Seminars of Innovation and Research in Informatics

This is a multi-month student competition. In this competition, big EDA (electronic design automation) companies define a several problems related to the field of EDA which students are called to solve. The competition takes place in teams under the supervision of an academic advisor and each team can try to solve one or more problems. The solutions are ranked based on some predefined criteria and can be improved over 3 phases, out of which the last one is used for ranking. The 3 top teams are invited to the conference to present their solutions, with a travel grant. In that case, the local organiser will accompany the qualified team(s). Moreover, the top 3 student teams receive monetary awards/prizes. Additional bonuses are provided for releasing the developed solution as open source. The first two of this year's problems require background typically obtained in EDA related courses e.g. Processor Design, Nanoelectronic Circuit Design, Algorithms for VLSI, VLSI, while the 3rd one requires knowledge of CUDA eg. obtained from the Parallel Programming Tools and Models course or PUMPS summer school.

The award ceremony of the top 3 teams will take place in November 2020 at San Diego, US.

The PUMPS Summer School is delivered by the GPU Center of Excellence (GCOE) awarded by NVIDIA to the Barcelona Supercomputing Center (BSC) in association with Universitat Politècnica de Catalunya (UPC). This eighth edition of the Programming and Tuning Massively Parallel Systems summer school (PUMPS) is aimed at enriching the skills of researchers, graduate students and teachers with cutting-edge technique and hands-on experience in developing applications for many-core processors with massively parallel computing resources like GPU accelerators.

Warning: Dates to be confirmed

The objectives of this course are to understand the basic concepts on programming with Python and its support for parallelism.The students who finish this course will be able to develop simple parallel benchmarks with Python, and analyze their execution and tune their behaviour in parallel architectures

The ACACES Summer School is organized by the HiPEAC Network in collaboration with the TETRAMAX Innovation Action. ACACES 2020 is the sixteenth edition of the Summer School. This year it has 58 hours online. The ACACES Summer School is a one week summer school for computer architects and tool builders working in the field of high-performance computer architecture and compilation for computing systems. The school aims at the dissemination of advanced scientific knowledge and the promotion of international contacts among scientists from academia and industry. A distinguishing feature of this Summer School is its broad scope ranging from low level technological issues to advanced compilation techniques. In the design of modern computer systems one has to be knowledgeable about architecture as well as about the quality of the code, and how to improve it. This summer school offers the ideal mix of the two worlds ¿ both at the entry level and at the most advanced level. The summer school is open to everybody but previous training and/or experience in computer science as well as a background in computer architecture or compilation is indispensable.

This course identifies topics that are both fundamental to computer architecture and relevant to the design of microprocessors of the future. The emphasis is always on insights that will be useful to the graduate student, whether he/she goes on for a PhD or joins a microprocessor design team. The course would also be useful to the non- computer-architecture student who realizes that a deeper awareness of what is being thought of in computer architecture could have major impact on his/her non- architecture future work.

Warning: Dates tot be confirmed

Curs Coursera https://www.coursera.org/learn/embedded-operating-system 12/05/2020 - 19/05/2020

Curs Coursera https//www.coursera.org/learn/parallelism-ia Fet del14/05/2020 al 21/04/2020.

Curso de coursera https://www.coursera.org/learn/parallel-programming-in-java, hecho del 28/4 al 08/05/2020. No lo registre antes porque no sabia que no dejaba registar seminarios a fechas pasadas y estaba esperando la confirmación de los anteriores.

Curs Coursera https://www.coursera.org/learn/neural-networks-deep-learning

The British Colloquium for Theoretical Computer Science (BCTCS) is an annual event for UK-based researchers in theoretical computer science. A central aspect of BCTCS is the training of PhD students, providing an environment for students to gain experience in presenting their work, to broaden their outlook on the subject, and to benefit from contact with established researchers. The scope of the colloquium includes all aspects of theoretical computer science, including automata theory, algorithms, complexity theory, semantics, formal methods, concurrency, types, languages and logics. BCTCS 2020 is the 36th conference in the series and is being held together with a workshop organized by AlgoUK, a network for the UK's algorithms and complexity research community. *** NOTICE: *** Due to the COVID-19 pandemic, this year's BCTCS will be held as a virtual conference via Zoom. We have limited experience doing this - so wish us well. We expect there to be some hiccups, but overall expect things to work out. Anyone can participate in the meeting (there is no registration fee). The instructions for joining can be found http://cs.swansea.ac.uk/bctcs2020/zoom . If you have any questions or difficulties, please email L.P.OReilly@swansea.ac.uk.

