BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260708T065828Z UID:59bbb0cb-a7aa-4b81-929c-176c49d49d6c DTSTART:20190313T080000Z DTEND:20190314T150000Z DESCRIPTION:Accelerator Programming\nGPU programming using CUDA\n\n13 - 14 March 2019\n\nDescription\n\nThe focus is to understand the basics of acce lerator programming with the CUDA parallel computing platform model. \n\nC UDA is a parallel computing platform and application programming interface (API) model created by NVIDIA. It allows software developers to use a CUD A-enabled graphics processing unit (GPU) for general purpose processing – an approach known as GPGPU. The CUDA platform is a software layer that gives direct access to the GPU’s virtual instruction set and parallel c omputational elements\, for the execution of compute kernels. \n\nThe cour se also contains performance and best practice considerations\, e.g.\, gpu libraries\, performance optimizations\, tools for debugging and profiling .\n\nAfter the course the participants should have the basic skills needed for utilizing CUDA and OpenACC in new\, or existing (own code) programs.\ n\nPrerequisites\n\nThe course addresses participants who are familiar wit h the C/C++ or Fortran programming languages and have working experience w ith the Linux operating system and the use of the command line. Experience with parallel programming or gpu programming (MPI\,OpenMP and CUDA) is no t required.\n\nBring your own laptop in order to be able to participate in the training hands on. Hands on work will be done in pairs so if you don ’t have a laptop you might work with a colleague. \n\nCourse language is English.\n\nRegistration\n\nThe maximum number of participants is 25. \n\ nRegistrations will be evaluated on a first-come\, first-served basis. GRN ET is responsible for the selection of the participants on the basis of th e training requirements and the technical skills of the candidates. GRNET will also seek to guarantee the maximum possible geographical coverage wi th the participation of candidates from many countries.\n\nVenue\n\nGRNET headquarters\n\nAddress: 2nd  Floor\, 7\, Kifisias Av. GR 115 23 Athens\n \nInformation on how to reach GRNET headquarters ia available on GRNET web site: https://grnet.gr/en/contact-us/  \n\nAccommodation options near GR NET can be found at: https://grnet.gr/wp-content/uploads/sites/13/2015/11/ Hotels-near-GRNET-en.pdf\n\nARIS - System Information\n\nARIS is the name of the Greek supercomputer\, deployed and operated by GRNET (Greek Researc h and Technology Network) in Athens. ARIS consists of 532 computational no des seperated in four “islands” as listed here:\n\n\n \n 426 thin node s: Regular compute nodes without accelerator.\n \n \n 44 gpu nodes: “2 x NVIDIA Tesla k40m” accelerated nodes.\n \n \n 18 phi nodes: “2 x INTE L Xeon Phi 7120p” accelerated nodes.\n \n \n 44 fat nodes: Fat compute n odes have larger number of cores and memory per core than a thin node.\n \ n\n\nAll the nodes are connected via Infiniband network and share 2PB GPFS storage.The infrastructure also has an IBM TS3500 library of maximum stor age capacity of about 6 PB. Access to the system is provided by two login nodes. \n\nAbout Tutors\n\nDr. Dellis (Male) holds a B.Sc. in Chemistry (1 990) and PhD in Computational Chemistry (1995) from the National and Kapod istrian University of Athens\, Greece. He has extensive HPC and grid compu ting experience. He was using HPC systems in computational chemistry resea rch projects on fz-juelich machines (2003-2005). He received an HPC-Europa grant on BSC (2009). In EGEE/EGI projects 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/2IP/3IP/4IP/5IP h e was involved in benchmarking tasks either as group member or as BCO (201 0-2017). Currently he holds the position of “Senior HPC Applications Sup port Engineer” at GRNET S.A. where he is responsible for activities rela ted to user consultations\, porting\, optimization and running HPC applica tions at national and international resources.\n\nNikolaos Nikoloutsakos h olds a diploma of Engineering in Computer Engineering and Informatics (201 4) from the University of Patras\, Greece. From 2015 he works as software engineer at GRNET S.A. where he is part of the user application support te am for the ARIS HPC system. He has been involved in major national and Eur opean projects\, such as PRACE and EUDAT. His main research interests incl ude parallel programming models\, co-processor programming using GPUs and Intel Xeon Phis.\n\nDr. Ioannis E. Venetis received his PhD in 2006 from the Computer Engineering and Informatics Department at the University of P atras\, Greece. Currently he teaches "Parallel Processing" and "Software a nd Programming for High Performance Systems" at the same Department. He ha s participated in numerous research projects in the area of Parallel Compu ting. His main research interests include parallel programming models\, ru n-time systems for supporting such models\, co-processor programming (espe cially using GPUs and the Intel Xeon Phi) and parallelization of computati onally demanding applications. \n\nDr Aristeidis Sotiropoulos received his BSc in Computer Science in 1998 from the University of Crete\, Greece and his PhD in Parallel Processing and Cluster Computing in 2004 from the Nat ional Technical University of Athens\, Greece. His interests mainly focus on the fields of Large Scale Computing &\; Storage Systems\, System Sof tware for Scalable High Speed Interconnects for Computer Clusters and Adva nced Microprocessor Architectures. He has published several scientific pap ers in international journals and conference proceedings. He has received the IEEE IPDPS 2001 best paper award for the paper "Minimizing Completion Time for Loop Tiling with Computation and Communication Overlapping". He h as worked in several European and National R&\;D programs in the field of High Performance Computing\, Grid Computing\, Cloud Computing and Stora ge. In 2013\, he was appointed as the Head of Operations and Financial Man agement Services\, in charge of 15 people. Currently\, he is managing EC p rojects at GRNET SA\, the Greek NREN responsible for the provision of adva nced e-infrastructure services to the Greek Academic and Research Communit y.\n\nAbout GRNET\n\nGRNET provides Internet connectivity\, high-quality e -Infrastructures and advanced services to the Greek Educational\, Academic and Research community.\n\nThrough its high-speed\, high-capacity infrast ructure that spans across the entire country\, GRNET interconnects more th an 150 institutions\, including all universities and technological institu tions\, as well as many research institutes and the public Greek School Ne twork.\n\nGRNET operates the National High Performance Computing system (a Tier-1 in the European HPC ecosystem) and offers user and application sup port services\, that provide Greek scientists with the computing infrastru cture and expertise they need for their research enabling them to perform large scale simulations.\n\nGRNET offers innovative IaaS cloud computing s ervices to the Greek and global research &\; education communities: “ ~okeanos” and “okeanos global” allow users to create multi-layer vi rtual infrastructure and instantiate virtual computing machines\, local ne tworks to interconnect them\, and a reliable storage space within seconds\ , with few\, simple mouse clicks.\n\nGRNET aims at contributing towards Gr eece’s Digital Convergence with the EU\, by supporting the development a nd encouraging the use of e-Infrastructures and services. The right and ti mely planning strategies\, together with the long experience and know-how of its people\, guarantee the continuation and enhancement of GRNET’s su ccessful course.\n\nGreek Research and Technology Network – Networking R eserach and Education:\n\nwww.grnet.gr\, hpc.grnet.gr\nhttps://events.prac e-ri.eu/event/796/ SUMMARY:Accelerator Programming @GRNET URL;VALUE=URI:https://events.prace-ri.eu/event/796/ END:VEVENT END:VCALENDAR