PRACE

Partnership for Advanced Computing in Europe

PRACE https://tess.oerc.ox.ac.uk/content_providers/prace Partnership for Advanced Computing in Europe /system/content_providers/images/000/000/043/original/1c2d412b-c20c-43b8-926d-6febf042f341?1516903802
Found 0 materials.
Showing 30 upcoming events out of 40. Found 433 past events. View all results.
  • Data Analytics with HPC @ EPCC at Queen's University Belfast

    28 February - 1 March 2018

    Data Analytics with HPC @ EPCC at Queen's University Belfast https://tess.oerc.ox.ac.uk/events/data-analytics-with-hpc-epcc-at-queen-s-university-belfast Unfortunately we have had to cancel the upcoming run of the Data Analytics with HPC course, 28 Feb - 1 Mar, due to the national strike action recently called by the University and College Union. We plan to reschedule the course in Belfast for a later date, probably in May or June - those already registered will have priority for places. We will keep you updated by email, or keep an eye on www.archer.ac.uk/training/. Apologies for any inconvenience   This course will take place at Queen's University Belfast. Data Analytics, Data Science and Big Data are a just a few of the many terms used in business and academic research. These refer to the manipulation, processing and analysis of data and are concerned with the extraction of knowledge from data whether for competitive advantage or to provide scientific insight. In recent years, this area has undergone a revolution in which HPC has been a key driver. This course provides an overview of data science and the analytical techniques that form its basis as well as exploring how HPC provides the power that has driven their adoption. The course will cover: key data analytical techniques such as, classification, optimisation, and unsupervised learning; key parallel patterns, such as Map Reduce, for implementing analytical techniques. Attendees should be familiar with basic Linux bash shell commands and have some previous experience with Python programming. Attendees will be given temporary access to the Data Analytics Cluster on ARCHER so will not require to have Python installed on their laptops, but will require the ability to use an ssh connection (using e.g. terminal (Mac/Linux) or putty (Win)) Timetable Below is a timetable from a previous run of this course - details may be subject to change. Day 1 09:00 – 09:30 Arrival/set-up/Welcome 09:30 – 10:30 What are data analytics, big data, data science 10:30 – 11:00 COFFEE 11:00 – 12:00 Data Cleaning 12:00 – 13:00 Practical: Data Cleaning 13:00 – 14:00 LUNCH 14:00 – 14:45 Supervised Learning, feature selection, trees, forests 14:45 – 15:30 Naïve Bayes 15:30 – 16:00 COFFEE 16:00 – 17:00 Naïve Bayes Practical 17:00 -  CLOSE OF DAY Day 2 09:00 – 10:00 Unsupervised learning 10:00 – 10:30 MapReduce 10:30 – 11:00 COFFEE 11:00 – 12:00 MapReduce/Hadoop 12:00 – 12:30 Hadoop demonstrations 12:30 – 13:30 LUNCH 13:30 – 14:15 Spark 14:15 – 14:45 Spark demonstration 14:45 – 15:15 COFFEE 15:15 – 16:00 Data streaming 16:00 – CLOSE OF COURSE Location details including travel directions and maps : http://www.archer.ac.uk/training/locations/ubelfast.php Course material : http://www.archer.ac.uk/training/course-material/2018/02/data-an-belfast/index.php   Trainer Terry Sloan Terry originally joined EPCC in 1994 and holds the position of Group Manager within EPCC’s Software Development Group. He has extensive experience of managing novel, HPC and Grid projects for Scottish SMEs, UK corporations, European and global collaborations. https://events.prace-ri.eu/event/695/ 2018-02-28 09:00:00 UTC 2018-03-01 17:30:00 UTC [] [] workshops_and_courses [] []
  • OpenMP GPU Directives for Parallel Accelerated Supercomputers - an alternative to CUDA from Cray perspective @ HLRS

    12 - 13 March 2018

    OpenMP GPU Directives for Parallel Accelerated Supercomputers - an alternative to CUDA from Cray perspective @ HLRS https://tess.oerc.ox.ac.uk/events/openmp-gpu-directives-for-parallel-accelerated-supercomputers-an-alternative-to-cuda-from-cray-perspective-hlrs-11c22c40-635f-49a2-8c3d-f6b23b9d4566 Overview This workshop will cover the directive-based programming model based on OpenMP v4 whose multi-vendor support allows users to portably develop applications for parallel accelerated supercomputers. It also includes comparison to the predecessor interface OpenACC v2. The workshop will also demonstrate how to use the Cray Programming Environment tools to identify application bottlenecks, facilitate the porting, provide accelerated performance feedback and to tune the ported applications. The Cray scientific libraries for accelerators will be presented, and interoperability of the directives approach with these and with CUDA will be demonstrated. Through application case studies and tutorials, users will gain direct experience of using both OpenMP and OpenACC directives in realistic applications. Users may also bring their own codes to discuss with Cray specialists or begin porting. This course provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves. For further information and registration please visit the HLRS course page. https://events.prace-ri.eu/event/684/ 2018-03-12 08:00:00 UTC 2018-03-13 15:30:00 UTC [] [] workshops_and_courses [] []
  • Parallel I/O and Portable Data Formats @ JSC

    12 - 14 March 2018

    Parallel I/O and Portable Data Formats @ JSC https://tess.oerc.ox.ac.uk/events/parallel-i-o-and-portable-data-formats-jsc-e29e6043-1eb2-43d8-882c-321e7eb198c6 Numerical simulations conducted on current high-performance computing (HPC) systems face an ever growing need for scalability. Larger HPC platforms provide opportunities to push the limitations on size and properties of what can be accurately simulated. Therefore, it is needed to process larger data sets, be it reading input data or writing results. Serial approaches on handling I/O in a parallel application will dominate the performance on massively parallel systems, leaving a lot of computing resources idle during those serial application phases. In addition to the need for parallel I/O, input and output data is often processed on different platforms. Heterogeneity of platforms can impose a high level of maintenance, when different data representations are needed. Portable, selfdescribing data formats such as HDF5 and netCDF are examples of already widely used data formats within certain communities. This course will start with an introduction to the basics of I/O, including basic I/O-relevant terms, an overview over parallel file systems with a focus on GPFS, and the HPC hardware available at JSC. Different I/O strategies will be presented. The course will introduce the use of the HDF5, the NetCDF (NetCDF4 and PnetCDF) and the SIONlib library interfaces as well as MPI-I/O. Optimization potential and best practices are discussed. Prerequisites: Experience in parallel programming with MPI, and either C/C++ or Fortran in particular. Application Registrations are only considered until 1 March 2018 due to available space, the maximal number of participants is limited. Applicants will be notified, whether they are accepted for participitation. Instructors: Sebastian Lührs, Dr. Michael Stephan, Benedikt Steinbusch, Dr. Kay Thust, JSC Contact For any questions concerning the course please send an e-mail to s.luehrs@fz-juelich.de. https://events.prace-ri.eu/event/704/ 2018-03-12 08:00:00 UTC 2018-03-14 15:30:00 UTC [] [] workshops_and_courses [] []
  • Hands-on Porting and Optimisation Workshop: Making the most of ARCHER @ EPCC at University of Oxford

    8 March 2018

    Hands-on Porting and Optimisation Workshop: Making the most of ARCHER @ EPCC at University of Oxford https://tess.oerc.ox.ac.uk/events/hands-on-porting-and-optimisation-workshop-making-the-most-of-archer-epcc-at-university-of-oxford Hands-on Porting and Optimisation Workshop: Making the most of ARCHER ARCHER, the UK's national supercomputing service, offers training in software development and high-performance computing to scientists and researchers across the UK. As part of our training service we are running a 1-day hands-on workshop on Porting and Optimisation at the University of Oxford on Thursday March 8th (9:30 - 16:30). Details Instead of a typical ARCHER course consisting of alternating lectures + practicals, this workshop is designed to provide an opportunity for attendees to gain individually tailored hands-on help and advice from the ARCHER team / HPC specialists and to ask questions pertaining directly to your use of ARCHER. Each attendee will be assigned a technical advisor. This advisor will work closely with you throughout the day to help run your application and any associated essential software on ARCHER and to advise on how the system can be used most efficiently, to help evaluate the application's performance (providing guidance on the use of available tools if appropriate), and to suggest possible changes that could be made to the code to improve its performance. The workshop is aimed at: Potential future users of the service looking to understand whether ARCHER is suitable for their computing needs and could potentially accelerate their research. New users of the ARCHER service looking to port existing software - be it their own code or a third-party application - to run on the machine for the first time or to explore its performance prior to an application for ARCHER time. Current users of the ARCHER service looking to improve the performance of their code, e.g. parallel scaling and/or IO, in order to make more efficient use of the machine. Users who want to learn more about data management or using the RDF (Research Data Facility) and how this can help their work on ARCHER. The workshop is not restricted to current users; it is open to anyone interested in using ARCHER. We encourage applications from small teams of collaborators whose current or future use of ARCHER is based on one particular application. As the workshop is tailored to individual participants we can cater to the needs of attendees from a wide range of previous experiences with high-performance computing. This course is free to all. Attendees will be given access to ARCHER for the duration of the workshop.Please note you will be required to bring your own laptop in order to connect to ARCHER as no desktop computers will be provided. If you are not familiar with ARCHER we encourage you to look at the online training material available here in advance of the workshop to ensure you gain the maximum benefit from the day. This material also prepares you for the online ARCHER driving test, which allows you to access the system with your own account and a time allocation independently of the workshop. Timetable Scheduled start and end times and breaks are given in the timetable below. The activities pursued during the workshop and their timings will vary depending on what you are looking to achieve and in consultation with your ARCHER advisor. The timetable shows the range of possible activities that could be undertaken as well as an example of how these might progress during the day. 09:30 Welcome 09:50 Introduction 10:00 Meet your helper 10:15 Porting, initial performance measurements 11:00 Coffee break 11:20 Exploration of runtime optimisations and efficient use of the machine 12:30 Lunch break 13:30 Detailed performance measurements, profiling 15:00 Coffee break 15:30 Profiling analysis and consultation on potential code optimisations 16:30 End Location For more location information including maps and advice on travel please see our  University of Oxford page. Trainer Arno Proeme Arno has taught on and organised a range of High Performance Computing and Software Carpentry courses, including training in HPC aimed at meeting the needs of researchers in the life sciences. He organises an annual ARCHER workshop on porting and optimisation, and is also a course organiser on EPCC's MSc in High Performance Computing.  Registration Please use the registration link at the left. Once you have registered, you will receive a follow up email with a request to provide the following information: Name of your application / code of interest and any other essential software (if applicable) What you want to achieve on the day Whether you are part of a small team that has decided to attend the workshop together Note: it is crucial that you respond to this email and provide the requested information to ensure the workshop meets your needs and in order to allow us to plan and allocate technical staff to advise you appropriately. If you are part of a small team applying for the workshop all team members should register individually. Questions? If you have any questions please contact the ARCHER Helpdesk. https://events.prace-ri.eu/event/700/ 2018-03-08 09:00:00 UTC 2018-03-08 16:30:00 UTC [] [] workshops_and_courses [] []
  • Object-Oriented Programming with Fortran @ EPCC at STFC Daresbury