http://cs.swansea.ac.uk/bctcs2020/

This is an expansion of the topic "OpenACC and other approaches to GPU computing" covered on last years editions of the Introduction to CUDA Programming. This course is delivered by the GPU Center of Excellence (GCOE) awarded by NVIDIA to the Barcelona Supercomputing Center (BSC) in association with Universitat Politecnica de Catalunya (UPC). It will provide very good introduction to the PUMPS Summer School run jointly with NVIDIA - also at Campus Nord, Barcelona.. 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.. (Please, previous registration on website)

This is a multi-month student competition organised by Google as part of the International Workshop on Logic & Synthesis (IWSL), which is co-located with the Design Automation Conference (DAC) at San Francisco, CA in July. In this competition the students are invited to implement machine learning solutions to learn an unknown boolean function. The solutions are ranked based on some predefined criteria. Although this contest requires basic knowledge on logic synthesis which can be obtained from EDA (Electronic Design Automation) related courses e.g. VLSI, Algorithms for VLSI, Nanoelectronic Circuit Design and Processor Design, it also requires some background in machine learning, which can be obtained from the courses of the Data Science specialisation. Students of both disciplines are capable of participating in the contest, although mixed groups formed by students of both specialisations are encouraged. The top teams are invited to the conference to present their solutions, with a travel grant. In that case, the local organiser will accompany the qualified team(s).

The award ceremony for top teams will take place 18-19 July 2020 at San Francisco, US.

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.

09:00h to 18:00h

To explain the different components that MareNostrum 4 is composed, which were the design decisions taken and why. To 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.

Recent advances in Artificial Intelligence (AI) have stimulated the widespread interest of integrating AI capabilities into software and services across industries and business sectors. Unfortunately, current AI technologies are not sufficiently democratized - building complex AI and ML systems requires deep expertise in computer science and extensive programming skills. It is an emerging demand on how to improve the productivity of data scientists, software engineers, and AI-ML practitioners in industry and academia. On top of current challenges for building software systems, AI adds additional concerns for developing, testing and deploying systems. Presenting topics in this seminar covers the-state-of-the-art Artificial Intelligence System development, the challenges, and currently known good practices.

Thursday from 16:00 to 19:00 and Friday from 15:00 to 18:00

The course will make the attendants familiar with simulation technologies used in Life Sciences and their specific adaptation to HPC environment Detailed outline: 1) Introduction to bio molecular simulation 2) Coarse-grained and atomistic simulation strategies 3) Automated setup for simulation 4) HPC specifics: Large scale parallelization, use of GPU's 5) Storage and strategies for large scale trajectory analysis Prerequisites: Basic knowledge of structural bioinformatics Basic knowledge of parallelization strategies

All human activities have implications on our society. Professional exercise in engineering, being a researcher or running innovation projects imply making decisions that are not exclusively technical, they involve ethical considerations. Theoretical sessions are complemented with numerous examples and cases.

Friday: 11:00-13:00

This tutorial will introduce the audience to the BSC tools for heterogeneous programming on FPGA devices. It describes OmpSs@FPGA, as a productive programming environment for compute systems with FPGAs. More specifically, the tutorial will: 1) Introduce the OmpSs@FPGA programming model, how to write, compile and execute applications on FPGAs 2) Show the "implements" feature to exploit parallelism across cores and IP cores. 3) Demonstrate how to analyze applications to determine which portions can be executed on FPGAs, and use OmpSs@FPGA to parallelize/optimize them. (Please, previous registration on website)

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: o MPI applications on clusters of SMPs, and o Leverage CUDA kernels with OmpSs on clusters of GPUs Prerequisites: Good knowledge of C/C++. Basic knowledge of CUDA/OpenCL and Paraver/Extrae (Please, previous registration on website)

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. (Please, previous registration on website)

In this student competition, which is organised as a part of the High Performance Graphics 2020 Conference, students are invited to implement an innovative solution in which they can use GPU hardware features, such as the tensor cores or RTX ray-tracing hardware extensions for a different purpose than the one for which they have been introduced. For example, the attendees of PUMPS 2019 may remember the presentation of a technique for the acceleration of reductions and scans using the tensor core units. The students of the best two projects will be invited to attend the High Performance Graphics Conference at Washington D.C. during July 16-18, with a travel grant. In this case, the local organiser will accompany the winning team(s).

