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:20260202T201808Z
LOCATION:276
DTSTART;TZID=America/Chicago:20251121T103000
DTEND;TZID=America/Chicago:20251121T105500
UID:submissions.supercomputing.org_SC25_sess232_ws_hpct101@linklings.com
SUMMARY:Testing and Benchmarking Emerging Supercomputers via the MFC Flow 
 Solver
DESCRIPTION:Benjamin Wilfong, Anand Radhakrishnan, Henry Le Berre, and Tan
 ush Prathi (Georgia Institute of Technology); Stephen Abbott (Hewlett Pack
 ard Enterprise (HPE)); and Spencer Bryngelson (Georgia Institute of Techno
 logy)\n\nDeploying new supercomputers requires testing and evaluation via 
 application codes. Portable, user-friendly tools enable evaluation, and th
 e Multicomponent Flow Code (MFC), a computational fluid dynamics (CFD) cod
 e, addresses this need. MFC is adorned with a toolchain that automates inp
 ut generation, compilation, batch job submission, regression testing, and 
 benchmarking. The toolchain design enables users to evaluate compiler-hard
 ware combinations for correctness and performance with limited software en
 gineering experience. As with other PDE solvers, wall time per spatially d
 iscretized grid point serves as a figure of merit. We present MFC benchmar
 king results for five generations of NVIDIA GPUs, three generations of AMD
  GPUs, and various CPU architectures, utilizing Intel, Cray, NVIDIA, AMD, 
 and GNU compilers. These tests have revealed compiler bugs and regressions
  on recent machines such as Frontier and El Capitan. MFC has benchmarked a
 pproximately 50 compute devices and 5 flagship supercomputers.\n\nRecordin
 g: Livestreamed, Recorded\n\nRegistration Category: Technical Program Reg 
 Pass, Workshop Reg Pass\n\nSession Chairs: Verónica G. Melesse Vergara (Oa
 k Ridge National Laboratory (ORNL)); Bilel Hadri (King Abdullah University
  of Science and Technology (KAUST)); Vasileios Karakasis (NVIDIA Corporati
 on); Nick Hagerty (Oak Ridge National Laboratory (ORNL)); and Andreas Hert
 en (Forschungszentrum Jülich, Jülich Supercomputing Centre (JSC))\n\n
END:VEVENT
END:VCALENDAR