BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20210314T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20210920T161102Z UID:2016E676-3997-44BD-8731-71A56126A99C DTSTART;TZID=US/Pacific:20210915T080000 DTEND;TZID=US/Pacific:20210915T120000 DESCRIPTION:Welcome to the [SPS Seasonal School](https://signalprocessingso ciety.org/blog/2021-ieee-sps-seasonal-school-signal-processing-and-communi cation-systems-5g) on Signal Processing and Communication Systems for 5G. The jointly\, internationally\, organized by IEEE Vizag Bay Section [Commu nications Society & SPS](https://r10.ieee.org/vizagbay/) Joint Chapter\, V izag\, India\, IEEE Long Island Section ([SPS](http://www.ieee.li/sp)) Cha pter\, New York\, USA\, and IEEE [Finland SP/CAS](https://site.ieee.org/fi nland/) Chapter\, Finland presents the following technical lecture:\n\nAbs tract:\n\nAs the rollout of 5G progresses and research for 6G begins\, the key themes of softwarization\, virtualization\, open systems and artifici al intelligence form foundational principles for communication systems of the future. The application of AI/MLto wireless communications an extremel y active research area with many 10’s to 100’s of papers published wee kly reporting new results on the application of AI/ML to the physical laye r (L1)\, MAC layer (L2) and at the network optimization level.\n\nTo reali ze the Industry’s vision of an AI/ML powered wireless future\, a full st ack solution supporting a software defined radio (SDR) approach for the vR AN\, together with optimized silicon for AI\, coupled with application dev elopment frameworks for AI/ML development is essential. NVIDIA GPU technol ogy and associated CUDA programming model\, together with arch suite of AI /ML SDKs (Software Development Kits) provides these capabilities.\n\nIn th is talk we present The Aerial software-defined GPU-based cloud native 5G N R RAN platform. Aerial implements not only 5G NR the baseband signal proce ssing\, but using GPU virtualization supports additional concurrently oper ating workloads\, such as AI/ML inference\, training and data analytics on this one hyper-converged system. We provide an overview of the L1 signal processing pipeline and describe efficient mechanisms for data movement be tween the GPU and NIC-based fronthaul interface using a GPU-enabled Data P lane Development Kit (DPDK). A brief survey of some of the promising deep learning approaches for L1 and L2enhancements is presented.\n\nSpeaker(s): Dr. Chris Dick \, \n\nVirtual: https://events.vtools.ieee.org/m/269884 LOCATION:Virtual: https://events.vtools.ieee.org/m/269884 ORGANIZER:signal@ieee.li SEQUENCE:13 SUMMARY:GPU Acceleration for 5G Signal Processing and Machine Learning URL;VALUE=URI:https://events.vtools.ieee.org/m/269884 X-ALT-DESC:Description: <br /><p>Welcome to the <a href="https://signalproc essingsociety.org/blog/2021-ieee-sps-seasonal-school-signal-processing-and -communication-systems-5g">SPS Seasonal School</a> on Signal Processing an d Communication Systems for 5G. The jointly\, internationally\, organized by IEEE Vizag Bay Section <a href="https://r10.ieee.org/vizagbay/">Communi cations Society &amp\; SPS</a> Joint Chapter\, Vizag\, India\, IEEE Long I sland Section&nbsp\;(<a href="http://www.ieee.li/sp">SPS</a>)&nbsp\;Chapte r\, New York\, USA\, and IEEE <a href="https://site.ieee.org/finland/">Fin land SP/CAS</a> Chapter\, Finland presents the following technical lecture :</p>\n<p>Abstract:</p>\n<p>As the rollout of 5G progresses and research f or 6G begins\, the key themes of softwarization\, virtualization\, open sy stems and artificial intelligence form foundational principles for communi cation systems of the future. The application of AI/MLto wireless communic ations an extremely active research area with many 10&rsquo\;s to 100&rsqu o\;s of papers published weekly reporting new results on the application o f AI/ML to the physical layer (L1)\, MAC layer (L2) and at the network opt imization level.</p>\n<p>To realize the Industry&rsquo\;s vision of an AI/ ML powered wireless future\, a full stack solution supporting a software d efined radio (SDR) approach for the vRAN\, together with optimized silicon for AI\, coupled with application development frameworks for AI/ML develo pment is essential. NVIDIA GPU technology and associated CUDA programming model\, together with arch suite of AI/ML SDKs (Software Development Kits) provides these capabilities.</p>\n<p>In this talk we present The <em>Aeri al </em>software-defined GPU-based cloud native 5G NR RAN platform. Aerial implements not only 5G NR the baseband signal processing\, but using GPU virtualization supports additional concurrently operating workloads\, such as AI/ML inference\, training and data analytics on this one hyper-conver ged system. We provide an overview of the L1 signal processing pipeline an d describe efficient mechanisms for data movement between the GPU and NIC- based fronthaul interface using a GPU-enabled Data Plane Development Kit ( DPDK). A brief survey of some of the promising deep learning approaches fo r L1 and L2enhancements is presented.</p> END:VEVENT END:VCALENDAR