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:20211207T054745Z
LOCATION:263
DTSTART;TZID=America/Chicago:20211116T110000
DTEND;TZID=America/Chicago:20211116T113000
UID:submissions.supercomputing.org_SC21_sess262_exforum122@linklings.com
SUMMARY:Powering Extreme-Scale AI and HPC Compute with Wafer-Scale Acceler
 ators
DESCRIPTION:Exhibitor Forum\n\nPowering Extreme-Scale AI and HPC Compute w
 ith Wafer-Scale Accelerators\n\nHock\n\nCompute requirements for deep lear
 ning (DL) and high-performance computing (HPC) are growing at an exponenti
 al rate. Many of the most important and valuable workloads in this domain 
 require more flexible and performant compute than traditional processors c
 an provide. Moreover, there is a growing population of converged AI + HPC 
 workloads that are not well-addressed by legacy machines. \n\nIn this pres
 entation, Dr. Andy Hock, vice president of product at Cerebras Systems, wi
 ll describe the Cerebras CS-2 machine and its application to large-scale H
 PC and AI workloads. This solution supports not just the largest models of
  today but extends seamlessly to giant models with more than 100 trillion 
 parameters, models that are impractical to implement today.\n\nCerebras’ w
 afer-scale accelerator technology features unprecedented compute density, 
 memory and communication bandwidth and is uniquely built for sparse linear
  algebra. Our co-designed software execution and hardware cluster technolo
 gy allows users to quickly and easily support enormous workloads that woul
 d require thousands of petaflops and take days or weeks to execute on ware
 house-sized clusters of legacy, general-purpose processors.  We will also 
 review our new software development kit that enables lower-level kernel pr
 ogramming for new or custom HPC and AI application development. \n\nCerebr
 as Systems builds the ultimate accelerator for AI and HPC workloads. With 
 this kind of horsepower, the possibilities are endless.\n\nTag: Architectu
 res, Extreme Scale Computing\n\nRegistration Category: Tech Program Reg Pa
 ss, Exhibit Hall Only
END:VEVENT
END:VCALENDAR