Posted on by Ana Maria Montero Martinez Posted in Participants 2017, PRACE Summer of HPC 2017 — No Comments ↓ 
Hello world!

Happily hiking in France, minutes before getting lost in the Mountain.

My name is Ana María Montero and I am a 23 years old Physics student. I am from Spain and I come from a nice town close to the border with Portugal called Badajoz, where I also study. I am about to finish my Bachelor’s studies in Physics at the University of Extremadura where I am preparing my thesis regarding the behavior of classical one-dimensional liquids (which means I put a lot of marbles in a line and check their properties).

 

 

Next year I will be travelling to Germany to pursue my Master’s degree in Simulation Sciences offered by RWTH Aachen and Forschungszentrum Julich as I would like to specialize in computer simulations. This is the main reason why I applied several months ago to be here today, participating in the Summer of HPC program and working in the best computing centers in Europe.

Apart from this, and though it seems like debugging stuff is my favorite activity (if it is not my favorite one, it definitely is the one I dedicate most time to) I also enjoy doing a lot of other activities: Regarding the musical world, I play the piano and the violin whenever I can and I also sing in my university choir. Regarding outdoors activities, I love hiking (even when I get lost in the middle of a mountain in France) and traveling (even when that means that I have to face the heartless Polish winter).

This is how a Spanish girl looks like in Poland in January.

This year’s vacation however, consists of spending a couple of months in Dublin, the city of Guinness, live music and Temple bar. But Dublin is also the city of ICHEC, where I will be working for two months studying and predicting “El Niño” and its consequences worldwide (who knows, maybe this helps Irish people predict their unpredictable weather). So, in general terms, I have already set up the algorithm for my summer plans, and, speaking in FORTRAN language, it looks like this:

—————————————————–

! Ana’s summer program 2017 for FORTRAN speakers:

Do day=1st of July, 8th of July, 1

     Amazing training week in Ostrava

End do

Do day=9th of July, 31st of August, 1

     If (day==weekday) then

           Work at the ICHEC in Dublin

     Else

           Visit and enjoy Ireland!

     End if

End do
-----------------------------------------------------

Enjoying the training week in Ostrava

 

Nevertheless, as amazing as the plans look like right now, by the end of the summer I will be able to show those plans to the world. My visualization work at the ICHEC will help me bring “El Niño” and its consequences to life and my camera will help me capture the rest of Ireland’s wonders.

After an incredible week at IT4Innovations in Ostrava, I cannot wait to start my project in Dublin and to put into practice everything I have learnt.

 

 

 

 

 

Posted on by Dimitra Anevlavi Posted in Blogs 2017, PRACE Summer of HPC 2017 — 10 Comments ↓

For sure, information about the city near the border of the Czech Republic where four rivers meet can be found in most tour guides. But I would still like to share with you how we discovered the hidden vibes of Ostrava during the training week for the PRACE Summer of HPC program. We were accommodated in Garni Hotel, which is situated in the University campus in Ostrava-Poruba. Finding the hotel and gathering together during the first days right before the training week felt like a treasure hunt game, but the sunset view and the fun we had there really paid off.

Ostrava is a quite city in general that is well suited for long walks not only in the parks but also in the heart of its industrial part. We arranged a tour in the Lower Vítkovice area in order to discover the unique collection of historic industrial architecture that is included in UNESCO’s World Heritage List. In addition to that, you can visit the Bolt tower that lies on top of an actual blast furnace if you feel brave enough to climb up. There is coffee and delicious cakes up there, in case you need motivation 🙂 . Make sure not to miss the world music festival “Colours of Ostrava” that takes place at the metallurgical center. The contrast between the immense metal structures of the coal-mining infrastructure and the lively colors of the music stages conveys the concept of the city’s steel heart. The architecture is definitely something to be noticed, so do not hesitate to walk around – even round the industrial part of the city.

The local pubs proved to be an actual meeting point for us 🙂 that ensured that a long day of seminars in High Performance Computing, held in IT4Innovations, ends in best way possible!!!

