BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Rome
BEGIN:DAYLIGHT
DTSTART:20240331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240409T204809Z
UID:CA93B8B0-0B91-492A-93B0-042036904045
DTSTART;TZID=Europe/Rome:20240304T170000
DTEND;TZID=Europe/Rome:20240304T183000
DESCRIPTION:Estimating the reliability of DNNs in the face of permanent GPU
  hardware failures\n\nMr. Juan Balaguera\, PhD Candidate\, DAUIN\n\nGraphi
 c Processing Units (GPUs) are crucial for modern Deep Neural\nNetwork (DNN
 ) acceleration. However\, these devices can be affectedby faults that migh
 t jeopardize the DNNs' realiability. My researchproposes fault simulation 
 strategies to effectively assess the impact of\npermanent defects on GPUs 
 regardless of the softwareimplementation of the neural networks.\n\nFuncti
 onal Stimuli Generation for Burn-In Test\n\nMr. Nick Deligiannis\, PhD Can
 didate\, DAUIN\n\nIn high-reliability applications\, Burn-In testing (BI) 
 is crucial to combat\nearly failures. Traditional static BI is inefficient
  for modern dense\ncircuits. In this work\, we propose automated methods a
 ble to\ngenerate effective\, functional stress inducing stimuli\, especial
 ly for\npipelined processors\, destined for dynamic BI test.\n\nReliabilit
 y and Performance Challenges of Next-Generation Smart Power Battery Manage
 ment Systems for Electric Mobility\n\nMr. Amirhossein Ahmadi\, PhD Candida
 te\, DET\n\nThis project discusses the impact of electromagnetic interfere
 nce\n(EMI) on the battery management systems (BMS) and BMS vertical\ninter
 face (VIF). The susceptibility to EMI is tackeld by transistor-level\nsimu
 lations and tests for the first time aiming to highlight the failure\nmech
 anisms and consequently to propose methods to enhance the\nperformance.\n\
 nRoom: Maxwell Room\, Bldg: DET\, Politecnico di Torino\, Corso Duca Degli
  Abruzzi 24\, Torino\, Piemonte\, Italy\, 10129
LOCATION:Room: Maxwell Room\, Bldg: DET\, Politecnico di Torino\, Corso Duc
 a Degli Abruzzi 24\, Torino\, Piemonte\, Italy\, 10129
ORGANIZER:sb.polito@ieee.org
SEQUENCE:21
SUMMARY:PITCHD 2024 EDITION: THE 1st PITCHD
URL;VALUE=URI:https://events.vtools.ieee.org/m/408418
X-ALT-DESC:Description: <br /><p><strong>Estimating the reliability of DNNs
  in the face of permanent GPU hardware failures</strong></p>\n<p><em>Mr. J
 uan Balaguera\, PhD Candidate\, DAUIN</em></p>\n<p>Graphic Processing Unit
 s (GPUs) are crucial for modern Deep Neural<br />Network (DNN) acceleratio
 n. However\, these devices can be affectedby faults that might jeopardize 
 the DNNs' realiability. My researchproposes fault simulation strategies to
  effectively assess the impact of<br />permanent defects on GPUs regardles
 s of the softwareimplementation of the neural networks.</p>\n<p>&nbsp\;</p
 >\n<p><strong>Functional Stimuli Generation for Burn-In Test</strong></p>\
 n<p><em>Mr. Nick Deligiannis\, PhD Candidate\, DAUIN</em></p>\n<p>In high-
 reliability applications\, Burn-In testing (BI) is crucial to combat<br />
 early failures. Traditional static BI is inefficient for modern dense<br /
 >circuits. In this work\, we propose automated methods able to<br />genera
 te effective\, functional stress inducing stimuli\, especially for<br />pi
 pelined processors\, destined for dynamic BI test.</p>\n<p>&nbsp\;</p>\n<p
 ><strong>Reliability and Performance Challenges of Next-Generation Smart P
 ower Battery Management Systems for Electric Mobility</strong></p>\n<p><em
 >Mr. Amirhossein Ahmadi\, PhD Candidate\, DET</em></p>\n<p>This project di
 scusses the impact of electromagnetic interference<br />(EMI) on the batte
 ry management systems (BMS) and BMS vertical<br />interface (VIF). The sus
 ceptibility to EMI is tackeld by transistor-level<br />simulations and tes
 ts for the first time aiming to highlight the failure<br />mechanisms and 
 consequently to propose methods to enhance the<br />performance.</p>
END:VEVENT
END:VCALENDAR