ETP4HPC Webinar - LUMI
The EuroHPC Joint Undertaking has installed three leadership-class supercomputers. We will discuss one of these systems, LUMI, located in Kajaani, Finland. LUMI is currently the fastest supercomputer in Europe and in general one of the most powerful and advanced computing systems in the world.
Dr. Pekka Manninen will present the technical architecture of the LUMI infrastructure and its status, together with plans and ambitions for the near future. Then, an overview of the scientific showcases and achievements from the first months of LUMI will be presented. These include, for example, contributions to the Destination Earth initiative, work on large language models and breakthroughs from extreme-scale computing capabilities in many fields of computational science.
Code of the Month: NekRS from CoEC
The Nek project, which was started at MIT in the mid 1980s, was designed to combine the speed and efficiency of spectral methods with the geometric flexibility of finite elements. The initial 3D version, Nekton 2.0, was the first commercial CFD software for distributed memory parallel computers and was marketed by Nektonics and ultimately by Fluent in the mid-90s. The research version (aka nek5000) was awarded the 1999 Gordon Bell Prize. Today the code is open source and features state-of-the-art, scalable algorithms that are fast and efficient on platforms ranging from laptops to the world’s fastest computers. Applications span a wide range of fields, including fluid flow, thermal convection, combustion, and magnetohydrodynamics. The user community includes 500+ scientists and engineers in academia, laboratories, and industry.
The upcoming webinar focuses on the newest version, nekRS targeting accelerators. It presents the basic concepts of the Nek project and highlights recent large-scale applications. nek5000/nekRS can easily be used (even at scale), for example, as part of the Jupyter-CoEC computing service hosted at the Jülich Supercomputing Centre. This will be demonstrated in the last part of our presentation.
LUMI Intro course
This one day online course serves as a short introduction to the LUMI architecture and setup. It will include lessons about the hardware architecture, compiling, using software and running jobs efficiently. After the course you will be able to work efficiently on both the CPU (LUMI-C) as well as GPU partition (LUMI-G).
The course is intended for users that have taken a previous general HPC introduction course or already have experience with computing on HPC clusters.
Read more and register: https://lumi-supercomputer.eu/events/lumi-intro-course-21sep23/
Machine Translation Marathon 2023
Organized by TartuNLP, Institute of Computer Science, University of Tartu, the 16th Machine Translation Marathon 2023 is a week-long gathering of machine translation researchers, developers, students and users.
Who can participate? Practically anyone — students who want to learn about machine translation, junior and senior researchers, hacking project proposers, industry representatives, etc.
Inno4scale publishes open call for innovation studies
The Inno4scale project will support the EuroHPC Joint Undertaking in achieving the efficient use of its supercomputing resources through the development of novel algorithms for applications on those resources. It will do this by funding a set of focused innovation studies that will realise proof-of-concept demonstrators of fundamentally new and innovative algorithms with a clearly identified potential impact through integration and use in important applications.
This call for proposals targets highest quality research and development studies leading to proof-of-concept demonstrators exhibiting enhanced performance relevant for important applications executed on exascale systems. The call addresses researchers that have identified novel concepts for computational solutions of important numerical problems in scientific applications and use cases which rely on exascale supercomputers. The central goal is the conversion of mathematical concepts for algorithms, for example by a fundamentally new decomposition of a numerical problem for the efficient use of hierarchical memory to exploit heterogeneous and massively parallel computing capabilities of upcoming exascale supercomputer architectures, into proof-of-concept implementations to explore and assess potential performance gains for common HPC applications.
Read more: https://www.inno4scale.eu/calls/
Code of the Month: RAISE
CoE RAISE follows the rules of open science and publishes its results open-access when they are ready for wider application.
All developments of CoE RAISE are being integrated into the Unique AI Framework (UAIF), which will not only contain the trained models but also documentation on how to use them on current Petaflop and future Exascale HPC, prototype, and disruptive systems.
The developments toward the Unique AI Framework are continuously progressing.
Parts of the UAIF are for example AI4HPC, an open-source library to train AI models with CFD datasets on HPC systems or Machine-Learned Particle-Flow (MLPF), an algorithm based on Graph Neural Networks (GNN) aimed at performing efficient, GPU-accelerated particle flow reconstruction at large particle detector experiments.
Our webinar gives an introduction to UAIF by Morris Riedel, with enough time for questions from the attendees. Whether you’re a developer, engineer or project manager – feel free to join us and learn what you could do with UAIF!
Puhuri assisted in the successful integration of a quantum computer with the LUMI supercomputer
On 15 June 2023, the attendees of the Digital Assembly hosted by the Swedish Presidency of the Council of the European Union and the European Commission witnessed a live demonstration of an operational Nordic hybrid quantum computing system.
At the Assembly, Miroslav Dobsicek, senior research engineer at the Chalmers University of Technology, introduced a hybrid system in which the state-of-the-art quantum computer QAL 9000, located in Sweden, was integrated with the LUMI supercomputer situated in Finland. The setup also included Puhuri, a resource allocation service created with co-funding from Nordic e-Infrastructure Collaboration (NeIC) and operated by the University of Tartu High Performance Computing Center. Puhuri can be considered an invisible gatekeeper and accountant providing seamless access to the computing infrastructure.
In a live demonstration, Dobsicek used his laptop to access and operate the hybrid system via the cloud and perform cross-border quantum calculations. First, the quantum computer tune-up across the internet was demonstrated. During this process, the quantum chip performs thousands of measurements per second to recalibrate itself. Tuning needs to be repeated periodically as the control parameters of the quantum chip and the classical electronics are drifting in time due to thermal noise and electromagnetic interference.
After the tune-up, QAL 9000 was ready to run a real quantum computation, in which a small neural network was trained on a problem of classifying points in the plane into two groups. Dobsicek connected remotely to the LUMI supercomputer and uploaded a script that submitted the machine learning algorithm to LUMI processing pipelines. 12 of 25 QAL 9000 qubits were used during the demonstration. All active qubits ran the same algorithm in parallel, and LUMI collected the results online. At the end of the process, the result was averaged for increased robustness.