Stodolni Street is a must both for locals and travelers, because it hosts unique pubs. We started from one point of the famous street and danced our way through the other corner. It was so much fun 🙂 . I also really enjoyed a local pizzeria near the University campus and a small bistro café that had awesome coffee, lunch, lemonades and cupcakes. I am sure almost everyone agrees with me on that. 😉

Final tips: If you have nice company, visit Ostrava and discover for yourself the hidden treasures of an industrial city near the borders with Poland. The weather is unpredictable and it matches for sure your adventures there. 🙂

Cheers 🙂

//

Posted on by Leon Kos Posted in PRACE Summer of HPC 2017 — No Comments ↓

Early-stage POstgraduate and late-stage undergraduate students are invited to apply for the PRACE Summer of HPC 2017 programme, to be held in July & August 2017. Consisting of a training week and two months on placement at top HPC centres around Europe, the programme affords participants the opportunity to learn and share more about PRACE and HPC, and includes accommodation, a stipend and travel to their HPC centre placement. Applications open 11 January 2017.

 

About the PRACE Summer of HPC

The PRACE Summer of HPC is a PRACE outreach and training programme that offers summer placements at top HPC centres across Europe to late-stage undergraduates and early-stage postgraduate students. Up to twenty top applicants from across Europe will be selected to participate. Participants will spend two months working on projects related to PRACE technical or industrial work and produce a report and a visualisation or video of their results.

 

PRACE SoHPC 2016 Participants and Trainers at Training Week in Juelich, Germany 

 

The programme will run from 2 July to 31 August 2017, with a kick-off training week at IT4I Supercomputing Centre in Ostrava attended by all participants. Flights, accommodation and a stipend will be provided to all successful applicants. Two prizes will be awarded to the participants who produce the best project and best embody the outreach spirit of the programme.

 

PRACE SoHPC 2016 Award winners Marta Čudova and Anurag Dogra,with PRACE members Sergio Bernardi, Florian Berberich, Leon Kos and Sanzio Bassini

 

Participating in the PRACE Summer of HPC

Applications are welcome from all disciplines. Previous experience in HPC is not required, as training will be provided. Some coding knowledge is a prerequisite but the most important attribute is a desire to learn, and share, more about HPC. A strong visual flair and an interest in blogging, video blogging or social media are desirable. Project outlines with more detailed prerequisites and more information on applying are available on the PRACE Summer of HPC website www.summerofhpc.prace-ri.eu.

Applications open on 11 January 2017 via www.summerofhpc.prace-ri.eu

For the latest information on the programme follow us on twitter @summerofhpc or visit us on Facebook http://www.facebook.com/SummerOfHPC

 

About PRACE

The Partnership for Advanced Computing in Europe (PRACE) is an international non-profit association with its seat in Brussels. The PRACE Research Infrastructure provides a persistent world-class high performance computing service for scientists and researchers from academia and industry in Europe. The computer systems and their operations accessible through PRACE are provided by 5 PRACE members (BSC representing Spain, CINECA representing Italy, CSCS representing Switzerland, GCS representing Germany and GENCI representing France). The Implementation Phase of PRACE receives funding from the EU’s Seventh Framework Programme (FP7/2007-2013) under grant agreement RI-312763 and from the EU’s Horizon 2020 Research and Innovation Programme (2014-2020) under grant agreements 653838 and 730913. For more information, see www.prace-ri.eu

 

Do you want more information? Do you want to subscribe to our mailing lists?

Please visit the PRACE website: http://www.prace-ri.eu

Or contact Marjolein Oorsprong, Communications Officer:

Telephone: +32 2 613 09 27 E-mail: M.Oorsprong@staff.prace-ri.eu

Posted on by SoHPC Team Posted in Blogs 2015

Applications are open from 11th of January 2017 to 19th of February 2017. See the Timeline for more details.

PRACE Summer of HPC programme is announcing projects for 2017 for preview and comments by students. Please send questions to coordinators directly by the 11th of January. Clarifications will be posted near the projects in question or in FAQ.

About the Summer of HPC program:

Summer of HPC is a PRACE programme that offers summer placements at HPC centres across Europe. Up to 20 top applicants from across Europe will be selected to participate. Participants will spend two months working on projects related to PRACE technical or industrial work to produce a visualisation or video. The programme will run from July 1st, to August 31th.

For more information, check out our About page and the FAQ!

Ready to apply? Click here! (Note, not available until January 11th, 2017)

Click here to take a closer look at the projects for 2017!