    27 - 28 February 2018

    Object-Oriented Programming with Fortran @ EPCC at STFC Daresbury https://tess.oerc.ox.ac.uk/events/object-oriented-programming-with-fortran-epcc-at-stfc-daresbury Object-Oriented Programming with Fortran This course provides an introduction to Object-Oriented Programming (OOP) with Fortran. Fortran is often used for scientific applications, but applications are mainly developed using the standard procedural programming techniques that Fortran was initially designed for. OOP is a programming methodology designed to enable safe and reusable programming, coupling procedures with the data they operate on in classes and using them as objects. More commonly associated with large programs, and programs written in industry/companies, there are many scientific applications that become very large and long-lived and therefore could benefit from such programming techniques to make development, maintenance, and extension of the code simpler and safer. Whilst Fortran is generally viewed as a procedural programming language there are features in the most recent versions of the Fortran standards (90, 95, and 2003) that enable development in OOP or OOP-like ways. We will introduce these language features and discuss/explore how they can be used in scientific applications. Familiarity with a Unix or Linux environment is assumed, and some experience with Fortran is advisable for getting the most out of the course material.   Trainer Adrian Jackson Adrian Jackson is a Research Architect at EPCC, where he works on a range of different research, from investigating new memory hardware and programming models, to optimising and porting parallel codes, and working with application scientists to enable their computational simulation or data analysis. He also teaches on EPCC's MSc in HPC, giving lectures on Programming Skills, HPC Architecture, and Performance Programming.   Details Topics include: object-oriented programming, fortran modules, datatypes, polymorphic variables and procedures, constructors and destructors, and inheritance. Intended learning outcomes On completion of this course students should be able to: Develop modularised Fortran programs. Define new datatypes and operators in Fortran. Understand basic OO concepts and strategies. Develop OO programs in Fortran. Compile and run Fortran programs on ARCHER. Understand basic design trade-offs for OOP in Fortran. Prerequisites Whilst there are no prerequisites for this course, a familiarity with a Unix or Linux environment is assumed and to fully benefit from the course some familiarity with Fortran programming would be beneficial. Timetable Details are subject to change, but start, end and break times will stay the same. Day 1 09:30 Introduction to Fortran 10:15 PRACTICAL: Fortran programming 11:00 BREAK 11:30 Introduction to Object Oriented Programming 12:00 PRACTICAL: Designing an object oriented program 12:15 Modules 13:00 BREAK: Lunch 14:00 PRACTICAL: Modules 14:30 Derived types and operators 15.00 PRACTICAL: Derived types 15:30 BREAK 16:00 PRACTICAL: Continuing practicals 16:30 CLOSE Day 2 09:30 Classes and data visibility 10:15 PRACTICAL: Fortran classes 11:15 BREAK 11:45 Inheritance and overloading 12.30 PRACTICAL: Generic classes and extensions 13.00 BREAK: Lunch 14.00 Design and performance considerations 14.45 PRACTICAL: Continuing practicals 15:15 BREAK 15:45 Further features 16:15 Summary 16:30 CLOSE Course Materials Slides and exercise material for this course are available here. https://events.prace-ri.eu/event/714/ 2018-02-27 09:00:00 UTC 2018-02-28 16:30:00 UTC [] [] workshops_and_courses [] []
  • Introduction to Parallel Programming with HPX @ HLRS

    15 - 16 March 2018

    Introduction to Parallel Programming with HPX @ HLRS https://tess.oerc.ox.ac.uk/events/introduction-to-parallel-programming-with-hpx-hlrs Overview The aim of this course is to introduce participants to the HPX library (https://github.com/STEllAR-GROUP/hpx and http://stellar-group.org/) and demonstrate how it can be used to write task based programs. The HPX library implements a lightweight threading model that allows both concurrent, asynchronous, parallel and distributed programming constructs to coexist within the same application with a consistent API based on C++ standards and using futures to synchronize between tasks. The course is aimed at participants with a good understanding of C++. The material covered will include an introduction to the HPX programming model; asynchronous programming concepts, execution policies and executors; parallel algorithms using tasks (including the parallel STL); writing distributed applications with HPX; profiling and debugging and a final section introducing heterogeneous programming using targets for GPU devices. Objective: The attendee will gain an understanding of the HPX library and task based programming in general For further information and registration please visit the HLRS course page. https://events.prace-ri.eu/event/685/ 2018-03-15 08:00:00 UTC 2018-03-16 14:30:00 UTC [] [] workshops_and_courses [] []
  • Efficient Parallel IO on ARCHER @ EPCC at Cambridge

    20 - 21 March 2018

    Efficient Parallel IO on ARCHER @ EPCC at Cambridge https://tess.oerc.ox.ac.uk/events/efficient-parallel-io-on-archer-epcc-at-cambridge Please note:  This course takes place in Cambridge. One of the greatest challenges to running parallel applications on large numbers of processors is how to handle file IO. Standard IO routines are not designed with parallelism in mind, and IO overheads can grow to dominate the overall runtime. Parallel file systems are optimised for large data transfers, but performance can be far from optimal if every process opens its own file or if all IO is funneled through a single master process. This hands-on course explores a range of issues related to parallel IO. It uses ARCHER and its parallel Lustre file system as a platform for the exercises; however, almost all the IO concepts and performance considerations are applicable to any parallel system. The IO part of the MPI standard gives programmers access to efficient parallel IO in a portable fashion. However, there are a large number of different routines available and some can be difficult to use in practice. Despite its apparent complexity, MPI-IO adopts a very straightforward high-level model. If used correctly, almost all the complexities of aggregating data from multiple processes can be dealt with automatically by the library. The first day of the course will cover the MPI-IO standard, developing IO routines for a regular domain decomposition example. It will also briefly cover higher-level standards such as HDF5 and NetCDF which are built on top of MPI-IO. The second day will concentrate on performance, covering how to configure the parallel file system and tune the MPI-IO library for best performance. Case studies from real codes will be presented. Prerequisites: The course assumes a good understanding of basic MPI programming in Fortran, C or C++. Knowledge of MPI derived datatypes would be useful but not essential. Timetable Day 1 09:30 - 10:15 : Parallel IO 10:15 - 11:00 : Practical : Basic IO 11:00 - 11:30 : Break 11:30 - 12:15 : Derived Datatypes for MPI-IO 12:15 - 13:00 : Practical: Derived Datatypes 13:00 - 14:00 : Lunch 14:00 - 14:45 : Basic MPI-IO Routines 14:45 - 15:30 : Practical: Basic MPI-IO 15:30 - 16:00 : Break 16:00 - 16:45 : MPI-IO Features and alternative libraries 16:45 - 17:30 : Practical : Alternative Libraries Day 2 09:30 - 10:15 : Lustre file system on ARCHER 10:15 - 11:00 : Practical: Lustre configuration 11:00 - 11:30 : Break 11:30 - 12:15 : Parallel IO libraries on ARCHER 12:15 - 13:00 : Practical: tuning parallel IO 13:00 - 14:00 : Lunch 14:00 - 14:45 : Case studies 14:45 - 15:30 : Individual consultancy session   Course Materials : http://www.archer.ac.uk/training/course-material/2018/03/parallel-io-camb/index.php Trainer David HentyDavid teaches on a wide range of EPCC's technical training courses, including MPI and OpenMP, and is overall course organiser for EPCC's MSc in High Performance Computing. https://events.prace-ri.eu/event/696/ 2018-03-20 09:30:00 UTC 2018-03-21 17:30:00 UTC [] [] workshops_and_courses [] []
  • GPU Programming with CUDA @ JSC

    23 - 25 April 2018

    GPU Programming with CUDA @ JSC https://tess.oerc.ox.ac.uk/events/gpu-programming-with-cuda-jsc-6fbf484a-4a2c-4e94-9c48-3eff63c78b88 GPU-accelerated computing drives current scientific research. Writing fast numeric algorithms for GPUs offers high application performance by offloading compute-intensive portions of the code to an NVIDIA GPU. The course will cover basic aspects of GPU architectures and programming. Focus is on the usage of the parallel programming language CUDA-C which allows maximum control of NVIDIA GPU hardware. Examples of increasing complexity will be used to demonstrate optimization and tuning of scientific applications. Topics covered will include: Introduction to GPU/Parallel computing Programming model CUDA GPU libraries like CuBLAS and CuFFT Tools for debugging and profiling Performance optimizations Prerequisites: Some knowledge about Linux, e.g. make, command line editor, Linux shell, experience in C/C++ Application Registrations are only considered until 31 March 2018 due to available space, the maximal number of participants is limited. Applicants will be notified, whether they are accepted for participitation. Instructors: Dr. Jan Meinke, Jochen Kreutz, Dr. Andreas Herten, JSC; Jiri Kraus, NVIDIA Contact For any questions concerning the course please send an e-mail to j.meinke@fz-juelich.de https://events.prace-ri.eu/event/705/ 2018-04-23 07:00:00 UTC 2018-04-25 14:30:00 UTC [] [] workshops_and_courses [] []
  • Advanced Threading and Optimization @ CSC

