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:20240116T191701Z
LOCATION:201-203
DTSTART;TZID=America/Denver:20231116T133000
DTEND;TZID=America/Denver:20231116T150000
UID:submissions.supercomputing.org_SC23_sess192_pan108@linklings.com
SUMMARY:Scalable and Adaptable Architectures for AI/HPC Advancement
DESCRIPTION:Panel\n\nKeren Bergman (Columbia University); John Shalf (Lawr
 ence Berkeley National Laboratory (LBNL)); Sadaf Alam (University of Brist
 ol); Vladimir Stojanovic (University of California, Berkeley; Ayar Labs); 
 Sergey Shumaray (Intel Corporation); Larry Dennison (NVIDIA Corporation); 
 and Vivek Raghunathan (Xscape Photonics)\n\nAI/Machine Learning usage is e
 xploding in both application and model size. Predictive analytics, physics
 , modeling, and new use cases for generative AI/ML are increasing model si
 zes by 10x every 18 months. The custom processors and accelerators used fo
 r AI/ML require continually higher I/O bandwidth to address this model gro
 wth. However, how does one deploy a high-performance architecture that is 
 scalable and adaptable through time to address this phenomenon? The panel 
 will discuss the architectures, I/O and large-scale system topologies that
  will be needed to grow well beyond 200 billion parameters. You will gain 
 insights into system concepts, scaled across workload size, that are both 
 cost-effective from a new configurability perspective as well as a focus o
 n energy-efficiency. Is there a new Billion Parameters per Watt metric? Th
 ese are the topics the panel will discuss and debate.\n\nTag: Artificial I
 ntelligence/Machine Learning\n\nRegistration Category: Tech Program Reg Pa
 ss\n\nSession Chair: Keren Bergman (Columbia University, Ayar Labs)
END:VEVENT
END:VCALENDAR