMARY:Scalable Execution Framework for R on Manycore Systems
DESCRIPTION:Xiran Zhang (King Abdullah University of Science and Technolog
 y (KAUST)), Javier Conejero (Barcelona Supercomputing Center (BSC)), Sameh
  Abdulah (King Abdullah University of Science and Technology (KAUST)), Jor
 ge Ejarque (Barcelona Supercomputing Center (BSC)), Ying Sun (King Abdulla
 h University of Science and Technology (KAUST)), Rosa M. Badia (Barcelona 
 Supercomputing Center (BSC)), and David E. Keyes and Marc G. Genton (King 
 Abdullah University of Science and Technology (KAUST))\n\nRCOMPSs is a sca
 lable execution framework that integrates the R programming language with 
 the COMPSs runtime to enable task-based parallel execution on manycore and
  distributed systems. RCOMPSs extends conventional R workflows by allowing
  functions to be annotated as tasks, which the runtime system analyzes to 
 construct a task dependency graph (DAG). This graph guides dynamic schedul
 ing, dependency resolution, and data transfers, thereby abstracting parall
 el execution from the user while preserving correctness. A straightforward
  example of dataset standardization illustrates the minimal programming ef
 fort needed to leverage parallelism. In contrast, more complex application
 s like K-means clustering demonstrate the framework's capability to repres
 ent iterative statistical algorithms in a task-oriented manner. Performanc
 e evaluation on Shaheen-III and MareNostrum~5 shows strong scalability up 
 to 32 nodes with near-linear speedup, efficient weak scalability with incr
 easing problem sizes, and effective utilization of up to 128 and 80 thread
 s per node, respectively.\n\nTag: Research & ACM SRC Posters\n\nRegistrati
 on Category: Technical Program Reg Pass\n\nSession Chairs: Kento Sato (RIK
 EN Center for Computational Science (R-CCS)); Chris Schlipalius (Pawsey Su
 percomputing Research Centre; Commonwealth Scientific and Industrial Resea
 rch Organisation (CSIRO), Australia); and Anja Gerbes (Georg-August-Univer
 sität Göttingen)\n\n
END:VEVENT
END:VCALENDAR