    4 - 6 April 2018

    Advanced Threading and Optimization @ CSC https://tess.oerc.ox.ac.uk/events/advanced-threading-and-optimization-csc-7e897667-6d1f-4e58-b4a5-1bdcbad35208 Description The course includes topics on code optimization for x86 platforms and efficient code parallelisation using OpenMP threading. Advanced aspects of threading and optimization, such as new features in OpenMP 4.5, will be covered during the course. Some performance aspects of hybrid MPI+OpenMP programs will also be discussed. Learning outcome Awareness of modern features of x86 CPUs Ability to vectorize computations Ability to use advanced features of OpenMP Ability to increase code performance using threading and x86 optimization Prerequisites Good knowledge of C/C++ or Fortran Good knowledge of threading using OpenMP Basic knowledge of MPI Basic knowledge of modern CPU architectures Agenda Day 1: Wednesday, April 4 Course introduction Performance analysis methods and tools Vectorization using SIMD Day 2: Thursday, April 5 More about SIMD vectorization Optimizing memory accesses Day 3: Friday, April 6 Advanced OpenMP features OpenMP performance considerations Hybrid MPI and OpenMP Lecturers:   Sami Ilvonen (CSC), Mikko Byckling (Intel) Language:  English Price:          Free of charge https://events.prace-ri.eu/event/718/ 2018-04-04 06:00:00 UTC 2018-04-06 13:00:00 UTC [] [] workshops_and_courses [] []
  • Systems Workshop: Programming MareNostrum 4 @ BSC

    9 - 10 April 2018

    Systems Workshop: Programming MareNostrum 4 @ BSC https://tess.oerc.ox.ac.uk/events/systems-workshop-programming-marenostrum-4-bsc-c7ce552e-a3bc-440e-9cf6-6ff9cad5a560 The registration to this course will open on January 2018. Please, bring your own laptop.  All the PATC courses at BSC are free of charge. Course convener: David Vicente  Objectives: The objective of this course is to present to potential users the new configuration of MareNostrum and a introduction on how to use the new system (batch system, compilers, hardware, MPI, etc).Also It will provide an introduction about RES and PRACE infrastructures and how to get access to the supercomputing resources available. Learning Outcomes: The students who finish this course will know the internal architecture of the new MareNostrum, how it works, the ways to get access to this infrastructure and also some information about optimization techniques for its architecture. Level: INTERMEDIATE -for trainees with some theoretical and practical knowledge; those who finished the beginners course. Prerequisites:  Any potential user of a HPC infrastructure will be welcome Agenda: DAY 1 09:00 Introduction to BSC, PRACE PATC and this training - David Vicente 09:30 MareNostrum 4 – the view from System administration group - Javier Bartolomé 10:30 Coffee break 11:00 Visualization at BSC - Carlos Tripiana 11:30 How to use MareNostrum 4: BASIC Things, BATCH system, Filesystems, Compilers, Modules, DT, DL, BSC commands - Miguel Bernabeu, Borja Arias 12:15 Hands-on I - Miguel Bernabeu, Borja Arias 13:00 Lunch (not hosted) 14:30 How to use MN3 – Advanced I MPI implementations (PR), MPI IO (PR), Tuning MPI values for different applications (DV)  - Pablo Ródenas, Janko Strassburg, David Vicente 15:15 Hands-on II - Pablo Ródenas, David Vicente 16:00 Coffee break 16:15 How to use MN4 – Advanced II GREASY (PR), MIC (JR), Mathematical libraries MKL (JR) - Pablo Ródenas, Jorge Rodríguez 17:00 End of the first day DAY 2 09:00 You choose! - MareNostrum 4 visit (In the chapel) - Doubts + Hands ON + Tunning your app (In the classroom) - David Vicente, Jorge Rodríguez 09:30 How can I get resources from you? - RES Jorge Rodríguez 10:00 How can I get Resources from you? - PRACE Janko Strassburg 10:30 Coffee break 11:00 Use case: Genomics - Miguel Bernabeu 11:25 Tuning applications   BSC performance tools (Extrae and Paraver) - BSC Tools Team 12:00 Hands-on III – Performance tools and tunning your application - BSC Tools Team 13:00 Wrap-up : Can we help you in your porting ? How ? when ? - David Vicente   13:30 END of COURSE https://events.prace-ri.eu/event/646/ 2018-04-09 08:00:00 UTC 2018-04-10 11:30:00 UTC [] [] workshops_and_courses [] []
  • Fortran for Scientific Computing @ HLRS

    9 - 13 April 2018

    Fortran for Scientific Computing @ HLRS https://tess.oerc.ox.ac.uk/events/fortran-for-scientific-computing-hlrs-3e0916b3-a2e9-4a81-b974-c33cfe38a66f Overview This course is dedicated to scientists and students to learn (sequential) programming with Fortran of scientific applications. The course teaches newest Fortran standards. Hands-on sessions will allow users to immediately test and understand the language constructs. This workshop provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves. Only the last three days of this course are sponsored by the PATC project. For further information and registration please visit the HLRS course page. https://events.prace-ri.eu/event/688/ 2018-04-09 06:30:00 UTC 2018-04-13 13:30:00 UTC [] [] workshops_and_courses [] []
  • VI-HPS Tuning Workshop @ LRZ

    23 - 27 April 2018

    VI-HPS Tuning Workshop @ LRZ https://tess.oerc.ox.ac.uk/events/vi-hps-tuning-workshop-lrz     Goals This workshop organized by VI-HPS, LRZ and IT4Innovations for the PRACE Advanced Training Centre (PATC) at LRZ will: give an overview of the VI-HPS programming tools suite explain the functionality of individual tools, and how to use them effectively offer hands-on experience and expert assistance using the tools To foster the Czech-German collaboration in high performance computing, a contingent of places has been reserved for participants from the Czech Republic. Programme Overview The detailed program will be available on the VI-HPS training web site. Presentations and hands-on sessions are planned on the following topics (tbc.) Setting up, welcome and introduction Score-P instrumentation and measurement Scalasca automated trace analysis TAU performance system Vampir interactive trace analysis Periscope/PTF automated performance analysis and optimisation Extra-P automated performance modeling Paraver/Extrae/Dimemas trace analysis and performance prediction [k]cachegrind cache utilisation analysis MAQAO performance analysis & optimisation MUST runtime error detection for MPI ARCHER runtime error detection for OpenMP JUBE script-based workflow execution environment ... and potentially others to be added A brief overview of the capabilities of these and associated tools is provided in the VI-HPS Tools Guide. The workshop will be held in English and run from 09:00 to not later than 18:00 each day, with breaks for lunch and refreshments. For participants from public research institutions in PRACE countries, the course fee is sponsored through the PRACE PATC program. All participants are responsible for their own travel and accommodation. A social event for participant and instructor networking is planned for the evening on Tuesday 24 April, consisting of a guided tour of the Weihenstephan Brewery followed by a self-paid dinner at the brewery restaurant (tbc.). Classroom capacity is limited, therefore priority may be given to applicants with parallel codes already running on the workshop computer system (CooLMUC3), and those bringing codes from similar Xeon Phi x86 cluster systems to work on. Participants are therefore encouraged to prepare their own MPI, OpenMP and hybrid MPI+OpenMP parallel application codes for analysis.   Picture: Participants of the 21st VI-HPS Tuning Workshop at LRZ in April 2016. Hardware Platform CooLMUC3: KNL-based x86 Linux cluster system: 148 compute nodes each with single Intel Xeon Phi 7210-F 'Knights Landing' MIC processors (1.3GHz, 64 cores per processor, 4 hardware threads per core) and 96GB RAM and 16GB HBM cluster modes: quad, snc2, snc4, a2a, hemi memory modes: flat, cache, hybrid network: Intel OmniPath interconnect parallel filesystem: GPFS (SCRATCH & WORK) software: SLES12-based GNU/Linux, Intel MPI; Intel, GCC and other compilers; SLURM batchsystem The local HPC system CooLMUC3 is the primary platform for the workshop and will be used for the hands-on exercises. Course accounts will be provided during the workshop to participants without existing accounts. Other systems where up-to-date versions of the tools are installed can also be used when preferred, though support may be limited and participants are expected to already possess user accounts on non-local systems. Regardless of whichever systems they intend to use, participants should be familiar with the relevant procedures for compiling and running their parallel applications (via batch queues where appropriate). Registration Via https://events.prace-ri.eu/event/648/registration/register Location, Transport and Accommodation The workshop will be held in Leibniz Rechenzentrum on the university campus outside Garching bei München, approximately 25 min north from the city centre of Munich. The U-bahn line U6 (station: Garching-Forschungszentrum) provides direct connection from the campus area to both Munich and Garching.Getting to/from LRZ It is recommended to choose a hotel in Garching or Munich city centre and use the U-bahn to reach LRZ.Accommodation in GarchingAccommodation in Munich https://events.prace-ri.eu/event/648/ 2018-04-23 08:00:00 UTC 2018-04-27 15:00:00 UTC [] [] workshops_and_courses [] []
  • Introduction to CUDA Programming @ BSC

