BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York 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:20240418T152105Z UID:DEE8350E-3863-435E-AFF9-D6CBDF2F3BEE DTSTART;TZID=America/New_York:20240417T140000 DTEND;TZID=America/New_York:20240417T150000 DESCRIPTION:IEEE Northern Virginia Communications Society (ComSoc) and Geor ge Mason University Department of Computer Science invite you to attend th e following CS Lecture Series Seminar:\n\nTitle: Deep Learning Compilers a nd Kernel Generation\n\nWhen: April 17\, 2024 from 2:00 PM to 3:00 PM\n\nS peaker: Vinod Grover\, NVIDIA\n\nLocation: Nguyen Engineering Building\, C onference Room 4201\n\nZoom Link: [https://gmu.zoom.us/j/99133375939?pwd=K 003K3JuYmR3L2FWYldPWWZrRUVFQT09](https://nam11.safelinks.protection.outloo k.com/?url=https%3A%2F%2Fgmu.zoom.us%2Fj%2F99133375939%3Fpwd%3DK003K3JuYmR 3L2FWYldPWWZrRUVFQT09&data=05%7C02%7Ckhassan1%40gmu.edu%7C7f98fa3c7c194c32 f75f08dc58cd04dd%7C9e857255df574c47a0c00546460380cb%7C0%7C0%7C638482884783 417855%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI 6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=AdtnvDXUbK6PsccONuQhjAY1O%2BY%2 B0flZNjMLGaTZISs%3D&reserved=0)\n\nAbstract:\n\nDeep Learning Compilers ha ve made great progress in recent years and started to be used in training and inference of models. Yet many challenges still remain. High performanc e model graphs are still written as kernels by experts and these are also deployed manually using custom operation hooks in frameworks. In this talk we will describe some of the challenges in compiling dynamic shapes and d esigning intermediate representations that enable automatic kernel generat ion.\n\nBio:\n\nVinod Grover is a Sr. Distinguished Engineer at NVIDIA. He has been with NVIDIA since 2007 where he led a team that developed the CU DA C++ language and compiler for programming GPUs. CUDA C++ has been a key catalyst in driving productivity\, performance and innovation in many fie lds. Since 2017\, Vinod has been focused on bringing the same productivity and performance to the problem of accelerating Deep Learning models by us ing important ideas from language design and compiler technology. He is cu rrently leading a small group that is focused on problems of performance a nd productivity to the development of ML models. Previously Vinod held eng ineering\, research and management positions at Sun Microsystems and Micro soft.\n\nVinod holds a Bachelor's degree in Physics from IIT Delhi and a M aster's degree in Computer Science from Syracuse University.\n\nCo-sponsor ed by: George Mason University - Department of Computer Science\n\nBldg: N guyen Engineering Building\, Conference Room 4201\, 4400 University Dr\, F airfax\, Virginia\, United States\, 22030\, Virtual: https://events.vtools .ieee.org/m/417186 LOCATION:Bldg: Nguyen Engineering Building\, Conference Room 4201\, 4400 Un iversity Dr\, Fairfax\, Virginia\, United States\, 22030\, Virtual: https: //events.vtools.ieee.org/m/417186 ORGANIZER:kafi@ieee.org SEQUENCE:21 SUMMARY:Deep Learning Compilers and Kernel Generation URL;VALUE=URI:https://events.vtools.ieee.org/m/417186 X-ALT-DESC:Description: <br /><p class="x_x_MsoNormal">IEEE Northern Virgin ia Communications Society (ComSoc) and George Mason University Department of Computer Science invite you to attend the following CS Lecture Series S eminar:</p>\n<p class="x_x_MsoQuote"><strong>Title: Deep Learning Compiler s and Kernel Generation</strong></p>\n<p class="x_x_MsoQuote"><strong>When </strong>: April 17\, 2024 from 2:00 PM to 3:00 PM</p>\n<p class="x_x_MsoQ uote"><strong>Speaker</strong>: Vinod Grover\, NVIDIA</p>\n<p class="x_x_M soQuote"><strong>Location</strong>: Nguyen Engineering Building\, Conferen ce Room 4201</p>\n<p class="x_x_MsoQuote"><strong>Zoom Link</strong>:&nbsp \;<a title="Original URL: https://gmu.zoom.us/j/99133375939?pwd=K003K3JuYm R3L2FWYldPWWZrRUVFQT09. Click or tap if you trust this link." href="https: //nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgmu.zoom.us%2F j%2F99133375939%3Fpwd%3DK003K3JuYmR3L2FWYldPWWZrRUVFQT09&amp\;data=05%7C02 %7Ckhassan1%40gmu.edu%7C7f98fa3c7c194c32f75f08dc58cd04dd%7C9e857255df574c4 7a0c00546460380cb%7C0%7C0%7C638482884783417855%7CUnknown%7CTWFpbGZsb3d8eyJ WIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C% 7C&amp\;sdata=AdtnvDXUbK6PsccONuQhjAY1O%2BY%2B0flZNjMLGaTZISs%3D&amp\;rese rved=0" target="_blank" rel="noopener noreferrer" data-auth="Verified" dat a-linkindex="1">https://gmu.zoom.us/j/99133375939?pwd=K003K3JuYmR3L2FWYldP WWZrRUVFQT09</a></p>\n<p class="x_x_MsoNormal">&nbsp\;</p>\n<p class="x_x_ MsoNormal"><strong>Abstract</strong>:</p>\n<p class="x_x_MsoNormal">Deep L earning Compilers have made great progress in recent years and started to be used in training and inference of models. Yet many challenges still rem ain.&nbsp\;High performance model graphs are still written as kernels by e xperts and these are also deployed manually using custom operation hooks i n frameworks.&nbsp\;In this talk we will describe some of the challenges i n compiling dynamic shapes and designing intermediate representations that enable automatic kernel generation.</p>\n<p class="x_x_MsoNormal"><strong >Bio</strong>:</p>\n<p class="x_x_MsoNormal">Vinod Grover is a Sr. Disting uished Engineer at NVIDIA. He has been with NVIDIA since 2007 where he led a team that developed the CUDA C++ language and compiler for programming GPUs. CUDA C++ has been a key catalyst in driving productivity\, performan ce and innovation in many fields. Since 2017\, Vinod has been focused on b ringing the same productivity and performance to the problem of accelerati ng Deep Learning models by using important ideas from language design and compiler technology. He is currently leading a small group that is focused on problems of performance and productivity to the development of ML mode ls. Previously Vinod held engineering\, research and management positions at Sun Microsystems and Microsoft.</p>\n<p class="x_x_MsoNormal">Vinod hol ds a Bachelor's degree in Physics from IIT Delhi and a Master's degree in Computer Science from Syracuse University.</p>\n<p class="x_x_MsoNormal">& nbsp\;</p> END:VEVENT END:VCALENDAR