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:20260202T201805Z
LOCATION:230
DTSTART;TZID=America/Chicago:20251119T161500
DTEND;TZID=America/Chicago:20251119T163000
UID:submissions.supercomputing.org_SC25_sess530_post211@linklings.com
SUMMARY:Using Hardware Metrics To Understand Performance of the RAJA Perfo
 rmance Suite Kernels in Different GPU Modes on MI300A
DESCRIPTION:Amr Abouelmagd (Tennessee Tech University) and Stephanie Brink
 , Michael McKinsey, David Boehme, Jason Burmark, Brian Ryujin, Tom Scoglan
 d, and Olga Pearce (Lawrence Livermore National Laboratory (LLNL))\n\nMode
 rn GPUs play a crucial role in accelerating a wide range of computational 
 workloads. However, their performance is often limited by the memory acces
 s patterns of the kernels they execute. AMD’s MI300A APU supports multiple
  logical GPU partitioning modes to optimize compute resource allocation, o
 ffering new opportunities for performance tuning. In this work, we evaluat
 e how different GPU kernels from the RAJA Performance Suite perform in var
 ious partitioning modes. Using hardware counters, we compare two kernels w
 ith identical computational complexity but different data layouts, highlig
 hting how memory organization can influence performance outcomes. The resu
 lts demonstrate that data layout and access patterns have a significant im
 pact on runtime performance across different partitioning modes, even when
  computational complexity and problem size remain constant.\n\nTag: Resear
 ch & ACM SRC Posters\n\nRegistration Category: Technical Program Reg Pass\
 n\nSession Chairs: Kento Sato (RIKEN Center for Computational Science (R-C
 CS)); Chris Schlipalius (Pawsey Supercomputing Research Centre; Commonweal
 th Scientific and Industrial Research Organisation (CSIRO), Australia); an
 d Anja Gerbes (Georg-August-Universität Göttingen)\n\n
END:VEVENT
END:VCALENDAR