    16 - 20 April 2018

    Introduction to CUDA Programming @ BSC https://tess.oerc.ox.ac.uk/events/introduction-to-cuda-programming-bsc-de48a94f-fd0b-4316-a4e3-e4177aa740bd The registration to this course will open in Jaunary. All PATC Courses at BSC do not charge fees. PLEASE BRING YOUR OWN LAPTOP. Local Web Page:   This course will provide very good introduction to the PUMPS Summer School run jointly with NVIDIA -also  at Campus Nord, Barcelona. For further information visit the school website  as this school has attendee selection process. You may also be interested in our Introduction to OpenACC course. Convener:  Antonio Pena, BSC Acting Director, NVIDIA GPU Center of Excellence Objectives:  The aim of this course is to provide students with knowledge and hands-on experience in developing applications software for processors with massively parallel computing resources. In general, we refer to a processor as massively parallel if it has the ability to complete more than 64 arithmetic operations per clock cycle. Many commercial offerings from NVIDIA, AMD, and Intel already offer such levels of concurrency. Effectively programming these processors will require in-depth knowledge about parallel programming principles, as well as the parallelism models, communication models, and resource limitations of these processors. Agenda to be announced shortly. The target audiences of the course are students who want to develop exciting applications for these processors, as well as those who want to develop programming tools and future implementations for these processors. Level: (All courses are designed for specialists with at least 1st cycle degree or similar background experience) BEGINNERS: for trainees from different background or very little knowledge. Agenda: Day 1 (April, 16) 09:00 – 10:45 The GPU hardware: Many-core Nvidia developments (MU) 10:45 – 11:15 Coffee break 11:15 – 13:00 CUDA Programming: Threads, blocks, kernels, grids (MU) 13:00 – 14:00 Lunch break 14:00 – 15:45 CUDA Tools: Compiling, debugging, profiling, occupancy calculator (MU) 15:45 – 16:15 Coffee break 16:15 - 18:00 CUDA Examples (1): VectorAdd, Stencil, ReverseArray (MU) 18:00 Adjourn   Day 2 (April, 17) 09:00 – 10:45 CUDA Examples (2): Matrices Multiply. Assorted optimizations (MU) 10:45 – 11:15 Coffee break 11:15 – 13:00 Inside Kepler and Maxwell: Dynamic parallelism, Hyper-Q, unified memory (MU) 13:00 – 14:00 Lunch break 14:00 – 15:45 Hands-on Lab 15:45 – 16:15 Coffee break 16:15 – 18:00 Hands-on Lab 18:00 Adjourn   Day 3 (April, 18) 09:00 – 10:45 Inside Pascal and Volta: Stacked memory, NV-link, tensor cores (MU) 10:45 – 11:15 Coffee break 11:15 – 13:00 OpenACC and other approaches to GPU computing. Bibliography (MU) 13:00 – 14:00 Lunch break 14:00 – 15:45 Hands-on Lab 15:45 – 16:15 Coffee break 16:15 – 18:00 Hands-on Lab 18:00 Adjourn   Day 4 (April, 19) 09:00 – 10:45 Atomics and Histogramming 10:45 – 11:15 Coffee break 11:15 – 13:00 Reduction operators 13:00 – 14:00 Lunch break 14:00 – 15:45 Hands-on Lab 15:45 – 16:15 Coffee break 16:15 – 18:00 Hands-on Lab 18:00 Adjourn   Day 5 (April, 20) 09:00 – 10:45 Lab: Prefix Scan 10:45 – 11:15 Coffee break 11:15 – 13:00 CUDA Streams 13:00 – 14:00 Lunch break 14:00 – 15:45 Hands-on Lab 15:45 – 16:15 Coffee break 16:15 – 18:00 Hands-on Lab 18:00 Adjourn   End of Course   MU: Manuel Ujaldón (Full Professor of Computer Architecture and former Nvidia CUDA Fellow)         https://events.prace-ri.eu/event/652/ 2018-04-16 07:00:00 UTC 2018-04-20 16:00:00 UTC [] [] workshops_and_courses [] []
  • Programming paradigms for GPU devices@Cineca

    18 - 20 April 2018

    Programming paradigms for GPU devices@Cineca https://tess.oerc.ox.ac.uk/events/programming-paradigms-for-gpu-devices-cineca This course gives an overview of the most relevant GPGPU computing techniques to accelerate computationally demanding tasks on HPC heterogeneous architectures based on GPUs. The course will start with an architectural overview of modern GPU based heterogeneous architectures, focusing on its computing power versus data movement needs. The course will cover both a high level (pragma-based) programming approach with OpenACC for a fast porting startup, and lower level approaches based on nVIDIA CUDA and OpenCL programming languages for finer grained computational intensive tasks. A particular attention will be given on performance tuning and techniques to overcome common data movement bottlenecks and patterns. Topics: Overview of architectural trends of GPUs in HPC. GPGPU parallel programming in heterogeneous architectures. Basis of OpenACC, CUDA and OpenCL programming. Skills: By the end of the course, students will be able to: understand the strengths and weaknesses of GPUs as accelerators program GPU accelerated applications using both higher and lower level programming approaches overcome problems and bottlenecks regarding data movement between host and device memories make best use of independent execution queues for concurrent computing/data-movement operations Target Audience: Researchers and programmers interested in porting scientific applications or use efficient post-process and data-analysis techniques in modern heterogeneous HPC architectures. Prerequisites: A basic knowledge of C or Fortran is mandatory. Programming and Linux or Unix. A basic knowledge of any parallel programming technique/paradigm is recommended. Grant: The lunch for the three days will be offered to all the participants and some grants are available. The only requirement to be eligible is to be not funded by your institution to attend the course and to work or live in an institute outside the Bologna area. The grant  will be 300 euros for students working and living outside Italy and 150 euros for students working and living in Italy (outside Bologna). Some documentation will be required and the grant will be paid only after a certified presence of minimum 80% of the lectures. Further information about how to request the grant, will be provided at the confirmation of the course: about 3 weeks before the starting date. https://events.prace-ri.eu/event/715/ 2018-04-18 07:00:00 UTC 2018-04-20 16:00:00 UTC [] [] workshops_and_courses [] []
  • Systems Workshop: Programming ARM based prototypes @ BSC

    11 May 2018

    Systems Workshop: Programming ARM based prototypes @ BSC https://tess.oerc.ox.ac.uk/events/systems-workshop-programming-arm-based-prototypes-bsc-0084c05d-b5c1-4d04-a257-415a1e975ddd The registration to this course will open in March. Please, bring your own laptop.  All the PATC courses at BSC are free of charge. Course convener: Filippo Mantovani Objectives: Get a comprehensive view of the architecture of the heterogeneous ARM-based platforms deployed in the framework of the Mont-Blanc project, including ARM multicore clusters based on mobile and server technology. Understand the basic concepts of architectural simulations (TaskSim and Gem5) Introduce the MUlti-scale Simulation Architecture, developed within Mont-Blanc 3 for the simulation of next-generation HPC architectures. Study and test simple cases of architectural simulations Topics: High performance computer architecture - The architecture of several ARM-based HPC platforms, deployed and tested during the last four years of research and development within the Mont-Blanc projects will be presented. Tools for architectural simulation: A complete software stack for performing architectural simulations at scale of thousand of cores will be made available. Benchmarks and applications analysis – Tracing and architectural parameter study of benchmarks and small applications running on innovative ARM-based platforms will be possible. Learning Outcomes: Understand how ARM multicore and ARM+GPU clusters work. Work with some example codes, compiling, debugging and executing trough system queues. Get a global view of the machines with their specific configuration (Operating system, batch system, debuggers, compilers, how to access to the machines, how to use the resources, etc) Target Group: Standard HPC users, some knowledge of multicore and GPU-accelerated systems is desirable, but not required. Level: INTERMEDIATE: for participants with some theoretical and practical knowledge (All courses are designed for specialists with at least 1st cycle degree) Requirements: Standard HPC users, with some knowledge in ARM CPU/GPU architecture (recommended, but not required). Agenda: Day 1 /  9:30am - 5:30pm: (3h lectures with 5 min breaks on the hour) Session 1 (2h): The Mont-Blanc Project ARM based machines: Architecture Overview Discussion Session 2 (1h + 1h hands-on): Simulating ARM based machines (TaskSim and Gem5) (1:30h)  Lunch Break (13:00 to 14:00) Session 3 (1h + 1h hands-on ): Simulation at scale: the MUltiscale Simulation Architecture (MUSA), performance and power evaluation of next generation large ARM based systems for scientific computingEND of COURSE   https://events.prace-ri.eu/event/653/ 2018-05-11 07:30:00 UTC 2018-05-11 15:30:00 UTC [] [] workshops_and_courses [] []
  • PRACE-MaX Tutorial on high-throughput computations: general methods and applications using AiiDA@Cineca

    30 May - 1 June 2018

    PRACE-MaX Tutorial on high-throughput computations: general methods and applications using AiiDA@Cineca https://tess.oerc.ox.ac.uk/events/tutorial-on-high-throughput-computations-general-methods-and-applications-using-aiida-cineca Description: AiiDA is a flexible and scalable informatics' infrastructure to manage, preserve, and disseminate the simulations, data, and workflows of modern-day computational science. The PRACE-MaX tutorial is targeted at about 40 students, postdocs and researchers interested in applying high-throughput computations in their research, and in particular to those interested in learning how to use the AiiDA platform. The tutorial will be held by members of the AiiDA developers team (Sebastiaan Huber, Leonid Kahle, Giovanni Pizzi Martin Uhrin and Spyros Zoupanos). Moreover, two scientific talks will be given by Giovanni Pizzi (Discovering two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds) and Leonid Kahle (Fast screening of solid-state lithium-ion conductors) on their research using AiiDA and high-throughput. Skills:   By the end of the tutorial the students should:  have an in depth understanding of AiiDA and how it can be used to facilitate and automatise their research know how to setup and manage AiiDA know how to submit calculations, write and submit workflows know how to query their results and manage their high-throughput research Target Audience: Researchers in materials science, chemistry and related fields interested in applying high-throughput computations in their research, and in particular to those interested in learning how to use the AiiDA platform. Poster session:Participants are typically expected to bring a poster. Please send an email to corsi.hpc@cienca.it with subject "PATC - AiiDA tutorial - Poster session" indicating the title and a brief abstract (max 1500 characters).  Pre-requisites: knowledge of Linux; familiarity with the use of a job scheduler (slurm, torque, pbspro, sge, ...); knowledge of Python will be valuable (please indicate your level in the registration form); knowledge of Quantum ESPRESSO will be valuable. Grant: The lunch for the three days will be offered to all the participants and some grants are available. In order to be eligible for a grant, you should not be funded by your institution and you should also work & live outside the Bologna area. The grant will be 300 euros for students working and living outside Italy and 150 euros for students working and living in Italy (outside Bologna area). It will be provided after the end of the tutorial, after a certified attendance to the lectures (minimum 80%) and some proof regarding the place of work or residence. Further information about how to request the grant, will be provided at the confirmation of the course: about 3 weeks before the starting date. Selection: The number of participants is limited to 40 students. Applicants will be selected according to their experience qualification and scientific interest BASED ON WHAT WRITTEN IN THE "Reason for participation" FIELD OF THE REGISTRATION FORM. Please indicate your Python level in the registration form and if you would like to attend a preliminary Python course the days before the tutorial. Social dinner: An evening buffet will be offered by the tutorial sponsors to all participants on the second day of the course. Important dates: Start of registration: February, 3rd 2018 End of registration: April, 16th 2018 Contact of successful applicants: May, 7th 2018   https://events.prace-ri.eu/event/709/ 2018-05-30 07:00:00 UTC 2018-06-01 16:00:00 UTC [] [] workshops_and_courses [] []
  • High-performance scientific computing in C++ @ JSC