Have some questions not found in the About section or the FAQ? Email us at sohpc16-coord@fz-juelich.de.

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1701

The focus of this project will be on  enhancing further hybrid (e.g. stochastic/ deterministic) method for Linear Algebra. The focus is on Monte Carlo and quasi-Monte Carlo hybrid methods and algorithms for matrix inversion and solving systems of linear algebraic equations. Recent development s led to efficient approaches  based on bulding an efficient stochastic preconditioner and then solving the corresponding System of Linear Algebraic Equations (SLAE) by applying an iterative method. Thepreconditioner is a Monte Carlo preconditioner based on Markov Chain Monte Carlo (MCMC) methods to compute a rough approximate matrix inverse first. The above Monte Carlo preconditioner is further used to solve systems of linear algebraic equations thus delivering hybrid stochastic/deterministic algorithms. The advantage of the proposed approach is that the sparse Monte Carlo matrix inversion has a computational complexity linear of the size of the matrix.  Current implementations are either pure MPI or mixed MPI/OpenMP ones.  The efficiency of the approach is usually  tested on a set of different test matrices from several matrix market collections.

The intern have to take the existing MPI or MPI/OpenMP code and will have to design mixed MPI/CUDA  implementation to run on the new NVIDIA P100 GPUs.  The efficiency of the new implementation will be investigated as possible comparisons with the pure MPI implementation will be carried out time permitting.

Project Mentor: Vassil Alexandrov

Site Co-ordinator: Maria Ribera Sancho

Learning Outcomes:

The student will learn to design parallel hybrid  Monte Carlo methods.

The student will learn how to implement these methods on modern computer architectures with latest NVIDIA P100 GPU accelerators as well as how to design and develop mixed MPI/CUDA code.

Student Prerequisites (compulsory): 

Introductory level of Linear Algebra, some parallel algorithms design and implementation concepts, parallel programming using MPI and CUDA.

 Student Prerequisites (desirable): 

Some skills in being able to develop mixed code such MPI/OpenMP will be an advantage.

Training Materials:

These can be tailored to the student once he/she is selected.

Workplan:

  • Week 1/: Training week
  • Week 2/:  Literature Review Preliminary Report (Plan writing)
  • Week 3 – 7/: Project Development
  • Week8/: Final Report write-up

Final Product Description: 

The final product will be a parallel application that can be executed on hybrid architectures with NVIDIA  P100 GPU accelerators.  Ideally we would like to publish the results in a paper on a conference or a workshop.

Adapting the Project: Increasing the Difficulty:

The project is on the appropriate cognitive level, taking into account the timeframe and the need to submit final working product and 2 reports

Resources:

The student will need access to a machine with NVIDIA P100 GPU accelerators, standard computing resources (laptop, internet connection) as well as an account in Marenostrum supercomputer.

Organisation:
Barcelona Supercomputing Centre

BSC_logo

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1702

Simulating realistic large scale crowd behaviours is a complex endeavour. The use of real data and realistic perception models is required. And once the behaviour is established, one must generate and animate varied characters for realistic visualization without consuming too much memory and computing resources. At the Extreme Computing group at BSC, we have been working on the development of methods for simulating, generating, animating and rendering crowds of varied aspect and a diversity of behaviours. The focus is on efficient simulations of large crowds that can be run on low cost systems because we use of modern programmable GPUs and to scale up for even larger crowds:  We subdivide the simulation into different regions and distribute the work to different nodes by using MPI and to the different CPUs and GPUs in each node by using OmpSS and within each GPU we use CUDA, striving to use all the computational resources available in these heterogeneous clusters. The ultimate goal is to simulate and visualize very large crowds (of over a million or several million characters) using a variety of advanced architectures in real time.

Further given our groups experience in Monte Carlo methods we would like to bring their advantages such as their increased level of parallelism and combine them with other machine learning approaches, in particular Deep Learning, and develop  new highly parallel Monte Carlo and Deep Learning approaches that use real data and simulation for more realistic large scale crowd simulation.

The students is expected to take the existing code and implement a Monte Carlo Deep Learning algorithm for crowd simulation. It is expected to test it on an NVIDIA  P100 GPU based cluster.