Possible extension of the submission deadline due to COVID-19.

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.). In addition, 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. (Please, previous registration on website)

The objective of this course is to learn how to use systems with more than one memory subsystem. We will see the different options on using Intel's KNL memory subsystems and systems equipped with Intel's Optane technology

09:00 - 18:00

This is a multi-month hardware security contest. The organisers provide the RTL code of a "buggy" SoC (last year it was the RISC-V Ariane with some vulnerabilities injected) together with a security specification. The participants, who can be from industry or students, are organised in teams of 4 under the supervision of an academic advisor and they have to perform security verification, so they need to find, fix and report as many security vulnerabilities as they can. The top teams of the first phase will be invited to compete in a similar, one day event at DAC and receive monetary prizes. In that case, the travel cost will be covered by a travel grant from the competition sponsors and the local organiser from UPC will accompany the qualified teams.

Possible extension of Phase I due to COVID19. If team qualifies for Phase II, it will finish July 23

The objective of this course is to give a panorama on the use of HPC-based computational mechanics in Engineering and Environment through the projects BSC are carrying on. This panorama includes the basics of what is behind the main tools: computational mechanics and parallelization. The students who finish this course will be able to take active part in such projects both in academia or industry.

A workshop to understand the tool (Flexsim) and be able to start using it for modelling, this workshop also includes a practical formation to experiment with some initial models. The workshop will be on Spanish language. To register to the seminar is mandatory to access this link https://www.eventbrite.es/e/entradas-flexsim-workshop-y-training-en-la-upc-88677921049

16:30-19:30

The course brings together key information technologies used in manipulating, storing, and analysing data including: - the basic tools for statistical analysis, - techniques for parallel processing, - tools for access to unstructured data, - storage solutions. (Please, previous registration on website)

Objectives: The objective of this course is to give an overview of BSC storage solutions, Hecuba and dataClay. These two platforms allow to easily store and manipulate distributed data from object-oriented applications, enabling programmers to handle object persistence using the same classes they use in their programs, thus avoiding time consuming transformations between persistent and non-persistent data models. Also, Hecuba and dataClay enable programmers to transparently manage distributed data, without worrying about its location. This is achieved by adding a minimal set of annotations in the classes. Learning Outcomes In the course, the Hecuba and dataClay syntax, programming methodology and an overview of their internals will be given. Also, an overview of COMPSs at user level will be provided in order to take advantage of the distribution of data with both platforms. The attendees will get a first lesson about programming with the common storage interface that will enable them to start programming with both frameworks. A hands-on with simple introductory exercises will be also performed for each platform, with and without COMPSs to distribute the computation. The students who finish this course will be able to develop simple Hecuba and dataClay applications and to run them both in a local resource and in a distributed platform (initially in a private cloud)

Objectives: The objectives of this course are COMPSs is a programming model which is able to exploit the inherent concurrency of sequential applications and execute them in a transparent manner to the application developer in distributed computing platform. This is achieved by annotating part of the codes as tasks, and building at execution a task-dependence graph based on the actual data used consumed/produced by the tasks. The COMPSs runtime is able to schedule the tasks in the computing nodes and take into account facts like data locality and the different nature of the computing nodes in case of heterogeneous platforms. Additionally, recently COMPSs has been enhanced with the possibility of coordinating Web Services as part of the applications. COMPSs supports Java, C/C++ and Python as programming languages. Learning Outcomes: In the course, the COMPSs syntax, programming methodology and an overview of the runtime internals will be given. The attendees will get a first lesson about programming with COMPSs that will enable them to start programming with this framework. A hands-on with simple introductory exercises will be also performed. The students who finish this course will be able to develop simple COMPSs applications and to run them both in a local resource and in a distributed platform (initially in a private cloud Prerequisites: Programming skills in Java