    11 - 13 June 2018

    High-performance scientific computing in C++ @ JSC https://tess.oerc.ox.ac.uk/events/high-performance-scientific-computing-in-c-jsc Modern C++, with its support for procedural, objected oriented, generic and functional programming styles, offers many powerful abstraction mechanisms to express complexity at a high level while remaining very efficient. It is therefore the language of choice for many scientific projects. However, achieving high performance on contemporary computer hardware, with many levels of parallelism, requires understanding C++ code from a more performance centric viewpoint. In this course, the participants will learn how to write C++ programs which better utilize typical HPC hardware resources of the present day. The course is geared towards scientists and engineers, who are already familiar with C++14, and wish to develop maintainable and fast applications. They will learn to identify and avoid performance degrading characteristics, such as unnecessary memory operations, branch mispredictions, and unintentionally strong ordering assumptions. Two powerful open source libraries to help write structured parallel applications will also be introduced: Intel (R) Threading Building Blocks NVIDIA Thrust Prerequisites: Good working knowledge of C++, especially the C++14 standard. Please check with these questions whether your C++ knowlegde fulfills the requirements. Application Registrations are only considered until 25 May 2018 due to available space, the maximal number of participants is limited. Applicants will be notified, whether they are accepted for participitation. Instructors: Dr. Sandipan Mohanty, JSC Contact For any questions concerning the course please send an e-mail to s.mohanty@fz-juelich.de https://events.prace-ri.eu/event/706/ 2018-06-11 07:00:00 UTC 2018-06-13 14:30:00 UTC [] [] workshops_and_courses [] []
  • School on Scientific Data Analytics and Visualization @ Cineca

    11 - 15 June 2018

    School on Scientific Data Analytics and Visualization @ Cineca https://tess.oerc.ox.ac.uk/events/school-on-scientific-data-analytics-and-visualization-cineca-9de9eefd-3994-4d83-a570-68b0f9fc9d76 Description: The increasing amount of scientific data collected through sensors or computational simulations can take advantage of new techniques for being processed in order to extract new insights out of raw data. The purpose of this one-week school is to present researchers and scientists with methods, tools and techniques for exploring and mining, large data sets using Cineca high performance resources. The school is an introductory set of lectures aimed at training beginners participants in the application of relevant statistical, machine and deep learning algorithms to create classification and predictive models using Cineca resources to execute efficient processing jobs. The school will consist of introductory lectures held by data scientists, and hands-on sessions. Skills: At the end of the course, the student will possess and know how to use the following skills: Use of Cineca HPC resources Machine Learning algorithms and libraries  Deep Learning frameworks Target Audience: Young students, PhD, and researchers in computational sciences and scientific areas with different backgrounds, looking for new technologies and methods to process and analyse large amount of data. Prerequisites: Participants must have basic knowledge in statistics, on the fundamentals of computer programming with python and in using GNU/Linux-based systems. Grant The lunch for the five days will be offered to all the participants and some grants are available. The only requirement to be eligible is to be not funded by your institution to attend the course and to work or live in an institute outside the Bologna area. The grant  will be 300 euros for students working and living outside Italy and 150 euros for students working and living in Italy. Some documentation will be required and the grant will be paid only after a certified presence of minimum 80% of the lectures. Further information about how to request the grant, will be provided at the confirmation of the course: about 3 weeks before the starting date. The number of participants is limited to 20 students. Applicants will be selected according to their experience, qualification and scientific interest BASED ON WHAT WRITTEN IN THE "Reason for participation" FIELD OF THE REGISTRATION FORM.    APPLICATION DEADLINE May 4th, 2018.  STUDENTS WILL BE NOTIFIED ON THEIR ADMISSION OR NOT WITH AN EMAIL ON MONDAY MAY,14TH.  Attendance is FREE.    https://events.prace-ri.eu/event/717/ 2018-06-11 08:00:00 UTC 2018-06-15 16:00:00 UTC [] [] workshops_and_courses [] []
  • Runtime systems for heterogeneous platform programming @ MdlS

    4 - 5 June 2018

    Runtime systems for heterogeneous platform programming @ MdlS https://tess.oerc.ox.ac.uk/events/runtime-systems-for-heterogeneous-platform-programming-mdls Keywords Runtime systems, thread programming, accelerators, hardware abstraction, performance portability.   Course description: This course will present the state of the art of runtime system support for programming heterogeneous platforms. Heterogeneous computing platforms—such as multicores equipped with accelerators—are notoriously difficult to program due to the strong differences in performance characteristics among the various available computing units and also to the discrete memory spaces of accelerating boards. The course will present the StarPU runtime system developed at Inria by the STORM Team in Bordeaux. Learning outcomes Participants will understand the benefit of the task-based programming model together with performance modeling, automatic data management and dynamic scheduling in speeding up application development on heterogeneous computing platforms and providing long term performance portability.Prerequisites Basic knowledge of C programming language and accelerator programming languages (nVidia Cuda, OpenCL). https://events.prace-ri.eu/event/681/ 2018-06-04 07:30:00 UTC 2018-06-05 10:30:00 UTC [] [] workshops_and_courses [] []
  • Node-Level Performance Engineering @ HLRS

    14 - 15 June 2018

    Node-Level Performance Engineering @ HLRS https://tess.oerc.ox.ac.uk/events/node-level-performance-engineering-hlrs-3719681b-7a3d-403a-a301-74d9a9d60475 Overview This course teaches performance engineering approaches on the compute node level. "Performance engineering" as we define it is more than employing tools to identify hotspots and bottlenecks. It is about developing a thorough understanding of the interactions between software and hardware. This process must start at the core, socket, and node level, where the code gets executed that does the actual computational work. Once the architectural requirements of a code are understood and correlated with performance measurements, the potential benefit of optimizations can often be predicted. We introduce a "holistic" node-level performance engineering strategy, apply it to different algorithms from computational science, and also show how an awareness of the performance features of an application may lead to notable reductions in power consumption.This course provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves. For further information and registration please visit the HLRS course page. https://events.prace-ri.eu/event/689/ 2018-06-14 07:00:00 UTC 2018-06-15 15:00:00 UTC [] [] workshops_and_courses [] []
  • Introduction to PETSc @ MdlS/Idris

    25 - 26 June 2018

    Introduction to PETSc @ MdlS/Idris https://tess.oerc.ox.ac.uk/events/introduction-to-petsc-mdls-idris The Portable, Extensible Toolkit for Scientific Computation (PETSc) is a suite of data structures and routines for the scalable (parallel) solution of scientific applications modeled by partial differential equations (www.mcs.anl.gov/petsc/). It enables researchers to delegate the linear algebra part of their applications to a specialized team, and to test various solution methods. The course will provide the necessary basis to get started with PETSc and give an overview of its possibilities. Presentations will alternate with hands-on sessions (in C or Fortran). Intended learning outcomes : On completion of this course, the participant should - Be able to build and solve simple PDE examples - Use and compare different solvers on these examples - Be familiar with using the on-line documentation - Be able to easily explore other PETsc possibilities relevant to his/her application. Prerequisites : C or Fortran programming. Notions of linear algebra, as well as notions of MPI, would be an asset. https://events.prace-ri.eu/event/682/ 2018-06-25 07:30:00 UTC 2018-06-26 15:00:00 UTC [] [] workshops_and_courses [] []
  • Efficient Parallel Programming with GASPI @ HLRS

    2 - 3 July 2018

    Efficient Parallel Programming with GASPI @ HLRS https://tess.oerc.ox.ac.uk/events/efficient-parallel-programming-with-gaspi-hlrs-449c9d17-bf45-47f8-913d-e1b9bec8d2e9 Overview In this tutorial we present an asynchronous data flow programming model for Partitioned Global Address Spaces (PGAS) as an alternative to the programming model of MPI. GASPI, which stands for Global Address Space Programming Interface, is a partitioned global address space (PGAS) API. The GASPI API is designed as a C/C++/Fortran library and focused on three key objectives: scalability, flexibility and fault tolerance. In order to achieve its much improved scaling behaviour GASPI aims at asynchronous dataflow with remote completion, rather than bulk-synchronous message exchanges. GASPI follows a single/multiple program multiple data (SPMD/MPMD) approach and offers a small, yet powerful API (see also http://www.gaspi.de and http://www.gpi-site.com). GASPI is successfully used in academic and industrial simulation applications. Hands-on sessions (in C and Fortran) will allow users to immediately test and understand the basic constructs of GASPI. This course provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves. For further information and registration please visit the HLRS course page. https://events.prace-ri.eu/event/690/ 2018-07-02 07:00:00 UTC 2018-07-03 13:30:00 UTC [] [] workshops_and_courses [] []
  • Introduction to Unified Parallel C (UPC) and Co-array Fortran (CAF) @ HLRS

    5 - 6 July 2018

    Introduction to Unified Parallel C (UPC) and Co-array Fortran (CAF) @ HLRS https://tess.oerc.ox.ac.uk/events/introduction-to-unified-parallel-c-upc-and-co-array-fortran-caf-hlrs-2ff001f6-4b22-48ba-ae27-060af8a49a85 Overview Partitioned Global Address Space (PGAS) is a new model for parallel programming. Unified Parallel C (UPC) and Co-array Fortran (CAF) are PGAS extensions to C and Fortran.UPC and CAF are language extensions to C and Fortran. Parallelism is part of the language. PGAS languages allow any processor to directly address memory/data on any other processors. Parallelism can be expressed more easily compared to library based approaches as MPI. This course gives an introduction to this novel approach of expressing parallelism. Hands-on sessions (in UPC and/or CAF) will allow users to immediately test and understand the basic constructs of PGAS languages. This course provides scientific training in Computational Science, and in addition, the scientific exchange of the participants among themselves. For further information and registration please visit the HLRS course page. https://events.prace-ri.eu/event/691/ 2018-07-05 06:30:00 UTC 2018-07-06 13:30:00 UTC [] [] workshops_and_courses [] []
  • Parallel I/O & Libraries @ VSB

    22 - 23 March 2018

    Parallel I/O & Libraries @ VSB https://tess.oerc.ox.ac.uk/events/parallel-i-o-libraries-vsb Numerical simulations conducted on current high-performance computing (HPC) systems face an ever growing need for scalability. Larger HPC platforms provide opportunities to push the limitations on size and properties of what can be accurately simulated. Serial approaches on handling I/O in a parallel application will dominate the performance on massively parallel systems. Heterogeneity of platforms can impose a high level of maintenance, when different data representations are needed. Portable, self-describing data formats such as HDF5 are examples of already widely used data formats within certain communities. See http://prace.it4i.cz/en/ParIO-03-2018 for further information and a detailed timetable. This training is organized as ajoint event between the IT4Innovations National Supercomputing Center, Maison de la Simulation and Cines  (PATC in France) and Jülich Supercomputing Center (PATC in Germany).  https://events.prace-ri.eu/event/713/ 2018-03-22 08:00:00 UTC 2018-03-23 16:00:00 UTC [] [] workshops_and_courses [] []
  • Spring School in Computational Chemistry 2018 @ CSC

