BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260705T020531Z UID:b0b3b90b-45f6-43da-964a-31a25c94b96d DTSTART:20210401T070000Z DTEND:20210402T143000Z DESCRIPTION:GPU programming using CUDA\n\n1 - 2 Apr. 2021\n\nDescription\n\ nThe focus of the training is to understand the basics of accelerator prog ramming with the CUDA parallel computing platform model. \n\nCUDA is a par allel computing platform and application programming interface (API) model created by NVIDIA. It allows software developers to use a CUDA-enabled gr aphics processing unit (GPU) for general purpose processing – an approac h known as GPGPU. The CUDA platform is a software layer that gives direct access to the GPU’s virtual instruction set and parallel computational e lements\, for the execution of compute kernels. \n\nThe course also contai ns performance and best practice considerations\, e.g.\, gpu libraries\, p erformance optimizations\, tools for debugging and profiling.\n\nParticipa nts will acquire the basic skills needed for utilizing CUDA in new or exis ting codes.\n\nThe training programme is comprised of short sessions\, whi le there will be time for Q&\;A.\n\nPrerequisites\n\nThe course is addr essed to people who are familiar with the C/C++ or Fortran programming lan guages and have working experience with the Linux operating system and the use of the command line. Experience with parallel programming or gpu prog ramming (MPI\,OpenMP and CUDA) is not required.\n\nCourse language is Engl ish.\n\nRegistration\n\nRegistrations will be evaluated on a first-come\, first-served basis. GRNET is responsible for the selection of the particip ants on the basis of the training requirements and the technical skills of the candidates. GRNET will also seek to guarantee the maximum possible g eographical coverage with the participation of candidates from many countr ies.\n\nConnection details will be mailed 2 days prior to the course. Sinc e the e-mail contains links\, please also check Spam folders.\n\n \n\nVen ue\n\nONLINE Using ZOOM\n\n \n\nTimetable:\n\n1 Apr. 2021\n\n10:00 - 10:3 0 : Opening\n\n10:30 - 11:00 : Introduction to PRACE\n\n11:00 - 13:30 : In troduction to GPU/Parallel computing (with breaks and Q&\;A)\n\n13:30 - 14:30 : Lunch Break\n\n14:30 - 17:30 : CUDA programming model (with break s and Q&\;A)\n\n \n\n2 Apr. 2021\n\n10:30 - 12:00 : Debuging - Profili ng (with breaks and Q&\;A)\n\n12:00 - 13:30 : Performance Optimizations (with breaks and Q&\;A)\n\n13:30 - 14:30 : Lunch Break\n\n14:30 - 17:0 0 : Libraries\, OpenACC (with breaks and Q&\;A)\n\nAbout Tutors\n\nDr. Dellis (Male) holds a B.Sc. in Chemistry (1990) and PhD in Computational C hemistry (1995) from the National and Kapodistrian University of Athens\, Greece. He has extensive HPC and grid computing experience. In EGEE/EGI pr ojects he acted as application support and VO software manager for SEE VO\ , grid sites administrator (HG-02\, GR-06)\, NGI_GRNET support staff (2008 -2014). In PRACE 1IP-6IP he was involved in benchmarking tasks either as g roup member or as BCO (2010-present). Currently he holds the position of “Head of HPC team” at GRNET S.A.\n\nDr. Ioannis E. Venetis received hi s PhD in 2006 from the Computer Engineering and Informatics Department at the University of Patras in Greece. Currently he is an Assistant Professor at the Informatics Department at the University of Piraeus in Greece\, wh ere he teaches\, among others\, "Parallel Computing". He has participated in numerous research projects in the area of Parallel Computing. His main research interests include parallel programming models\, run-time systems for supporting such models\, co-processor programming (especially using GP Us and the Intel Xeon Phi) and parallelization of computationally demandin g applications.\n\nAbout GRNET\n\nGRNET - National Infrastructures for Res earch and Technology\, provides advanced network\, cloud computing and IT infrastructures and services to academic and research institutions\, to ed ucational bodies at all levels\, as well as to agencies of the public\, br oader public and private sector. It holds a key role as the coordinator of all e-infrastructures in education and research\, leveraging the educatio nal and research activity in the country towards the development of applie d and technological research. GRNET\, supervised by the Ministry of Digita l Governance\, contributes to the country’s Digital Transformation via i n-depth analysis\, technological studies\, standard solutions and speciali zed know-how\, serving at the same time hundreds of thousands of users on a daily basis in the strategic fields of Public Administration\, Education \, Research\, Health and Culture.\n\nhttps://hpc.grnet.gr/ https://grnet.g r/\nhttps://events.prace-ri.eu/event/1189/ SUMMARY:[ONLINE] GPU programming using CUDA @GRNET URL;VALUE=URI:https://events.prace-ri.eu/event/1189/ END:VEVENT END:VCALENDAR