BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T234543Z
LOCATION:B314
DTSTART;TZID=America/New_York:20241118T140000
DTEND;TZID=America/New_York:20241118T143000
UID:submissions.supercomputing.org_SC24_sess758_misc385@linklings.com
SUMMARY:Accelerating Machine Learning with Tensor Processing Units: A Jour
 ney of Full-stack Optimization and Co-design
DESCRIPTION:Lifeng Nai (Google)\n\nInspired by the success of the first TP
 U for ML inference deployed in 2015, Google has developed multiple generat
 ions of machine learning supercomputers for efficient ML training and serv
 ing, enabling near linear scaling of ML workloads. In this talk, we will p
 resent how TPU works as a machine learning supercomputer to benefit a grow
 ing number of Google services, including Gemini and Ads. Furthermore, we w
 ill have a deep dive into our full-stack co-design methodology that spans 
 across model, software and hardware layers, and how it turns accelerator c
 oncepts into reality.\n\nTag: Artificial Intelligence/Machine Learning, Co
 design\n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs: John
  Feo (Pacific Northwest National Laboratory (PNNL)), Jiyuan Zhang (Meta), 
 and Amelie Chi Zhou (Hong Kong Baptist University)\n\n
END:VEVENT
END:VCALENDAR