    13 - 16 March 2018

    Spring School in Computational Chemistry 2018 @ CSC https://tess.oerc.ox.ac.uk/events/spring-school-in-computational-chemistry-2018-csc Description The Spring School provides a comprehensive, tutorial-style, hands-on, introductory and intermediate-level treatment to the essential ingredients for molecular modeling and computational chemistry using modern supercomputers. The School program is being prepared, but the main content will be similar to last years and consists of: Classical molecular dynamics, intro + hands on (1 day) Electronic structure theory, intro  + hands on (1 day) Machine learning in chemistry Special topics: e.g. on QM/MM, etc. The school is a must for graduate students in the field, providing an overview on "what can be calculated and how should it be done", without forgetting the important aspect of network building. Learning outcome The learning outcome is to gain an overview of the two main methods in computational chemistry — molecular dynamics and electronic structure calculations — in connection with related HPC software packages and other useful skills in the trade. The workshop is also suited for an intensive crash course (the first two days) in computational modelling and is expected to be useful for students and researchers also in physics, materials sciences and biosciences. The following "Special topics" then build on this foundation. Prerequisites Working knowledge and some work experience from some branch of computational chemistry will be useful. Basic linux skills for hands-on exercises and elementary Python for Machine Learning hands-on. More detailed description of pre-requisites and links for self study. Programme See Timetable on the left menu or comments from participants in 2017. Lecturers:  Dr. Filippo Federici Canova, Aalto University, Finland Dr. Mikael Johansson, University of Helsinki, Finland Prof. Ville Kaila, Technical University of Munich, Germany Dr. Luca Monticelli, IBCP (CNRS), Lyon, France Dr. Michael Patzschke, Helmholtz-Zentrum Dresden-Rossendorf, Germany Dr. Markus Koskela, CSC - IT Center for Science, Finland Dr. Martti Louhivuori, CSC - IT Center for Science, Finland Dr. Atte Sillanpää, CSC - IT Center for Science, Finland Dr. Nino Runeberg, CSC- IT Center for Science, Finland to be continued   Language:  EnglishPrice:         Free of charge https://events.prace-ri.eu/event/674/ 2018-03-13 07:00:00 UTC 2018-03-16 14:00:00 UTC [] [] workshops_and_courses [] []
  • Petaflop System Administration; Marenostrum 4 @ BSC

    22 - 23 March 2018

    Petaflop System Administration; Marenostrum 4 @ BSC https://tess.oerc.ox.ac.uk/events/petaflop-system-administration-marenostrum-4-bsc The registration to this course will open in December. Please, bring your own laptop. All the PATC courses at BSC are free of charge. Course Convener: Javier Bartolome Objectives: Explain the different components that MareNostrum 4 is composed, which were the design decisions taken and why. Explain how the system administration is taken in this Petaflop system. Learning Outcomes: The students will learn how MareNostrum 4 is organized and how it works. This can have some insights and ideas about how to manage clusters of thousands of nodes in a HPC or no-HPC environment. Level: INTERMEDIATE, for trainees with some theoretical and practical knowledge; those who finished the beginners course. Prerequisites: Experience on Linux system administration is required. Agenda: Day 1 (March, 22) 9am – 18pm9h-9:20h Introduction & outline of the course9:20h-9:40h MareNostrum4 Overview9:40h-10:40h Storage in MareNostrum410:40h-11h COFFE BREAK11h-11:30h Networks on MareNostrum411:30h -13h Clustering Software13h-14h LUNCH BREAK14h-15:30h Practice on clustering software 15:30h-16:30h Monitoring MareNostrum416:30h-17h MareNostrum4 Facility17h-18h Visit to MareNostrum4Day 2 (March, 23) 9am – 12:30pm 9h-10h MareNostrum4 Schedule system 10h-11h PRACE Project and Services11h-11:15h COFFEE BREAK11:15h-12h MareNostrum4 software stack12h-12:30h Questions/Wrap-up https://events.prace-ri.eu/event/645/ 2018-03-22 08:00:00 UTC 2018-03-23 12:00:00 UTC [] [] workshops_and_courses [] []
  • Introduction to OpenACC @ BSC

    12 - 13 April 2018

    Introduction to OpenACC @ BSC https://tess.oerc.ox.ac.uk/events/introduction-to-openacc-bsc-33ece9fc-0f2a-46c5-a6fc-d0f2005f7956 The registration to this course will open in January. All PATC Courses at BSC do not charge fees. PLEASE BRING YOUR OWN LAPTOP. Local Web Page: This is an expansion of the topic "OpenACC and other approaches to GPU computing" covered on this year's and last year's editions of the Introduction to CUDA Programming. This course will provide very good introduction to the PUMPS Summer School run jointly with NVIDIA -  also  at Campus Nord, Barcelona. For further information visit the school website. Convener:  Antonio Pena, BSC Acting Director, NVIDIA GPU Center of ExcellenceObjectives:  As an NVIDIA GPU Center of Excellence, BSC and UPC are deeply involved in research and outreach activities around GPU Computing. OpenACC is a high-level, directive-based programming model for GPU computing. It is a very convenient language to leverage the GPU power with minimal code modifications, being the preferred option for non computer scientists. This course will cover the necessary topics to get started with GPU programming in OpenACC, as well as some advanced topics. The target audiences of the course are students who want to develop exciting applications for these processors, as well as those who want to develop programming tools and future implementations for these processors. Level: (All courses are designed for specialists with at least 1st cycle degree or similar background experience) BEGINNERS: for trainees from different background or very little knowledge. Agenda: DAY 1 9:00 - 10:00 Introduction to OpenACC on x86 CPU and GPU 10:00 - 11:00 Hands-on: Introduction 11:00 - 11:30 Break 11:30 - 12:30 Profiling and Parallelizing with the OpenACC Toolkit 12:30 - 13:30 Hands-on: Profiling and Parallelizing 13:30 - 15:00 Lunch break 15:00 - 17:00 Hands-on: Open LabsDAY 2 9:00 - 10:00 Expressing Data Locality and Optimizations with OpenACC 10:00 - 11:00 Hands-on: Data Locality and Optimizations 11:00 - 11:30 Break 11:30 - 12:30 Advanced OpenACC Techniques: Interoperability, MPI, and Pipelining 12:30 - 13:30 Hands-on: Advanced Techniques 13:30 - 15:00 Lunch break 15:00 - 17:00 Hands-on: Open LabsEnd of Course https://events.prace-ri.eu/event/651/ 2018-04-12 07:00:00 UTC 2018-04-13 16:00:00 UTC [] [] workshops_and_courses [] []
  • Parallel filesystems and parallel IO libraries @MdlS

    23 - 24 April 2018

    Parallel filesystems and parallel IO libraries @MdlS https://tess.oerc.ox.ac.uk/events/parallel-filesystems-and-parallel-io-libraries-mdls-4d190d03-8f8c-46de-91d4-0208be38e0b9 The increase in computational power goes hand in hand with an increase in the size of the data to be managed, both on the input and on the output sides. IO can easily become a bottleneck for large scale architectures. The understanding of parallel file system mechanisms and parallel IO concepts enables users to efficiently use existing high level libraires like Netcdf or HDF5. In addition this course will provide an introduction to the well established IO technology in the climate community: XIOS.   Topics: • HDF5 High level IO libraries (3h) • Parallel HDF5 and focus on MPI-IO hints (3h) • Parallel file systems: Lustre (1h30) • PDI: Parallel Data Interface (4h30)   Instructors: M. Haefele (Maison de la Simulation, CNRS), Thomas Leibovici (TGCC, CEA), Julien Bigot (maison de la Simulation) Learning outcomes: After this course, participants should understand the tradeoffs implied by using a parallel file-system, and know how to efficiently use parallel IO libraries. Prerequisites: Knowledge of C or Fortran programming language, parallel programing with MPI https://events.prace-ri.eu/event/698/ 2018-04-23 07:30:00 UTC 2018-04-24 15:00:00 UTC [] [] workshops_and_courses [] []
  • Uncertainty quantification @ MdlS

    16 - 18 May 2018

    Uncertainty quantification @ MdlS https://tess.oerc.ox.ac.uk/events/uncertainty-quantification-mdls-59917850-f2a8-4615-880d-52b29d35d749 Uncertainty in computer simulations, deterministic and probabilistic methods for quantifying uncertainty, OpenTurns software, Uranie softwareContent Uncertainty quantification takes into account the fact that most inputs to a simulation code are only known imperfectly. It seeks to translate this uncertainty of the data to improve the results of the simulation. This training will introduce the main methods and techniques by which this uncertainty propagation can be handled without resorting to an exhaustive exploration of the data space. HPC plays an important role in the subject, as it provides the computing power made necessary by the large number of simulations needed. The course will present the most important theoretical tools for probability and statistical analysis, and will illustrate the concepts using the OpenTurns software.Course OutlineDay 1 - General methodology for handling uncertainty, presentation of a case study - Fundamental notions from probability and statistics - General introduction to the software tools: OpenTurns and Uranie  Day 2 - Statistical estimation: parametric and non-parametric, testing - Modeling with non-numerical data: expert judgement, entropy - Central trend: local and gloal sensitivity indices (design of experiments, sampling, Sobol indices) - computing the probability of rare events, simulation methods, FORM/SORM  Day 3 - Distributed computing: parallel solvers, batch jobs submission on a parallel computer, implementation within OpenTurns / Salomeie and Uranie - Introduction to meta-model building, least-squares, other response surface, Kriging, neural networks - Introduction to polynomial chaosLearning outcomes Learn to recognize when uncertainty quantification can bring new insight to simulations. Know the main tools and techniques to investigate uncertainty propagation. Gain familiarity with modern tools for actually carrying out the computations in a HPC context.Prerequisites Basic knowledge of probability will be useful, as will a basic familiarity with Linux. https://events.prace-ri.eu/event/680/ 2018-05-16 07:30:00 UTC 2018-05-18 15:30:00 UTC [] [] workshops_and_courses [] []
  • Introduction to Python programming@Cineca