Project Mentor: Vassil Alexandrov

Site Co-ordinator: Maria Ribera Sancho

Learning Outcomes:

The student will learn to design parallel hybrid  Monte Carlo and Deep Learning  methods.

The student will learn how to implement these methods on modern computer architectures with latest NVIDIA P100 GPU accelerators as well as how to design and develop mixed MPI/OmpSs/CUDA code.

Student Prerequisites (compulsory): 

Knowledge of parallel algorithm design, CUDA and MPI.

 Student Prerequisites (desirable): 

Some skills in being able to develop mixed code such MPI/OpenMP will be an advantage. Additional support of learning OmpSs would be provided if needed.

Training Materials:

These can be tailored to the student once he/she is selected.

Workplan:

  • Week 1/: Training week
  • Week 2/:  Literature Review Preliminary Report (Plan writing)
  • Week 3 – 7/: Project Development
  • Week8/: Final Report write-up

Final Product Description: 

The final product will be a parallel application that can be executed on hybrid architectures with NVIDIA  P100 GPU accelerators.  We expect to make a movie to showcase the work. Ideally we would like to publish the results in a paper on a conference or a workshop.

Adapting the Project: Increasing the Difficulty:

The project is on the appropriate cognitive level, taking into account the timeframe and the need to submit final working product and 2 reports

Resources:

The student will need access to a machine with NVIDIA P100 GPU accelerators, standard computing resources (laptop, internet connection) as well as, if needed, an account on Minotauro supercomputer.

Organisation:
Barcelona Supercomputing Centre

BSC_logo

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1703

This project started as a SoHPC 2016 project, where we implemented routinely used quantum chemistry Hartree-Fock (HF) method in Apache Spark framework. Due to a lack of time, several goals remained unreached, such as: how efficient can a parallel Apache Spark code be compared to MPI if all affordable optimizations are applied?; how resilient is the parallel calculation, especially in comparison with MPI?; etc.

Student is expected to further cooperate in optimization of the existent HF Apache Spark code written in Scala, implement and optimize other popular quantum chemistry algorithms, such as Density Function Theory (DTF) and/or  Second-order Møller-Plesset perturbation using the same framework.

Despite the fact that Apache Spark runs on top of JVM (Java Virtual Machine), thus can hardly match the FPO performance of Fortran/C(++) MPI programs compiled to machine code, it has many desirable features of (distributed) parallel application: fault-tolerance, node-aware distributed storage, caching or automated memory management. Yet we are curious about the limits of the performance of Apache Spark application by, e.g. substituting critical parts with compiled native code or by using efficient BLAS-like libraries.

We do not expect the resulting code to be (performance wise) truly competitive with MPI in production applications. Still, such experiment may be valuable for programmers from the Big Data world implementing (often computationally demanding) e.g. machine-learning algorithms, etc.

The choice of the implementation target, i.e. the aforementioned quantum chemistry methods, results from the professional background of the project mentor and certainly is a subject of negotiation. Any HPC application with non-negligible data flow is acceptable as well.

Directed Acyclic Graph of transformations of RDDs (Resilient Distributed Dataset) in Apache Spark program execution.

Project Mentor: Doc. Mgr. Michal Pitoňák, PhD.

Site Co-ordinator: Mgr. Lukáš Demovič, PhD.

Learning Outcomes:

Student will learn a lot aboutMPI, Scala programming language, Apache Spark as well as ideas of efficient implementation of tensor-contraction based HPC applications, particularly in quantum chemistry.

Student Prerequisites (compulsory): 

Basic knowledge of Fortran/C/C++, MPI, Scala or advanced knowledge of Java.Background in quantum-chemistry or physics.

Student Prerequisites (desirable): 

Advanced knowledge of Scala, basic knowledge of Apache Spark, BLAS libraries and other HPC tools.

Training Materials:
http://www.scala-lang.org,

http://spark.apache.org,

http://spark.apache.org,

http://nd4j.org/scala.html

Workplan:

Week 1: training; weeks 2-3: introduction to Scala, Apache Spark, theory andefficient implemented quantum chemistry methods, weeks 4-7: implementation, optimization and extensive testing/benchmarking of the code, week 8: report completion and presentation preparation

Final Product Description: 

The resulting Apache Spark computer program will be resilient enough to successfully complete (e.g. quantum-chemistry) calculations with on-the-fly crashing/failing compute nodes. What may be interesting about this project from the outreach/dissemination perspective is bridging HPC and much more “popular” Big Data world. We do not expect it will directly lead to visually appealing outputs, but we will try to produce some (molecules, orbitals, execution graphs, etc.)

Adapting the Project: Increasing the Difficulty:

The goal is to push the efficiency of the Apache Spark code to maximum, which is, by its own,“infinitely difficult”.

Resources:

Student will obtain access to (multimode) Apache Spark cluster. Apache Spark is an open-source project, accessible and easy to installon any commodity hardware cluster. Moreover, there are several free virtual machine images with preinstalled software available from companies like Cloudera, MapR or Hortonworks, ideal for learning and pivotal development.

Organisation:
Computing Centre of the Slovak Academy of Sciences

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1704

In calculations of nanotubes prevail methods based on a one-dimensional translational symmetry using a huge unit cell. A pseudo two-dimensional approach, when the inherent helical symmetry of general chiralitynanotubes is exploited, has been limited to simple approximate model Hamiltonians. Currently, we are developing a new unique codefor fully ab initio calculations of nanotubes that explicitly uses the helical symmetry properties. Implementation is based on a formulation in two-dimensional reciprocal space where one dimension is continuous whereas the second one is discrete. Independent particle quantum chemistry methods, such as Hartee-Fock and/or DFT or simple post Hartree-Fock  MP2are used to calculate the band structures.

Student is expected to cooperate on the parallelization of this newly developed implementation and/or on a performance testing for simple general nanotube model cases. Message Passing Interface (MPI) will be used as the primary tool to parallelize the code.

The aim of this work is to implement MPI parallelization to enable highly accurate calculations for the band structures of nanotubes on distributed nodes, with distributed memory. The current code is limited to shared memory, and distribution of the memory usage over the nodes would be desirable at least at the level of outer loops. On the other hand the second level parallelization in inner loops over the processors of individual nodes would certainly enhance the performance together with a combination with using threaded BLAS routines.

By improving the performance of our new software we will open up new possibilities for tractable highly accurate calculations of energies and band structures for nanotubes with predictive power and with facilitated band topology whose interpretation is much more transparent than in the conventionally used one-dimensional approach. We believe that this methodology soon becomes a standard tool for in silico design and investigation in both the academic and commercial sectors.

General case nanotube with helical translational symmetry

Project Mentor: Prof. Dr. Jozef Noga, DrSc.

Site Co-ordinator: Mgr. Lukáš Demovič, PhD.

Learning Outcomes:

The student will familiarize himself with MPI programming and testing, as well as with ideas of efficient implementation of complex tensor-contraction based HPC applications. A basic understanding of treating the translationally periodic systems in physics will be gained along with the detailed knowledge of profiling tools and parallelization techniques.

Student Prerequisites (compulsory): 

Basic knowledge of MPI and Fortran.

Student Prerequisites (desirable): 

BLAS libraries and other HPC tools, knowledge of C/C++.

Training Materials:

Articles and test examples to be provided according to an actual student’s profile and skills

Workplan:

Weeks 1-3: training; profiling of the software and design simple MPI implementation, Deliver Plan at the end of week 3. Weeks 4-7: implementation, optimization and extensive testing/benchmarking of the code, week 8: report completion and presentation preparation

Final Product Description: 

The resulting code will be capable of successfully and more efficiently completing the electronic structure calculations of nanotubes with a much simplified and transparent topology of the band structure.

Adapting the Project: Increasing the Difficulty:

A more efficient implementation with the hybrid model using both MPI and Open Multi-Processing  (OpenMP)

Resources:

The student will need access to Fortran and a C++ compiler as well as MPI and OpenMPenvironment  which can be provided by the hostCC SAS