Afopa és una agrupació d'Aules dedicades a la formació permanent de la gent gran que concentra els seus esforços en sensibilitzar als ciutadans de la necessitat de seguir una formació per al desenvolupament personal, cultural i social de les persones. L'objectiu prioritari de l'agrupació és millorar la qualitat de vida de la gent gran seguint el camí de la cultura. I això és possible gràcies a les col·laboracions amb un conjunt d'Aules que fan possible l'accés de la gent gran al conjunt de l'oferta formativa existent. Els estudiants de màster poden contribuir definitivament a la formació de la gent gran mitjançant una xerrada tècnica, a més de poder rebre un interessant feedback. Qui vulgui presentar un treball de recerca, un treball dirigit o la seva feina en el seu TFM, poden proposar una xerrada a la persona de contacte a l'UPC. Envieu un títol orientatiu, la temàtica o paraules claus, i una breu descripció.

Tot el quadrimestre

This course is the first course in the University of Toronto's Self-Driving Cars Specialization. Self-driving cars are one of the state-of-the-art research topic for machine learning, which is a crucial part of Data Science. In this course I obtained crucial knowledge about deep learning techniques that can be applied to self-driving cars, and provided me basic knowledge for a next step in my career.

Flexible

Novartis organized their 2nd edition of datathon with the collaboration of Eurecat. The aim was solving a data science challenge related to financial data, the team that do a prediction more effectively win the competition.

Organized by FIB, BSC-CNS, hackersUPC, Sant Joan de Deu, CREB and rarehacks. During three days, students, professors, researchers and people related to health and IT will work together to achieve solutions to some rare diseases problems. The possible solutions will imply technologies in AI, Big Data, Virtual Reality, Computer Graphics, HPC, 3D printer, etc. There will be talks and workshops in technologies. Breakfast, lunch and dinner are free. There will be lot of solidarity and fun. And... you may use Marenostrum!

Friday (18-23:30h), Saturday (9-23h), Sunday (9-17h)

This course focuses on modelling two of the highest impact natural hazards, volcanic eruptions and tsunamis. The objective is to give a succinct theoretical overview and then introduce students on the use of different HPC flagship codes included in the Center of Excellence for Exascale in Solid Earth (ChEESE). Learning Outcomes: Participants will learn and gain experience in installing SE codes and related utilities and libraries, running numerical simulations, monitoring the execution of supercomputing jobs, analyzing and visualizing model results. At least University degree in progress on Earth Sciences, Computer Sciences or related area. o Basic knowledge of LINUX o Knowledge of C, FORTRAN, MPI or openMP is recommended o Knowledge of Earth Sciences data formats is recommended (grib, netcdf, hdf,¿) o Basic knowledge of python

Novartis organized their 2nd edition of datathon with the collaboration of Eurecat. The aim was solving to data science challenge related to financial data, the team do a prediction more effectively win the competition.

The objective of this PATC course is to cover the basics of a high performance computing (HPC) environment oriented towards earth science applications, specifically chemical weather modelling and climate modelling. More precisely, the course will cover: - Introduction to earth science fundamentals and modelling; - Basic usage of an HPC environment: shell, compilers, libraries, file systems, queuing system; - Build and configure targeted earth science applications with the NMMB/BSC-CTM chemical transport model and with the EC-EARTH climate model; - Execute and monitor numerical experiments using a workflow manager; - Analyse and visualise model outputs with a wide set of tools. Prerequisites: - At least University degree in progress on Earth Sciences, Computer Sciences or related area - Basic knowledge of UNIX - Knowledge of C, FORTRAN, MPI or openMP is recommended - Knowledge of Earth Sciences data formats is recommended (grib, netcdf, hdf,¿) - knowledge of R and python

In its fourth edition, IN(3D)USTRY becomes INDUSTRY From Needs to Solutions to include more industrial sectors. Our main goal is to cover the entire value chain and provide intelligent manufacturing solutions.

The objectives of this course are to understand the fundamental concepts supporting message-passing and shared memory programming models. The course covers the two widely used programming models: MPI for the distributed-memory environments and OpenMP for the shared-memory architectures. The course also presents the main tools developed at BSC to get information and analyze the execution of parallel applications, Paraver and Extrae. It also presents the Parallware Assistant tool, which is able to automatically parallelize a large number of program structures, and provide hints to the programmer with respect to how to change the code to improve parallelization. It deals with debugging alternatives, including the use of GDB and Totalview. The use of OpenMP in conjunction with MPI to better exploit the shared-memory capabilities of current compute nodes in clustered architectures is also considered. Paraver will be used along the course as the tool to understand the behavior and performance of parallelized codes. The course is taught using formal lectures and practical/programming sessions to reinforce the key concepts and set up the compilation/execution environment.

