BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250425T141940Z
UID:202A2877-A9DB-47F5-AF4C-1A8DE314DDE8
DTSTART;TZID=America/New_York:20250422T190000
DTEND;TZID=America/New_York:20250422T200000
DESCRIPTION:Distributed Machine Learning for FPGAs in the Cloud\nMachine Le
 arning (ML) is a growing area in both research and applications. Trends\ni
 nclude larger and larger ML models and the interest in getting results fro
 m ML with low\nlatency and high throughput. To address these trends\, rese
 archers are increasingly\nlooking at accelerators (such as Graphics Proces
 sing Units (GPUs) and Field\nProgrammable Gate Arrays (FPGAs)\, especially
  those that are directly connected to the\nnetwork to achieve low latency 
 access to data.\nIn this talk\, I will introduce the Open Cloud Testbed (O
 CT): https://octestbed.org/\nOCT is available to researchers who are inter
 ested in conducting cloud research with\naccelerators. We provide GPUS\, F
 PGAs\, and AI engines from AMD. The FPGAs and\nAI engines are directly con
 nected to the network.\nI will discuss experiments on using OCT for distri
 buted ML using multiple network\nconnected FPGAs. Specifically I will pres
 ent results for running Resnet50 inference on\nthe imagenet dataset.\nNo h
 ardware knowledge is assumed for this webinar.\n\nSpeaker(s): Miriam\n\nVi
 rtual: https://events.vtools.ieee.org/m/473027
LOCATION:Virtual: https://events.vtools.ieee.org/m/473027
ORGANIZER:ieee.lvs.wie@gmail.com
SEQUENCE:12
SUMMARY:Women in AI Series 2025 - Distributed Machine Learning for FPGAs in
  the Cloud: Dr. Miriam Leeser
URL;VALUE=URI:https://events.vtools.ieee.org/m/473027
X-ALT-DESC:Description: &lt;br /&gt;&lt;p&gt;Distributed Machine Learning for FPGAs in 
 the Cloud&lt;br&gt;Machine Learning (ML) is a growing area in both research and 
 applications. Trends&lt;br&gt;include larger and larger ML models and the intere
 st in getting results from ML with low&lt;br&gt;latency and high throughput. To 
 address these trends\, researchers are increasingly&lt;br&gt;looking at accelera
 tors (such as Graphics Processing Units (GPUs) and Field&lt;br&gt;Programmable G
 ate Arrays (FPGAs)\, especially those that are directly connected to the&lt;b
 r&gt;network to achieve low latency access to data.&lt;br&gt;In this talk\, I will 
 introduce the Open Cloud Testbed (OCT): https://octestbed.org/&lt;br&gt;OCT is a
 vailable to researchers who are interested in conducting cloud research wi
 th&lt;br&gt;accelerators. We provide GPUS\, FPGAs\, and AI engines from AMD. The
  FPGAs and&lt;br&gt;AI engines are directly connected to the network.&lt;br&gt;I will 
 discuss experiments on using OCT for distributed ML using multiple network
 &lt;br&gt;connected FPGAs. Specifically I will present results for running Resne
 t50 inference on&lt;br&gt;the imagenet dataset.&lt;br&gt;No hardware knowledge is assu
 med for this webinar.&lt;/p&gt;
END:VEVENT
END:VCALENDAR