BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260703T114545Z UID:a3a3db0b-d34b-40b9-a22c-21e7997201e5 DTSTART:20220510T070000Z DTEND:20220513T130000Z DESCRIPTION:\nThis course will be delivered as an ONLINE EVENT for remote p articipation\n\nOverview\n\nLearn how to accelerate your applications with OpenACC and CUDA\, how to train and deploy a neural network to solve real -world problems\, and how to effectively parallelize training of deep neur al networks on Multi-GPUs.\n\nThe online workshop combines lectures about Accelerated Computing with OpenACC and CUDA with lectures about Fundamenta ls of Deep Learning for single and for Multi-GPUs.\n\nThe lectures are int erleaved with many hands-on sessions using Jupyter Notebooks. The exercise s will be done on a fully configured GPU-accelerated workstation in the cl oud.\n\nThe workshop is part of PRACE Training Centres activity and co-org anized by LRZ – Leibniz Supercomputing Centre (Garching near Munich) as part of Gauss Centre for Supercomputing (Germany)\, IT4I – National Supe rcomputing Center VSB Technical University of Ostrava (Czech Republic)\, C SC – IT Center for Science Ltd (Finland) and NVIDIA Deep Learning Instit ute (DLI) for the Partnership for Advanced Computing in Europe (PRACE).\n\ nThe NVIDIA Deep Learning Institute delivers hands-on training for develop ers\, data scientists\, and engineers. The program is designed to help you get started with training\, optimizing\, and deploying neural networks to solve real-world problems across diverse industries such as self-driving cars\, healthcare\, online services\, and robotics.\n\nAll instructors are NVIDIA certified University Ambassadors.\n\nLecturers:  \n\nDr. Momme Al lalen\, Dr. Juan Durillo Barrionuevo\, Dr. Volker Weinberg (LRZ and NVIDIA University Ambassadors)\, Georg Zitzlsberger (IT4Innovations and NVIDIA University Ambassador)\n\nLanguage:  English\n\nPrice and Eligibility: Th is 4 day course is OPEN and FREE of charge for academic participants from the Member States (MS) of the European Union (EU) and Associated/Other Cou ntries to the Horizon 2020 programme.\n\nAgenda / Learning outcomes\n\n1st day: Fundamentals of Accelerated Computing with OpenACC (10:00-16:00 EEST | 09:00-15:00 CEST)\n\nOn the first day you learn the basics of OpenACC\, a high-level programming language for programming on GPUs. Discover how t o accelerate the performance of your applications beyond the limits of CPU -only programming with simple pragmas. You’ll learn:\n\n\n \n How to pro file and optimize your CPU-only applications to identify hot spots for acc eleration\n \n \n How to use OpenACC directives to GPU accelerate your cod ebase\n \n \n How to optimize data movement between the CPU and GPU accele rator\n \n \n Upon completion\, you'll be ready to use OpenACC to GPU acce lerate CPU-only applications.\n \n\n\n2nd day: Fundamentals of Accelerated Computing with CUDA C/C++ (10:00-16:00 EEST | 09:00-15:00 CEST)\n\nThe CU DA computing platform enables the acceleration of CPU-only applications to run on the world’s fastest massively parallel GPUs. On the 2nd day you experience C/C++ application acceleration by:\n\n\n \n Accelerating CPU-on ly applications to run their latent parallelism on GPUs\n \n \n Utilizing essential CUDA memory management techniques to optimize accelerated applic ations\n \n \n Exposing accelerated application potential for concurrency and exploiting it with CUDA streams\n \n \n Leveraging command line and vi sual profiling to guide and check your work\n \n\n\nUpon completion\, you ’ll be able to accelerate and optimize existing C/C++ CPU-only applicati ons using the most essential CUDA tools and techniques. You’ll understan d an iterative style of CUDA development that will allow you to ship accel erated applications fast.\n\n3rd day: Fundamentals of Deep Learning (10:00 -16:00 EEST | 09:00-15:00 CEST)\n\nExplore the fundamentals of deep learni ng by training neural networks and using results to improve performance an d capabilities.\n\nDuring this day\, you’ll learn the basics of deep lea rning by training and deploying neural networks. You’ll learn how to:\n\ n\n Implement common deep learning workflows\, such as image classificatio n and object detection\n Experiment with data\, training parameters\, netw ork structure\, and other strategies to increase performance and capabilit y\n\n\nUpon completion\, you’ll be able to start solving problems on you r own with deep learning.\n\n4th day: Fundamentals of Deep Learning for Mu lti-GPUs (10:00-16:00 EEST | 09:00-15:00 CEST)\n\nThe computational requir ements of deep neural networks used to enable AI applications like self-dr iving cars are enormous. A single training cycle can take weeks on a singl e GPU or even years for larger datasets like those used in self-driving ca r research. Using multiple GPUs for deep learning can significantly shorte n the time required to train lots of data\, making solving complex problem s with deep learning feasible.\n\nOn the last day we will teach you how to use multiple GPUs to train neural networks. You'll learn:\n\n\n \n Approa ches to multi-GPUs training\n \n \n Algorithmic and engineering challenges to large-scale training\n \n \n Key techniques used to overcome the chall enges mentioned above\n \n \n Upon completion\, you'll be able to effectiv ely parallelize training of deep neural networks using TensorFlow.\n \n De ploy your neural networks to start solving real-world problems\n\n\nPrereq uisites and content level\n\nThe content level of the course is broken dow n as: beginner's - 20%\, intermediate - 55%\, advanced - 25%\, community-t argeted content - 0%.\n\nPrerequisites: technical background\, basic under standing of machine learning concepts\, basic C/C++ or Fortran programming skills.\n\nFor the 3rd day: basics in Python will be helpful. Since Pytho n 2.7 is used\, the following tutorial can be used to learn the syntax: do cs.python.org/2.7/tutorial/index.html\n\nFor the 4th day: familiarity with TensorFlow (1.x) and Keras will be a plus as used in the hands-on session s. For those who did not use these before\, you can find tutorials here: g ithub.com/tensorflow/docs/tree/master/site/en/r1/tutorials/keras. Even tho ugh the course still uses Tensorflow 1.x\, it is not critical for the cont ent. We'll be using Horovod mainly\, which would be applicable the same wa y for Tensorflow 2.x.\n\nHands-on: The lectures are interleaved with many hands-on sessions using Jupyter Notebooks. The exercises will be done on a fully configured GPU-accelerated workstation in the cloud.\n\nImportant i nformation\n\nAfter you are accepted\, please create an account under cour ses.nvidia.com/join .\n\nEnsure your laptop / PC will run smoothly by goin g to http://websocketstest.com/ \n\nMake sure that WebSockets work for you by seeing under Environment\, WebSockets is supported and Data Receive\, Send and Echo Test all check Yes under WebSockets (Port 80). If there are issues with WebSockets\, try updating your browser. If you have any questi ons\, please contact Marjut Dieringer at mdieringer"at"nvidia.com. \n\nRE GISTRATION is OBLIGATORY since the details to access the online course wil l be provided to the registered and accepted attendees only. If you have r egistered to this course and you are not able to attend\, please CANCEL yo ur registration in advance by sending an email to patc@csc.fi\nhttps://eve nts.prace-ri.eu/event/1366/ SUMMARY:[ONLINE] Deep Learning and GPU Programming Workshop @ CSC URL;VALUE=URI:https://events.prace-ri.eu/event/1366/ END:VEVENT END:VCALENDAR