BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Hyperight Data Club - ECPv4.3.5//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Hyperight Data Club
X-ORIGINAL-URL:https://www.hyperightdataclub.com
X-WR-CALDESC:Events for Hyperight Data Club
BEGIN:VEVENT
DTSTART;TZID=Europe/Stockholm:20180716T120000
DTEND;TZID=Europe/Stockholm:20180716T210000
DTSTAMP:20260503T121013
CREATED:20180621T131051Z
LAST-MODIFIED:20180716T072127Z
UID:16030-1531742400-1531774800@www.hyperightdataclub.com
SUMMARY:Ground-Breaking AI Speed and Scale - Meet the World’s Largest GPU: NVIDIA DGX-2
DESCRIPTION:\nModern enterprises need to rapidly deploy AI power in response to business imperatives\, and need\nto scale-out AI\, without scaling-up cost or complexity. In addition\, deep neural networks are rapidly\ngrowing in size and complexity\, in response to the most pressing challenges in business and research.\nThe computational capacity needed to support today’s modern AI workloads has outpaced\ntraditional data center architectures. Modern techniques that exploit increasing use of model\nparallelism are colliding with the limits of inter-GPU bandwidth\, as developers build increasingly large\naccelerated computing clusters\, pushing the limits of data center scale.\n\n \n\nMeet the world´s largest GPU: NVIDIA DGX-2 at the Hyperight Data Club in Stockholm\n\nNVIDIA® DGX-2™ is the world’s first 2 petaFLOPS system\, packing the power of 16 of the world’s\nmost advanced GPUs\, accelerating the newest deep learning model types that were previously\nuntrainable. With ground-breaking GPU scale\, you can train models 4X bigger on a single node. In\ncomparison with legacy x86 architectures\, DGX-2’s ability to train ResNet-50 would require the\nequivalent of 300 servers with dual Intel Xeon Gold CPUs.\n\nOn 16 th of July for the first time in Sweden\, the NVIDIA® DGX-2™ will be displayed at the Hyperight\nData Club followed by an evening program. You will discover the performance\nand features of NVIDIA® DGX-2™\, and gain insights into new ground-breaking practices of AI at\nScale on a whole new level.\n\n \n\nProgram – 16th of July 2018\n12:00 – 18:00\nDrop-in and free product consultation\n18:00 – 18:45\nPushing Deep Learning Boundaries with Mixed Precision and DGX-2 at Peltarion\n– Anders Arpteg\, Principal Data Scientist\, Peltarion\n19:00 – 21:00\nNVIDIA® DGX-2™ Official Program and Mingle:\nJim McHugh - Vice President & General Manager\, NVIDIA\nElan Raja - CEO of Scan Business\, Scan\nOskar Burstrand - Investment & Sales Manager\, Node Pole\nChristoffer Göransson - Sales Business Development Executive\, Inovia AB\nKiril Serafimovski – Manager\, Hyperight Data Club\n\n \n\nRefreshments\, appetisers and snacks will be served\n\n \n\nLocation:\nHyperight Data Club – Tegnergatan 14\, 113 58 Stockholm\nNearest Metro -Rådmansgatan (exit – Tegnergatan)\n\nNotice:\nDuring the Drop-in hours considering the capacity of the location and interests so far\,\nplease be advised that queues might occur.\nRegistration for attending the event is mandatory.\n\n \n     \n 
URL:https://www.hyperightdataclub.com/event/ground-breaking-ai-speed-and-scale-meet-the-worlds-largest-gpu-nvidia-dgx-2/
LOCATION:Tegnérgatan 14\, Stockholm\, 11358\, Sverige
END:VEVENT
END:VCALENDAR