Comprehensive general LUMI course
This four day hybrid (on-site in Tallinn and online) course serves as a general comprehensive introduction to the LUMI architecture and programming environment. It will include lessons about compiling and using software, programming models (HIP and OpenMP offload), porting, executing jobs, and optimizing applications to run on AMD MI250X. After the course you will be able to work efficiently on both the CPU (LUMI-C) as well as GPU partition (LUMI-G).
The course will be jointly conducted by the LUMI HPE Centre of Excellence (HPE CoE), AMD and the LUMI User Support Team (LUST). We intend this course for users with ongoing projects on LUMI, users with project proposals in one of the national or EuroHPC channels, and support staff of local organisations of the LUMI consortium members.
Read more and register: https://ssl.eventilla.com/event/d1EQq
Introducing SAPU, the platform for sensitive data analysis
On April 28, 2023, NCC Estonia organized a webinar where SAPU, an environment for processing sensitive data, was introduced. In addition to Estonian stakeholders, invited guests from Denmark and Bulgaria also participated in the webinar.
HPC centres often store valuable research data that could be used by other scientists and institutes to perform research and answer questions. This data is often sensitive, or potentially sensitive in certain circumstances. At this point, a contradiction arises between security and research worlds. Security demands that this data should be locked in a box accessible for only very specific people. On the other hand, research wants to make this data available for everyone to convey scientific knowledge and solve problems. By accepting some risks, and replacing some aspects of the physical boundary with legal ones, it is possible to use technology to achieve something similar to the locked box.
More information: https://docs.hpc.ut.ee/services/SAPU/
Online exaFOAM Workshop about the boundaries of CFD technology using OpenFOAM
We invite researchers, practitioners, and students from academia, industry and government organizations to attend this workshop to learn more about the exaFOAM project and its innovative approach to Computational Fluid Dynamics (CFD). Participants will also have the opportunity to engage in discussions with experts in the field. There are no fees to participate.
The exaFOAM project seeks to overcome the current limitations of CFD, particularly in the area of massively parallel High-Performance Computing (HPC) architectures. The project involves the development and validation of a range of algorithmic improvements across the entire CFD process chain, including preprocessing, simulation, I/O, and post-processing. The effectiveness of these improvements will be demonstrated through a suite of HPC Grand Challenges and Industrial Application cases, where engineering design through CFD has contributed significantly to industrial competitiveness and sustainability across various sectors such as transportation, power generation, and disaster prevention, among others.
More information and agenda are available here.
Summer school on quantum information processing
The Jülich Supercomputing Centre will host the summer school on “Quantum Information Processing – Applications on Gate-based and Annealing Systems” from August 28 to September 01, 2023. The school focuses on hands-on experiences in developing and implementing algorithms on both gate-based devices and quantum annealers. Therefore the attendees will make use of JUNIQ’s cloud-programming platform to access quantum devices located at the Jülich Supercomputing Centre. The hands-on sessions will be accompanied by several lectures covering basic concepts of gate-based and annealing systems, the design and implementation of use-cases, and big-picture lectures, all given by experts from the field. The spring school will be complemented by a poster session where attendees present their research activities to each other.
OneAPI Hybrid Workshop
On behalf of the German National Competence Centre for High-Performance Computing, you are cordially invited to take part in the EuroCC2 OneAPI Hybrid Workshop on 5-7 June 2023. This Workshop is co-organized by Intel and the Leibniz Supercomputing Centre (LRZ). The Workshop is an introduction to the modern Intel oneAPI Development Environment. It allows you to program enterprise and HPC applications once with just a single source code for mixed architectures (CPU, GPU and others) from multiple hardware vendors. This 3-day hybrid (combined online and onsite) workshop will teach the participants about the latest and expanded features of the Intel oneAPI toolkits. The presenters will show you how to write applications on heterogenous hardware platforms. In addition, the workshop will be accompanied by an attractive supporting program with catering service
Advanced Application Profiling Course
This one day (13.4.23) online course serves as a detailed introduction to profiling and benchmarking application running on LUMI-C and LUMI-G.
This course is targeted at advanced users with experience on running jobs on LUMI or other Cray machines. We expect participants to have joined one of the previous LUMI courses or equivalent proficiency.
The course will be jointly conducted by the LUMI HPE Centre of Excellence (HPE CoE), AMD and the LUMI User Support Team (LUST).
The course is intended for users with ongoing projects on LUMI, users with project proposals in one of the national or EuroHPC channels, and support staff of local organisations of the LUMI consortium members.
Register for the course latest by 7th April 2023 16:00 CET.
See the agenda and register: https://lumi-supercomputer.eu/events/profiling-course-apr23/
Workshop & hackathon: Exascale women on stage
On June 12-14 2023, the Humboldt-Universität zu Berlin will host the workshop and hackathon “Exascale women on stage”. This event is organized by women for women to learn about each others’ research and build professional networks.
The event is open to all female scientists at all professional levels – including master students, PhD students, postdocs, and professors – working on the development of methods and codes to bring electronic-structure theory to the exascale. The event serves two purposes: First, the scientists will discuss their research and share experiences. Second, they will gather ideas and develop a joint strategy on how to attract more female colleagues to the field. In a hackathon style, they will develop materials for their needs.
Please note that the event is limited to 30 participants. Read more and register by May 10.
Practical Deep Learning Course
This 3-day (3.-5.5.2023) course gives a practical introduction to deep learning, convolutional and recurrent neural networks, transformer models, GPU computing, and tools to train and apply deep neural networks for natural language processing, images, and other applications. The course will be held in hybrid mode, so both online and on-site participation are possible.
After the course the participants should have the skills and knowledge needed to begin applying deep learning for different tasks and utilizing the GPU resources available at CSC for training and deploying their own neural networks.
The participants are assumed to have working knowledge of Python and suitable background in data analysis, machine learning, or a related field. Previous experience in deep learning is not required, but the fundamentals of machine learning are not covered on this course. Basic knowledge of a Linux/Unix environment will be assumed.
See the agenda and register: https://ssl.eventilla.com/event/8aPek
NCC Estonia participated in sTARTUp Day 2023
sTARTUp Day is an annual event that brings together startup-minded people to celebrate entrepreneurship in the smart city of Tartu. This year’s sTARTUp Day took place on March 16-17 with the participation of 3200 attendees and 270 startups from 45 countries. NCC Estonia participated in sTARTUp Day for the first time and immediately received a lot of attention. The NCC’s staff used an AI image generation tool Stable Diffusion to demonstrate how quickly results can be achieved with high computing power. As HPC is becoming more and more important for startups, NCC Estonia is happy to provide comprehensive advice to new potential users.
