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:240
DTSTART;TZID=America/Chicago:20251117T140000
DTEND;TZID=America/Chicago:20251117T150000
UID:submissions.supercomputing.org_SC25_sess222_misc131@linklings.com
SUMMARY:Featured Talk - ARMing GPUs: On the Memory Subsystem of Grace Hopp
 er GH200
DESCRIPTION:Torsten Hoefler (ETH Zurich)\n\nHeterogeneous supercomputers h
 ave become the standard in HPC. GPUs in particular have dominated the acce
 lerator landscape, offering unprecedented performance in parallel workload
 s and unlocking new possibilities in fields like AI and climate modeling. 
 With many workloads becoming memory-bound, improving the communication lat
 ency and bandwidth within the system has become a main driver in the devel
 opment of new architectures. The Grace Hopper Superchip (GH200) is a signi
 ficant step in the direction of tightly coupled heterogeneous systems, in 
 which all CPUs and GPUs share a unified address space and support transpar
 ent fine grained access to all main memory on the system. We characterize 
 both intra- and inter-node memory operations on the Quad GH200 nodes of th
 e new Swiss National Supercomputing Centre Alps supercomputer, and show th
 e importance of careful memory placement on example workloads, highlightin
 g tradeoffs and opportunities.\n\nRecording: Livestreamed, Recorded\n\nReg
 istration Category: Technical Program Reg Pass, Workshop Reg Pass\n\nSessi
 on Chairs: Antonio J. Peña (Barcelona Supercomputing Center (BSC); Univers
 itat Politècnica de Catalunya (UPC), Spain); João Barreto (INESC-ID, IST, 
 University of Lisbon; Universidade de Lisboa); and Harald Servat (Intel Co
 rporation)\n\n
END:VEVENT
END:VCALENDAR