    28 - 29 May 2018

    Introduction to Python programming@Cineca https://tess.oerc.ox.ac.uk/events/introduction-to-python-programming-cineca Description: Python is a dynamic object-oriented programming language. Because of its powerful and flexible syntax, Python excels as a platform for scientific computing. Versatility, simplicity of use, high portability and the large number of open source modules and packages make it very popular for scientific use. This course is designed to provide a solid foundation on the basic elements of the language. For this reason during the course some good programming practices will be pointed out, many of which are useful for any language. A quick overview of the most important scientific modules is planned. Skills: By the end of the course each student should be able to: understand the key features of Python language write a Python program/module using the basic syntax elements understand the best practices for programming in Python Target Audience: Researchers and programmers interested in an introduction to the Python programming language. Pre-requisites: Knowledge of the basic fundamentals of programming is useful but not necessary. Grant The lunch for the two days will be offered to all the participants and some grants are available. The only requirement to be eligible is to be not funded by your institution to attend the course and to work or live in an institute outside the Bologna area. The grant  will be 200 euros for students working and living outside Italy and 100 euros for students working and living in Italy. Some documentation will be required and the grant will be paid only after a certified presence of minimum 80% of the lectures. Further information about how to request the grant, will be provided at the confirmation of the course: about 3 weeks before the starting date.   https://events.prace-ri.eu/event/708/ 2018-05-28 07:00:00 UTC 2018-05-29 16:00:00 UTC [] [] workshops_and_courses [] []
  • Introduction to the DAVIDE OpenPower GPU cluster@Cineca

    16 - 17 April 2018

    Introduction to the DAVIDE OpenPower GPU cluster@Cineca https://tess.oerc.ox.ac.uk/events/introduction-to-the-davide-openpower-gpu-cluster-cineca DAVIDE (Development of an Added Value Infrastructure Designed in Europe) is an energy-aware Petaflops Class High Performance Cluster based on IBM Power Architecture and coupled with NVIDIA Tesla Pascal GPUs with NVLink. The innovative design of DAVIDE has been developed by E4 Computer Engineering for PRACE, with the aim of providing a leading edge HPC cluster showing higher performance, reduced power consumption and ease of use.  A key technology of the architecture, developed in collaboration with the University of Bologna, is an innovative infrastructure for measuring, monitoring and capping the power consumption of the node and of the whole system. With a focus on energy efficiency, in this introductory course we describe in more detail the DAVIDE architecture and, with the help of uses cases in fields such as materials science and deep learning, illustrate the new opportunities available to users thanks to the introduction of this system into the Cineca HPC infrastructure. Skills: By the end of the course, participants will be expected to: have a good understanding of the technologies employed in the DAVIDE HPC supercomputer recognize the types of problem and application particularly suited to the cluster understand how the energy monitoring system can be used to improve the energy efficiency of applications Target Audience: Researchers who may wish to use the cluster in the future for their research or simply those interested in the evolving field of energy monitoring and efficiency in HPC. Grant The lunch for the two days will be offered to all the participants and some grants are available. The only requirement to be eligible is to be not funded by your institution to attend the course and to work or live in an institute outside the Bologna area. The grant  will be 200 euros for students working and living outside Italy and 100 euros for students working and living in Italy. Some documentation will be required and the grant will be paid only after a certified presence of minimum 80% of the lectures. Further information about how to request the grant, will be provided at the confirmation of the course: about 3 weeks before the starting date. https://events.prace-ri.eu/event/716/ 2018-04-16 07:00:00 UTC 2018-04-17 15:00:00 UTC [] [] workshops_and_courses [] []
  • Advanced Fortran Programming @ CSC

    26 - 28 March 2018

    Advanced Fortran Programming @ CSC https://tess.oerc.ox.ac.uk/events/advanced-fortran-programming-csc-18d7f868-aef0-4bdf-acfb-c91287ea6f5d Description This course covers the modern features of the Fortran programming language. Topics include object-oriented features, language interoperability and several other enhancements available at the Fortran 2008 standard. In addition, a way to express distributed memory parallelism via Fortran coarrays will be discussed in detail. Learning outcome The course provides an overview on all the relevant features of Fortran beyond the 95 standard. You also will be able to write parallel programs using the Fortran coarrays concept. Prerequisites Solid knowledge of Fortran 95/2003. The concepts discussed in the PATC introduction course Fortran Programming for Scientific Computing is the minimum. Knowledge of C will also be needed for understanding topics on language interoperability. Some familiarity with object-oriented programming concepts will be assumed. Some knowledge of parallel programming with message-passing interface (MPI) will be assumed when discussing the coarrays concept. Agenda Day 1: Monday, March 26 09.00-09.15  Course introduction 09.15-10.00  Useful new features beyond F95 10.00-10.15  Coffee break 10.15-11.00  Advanced topics in Fortran I/O 11.00-11.45  Exercises 11.45-12:00  Working with Fortran compilers 12.00-13.00  Lunch break 13.00-14.00  Interoperability with C 14.00-14.45  Exercises 14.45-15.00  Coffee break 15.00-16.00  Exercises Day 2: Tuesday, March 27 09.00-09.45  Introduction to Fortran coarrays 09.45-10.00  Coffee break 10.00-11.15  Exercises 11.15-12.00  More coarray features 12.00-13.00  Lunch break 13.00-14.00  Exercises 14.00-14.45  Advanced topics in coarrays 14.45-15.00  Coffee break 15.00-16.00  Exercises Day 3: Wednesday, March 28 09.00-10.00  Additional capabilities of Fortran types, procedure pointers 10.00-10.15  Coffee break 10.15-11.00  Exercises 11.00-12.00  Type extensions, type-bound procedures 12.00-13.00  Lunch break 13.00-14.00  Exercises 14.00-14.45  More complex data structures with Fortran 14.45-15.00  Coffee break 15.00-16.00  Exercises Lecturers:  Juhani Kataja (CSC), Pekka Manninen (CSC) Language:  English Price:          Free of charge https://events.prace-ri.eu/event/694/ 2018-03-26 06:00:00 UTC 2018-03-28 13:00:00 UTC [] [] workshops_and_courses [] []
  • Advanced Topics in High Performance Computing

    26 - 29 March 2018

    Advanced Topics in High Performance Computing https://tess.oerc.ox.ac.uk/events/advanced-topics-in-high-performance-computing In this add-on course to the parallel programming course special topics are treated in more depth, in particular performance analysis, I/O and PGAS concepts. It is provided in collaboration of Erlangen Regional Computing Centre (RRZE) and LRZ within KONWIHR. The course is a PRACE Advanced Training Center event. Each day is comprised of approximately 5 hours of lectures and 2 hours of hands-on sessions. Tentative schedule: Day 1 (09:00-17:00) Processor-Specific Optimization (Eitzinger) Day 2 (09:00-17:00) 09:00-12:30 Parallel I/O with MPI IO (Wittmann) 13:30-14:30 SuperMUC Tour (Weinberg) 14:30-17:00 Tuning I/O on LRZ's HPC systems / I/O Profiling: Darshan tool (Mendez) Day 3 (09:00-17:00) 09:00-12:30 Scientific Data Libraries: HDF5 / Scalable I/O library: SIONlib (Mendez) 13:30 - 17:00 Introduction into Intel Xeon Phi (KNL) Programming (Weinberg) Day 4 (09:00-17:00) PGAS programming with coarray Fortran and Unified Parallel C (Bader) https://events.prace-ri.eu/event/675/ 2018-03-26 07:00:00 UTC 2018-03-29 15:00:00 UTC [] [] workshops_and_courses [] []
  • Simulation Environments for Life Sciences @ BSC

    14 - 15 March 2018

    Simulation Environments for Life Sciences @ BSC https://tess.oerc.ox.ac.uk/events/simulation-environments-for-life-sciences-bsc-3ea41837-e9bf-4942-952c-be391b475333 The registration to this course will open in January. Please, bring your own laptop. All the PATC courses at BSC are free of charge. Objectives: The course will make the attendants familiar with simulation technologies used in Life Sciences and their specific adaptation to HPC environment Course convener: Josep Gelpi Detailed outline: Introduction to biomolecular simulation Coarse-grained and atomistic simulation strategies Automated setup for simulation HPC specifics: Large scale parallelization, use of GPU’s Storage and strategies for large scale trajectory analysis Learning Outcomes: Setup, execute, and analyze standard simulations in HPC environment Level: (All courses are designed for specialists with at least 1st cycle degree or similar background experience) INTERMEDIATE: for trainees with some theoretical and practical knowledge. Course Program Outline: Day 1 Session 1 09.00h – Welcome & Introduction (JLG) 10.30h – Break 11.00h – Atomistic MD Algorithm (JLG) 11.45h –  Algorithm improvements & HPC (JLG) 12.30h – Break Session 2 14.00h – Simulation Setup (AH) 15.00h – Setup and Analysis Hands On (AH) 16.00h – Break 16.30h – Setup and Analysis Hands On (AH)   18.00h – Adjourn -------------------------------------------------------------------------------------------------------- Day 2 Session 3 09.00h – Simulation DBs (MoDEL) (RG) 10.00h – Simulation Data Management (PA) 10.30h – Break 11.00h – Coarse Grained MD (AE) 12.00h – Application Examples (MO) 13.00h – Break Session 4 14.00h – Coarse Grained MD manual slides Hands on (AE) 16.00h – Break 16.30h – Free  Hands-on 18.00h – End of the course AE: Agustí Emperador (IRB) , AH: Adam Hospital (IRB), JLG: Josep Ll. Gelpi (BSC-IRB- UB), MO: Modesto Orozco (BSC-IRB-UB), PA: Pau Andrio (BSC), RG: Ramón Goñi (BSC)   https://events.prace-ri.eu/event/655/ 2018-03-14 08:00:00 UTC 2018-03-15 17:00:00 UTC [] [] workshops_and_courses [] []
  • Performance Analysis and Tools @ BSC

    7 - 8 May 2018

    Performance Analysis and Tools @ BSC https://tess.oerc.ox.ac.uk/events/performance-analysis-and-tools-bsc-52792e5e-526e-46aa-ae80-ae1f77d74a1f The registration to this course will open in March. Please, bring your own laptop.  All the PATC courses at BSC are free of charge. Course convener: Judit Gimenez Objectives: The objective of this course is to learn how Paraver and Dimemas tools can be used to analyze the performance of parallel applications and to familiarize with the tools usage as well as instrumenting applications with Extrae. Learning Outcomes:The students who finish this course will have a basic knowledge on the usage of the BSC performance tools. They will be able to apply the same methodology to their applications, identifying potential bottlenecks and getting hints on how to improve the applications performance. Level:  INTERMEDIATE - for trainees with some theoretical and practical knowledge. (All courses are designed for specialists with at least finished 1st cycle degree) Course Outline: Day 1 / Session 1 / 9:30am - 1 pm: 1. Introduction to Paraver 2. Paraver guided demo Day 1 / Session 2 / 2 pm- 5:30 pm: Paraver Hands-on -------------------------------------------------------------------------------------------------------- Day 2 / Session 3/ 9:30am- 1 pm: 1. Advanced analysis 2. Introduction to Dimemas 3. Dimemas guided demo Day 2 / Session 4 / 2 pm- 5:30pm: Tools Hands-on END of COURSE https://events.prace-ri.eu/event/654/ 2018-05-07 07:30:00 UTC 2018-05-08 15:30:00 UTC [] [] workshops_and_courses [] []
  • High Performance Molecular Dynamics@CINECA