Access to LUMI
This course is dedicated to the supercomputer LUMI. EuroHPC Joint Undertaking’s LUMI supercomputer reached the third spot on the Top500 list of the world’s fastest supercomputers released at the SC22 conference in Dallas, USA, on 14 November 2022. LUMI reached a measured High-Performance Linpack (HPL) performance of 309 petaflops. This makes LUMI the fastest supercomputer in Europe.
Participants will learn about its architecture and key parameters, how to access LUMI resources, how to run jobs, and how to use the GPU accelerated partition for AI applications.
The course takes place on February 14, 2023, 9 am to 3 pm CET.
See the agenda and register: https://events.it4i.cz/event/160/
EuroCC 2 and CASTIEL 2: Promoting HPC to boost digital skills and competitiveness in Europe
EuroCC 2 and CASTIEL 2 are two linked projects which work to identify and address the skills gaps in the European HPC ecosystem and coordinate cooperation across Europe to ensure a consistent skills base. The role of EuroCC 2 is to establish and run a network of more than 30 national competence centers (NCCs) across the EuroHPC participating states. NCC Estonia was established on the basis of the ETAIS consortium. EuroCC 2 delivers training, interacts with SMEs, develops competence mapping and communication materials and activities, and supports the adoption of HPC services in other related fields, such as quantum computing and AI to expand the HPC user base. CASTIEL 2 promotes interaction and exchange of expertise and competence across the NCC network. Starting on 1st January 2023, the project EuroCC2 will run for a 3-year period with a total budget of up to €62 million, provided by the Digital Europe Programme and the EuroHPC participating states. CASTIEL 2 will also run for a 3-year period starting 1st January 2023 and receive up to €3 million funding from the Digital Europe Programme.
EuroCC 2 and CASTIEL 2 follow on from EuroCC and CASTIEL, which started on 1 September 2020 and ran for two years. The two projects received funding from Horizon 2020. The two projects will be coordinated by the High-Performance Computing Centre Stuttgart (HLRS).
The EuroCC project has been successfully completed
The 2-year EuroCC project, funded by the EuroHPC Joint Undertaking and 33 participating European states, has come to a successful end. The main aim of the EuroCC was to build a sustainable and globally competitive European HPC ecosystem. To achieve this goal, each of the 33 member states have established National Competence Centres (NCCs). At the same time, Coordination and Support Action CASTIEL has coordinated activities like international workshops, mentoring and twinning partnerships, and topic-specific working groups to address issues of shared interest. The two projects have bridged the existing HPC skills gaps while promoting cooperation and the implementation of best practices across Europe. NCC Estonia was established on 1st of September 2020 on the basis of the ETAIS consortium. The mission of NCC has been to analyze, implement and coordinate all necessary activities and offer services to Estonian end users to cover their needs: from access to resources, from technological consultancy to the provision of training courses for academia, public administrations and industry.
Comprehensive general LUMI course
This four day (14.-17.2.2023) online course serves as a general comprehensive introduction to the LUMI architecture and programming environment. It will include lessons about compiling and using software, programming models (HIP and OpenMP offload), porting, executing jobs, and optimizing applications to run on AMD MI250X. After the course you will be able to work efficiently on both the CPU (LUMI-C) as well as GPU partition (LUMI-G).
The course will be jointly conducted by the LUMI HPE Centre of Excellence (HPE CoE), AMD and the LUMI User Support Team (LUST). The course is intended for users with ongoing projects on LUMI, users with project proposals in one of the national or EuroHPC channels, and support staff of local organisations of the LUMI consortium members.
The registration deadline is 7. February 2023 16:00 CET. Attendance is free of charge.
More information is available here: https://lumi-supercomputer.eu/events/general-lumi-course-feb23/
Creative AI Webinar organized by NCC Sweden
The last year has seen an explosion in “creative Al”, in particular, the performance of text generation models (such as chatGPT) and image generation models (such as Stable Diffusion, Dalle-2 and Midjourney) has left many outside of the field shocked by the suddenly impressive capabilities of Al.
NCC Sweden will organize a webinar on February 24 (09:00 – 12:00 CET) in order to give an overview of where these models come from, how they work and what can be expected in the future.
The webinar will be on a popular science level, you are not assumed to be a machine learning expert but should know what it is and have a basic knowledge of neural networks.
Read more and register: https://enccs.se/events/creative-ai-webinar-feb-2023/
INTERNATIONAL HPC SUMMER SCHOOL 2023
Graduate students and postdoctoral scholars from institutions in Canada, Europe, Japan, Australia and the United States are invited to apply for the 12th International High Performance Computing (HPC) Summer School, to be held on July 9-14, 2023 in Atlanta, Georgia, USA, hosted by the Extreme Science and Engineering Discovery Environment (XSEDE). The deadline for application is 23:59 Anywhere on Earth (AoE) on January 31, 2023.
The summer school will familiarize the best students in computational sciences with major state-of-the-art aspects of HPC and Big Data Analytics for a variety of scientific disciplines, catalyze the formation of networks, provide advanced mentoring, facilitate international exchange and open up further career options.
Leading Canadian, European, Japanese, Australian and American computational scientists and HPC technologists will offer instruction in parallel sessions on a variety of topics such as:
- HPC and Big Data challenges in major scientific disciplines
- Big Data analytics
- Performance analysis and optimization on modern CPUs and GPUs
- GPU programming
- Distributed-memory programming
Read more: https://ss23.ihpcss.org/
AIPlan4EU has launched its 2nd open call for innovators
AIPlan4EU, an EU-funded project, has launched its 2nd and final open call for innovators, offering up to €90,000 in funding for AI planning technology, software development and use cases across all business sectors.
Open call #2 for innovators features three different tracks, distinguishing three different kinds of contributions. Track A is mainly of interest for planning experts, while Tracks B and C mostly require more general software development. In track B, AIPlan4EU is also looking for additional use-cases, which can potentially be of interest for everyone.