HackUPC is the first student hackathon in Spain. This will be our sixth edition with 700 awesome hackers and lots of side activities to learn new technologies, meet interesting people and have fun. Come make history with us!

Friday 3pm to Sunday 5pm

Conferencia de Python en la que se imparten varias charlas y talleres sobre Machine Learning y Big Data con Python. La agenda de la conferencia, en la que pueden encontrarse todas las charlas/talleres anteriormente mecionados puede encontrarse en la web de la PyCon (adjuntada en la petición).

GECON 2019 builds upon the very successful tradition of the conference previous editions since 2003, (http://www.gecon-conference.org). GECON solicits contributions that are interdisciplinary, combining business and economic aspects with engineering and computer science related themes. Contributions to this conference can include extensions to existing technologies, successful deployments of technologies, economic analyses, analyses of technology adoptions, and theoretical models. We welcome papers that combine micro- and macro-economic principles with resource management strategies in computer science and engineering. Case studies, which demonstrate practical use of economic strategies, benefits and limitations, are particularly encouraged. The purpose of this event is to gather original work and build a strong multidisciplinary community in this increasingly important area of a future information and knowledge economy.

http://gecon2019.gecon.info/index.php/program

GECON 2019 builds upon the very successful tradition of the conference previous editions since 2003, (http://www.gecon-conference.org). GECON solicits contributions that are interdisciplinary, combining business and economic aspects with engineering and computer science related themes. Contributions to this conference can include extensions to existing technologies, successful deployments of technologies, economic analyses, analyses of technology adoptions, and theoretical models. We welcome papers that combine micro- and macro-economic principles with resource management strategies in computer science and engineering. Case studies, which demonstrate practical use of economic strategies, benefits and limitations, are particularly encouraged. The purpose of this event is to gather original work and build a strong multidisciplinary community in this increasingly important area of a future information and knowledge economy.

http://gecon2019.gecon.info/index.php/program

GECON 2019 builds upon the very successful tradition of the conference previous editions since 2003, (http://www.gecon-conference.org). GECON solicits contributions that are interdisciplinary, combining business and economic aspects with engineering and computer science related themes. Contributions to this conference can include extensions to existing technologies, successful deployments of technologies, economic analyses, analyses of technology adoptions, and theoretical models. We welcome papers that combine micro- and macro-economic principles with resource management strategies in computer science and engineering. Case studies, which demonstrate practical use of economic strategies, benefits and limitations, are particularly encouraged. The purpose of this event is to gather original work and build a strong multidisciplinary community in this increasingly important area of a future information and knowledge economy.

http://gecon2019.gecon.info/index.php/program

Research and solution design

Solution Implementation

Workshops and formation of the students

This course aims to provide an extremely practical vision of the application to real problems of modeling techniques, from the most basic to the most state-of-the art ones, in highly quantitative business environments (banking and finance). The goals of this course is to learn the challenges involved in creating a model in the real world from obtaining the data to the best model to be used and the validation mechanisms depending on the type of problem. Good practices and description of the usual problems in a large modeling project.

The course taught by Dr. Christian Weiss comprises an introduction to the modeling of discrete time-series, by looking at the different models for discrete count-like, ordinal and categorical time-series. Throughout the lectures, models and methods are illustrated with diverse real-data time series using the statistical software R.

25-27 9:00~13:00, 28 8:00~11:00

Knowing how to classify a categorical response variable based on information provided by predictor variables is a necessary skill for any data scientist. This course will teach statistical and machine learning methods for classification and illustrate their application by analyzing a variety of real datasets using R. The participants will be given a similar dataset to analyze to gain hands-on experience.Course goalsThis course will provide a hands-on training in statistical and machine learning methods for classification, their implementation using R, and their application.Course contents The course will be taught using the book, An Introduction to Statistical Learning with Applications in R, by James, Witten, Hastie, and Tibshirani, Springer, 2013. A free PDF copy of the book can be downloaded from http://www-bcf.usc.edu/~gareth/ISL/. The following is a tentative schedule and list of topics to be covered: