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:20260522T162632Z
LOCATION:Bldg. 6 - Room 104
DTSTART;TZID=Europe/Stockholm:20260629T120000
DTEND;TZID=Europe/Stockholm:20260629T123000
UID:submissions.pasc-conference.org_PASC26_sess171_pap119@linklings.com
SUMMARY:Inline Lossy Compressed MPI Communications in GPU-based Plasma Tur
 bulence Simulations
DESCRIPTION:Diego Jimenez (Max Planck Computing and Data Facility), Felix 
 Jung (Technical University of Munich), Nils Schild (Max Planck Institute f
 or Plasma Physics), Jan Laukemann (Friedrich-Alexander-Universität Erlange
 n-Nürnberg), Carl-Martin Pfeiler (Max Planck Institute for Plasma Physics)
 , Tilman Dannert (Max Planck Computing and Data Facility), Martin Schulz (
 Technical University of Munich), and Erwin Laure (Max Planck Computing and
  Data Facility)\n\nThe performance gap between computing power and data mo
 vement bandwidth across the HPC hardware stack is one of the primary obsta
 cles to application scaling at exascale. Fusion Plasma simulations are par
 ticularly affected by this due to their high-dimensional phase-space repre
 sentation and communication requirements. This work explores the use of ag
 nostic lossy compression inline with MPI communications as a way to reduce
  network contention and improve application performance. By striking a bal
 ance between compressor throughput, ratio, and fidelity preservation, comm
 unication-bound HPC applications could potentially benefit from this data 
 reduction technique. We develop a set of performance models that help dete
 rmine whether compression libraries provide enough throughput for inline u
 sage. We then evaluate three state-of-the-art lossy compressors with the p
 roposed models: ZFP, SZ and MGARD. Additionally, we illustrate the process
  of compressing MPI boundary exchanges and analyze the impact of applying 
 lossy reduction in-simulation to target Quantities of Interest in two plas
 ma turbulence applications: GENE and BSL6D. Our main findings show that on
  both applications, message sizes can be reduced by a factor of 8 while st
 ill providing sound physics information and achieving up to 3X and 6X time
  improvements in boundary exchanges for GENE and BSL6D, respectively.\n\nS
 ession Chair: Marta Garcia-Gasulla (Barcelona Supercomputing Center)\n\n
END:VEVENT
END:VCALENDAR