The design of the various activities in AIPlan4EU is derived from user needs, considering use-cases relevant in the scope of AI planning, regardless of their sector. For example, the use-cases provided by the project partners themselves are from the following areas:
- Planning for space
- Planning for agriculture
- Planning for manufacturing
- Planning for logistics
- Planning for autonomous driving
- Planning for automated experimentation
- Planning for subsea robotics
The closing date for this call is 31/01/2023. Read more: https://www.aiplan4eu-project.eu/call-for-use-cases/open-call-2-for-innovators/
INVITATION TO THE WEBINAR: CYBER SECURITY IN INDUSTRIAL COMPANIES – THREATS, TRENDS AND RISKS
AIRE (AI & Robotics Estonia) invites you to a webinar where cyber security and information security and its importance for an industrial company will be discussed. We will talk about the main threats of the moment, future trends and the risks associated with them. We provide recommendations and tips on how to avoid threats and how to get started with corporate cyber security.
Small and medium-sized processing industry (EMTAK C) and manufacturing companies are welcome.
The courses are aimed at employees of industrial companies who want to get acquainted with the possibilities of digitization of production and industrial robots. In professions: industrial managers, engineers, foremen, automatists, mechatronics, technicians and locksmiths and industrial operators and product manufacturers (including warehouse workers, electricians), IT specialists, etc.
The webinar will be conducted by Tommy Tomson, information security advisor of the University of Tartu Center for Scientific Computing.
Upon successful completion of the webinar, participants will gain knowledge of:
• What is cyber security and why is it important and necessary.
• What is the legislation related to cyber security.
• What are the main cyber security threats and trends.
• What is data security, data protection.
• How to get started with cyber security in your business.
The deadline for registering on the website is January 6, 2023. The webinar will be held in Estonian.
AMD GPU Hackathon
This hackathon is for teams of research software developers who want to accomplish one or more of the following goals:
- Port their code to run on AMD Instinct™ GPUs using a GPU programming framework like HIP, OpenMP, SYCL etc.
- Improve the performance of a code that already runs on AMD Instinct™ GPUs.
- Scale up their codes to multiple AMD Instinct™ GPUs.
During the hackathon, project teams will be paired up with expert mentors from HPE, AMD, PDC and ENCCS who will guide them during the hackathon to accomplish their stated goals. Teams should have at least two members who are prepared to work full-time on their projects for the duration of the hackathon.
This hackathon will take place over four days split over two weeks. The first day of the hackathon, March 7, will be online while the main work will be hosted on-site on KTH Campus at Drottning Kristinas väg 61, 114 28 in Stockholm, Sweden, on March 14-16.
- Teams should consist of at least two, and preferably three, members who are ready to actively participate during the event.
- Teams should know their application well and have the programming experience to modify the code.
- Projects should be under an open-source license.
No advanced GPU skills are required, but it is helpful for teams to know the basics of GPU programming and profiling. Team members should get familiar with aspects of the AMD ROCm™ open software and the AMD HIP programming language.
Read more and register: https://enccs.se/events/2023-03-amd-gpu-hackathon/
Collaboration/knowledge transfer between the ELIXIR-EE and ELIXIR-SI
The goal of ELIXIR is to coordinate these resources so that they form a single high quality infrastructure. This coordinated infrastructure makes it easier for researchers to find and share data, analyse their experiments, exchange knowledge, and agree on best practices.
In July 2022, Ott Oopkaup from ELIXIR Estonia and NCC Estonia successfully mentored the setup and knowledge transfer of the national Galaxy in the ELIXIR Slovenia research infrastructure. It strengthens the ties between the researchers of the two countries and demonstrates the important role of NCCs in technology transfer.
Galaxy is a scientific workflow, data integration, and data and analysis persistence and publishing platform that aims to make computational biology accessible to research scientists that do not have computer programming or systems administration experience.
A free online course: Efficient Parallel IO
One of the greatest challenges to running parallel applications on large numbers of processors is how to handle file IO. Standard Unix 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 volumes of data, but performance can be far from optimal if every process opens its own file or if all IO is funnelled through a single controller process.
This hands-on course explores a range of issues related to parallel IO. It uses ARCHER2 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 course does not teach the detailed syntax of the various parallel IO libraries, but the Fortran source code provided for the benchmarking application used in the practical sessions should be useful reference material.
The course assumes an understanding of basic MPI programming in C, C++ or Fortran. Knowledge of MPI derived datatypes would be useful but not essential.
This course is part-funded by the PRACE project and is free to all. The course takes place on 23 August 2022 09:30 – 16:30 BST.
Read more and register: https://events.prace-ri.eu/event/1423/
The 2022 ACM Europe Summer School
The summer school is open to young computer science researchers and engineers, outstanding MSc students, and senior undergraduate students. Accepted participants will attend formal lectures and practical hands-on sessions.
Upon successful completion of the school, all attendees will receive a certificate. Based on scores obtained in practical exercises, the best performing students will receive certificates of honour.
Student participation in the school is free of charge, and the ACM School will cover living expenses related to accommodation and meals for the duration of the school. However, travel costs will not be covered. For exceptionally meritorious, students who cannot afford the cost of travel, the school will provide travel grants up to €250 upon successful completion of the school week.
Workshop: Introduction to Quantum Computing & Hybrid HPC-QC Systems
Recent developments in quantum technology are bringing the world closer to a new technological revolution – the advent of usable quantum computers able to provide enormous acceleration to important computational tasks. In coming years, quantum computing is expected to have a huge impact on practically all areas of research that can utilise computational modelling.
Starting operations in April this year, the NordΙQuEst project brings together a consortium of seven partners from five Nordic and Baltic countries to connect world-leading traditional HPC resources and quantum computers across national borders with the aim to establish a quantum computing platform customised to the needs of the region.
ENCCS is now joining forces with NordIQuEst to deliver a two-day training workshop covering the fundamentals of quantum computing. Morning lectures are combined with afternoon hands-on sessions where participants learn to use high-level QC programming languages using simulators. For the hands-on training sessions, basic familiarity with Python and some experience working in a Unix environment are desirable. No previous experience with quantum computers expected.
LUMI ranked third on Top500 list
EuroHPC Joint Undertaking’s LUMI supercomputer reached the third spot on the latest Top500 list of world’s fastest supercomputers released at the ISC22 conference in Hamburg, Germany on 30 May 2022. LUMI reached a measured High-Performance Linpack (HPL) performance of 151.9 petaflops. This makes LUMI the fastest supercomputer in Europe. The No. 1 spot in the Top500 list is now held by the Frontier system at Oak Ridge National Laboratory in the US.
