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:20211207T054747Z
LOCATION:263
DTSTART;TZID=America/Chicago:20211118T143000
DTEND;TZID=America/Chicago:20211118T150000
UID:submissions.supercomputing.org_SC21_sess269_exforum102@linklings.com
SUMMARY:HPC and AI Convergence in a Heterogeneous Exascale Cluster
DESCRIPTION:Exhibitor Forum\n\nHPC and AI Convergence in a Heterogeneous E
 xascale Cluster\n\nReiner\n\nHigh-performance computing and artificial int
 elligence have many similarities.  Both classes of workloads are very comp
 ute-intensive, highly parallel, and address problems that benefit from lar
 ge clusters.  One key difference between HPC and AI is in the level of pre
 cision that is often required.  The level of data analysis required for HP
 C applications typically needs double-precision or possibly single-precisi
 on.   AI, however, frequently requires lower precision, with the reduced p
 recision enabling much higher performance. \n\nAn emerging trend gaining p
 opularity for both HPC and AI is the use of various types of hardware acce
 lerators to augment the processor performance for the highly parallel work
 loads characteristic of both HPC and AI.  The heterogeneous compute enviro
 nments utilizing these accelerators provide increased performance, but at 
 a high cost.  The accelerators are expensive, power-hungry, consume server
  space and require special software support, so they are more difficult to
  program and maintain.  \n\nIn 2022 an exascale-class supercomputer is pla
 nned for deployment in Slovakia that will deliver mixed-precision floating
 -point operations that support a range of computations from double-precisi
 on to AI floating-point data types and will be deployed in a fully homogen
 eous environment.  The wide range of mixed precision coupled with the homo
 geneous environment will deliver the highest performance supercomputer in 
 the world for the most demanding HPC and AI workloads, providing 64 AI exa
 flops over 64 compute racks.  This presentation compares HPC and AI worklo
 ads, and presents an overview of the Slovakian Supercomputer, which will d
 eliver an optimal solution for both HPC and AI.\n\nTag: Data Management, E
 xtreme Scale Computing\n\nRegistration Category: Tech Program Reg Pass, Ex
 hibit Hall Only
END:VEVENT
END:VCALENDAR