BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082410Z
LOCATION:HG F 30 Audi Max
DTSTART;TZID=Europe/Stockholm:20240603T185700
DTEND;TZID=Europe/Stockholm:20240603T185800
UID:submissions.pasc-conference.org_PASC24_sess156_pos126@linklings.com
SUMMARY:P08 - Complete Asynchronous Task-Based Implementation of a Particl
 e-In-Cell Code: Performance Studies and Benchmark
DESCRIPTION:Poster\n\nJuan José Silva Cuevas (Maison de la Simulation)\n\n
 In this work, a cutting-edge full implementation of task-based programming
  paradigms applied to a complete particle-in-cell code is shown. The core 
 of the implementation has been based on the algorithm of the particle-in-c
 ell code Smilei (https://smileipic.github.io/Smilei/), although a complete
  code has been built up from scratch. The task-based model has been implem
 ented in the particle-in-cell code throughout the backend OpenMP and the l
 ibrary Eventify, being the last one currently developed at the Jülich Supe
 rcomputing Centre. Four physical studies were selected as benchmarks: ther
 mal plasma, plasma beam diffusion, a laser colliding with a plasma beam sp
 here, and thermal plasma with an imbalanced artificial operator. Besides, 
 different parametric studies were designed to measure the scalability of t
 he implementation at different numbers of cores and different physical con
 ditions. To measure the performance scalability under different architectu
 res, the current parametric studies were performed in an Intel cascade lak
 e-based machine and an AMD EPYC-based machine. Results show a significant 
 gain in performance in the task-based implementation compared to the class
 ical omp for implementation when a high load-imbalance benchmark is presen
 ted.\n\nSession Chair: Erik W. Draeger (Lawrence Livermore National Labora
 tory)
END:VEVENT
END:VCALENDAR