BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Canada/Eastern
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240822T032456Z
UID:494413CA-F4B8-4AEC-9B9E-4AD8AD506800
DTSTART;TZID=Canada/Eastern:20240821T133000
DTEND;TZID=Canada/Eastern:20240821T150000
DESCRIPTION:Abstract : Digital computing is approaching its fundamental lim
 its just as compute-intensive workloads like machine learning are taking o
 ff. To address this\, we are building a new kind of computer–an analog o
 ptical computer–to accelerate AI inference and hard optimization workloa
 ds. The computer has the potential to improve the efficiency and sustainab
 ility of these workloads by around 100x by stepping away from several fund
 amentally limiting aspects of general-purpose digital computing. It levera
 ges chip-scale optical and electronic technologies from the consumer space
  that are low cost and scalable. In this talk\, I will describe two genera
 tions of this computer that we have built\, outline our roadmap for scalin
 g\, and discuss the importance of hardware-software co-design for such eme
 rging computers and their potential for accelerating real-world problems i
 n the post-Moore Law’s era.\n\nSpeaker(s): Dr. Hitesh Ballani\, \n\nBldg
 : McConnell Engineering building\, \, Room MC603\, 6th floor\, 817 Sherbro
 oke St W\, \, Montreal\, Quebec\, Canada\, H3A 0C3\, Virtual: https://even
 ts.vtools.ieee.org/m/430520
LOCATION:Bldg: McConnell Engineering building\, \, Room MC603\, 6th floor\,
  817 Sherbrooke St W\, \, Montreal\, Quebec\, Canada\, H3A 0C3\, Virtual: 
 https://events.vtools.ieee.org/m/430520
ORGANIZER:odile.liboiron-ladouceur@mcgill.ca
SEQUENCE:16
SUMMARY:Analog Optical Computing for sustainable AI and beyond
URL;VALUE=URI:https://events.vtools.ieee.org/m/430520
X-ALT-DESC:Description: <br /><p><strong>Abstract :</strong> &nbsp\;Digital
  computing is approaching its fundamental limits just as compute-intensive
  workloads like machine learning are taking off. To address this\, we are 
 building a new kind of computer&ndash\;an analog optical computer&ndash\;t
 o accelerate AI inference and hard optimization workloads. The computer ha
 s the potential to improve the efficiency and sustainability of these work
 loads by around 100x by stepping away from several fundamentally limiting 
 aspects of general-purpose digital computing. It leverages chip-scale opti
 cal and electronic technologies from the consumer space that are low cost 
 and scalable. In this talk\, I will describe two generations of this compu
 ter that we have built\, outline our roadmap for scaling\, and discuss the
  importance of hardware-software co-design for such emerging computers and
  their potential for accelerating real-world problems in the post-Moore La
 w&rsquo\;s era.</p>\n<p>&nbsp\;</p>\n<p><img src="https://events.vtools.ie
 ee.org/vtools_ui/media/display/5520af42-b22d-4d99-adaf-a9d44189f6b4" width
 ="1004" height="565"></p>\n<p>&nbsp\;</p>\n<p>&nbsp\;</p>
END:VEVENT
END:VCALENDAR