In addition, LUMI supercomputer reached the third spot on the new Green500 list which ranks supercomputers from the Top500 list in terms of energy efficiency. The GFlops/Watts ratio for LUMI is 51.6, making it one of the greenest supercomputers in the world.
LUMI is a unique endeavour thanks to its scale, sustainability and pan-European nature, hosted by a consortium of ten countries, including Estonia.
Read more about the latest Top500 list: https://top500.org/lists/top500/2022/06/
Workshop "Programming on accelerators"
The Coordination and Support Action CASTIEL invites you to the online workshop “Programming on accelerators” which will take place on the 23rd May, 9:30 – 13:00 (CET).
The covered topics include introduction to GPU programming, performance optimization as well as multi-GPU and multi-stream programming.
Find out more and register: https://sway.office.com/uN7yUmeaMD9z7GdD
The CSC Summer School in High-Performance Computing
CSC Summer School brings together undergraduate and graduate students and postdoctoral researchers in different disciplines of scientific computing from all over the world. The contents consist of lectures and hands-on training on parallel programming, code optimization and other necessary skills in development of scientific software.
The school is aimed for graduate students working in various fields of science, e.g., chemistry, physics, life sciences, engineering or economics as well as Industrial R&D professionals. Also undergraduates as well as post-docs will find the school very useful.
The ten days of school are filled with coding, sports, leisure activities and having good time together. It will be an experience you will never forget with the midnight sun in the Nordic night next to breathtaking wilderness!
ESTONIA-GEORGIA JOINT TEAM TO WIN THIRD PLACE IN LOCKED SHIELDS 2022
More than 2000 participants were involved in cyber defence exercise Locked Shields 2022 that took place from April 19 to 22. This year, one of the venues of the event was the Delta Centre in Tartu. Employees of the HPC Center of the University of Tartu and the Institute of Computer Science participated in the Estonian team.
Locked Shields is known as the largest and most complex international cyber defence exercise in the world. It is organised by the NATO Cooperative Cyber Defence Centre of Excellence (CCDCOE) in cooperation with other partners annually since 2010. Locked Shields offers cyber experts a cutting-edge challenge to practice their skills in protection of civilian and military IT systems as well as critical infrastructure.
Locked Shields is a Red Team vs. Blue Team exercise with teams formed by member states and partners of the CCDCOE. According to the scenario, a fictional island country Berylia faces a large-scale cyber attack with its neighbour and rival country Crimsonia supposedly behind it. These attacks have caused severe disruptions to the operation of government and military networks, communications, water purification systems and electric power grid. The Blue Teams play the role of national rapid reaction teams that are deployed to assist Berylia in handling cyber incidents and their implications. The Red Team are the attackers who challenge the training audience by testing their ability to secure their systems under time and resource pressure.
Locked Shields follows the current geopolitical situation and draws a realistic vision of a contemporary world where cyber incidents are employed as part of a wider geopolitical strategy. Attacking is easier than defending as the attacker may just need access to one entry point while the defender must protect all the possibilities. This year, the multi-day exercise evolved around 5,500 virtualized systems that were subject to more than 8,000 live-fire attacks. To be successful, the teams must practice cooperation between both civilian and military units, as well as public and private sectors. The strategic decision-makers and technicians need to work together in securing complex IT systems, reporting incidents and solving various challenges. For the first time, this year’s exercise also included the simulation of reserve management and financial messaging systems of a central bank in the cyber range environment.
Locked Shields 2022 included 24 teams and more than 30 nations. Although the competition was very intense, the Finnish team outperformed others because of solid defence against network and web attacks and excellence in situation reporting. The joint team Lithuania-Poland came second, while the joint Estonia-Georgia team took a valuable third place.
Most contemporary conflicts involve a cyber dimension. The importance of Locked Shields lies in the fact that it provides participating nations a unique opportunity to test their skills in a safe environment while being aggressively challenged by a highly skilled adversary. Such collaborative exercises have become vital as cyber defence has been on high alert since the outbreak of the war in Ukraine. In addition, societies have become more dependent on virtual solutions during the global pandemic. This has greatly increased the attack surface for malicious actors and requires effective collaboration between public and private entities to ensure the systems we depend on can be protected.
Parallel Computing on GPUs with CUDA
The NCC Turkey would like to invite you to participate in the training entitled “Parallel Computing on GPUs with CUDA” (26-27 April 2022). The training language will be English.
– Introduction to Parallel Computing
– Introduction to GPUs and their Architecture
– CUDA Programming Model
– Using Multiple GPUs and Multiple Streams
– Debugging and Profiling Performance
– Performance Optimization and Efficiency
– Some Libraries and Remaining Issues
– CUDA Samples
Registration link: https://indico.truba.gov.tr/event/84/
Detailed introduction to the LUMI-C environment and architecture
This two day on-line course serves as a detailed introduction to the LUMI-C environment and architecture. Participants will also learn about porting, executing and optimising applications for the environment. The course will be jointly conducted by the LUMI HPE Centre of Excellence and the LUMI User Support Team. The course is intended for users with ongoing projects on LUMI-C and support staff of local organisations of the LUMI consortium members. Participation will be moderated due to the limited number of participants, but we encourage registrations. This will facilitate the planning of further training events.
There will be a waiting list if registrations exceed the number of planned participants. Registration deadline is April 22, 2022 16:00 CEST.
Read more and register: https://lumi-supercomputer.eu/events/detailed-introduction-to-lumi-c-april-2022/
A free online SYCL workshop
Take the opportunity to praticipate in the free SYCL workshop, organized by the EuroCC National Competence Centre Sweden.
SYCL is a C++ abstraction layer for programming heterogeneous hardware with a single-source approach. SYCL is high-level, cross-platform, and extends standard ISO C++17. There are numerous compilers implementing the SYCL standard and they use different backends to target CPUs, GPUs, and even specialized hardware such as field-programmable gate arrays (FPGA) and vector engines.
In this online workshop you will learn to:
- Use the hipSYCL compiler to generate executables for multiple hardware targets.
- Write hardware-agnostic code to express parallelism using the queue, command group, and kernel abstractions.
- Use buffer and accessors to handle memory across devices.