    26 - 28 March 2018

    High Performance Molecular Dynamics@CINECA https://tess.oerc.ox.ac.uk/events/high-performance-molecular-dynamics-cineca-1d57847b-2c5c-4b6e-8369-63a2f03f0129 Description: This course is designed for those users who wish run classical molecular dynamics programs such as GROMACS and NAMD on modern supercomputers. By understanding better the HPC infrastructures and the algorithms used to exploit them, the aim is to give researchers the tools to run simulations in the most efficient way possible on current and future supercomputers. The course will consist of presentations and practical sessions where students will be able to prepare and run examples of popular programs such as GROMACS and NAMD on the supercomputers of Cineca. Skills: By the end of the course each student should be able to: comprehend the basic principles of classical molecular dynamics (MD). understand the common algorithms for the optimization and parallelization of MD applications and the factors limiting the performance and parallel scaling. run and optimize MD simulations on advanced, multicore architectures equipped with both conventional processors and accelerators such as NVIDIA GPUs. design a simulation project for a computing resource application. Target Audience: Scientists with research interests in classical molecular dynamics in computational biology, chemistry or biophysics. Pre-requisites: Research interest in classical molecular dynamics with a focus on the simulation of biomolecular systems. Basic knowledge of UNIX and concepts of parallel computing. Grant: A grant of 300 EUR (for foreign students) and 150 EUR (for Italian students) will be available for participants not funded by their institution and not working in the Rome area. Some documentation will be required and the grant will be paid only after a certified presence of minimum 80% of the lessons and about 1 month after the ending of the course. For further information about how to submit for the grant, please wait the confirmation email that you are accepted to the course about 3 weeks before the date of the beginning of the lessons.  The lunch for the 3 days will be provided by Cineca.   https://events.prace-ri.eu/event/710/ 2018-03-26 07:00:00 UTC 2018-03-28 16:00:00 UTC [] [] workshops_and_courses [] []
  • Performance portability for GPU application using high-level programming approaches @ MdlS /Idris

    31 May - 1 June 2018

    Performance portability for GPU application using high-level programming approaches @ MdlS /Idris https://tess.oerc.ox.ac.uk/events/performance-portability-for-gpu-application-using-high-level-programming-approaches-mdls-idris-dc0301ac-b627-4c5a-88cd-ac0999c5982a When developing a numerical simulation code with high performance and efficiency in mind, one is often compelled to accept a trade-off between using a native-hardware programming model (like CUDA or OpenCL), which has become tremendously challenging, and loosing some cross-platform portability. Porting a large existing legacy code to a modern HPC platform, and developing a new simulation code, are two different tasks that may be benefit from a high-level programming model, which abstracts the low-level hardware details. This training presents existing high-level programming solutions that can preserve at best as possible performance, maintainability and portability across the vast diversity of modern hardware architectures (multicore CPU, manycore, GPU, ARM, ..) and software development productivity. We will first review the basics of the OpenACC programming model, as well as performance monitoring tools for Nvidia GPU. Several detailed examples in C/C++/Fortran will be used in hands-on session on the high-end hardware platform Ouessant (http://www.idris.fr/ouessant/), equipped with Nvidia Pascal GPUs. We will then provide an introduction to the high-level C++ programming model Kokkos https://github.com/kokkos, and show basic code examples  to illustrate the following concepts through hands-on sessions: hardware portability: design an algorithm once and let the Kokkos back-end (OpenMP, CUDA, ...) actually derive an efficient low-level implementation; efficient architecture-aware memory containers: what is a Kokkos::view; revisit fundamental parallel patterns with Kokkos: parallel for, reduce, scan, ... ; explore some mini-applications. Prerequisites: Some basic knowledge of the CUDA programming model and of C++. https://events.prace-ri.eu/event/712/ 2018-05-31 07:30:00 UTC 2018-06-01 15:00:00 UTC [] [] workshops_and_courses [] []
  • Advanced OpenMP @ EPCC at Cambridge 17-19 July 2018

    17 - 19 July 2018

    Advanced OpenMP @ EPCC at Cambridge 17-19 July 2018 https://tess.oerc.ox.ac.uk/events/advanced-openmp-epcc-at-cambridge-17-19-july-2018 OpenMP is the industry standard for shared-memory programming, which enables serial programs to be parallelised using compiler directives.This course is aimed at programmers seeking to deepen their understanding of OpenMP and explore some of its more recent and advanced features. This 3-day course will cover topics including nested parallelism, OpenMP tasks, the OpenMP memory model, performance tuning, hybrid OpenMP + MPI, OpenMP implementations, and new features in OpenMP 4.0/4.5. Hands-on practical programming exercises make up a significant, and integral, part of this course. Attendees should be familiar with the basics of OpenMP, including parallel regions, data scoping, work sharing directives and synchronisation constructs. Access will be given to appropriate hardware for all the exercises, although many of them can also be performed on a standard Linux laptop.   Pre-course setup All attendees should bring their own wireless-enabled laptop. Practical exercises will be done using a guest account on ARCHER. You will need an ssh client such as terminal on a Mac or Linux machine, or putty or MobaXterm on Windows. The course tutor will be able to assist with settings to connect on the day. You should also have a web browser, a pdf reader and a simple text editor.   Timetable Day 1 09:00 - 11:00  Lectures: OpenMP basics: Parallel regions, Worksharing, Synchronisation 11:00 - 11:30  Coffee 11:30 - 13:00  Practical: Parallel regions 13:00 - 14:00  Lunch 14:00 - 15:30  Lectures: Multicore and multithreaded CPUs, Caches, Cache coherency, NUMA 15:30 - 16:00  Tea 16:00 - 17:00  Practicals: Streams, Coherency Day 2 09:00 - 11:00  Lectures: Tasks, Nested parallelism, Memory model 11:00 - 11:30  Coffee 11:30 - 13:00  Practicals: Mandelbrot with nested loops, collapse, and tasks 13:00 - 14:00  Lunch 14:00 - 15:30  Lectures: OpenMP + MPI 15:30 - 16:00  Tea 16:00 - 17:00  Practicals: OpenMP + MPI Day 3 09:00 - 11:00  Lectures: OpenMP tips, tricks and pitfalls, Performance issues 11:00 - 11:30  Coffee 11:30 - 13:00  Practicals: MD tuning 13:00 - 14:00  Lunch 14:00 - 15:30  OpenMP 4.0/4.5 features, alternative APIs 15:30 - 16:00  Tea 16:00 - 17:00  Consultancy session: bring your own code! Course Materials http://www.archer.ac.uk/training/course-material/2018/07/AdvOpenMP-camb/index.php  https://events.prace-ri.eu/event/722/ 2018-07-17 08:00:00 UTC 2018-07-19 16:30:00 UTC [] [] workshops_and_courses [] []
  • Heterogeneous Programming on GPUs with MPI + OmpSs @ BSC

    9 - 10 May 2018

    Heterogeneous Programming on GPUs with MPI + OmpSs @ BSC https://tess.oerc.ox.ac.uk/events/heterogeneous-programming-on-gpus-with-mpi-ompss-bsc-de6b0bb1-7b88-42bc-8166-04b89303b707 The registration to this course will open in March. Please, bring your own laptop. All the PATC courses at BSC are free of charge. Objectives:  The tutorial will motivate the audience on the need for portable, efficient programming models that put less pressure on program developers while still getting good performance for clusters and clusters with GPUs. More specifically, the tutorial will: Introduce the hybrid MPI/OmpSs parallel programming model for future exascale systems Demonstrate how to use MPI/OmpSs to incrementally parallelize/optimize: MPI applications on clusters of SMPs, and Leverage CUDA kernels with OmpSs on clusters of GPUs Level: INTERMEDIATE: for trainees with some theoretical and practical knowledge; those who finished the beginners course ADVANCED: for trainees able to work independently and requiring guidance for solving complex problems Requirements:  Good knowledge of C/C++ Basic knowledge of CUDA/OpenCL Basic knowledge of Paraver/Extrae Learning Outcomes: The students who finish this course will be able to develop benchmarks and simple applications with the MPI/OmpSs programming model to be executed in clusters of GPUs. https://events.prace-ri.eu/event/650/ 2018-05-09 07:30:00 UTC 2018-05-10 15:30:00 UTC [] [] workshops_and_courses [] []
  • High-performance computing with Python @ JSC

    18 - 19 June 2018

    High-performance computing with Python @ JSC https://tess.oerc.ox.ac.uk/events/high-performance-computing-with-python-jsc-3f05e358-0b27-4a43-8ebf-b2b2fa2f246d Python is increasingly used in high-performance computing projects. It can be used either as a high-level interface to existing HPC applications and libraries, as embedded interpreter, or directly. This course combines lectures and hands-on sessions. We will show how Python can be used on parallel architectures and how to optimize critical parts of the kernel using various tools. The following topics will be covered: Interactive parallel programming with IPython Profiling and optimization High-performance NumPy Just-in-time compilation with numba Distributed-memory parallel programming with Python and MPI Bindings to other programming languages and HPC libraries Interfaces to GPUs This course is aimed at scientists who wish to explore the productivity gains made possible by Python for HPC. Prerequisites: Good working knowledge of Python and NumPy Application Registrations are only considered until 31 May 2018 due to available space, the maximal number of participants is limited. Applicants will be notified, whether they are accepted for participitation. Instructors: Dr. Jan Meinke, Dr. Olav Zimmermann, JSC Contact For any questions concerning the course please send an e-mail to j.meinke@fz-juelich.de https://events.prace-ri.eu/event/707/ 2018-06-18 07:00:00 UTC 2018-06-19 14:30:00 UTC [] [] workshops_and_courses [] []
Ajax loader