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:20260422T000711Z
LOCATION:203
DTSTART;TZID=America/Denver:20231112T083000
DTEND;TZID=America/Denver:20231112T120000
UID:submissions.supercomputing.org_SC23_sess212_tut139@linklings.com
SUMMARY:Programming Novel AI Accelerators for Scientific Computing
DESCRIPTION:Murali Emani (Argonne National Laboratory (ANL)), Petro Junior
  Milan (SambaNova Systems), Claire Zhang (Cerebras Systems), Alex Tsyplikh
 in (Graphcore), Leon Tran (Habana), Sanjif Shanmugavelu (Groq), and Sid Ra
 skar and Varuni Sastry (Argonne National Laboratory)\n\nScientific applica
 tions are increasingly adopting Artificial Intelligence (AI) techniques to
  advance science. There are specialized hardware accelerators designed and
  built to run AI applications efficiently. With a wide diversity in the ha
 rdware architectures and software stacks of these systems, it is challengi
 ng to understand the differences between these accelerators, their capabil
 ities, programming approaches, and how they perform, particularly for scie
 ntific applications. In this tutorial, we will cover an overview of the AI
  accelerators landscape with a focus on SambaNova, Cerebras, Graphcore, Gr
 oq, and Habana systems along with architectural features and details of th
 eir software stacks. We will have hands-on exercises that will help attend
 ees understand how to program these systems by learning how to refactor co
 des written in standard AI framework implementations and compile and run t
 he models on these systems. The tutorial will enable the attendees with an
  understanding of the key capabilities of emerging AI accelerators and the
 ir performance implications for scientific applications.\n\nTag: Accelerat
 ors, Artificial Intelligence/Machine Learning\n\nRegistration Category: Tu
 torial Reg Pass\n\n
END:VEVENT
END:VCALENDAR