- Evaluate drawbacks and advantages of unified shared memory.
This workshop will be given by ENCCS expert Roberto Di Remigio Eikås, PhD. Supercomputer Karolina is going to provide computing resources for this workshop..
Time: April 19 @ 09:00 – April 21 @ 12:10 CEST
GTN Smörgåsbord 2 starts on March 14
GTN Smörgåsbord 2 is a free, global, week-long Galaxy training event showcasing a wide variety of Galaxy Training Network tutorials.
Galaxy, a scientific workflow system, aims to make computational biology accessible to research scientists that do not have computer programming or systems administration experience. Although it was initially developed for genomics research, it is largely domain agnostic and is now used as a general bioinformatics workflow management system.
The format of training event is virtual and asynchronous. All training session are pre-recorded and captioned, you can work through these at your own pace, with instructors available online for support.
When: March 14-18, 2022 (all time zones).
Who: Open for everybody
When: March 14-18, 2022 (all time zones).
Check out the schedule and register: https://gallantries.github.io/posts/2021/12/14/smorgasbord2-tapas/
Upcoming course: Introduction to artificial intelligence
This introductory course aims to introduce what is Artificial Intelligence in theory and in practice for those who have little or no prior contact with data science and programming.
The course is conducted fully online in the University of Tartu’s Moodle environment.
The course will takes place from March 14 to May 9, 2022 and is held in Estonian. Participation is free. The training is funded by the ESF through the ‘Promoting Adult Learning and Expanding Learning Opportunities’ program.
Registration is open until March 6, 2022.
Online course on Hybrid Programming in HPC – MPI+X
Most HPC systems are clusters of shared memory nodes. To use such systems efficiently both memory consumption and communication time has to be optimized. Therefore, hybrid programming may combine the distributed memory parallelization on the node interconnect (e.g., with MPI) with the shared memory parallelization inside of each node (e.g., with OpenMP or MPI-3.0 shared memory). This course analyzes the strengths and weaknesses of several parallel programming models on clusters of SMP nodes. Multi-socket-multi-core systems in highly parallel environments are given special consideration. MPI-3.0 has introduced a new shared memory programming interface, which can be combined with inter-node MPI communication. It can be used for direct neighbor accesses similar to OpenMP or for direct halo copies, and enables new hybrid programming models. These models are compared with various hybrid MPI+OpenMP approaches and pure MPI. Numerous case studies and micro-benchmarks demonstrate the performance-related aspects of hybrid programming.
This course is a PRACE training event. It is organized by the VSC Research Center, TU Wien, in cooperation with HLRS and NHR@FAU.
The course will take place on 5-7 April 2022. Read more and register here!
The EuroHPC Summit Week 2022
The EuroHPC Summit Week (EHPCSW) 2022 takes place in Paris on 22-24 March 2022. This event will gather the main European HPC stakeholders from technology suppliers and HPC infrastructures to scientific and industrial HPC users in Europe. As in previous years, PRACE, the Partnership for Advanced Computing in Europe, co-locates its Scientific and Industrial Conference (PRACEdays22) at the EuroHPC Summit Week 2022. Furthermore, the EHPCSW 2022 will provide a great opportunity for the attendees to network.
The main organisers of the EHPCSW 2022 are the Partnership for Advanced Computing in Europe (PRACE), and the European Technology Platform for High-Performance Computing (ETP4HPC). The EuroHPC Joint Undertaking (EuroHPC JU) and the European Commission are also involved in the organisation of the conference.
ESTONIAN-FINNISH JOINT WEBINAR "HIGH PERFORMANCE COMPUTING FOR SMES"
The NCC Estonia and the NCC Finland will organize a webinar for companies to demonstrate the added value that high performance computing can provide. Small and medium enterprises (SMEs) can hugely benefit from HPC systems as these technologies increase competitiveness while saving time and money.
The webinar will take place on March 3rd as an online event. Participation is free of charge.
Specialists of the University of Tartu’s HPC Center made LUMI supercomputer accessible to users
EuroHPC Call for Centres of Excellence in HPC
The European High Performance Computing Joint Undertaking (EuroHPC JU) is preparing the transition towards exascale with a new call on Centres of Excellence for HPC. Exascale supercomputers are capable of more than a billion billion operations per second.
The call is funded by Horizon Europe, the EU funding program for research and innovation with a total budget of up to EUR 90 million including up to EUR 45 million of EU contribution to be matched by equivalent national contributions. Applications are invited for two topics:
The call will be open for submissions from January 27, 2022 until April 6, 2022. The selected projects are expected to start by January 1, 2023 for a period of four years. Proposed applications will have to commit to co-design activities with regards to hardware, software and codes as this will be key in ensuring that future HPC architectures are well suited for the applications and their users. Coordination with the Competence Centres will be required in order to address the current HPC skills gap, develop available HPC competences and ensure wider access to exascale applications.
AIRE - the AI & Robotics Estonia technology hub - supports Estonian manufacturers
AIRE brings together Estonian manufacturing companies, solution providers, universities and science parks, with everyone striving for a single goal. AIRE works for industrial development and innovation in the whole of Estonia by offering manufacturing companies training, advice, and new, digital, tailor-made solutions that cannot be found on the open market.
AIRE offers companies the chance to use scientific and research laboratories and support big data management within High Performance Computing centres, thereby assisting to make Estonian manufacturing companies more competitive in foreign markets.
AIRE is led by Tallinn University of Technology, and its partners are the University of Tartu, the Estonian University of Life Sciences, Tehnopol Science and Business Park, Tartu Science Park, and the Innovative Manufacturing Engineering Systems Competence Centre IMECC. One important goal is to help companies find additional funding for applying artificial intelligence and robotics in their development projects, using funds from structural grants, the recovery fund, the Horizon programme, the Digital Europe Programme (DEP) and elsewhere.
NVIDIA offers free online training courses
Whether you’re an individual looking for self-paced, online training or an organization wanting to develop your workforce’s skills, the NVIDIA Deep Learning Institute (DLI) can help. Currently they offer five courses that are free for anybody to take self-paced.
Speed Up DataFrame Operations With cuDF demonstrates significant speed up by moving common DataFrame operations to the GPU with minimal changes to existing code.
Getting Started with Universal Scene Description for Collaborative 3D Workflows explains how to generate a scene using human-readable Universal Scene Description ASCII (.USDA) files.
