BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000712Z
LOCATION:503-504
DTSTART;TZID=America/Denver:20231117T091000
DTEND;TZID=America/Denver:20231117T093500
UID:submissions.supercomputing.org_SC23_sess464_ws_hpct105@linklings.com
SUMMARY:Experiences Detecting Defective Hardware in Exascale Supercomputer
 s
DESCRIPTION:Nick Hagerty, Jordan Webb, Veronica Melesse Vergara, and Matt 
 Ezell (Oak Ridge National Laboratory (ORNL))\n\nIn May 2022, the newest su
 percomputer to top the TOP 500 list was Frontier at Oak Ridge National Lab
 oratory, capable of computing more than 1.1 quintillion (10^18) floating-p
 oint calculations every second. Driving this ground-breaking rate of compu
 ting is Frontier's more than 37,000 graphics processing units (GPUs) and 9
 ,408 central processing units (CPUs). At this scale, the smallest margin o
 f error may generate hundreds of errors across the system. In this work, w
 e describe and evaluate two strategies for finding hardware-level faults i
 n Frontier's 9,408 compute nodes. There are two strategies developed: the 
 first uses the Slurm scheduler to scavenge available compute time to run t
 he node screen, the second enforces a weekly screen of each node. Using Ju
 ne 2023 as a case study, we find that the first scheduling strategy consum
 ed ten times the resources as the second scheduling strategy, but successf
 ully detected five hardware defects in Frontier.\n\nTag: Applications, Exa
 scale, Heterogeneous Computing, Programming Frameworks and System Software
 , State of the Practice\n\nRegistration Category: Workshop Reg Pass\n\nSes
 sion Chairs: Bilel Hadri (King Abdullah University of Science and Technolo
 gy (KAUST)), Vasileios Karakasis (NVIDIA Corporation), and Verónica G. Mel
 esse Vergara (Oak Ridge National Laboratory (ORNL))\n\n
END:VEVENT
END:VCALENDAR