BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Canada/Eastern
BEGIN:DAYLIGHT
DTSTART:20210314T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20211107T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210908T200313Z
UID:D3782A4F-33A2-4B24-BCB7-506258B56E80
DTSTART;TZID=Canada/Eastern:20210915T123000
DTEND;TZID=Canada/Eastern:20210915T133000
DESCRIPTION:As the rollout of 5G progresses and research for 6G begins\, th
 e key themes of softwarization\, virtualization\, open systems and artific
 ial intelligence form foundational principles for communication systems of
  the future.\n\nThe application of AI/ML to wireless communication is an e
 xtremely active research area with many 10’s to 100’s of papers publis
 hed weekly reporting new results on the application of AI/ML to the physic
 al layer (L1)\, MAC layer (L2) and at the network optimization level.\n\nT
 o realize the Industry’s vision of an AI/ML powered wireless future\, a 
 full stack solution supporting a software defined radio (SDR) approach for
  the vRAN\, together with optimized silicon for AI\, coupled with applicat
 ion development frameworks for AI/ML development is essential. NVIDIA GPU 
 technology and associated CUDA programming model\, together with a rich su
 ite of AI/ML SDKs (Software Development Kits) provides these capabilities.
 \n\nIn this talk we present The Aerial software-defined GPU-based cloud na
 tive 5G NR RAN platform. Aerial implements not only 5G NR the baseband sig
 nal processing\, but using GPU virtualization supports additional concurre
 ntly operating workloads\, such as AI/ML inference\, training and data ana
 lytics on this one hyper-converged system. We provide an overview of the L
 1 signal processing pipeline and describe efficient mechanisms for data mo
 vement between the GPU and NIC-based fronthaul interface using a GPU-enabl
 ed Data Plane Development Kit (DPDK). A brief survey of some of the promis
 ing deep learning approaches for L1 and L2 enhancements is presented.\n\nS
 peaker: Dr. Chris Dick\, NVIDIA\n\nCo-sponsored by: Canadian Conference on
  Electrical and Computer Engineering (CCECE) 2021\n\nSpeaker(s): Dr. Chris
  Dick\, \n\nVirtual: https://events.vtools.ieee.org/m/280085
LOCATION:Virtual: https://events.vtools.ieee.org/m/280085
ORGANIZER:murraymacdonald@ieee.org
SEQUENCE:2
SUMMARY:CCECE 2021 Keynote Speech - Aerial: An AI/ML Enabled Software Defin
 ed Radio Approach for Next Generation Wireless
URL;VALUE=URI:https://events.vtools.ieee.org/m/280085
X-ALT-DESC:Description: <br /><p>As the rollout of 5G progresses and resear
 ch for 6G begins\, the key themes of softwarization\, virtualization\, ope
 n systems and artificial intelligence form foundational principles for com
 munication systems of the future.</p>\n<p>The application of AI/ML to wire
 less communication is an extremely active research area with many 10&rsquo
 \;s to 100&rsquo\;s of papers published weekly reporting new results on th
 e application of AI/ML to the physical layer (L1)\, MAC layer (L2) and at 
 the network optimization level.</p>\n<p>To realize the Industry&rsquo\;s v
 ision of an AI/ML powered wireless future\, a full stack solution supporti
 ng a software defined radio (SDR) approach for the vRAN\, together with op
 timized silicon for AI\, coupled with application development frameworks f
 or AI/ML development is essential. NVIDIA GPU technology and associated CU
 DA programming model\, together with a rich suite of AI/ML SDKs (Software 
 Development Kits) provides these capabilities.</p>\n<p>In this talk we pre
 sent The <em>Aerial</em> software-defined GPU-based cloud native 5G NR RAN
  platform.&nbsp\; Aerial implements not only 5G NR the baseband signal pro
 cessing\, but using GPU virtualization supports additional concurrently op
 erating workloads\, such as AI/ML inference\, training and data analytics 
 on this one hyper-converged system.&nbsp\; We provide an overview of the L
 1 signal processing pipeline and describe efficient mechanisms for data mo
 vement between the GPU and NIC-based fronthaul interface using a GPU-enabl
 ed Data Plane Development Kit (DPDK). A brief survey of some of the promis
 ing deep learning approaches for L1 and L2 enhancements is presented.</p>\
 n<p>Speaker: Dr. Chris Dick\, NVIDIA</p>
END:VEVENT
END:VCALENDAR