LUMI’s full system architecture revealed
The AMD MI250X GPU is in a class of its own now and for a long time to come. The technical supremacy and performance per watt were the primary reasons why AMD’s MI250X GPUs were selected for LUMI, explains Pekka Manninen, Director of LUMI Leadership Computing Facility.
The full system architecture of LUMI is the following:
The LUMI system is supplied by Hewlett Packard Enterprise (HPE), based on an HPE Cray EX supercomputer.
The GPU partition will consist of 2560 nodes, each node with one 64 core AMD Trento CPU and four AMD MI250X GPUs.
Each GPU node features four 200 Gbit/s network interconnect cards, i.e. has 800 Gbit/s injection bandwidth.
Each MI250X GPU consists of two compute dies, each with 110 compute units each, and each compute unit has 64 stream processors for a total of 14080 stream processors.
The committed Linpack performance of LUMI-G is 375 Pflop/s.
The MI250X GPU comes with a total of 128 GB of HBM2e memory offering over 3.2 TB/s of memory bandwidth.
A single MI250X card is capable of delivering 42.2 TFLOP/s of performance in the HPL benchmarks.
In addition to the GPUs in LUMI there is another partition (LUMI-C) using CPU only nodes, featuring 64-core 3rd-generation AMD EPYC™ CPUs, and between 256 GB and 1024 GB of memory. There are 1,536 dual-socket CPU nodes in total. LUMI-C was #5 on the November 2021 Graph500 list and #76 on the November 2021 Top500 list.
LUMI also has a partition with large memory nodes, with a total of 32 TB of memory in the partition.
When completed LUMI will take over 150m2 of space, which is about the size of a tennis court. The weight of the system is nearly 150 000 kilograms (150 metric tons).
ETAIS & ELIXIR seminar UT HPC Usage 101
During this UT HPC Usage 101 lecture course we will provide the participants basic knowledge required to use to submit, monitor, and control jobs on the compute nodes of UT HPC. We will talk about the principles of computing in a cluster and the difference between computing directly from the command line of a private server. We will introduce the good practices and standards of behavior that good cluster usage practice requires. Also the convenient graphical tools for monitoring the resource of your work will be covered. Finally, we might touch on the basic Slurm commands.
We expect the users to have basic LINUX command line experience, but very little or no cluster compute experience yet.
Learning outcome: Knowing how to submit, monitor and control jobs at UT HPC.
The seminar will take place in Zoom on 18th of November 2021 at 14.00 and will last approximately 90 minutes.
Registration is open at https://forms.gle/pVe86HVqjWB6GpLg8 and will close on 16th of November or when the course gets full.
An OpenMP training organized by the LUMI User Support Team
The course will take place online on November 9. – 10.
This course is part of the first OpenMP training organized by the LUMI User Support Team (LUST) and supported by CSC – IT Center for Science Ltd (Finland) and CSC Autumn of HPC 2021 (five modules program on teaching essential skills in parallel programming for modern GPU-accelerated supercomputers) under PRACE Training Centres activity.
This training aims to help the users to port their code to LUMI, the European pre-exascale supercomputer, that will achieve its high computing power thanks to a large number of nodes with AMD GPUs.
This course address the use of OpenMP for programming co-processors such as GPUs. It focuses on how to get the best out of OpenMP in terms of performance by exploring the implications of possible OpenMP parallelization strategies. Advanced topics such as asynchronous execution, interoperability with CUDA/HIP and the use of multiple GPUs are covered.
Registration is obligatory since the details to access the online course will be provided to the registered and accepted attendees only.
Read more about the course and register now at the PRACE Training website.
ENCCS GPU Hackathon 2021
The EuroCC National Competence Centre Sweden (ENCCS) will be hosting an online NVIDIA GPU hackaton that will take place on December 6th and December 13-15.
GPU Hackathons provide exciting opportunities for scientists to accelerate their AI research or HPC codes under the guidance of expert mentors from National Labs, Universities and Industry leaders in a collaborative environment. Teams of researchers are paired with experienced GPU mentors to learn and apply the accelerated and parallel computing skills needed by the scientific community. Both current or prospective users of large hybrid CPU/GPU HPC clusters who develop HPC and AI applications that could benefit from GPU acceleration are encouraged to participate!
Teams are expected to bring their own code or project to the event and be motivated to make progress during the hackathon. No advanced GPU skills required, but teams are expected to know the basics of GPU programming and profiling at the event.
The application deadline is October 31, 2021. Please click here to find out more about the event.
A free course on Shared Memory Programming with OpenMP
The EuroCC-funded UK National Competence Centre offers an online OpenMP course that will be supported by staff from EuroCC and PRACE to answer questions via chatboards and run regular online tutorials. This course covers OpenMP, the industry standard for shared-memory programming, which enables serial programs to be parallelised easily using compiler directives. Users of desktop machines can use OpenMP on its own to improve program performance by running on multiple cores; users of parallel supercomputers can use OpenMP in conjunction with MPI to better exploit the shared-memory capabilities of the compute nodes.
The course starts on November 1 and ends on December 3. All participants will be offered an account on ARCHER2, the UK National HPC Service, for the duration of the course.
The course is part-funded by the PRACE project and is free to all. Please follow this link for more information and registration.
EuroHPC SUMMIT WEEK TO BE HELD IN PARIS, MARCH 22-24
The EuroHPC Summit Week (EHPCSW) 2022 will gather the main European HPC stakeholders from technology suppliers and HPC infrastructures to scientific and industrial HPC users in Europe. As in previous years, PRACE, the Partnership for Advanced Computing in Europe, co-locates its Scientific and Industrial Conference (PRACEdays22) at the EuroHPC Summit Week 2022. Furthermore, the EHPCSW 2022 will provide a great opportunity for the attendees to network.
The main organizers of the EHPCSW 2022 are the Partnership for Advanced Computing in Europe (PRACE), and the European Technology Platform for High-Performance Computing (ETP4HPC). The European Commission (EC) will represent the EuroHPC Joint Undertaking (EuroHPC) in the organization of the conference. The logistical organization is supported by a local host: for the 2022 edition, this will be GENCI (Grand equipement national de calcul intensif).
For more information visit this link and stay tuned for more details.
THE NCC ESTONIA IS CELEBRATING ITS FIRST BIRTHDAY
The HPC Competence Centre of Estonia was established within the scope of the EuroCC project exactly one year ago – on September 1, 2020. Our first year of operation has been full of intensive work, exciting challenges and interesting meetings. We have just completed our annual report, which summarizes the activities and achievements that have taken place during the last year. We are pleased to confirm that the activities of NCC Estonia have proceeded according to initial plan. Most of the key perfomance indicators are fulfilled or even exceeded.
We would also like to congratulate the CASTIEL team, as they are also celebrating its first year of operation. Some essential deliverables of the CASTIEL and EuroCC projects are now available for public.
FF4EuroHPC TO LAUNCH THE SECOND OPEN CALL FOR HPC EXPERIMENTS
FF4EuroHPC is a European initiative that helps facilitate access to HPC related technologies for SMEs. Within the FF4EuroHPC project, European SMEs can develop unique products, innovative business opportunities and become more competitive by using European high-end HPC services. Whether it is running high-resolution simulations, doing large-scale data analyses, or incorporating AI applications into SMEs´ workflows, FF4EuroHPC connects business with cutting-edge technologies.
Two open calls will be offered through the project. The second call for proposals targets highest quality experiments involving innovative, agile SMEs and putting forward work plans built around innovation targets arising from the use of advanced HPC services. Priority will be given to consortia centred on SMEs that are new to the use of advanced HPC services.
Key call details
Submission Deadline: 29th September 2021, at 17:00 Brussels local time.
Expected duration of experiments: maximum 15 months with expected commencement 1st March 2022.
Funding for Call-2: The indicative total funding budget is € 5 M.
Maximum funding request per proposal: € 200,000 (covering all participants).
Find out all the details about the open call and application process: https://www.ff4eurohpc.eu/en/open-calls/open-call/
WORKSHOP ON SARS-COV2 DATA ANALYSIS and monitoring WITH GALAXY
The goal of this upcoming workshop is to build capacity in SARS-CoV-2 data analysis and data management, including data submission to ENA. After the workshop, all participants will be able to upload viral sequencing data, call all variants, create a variety of reports and create consensus alignments.
It will be a 4-day event introducing scalable and reproducible SARS-CoV-2 data analysis with Galaxy. The sessions will be pre-recorded and provided in advance. During the workshop, there will be live support in chat and live Q&A sessions, in which experts will answer questions.
PRACE AUTUMN SCHOOL 2021:
HARNESSING the EuroHPC Flagship supercomputers
The PRACE Autumn School 2021 will bring together undergraduate and graduate students and postdoctoral researchers in different disciplines of scientific computing.
The course consists of lectures and hands-on training on modern, GPU-accelerated high-performance computing: GPU programming and GPU code optimization at scale, as well as understanding and applying machine learning methods. The course includes also scientific case studies about using GPUs in various disciplines. The tutors and lecturers are experts in these fields providing various interesting aspects in the course topics.
The five days of school, organised by CSC – IT Center for Science, are filled with hacking, leisure activities and having good time together in Vuokatti, Finland. Also, the Autumn School includes a visit to the CSC’s Data Center in Kajaani, the home of one of the most powerful supercomputers in the world: LUMI. It is a unique opportunity for the participants to familiarize themselves with the cutting-edge data infrastructure in the field of HPC.
Data Science Seminar:
High-Performance Computing: Big Is Beautiful
High-Performance Computing (HPC) is the application of “supercomputers” to computational problems that are either too large for standard computers or would take too long to solve. HPC is a pervasive tool for both academia and industry. “Today, to Out-Compute is to Out-Compete” best describes the role of HPC.
A recent seminar brought together HPC users, administrators and visionaries. Researchers talked about their experiences with using HPC in their daily work. The administrator of Tartu HPC center introduced the backstage of managing large amounts of data. Finally, we took a closer look at the new supercomputer LUMI, which will launch in 2021, to take computing performance to a new unprecedented level.
Galaxy-ELIXIR webinars series:
Galaxy is supported by a large and active community distributed across the globe, which leads to rapid developments in every release. However, many of this features remain unknown by most of the users.
With this series of four webinars chaired by Hans-Rudolf Hotz, the global Galaxy community will present such advanced features, touching upon workflows, data processing and management, interoperability and interactive tools, among others.
The webinar series takes place between 3 and 24 March 2021.
A new supercomputer LUMI starts operating in summer 2021
A new supercomputer LUMI (Large Unified Modern Infrastructure) is being built in Finland. It is expected to open for users from July 2021.
At the time of installation, LUMI will be one of the world’s fastest computer systems. LUMI’s performance will be more than tenfold compared to one of Europe’s fastest supercomputer today (Piz Daint, Switzerland). LUMI will also be one of the world’s leading platforms for artificial intelligence.
LUMI will be capable of executing 375 petaflops, or more than 375 million billion calculations per second. Theoretically, it’s maximum performance will be more than 550 petaflops per second, equalling that of 1.5 million laptops.
LUMI will be located at CSC’s (IT Center for Science) data center in Kajaani town. LUMI is using 100% hydropowered energy. The waste heat of LUMI will produce 20 percent of the district heat of the area.
The supercomputer will be hosted by the LUMI consortium including ten European countries: Finland, Belgium, the Czech Republic, Denmark, Estonia, Iceland, Norway, Poland, Sweden, and Switzerland.
As a member of the consortium, Estonia can use 2% of LUMI’s supercomputer resources. This opens up unprecedented technological opportunities for Estonian HPC users.
estonia has Joined the eurocc project
Estonia is participating in the EuroCC project, that brings together the necessary expertise to set up a network of more than 30 National Competence Centres (NCCs) in HPC across Europe.
The NCCs will coordinate activities in all HPC-related fields at the national level and serve as a contact point for customers from industry, science, HPC experts, and the general public alike.
The EuroCC project aims to elevate the participating countries to a common high level in the fields of HPC, High Performance Data Analytics (HPDA) and artificial intelligence. Ultimately, the goal is to promote the use of HPC in Europe and to increase the competences of its users.
The EuroCC activities are coordinated by the High-Performance Computing Center Stuttgart (HLRS). The EuroCC project is funded 50 percent through H2020 (EuroHPC Joint Undertaking) and 50 percent through national funding programs within the partner countries.