Organisation:
Computing Centre of the Slovak Academy of Sciences

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1705

Energy Efficency is one of the most timely problems in managing HPC facilities. This problem can be addressed at different scale and from different perspective:  chip and board design, cooling technologies, batch scheduler tuning. In order to help insight and tuning, fine grained monitoring of cluster status and activity is believed to be of great importance. Our research group has already developed and deployed a lightweight scalable technology to collect physical parameter and scheduling status of several observable, up to the single core temperature an job id running, with temporal frequencies in the order of few seconds.  While the ultimate goal of this data collection will be the automated maximization of energy efficiency, our research group is currently focusing on real time and historical analysis of the most important observables. While large statistical data analysis will be of much use, we believe that this data analysis task could benefit from a finer grade, real time, physical mapped data representation of the required observables (e.g. the numbers of job running, average temperature of the CPUs per job, top temperatures and so on). Within this project we propose to explore interactive web visualization techniques to browse the collected data using proper visual presentation. The final result will be a web application presenting cluster status. This application will target: (i) both system administrators and researchers trying to tune available parameters for optimizing efficiency, (ii) HPC users for monitoring system and job status and finally (iii) the large public for dissemination purposes.

Simple Blend4web model of CINECA phisical cluster layout

The picture represents on the left a supercomputing installation augmented with fine-grain monitoring back-end and on the right a visualization front-end. The monitoring system regularly collects statistics on jobs entering the system, on the status of computing nodes (load, temperature and power consumption) and on the facility operating conditions. These values are fed into a web-server which serves as visualization front-tend. The visualization frontend aggregates the multi-scale and multi-physics information into informative graphical view of the supercomputing status, usage and efficiency

Project Mentor: Dr. Andrea Bartolini

Site Co-ordinator: Dr. Massimiliano Guarrasi

Learning Outcomes:

Increase student’s skills about:

  • Web technologies (e.g. javascript)
  • Python
  • Big Data Analysis
  • Blender
  • HPC schedulers (e.g. PBS)
  • Internet of Things (MQTT)
  • HPC infrastructures
  • Monitoring of Energy efficiency

Student Prerequisites (compulsory): 

  • Javascript or similar web technology
  • Python or C/c++ language (python wil be preferred)
  • MPI
  • PBS

Student Prerequisites (desirable): 

  • Cassandra
  • Apache Spark
  • elasticsearch,graphana
  • Blender
  • Blender4Web
  • MQTT

Training Materials:

None.

Workplan:

  • Week 1: Common Training session
  • Week 2: Introduction to CINECA systems, small tutorials on parallel visualization and detailed work planning.
  • Week 3: Problem analysis and deliver final Workplan at the end of week.
  • Week 4, 5: Production phase (set-up of the web page).
  • Week 6, 7: Final stage of production phase (Depending on the results and timeframe, the set of observables will be increased). Preparation of the final movie.
  • Week 8: Finishing the final movie. Write the final Report.

Final Product Description: 

An interactive web page will be created. This page will show a series of parameters related to energy efficiency of a HPC system. This web page will be also used to show some statistics about the jobs running in the selected system.

Adapting the Project: Increasing the Difficulty:

We can prepare a 3D rendering of the HPC cluster, via Blender4Web in order to visualize the energy load directly on the cluster.

Resources:

The student will have access to our facility, our HPC systems, the two databases containing all energy parameters, and job information. They will also manage a dedicated virtual machine on our PICO HPC cluster.

Organisation:
CINECA
cineca_logo

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1706

 

OGSTM is an optimized code to solve 3D transport reactions non linear PDE applied to biogeochemical problems. It exploits the domain decomposition paradigm based on the MPI and the OPEN-MP library to scale the computation to large number of cores.

The tool simulates biogeochemical fluxes at Mediterranean scale and is used in several European projects and in the Copernicus service (CMEMS infrastructure, http://marine.copernicus.eu) and to perform multi decadal simulations to estimate the impact of global change to environmental indicators.

As high performance computing moves towards the exascale era, in situ approach is widely predicted to become more and more important as an efficient tool for speed-up of large scale simulations.

Following this pattern, the code, that is written in fortran90, has been recently equipped with a C++ ParaView Catalyst adaptor to exploit the in-situ approach.

This solution (still in development) interface the model with  ParaView software providing  interactive on-the-fly visualization  of the live simulation data, filtered by python visualization pipeline defined by the user.

The usage model that are currently supported are either the direct access with ParaView client or full batch image sequence production.

With this proposal we aim at explore web presentation capabilities of ParaView ecosystem to extend to the web current in-situ prototype a web presentation of day-to-day simulation activity.

We propose to explore web presentation capabilities of ParaView ecosystem to add web presentation features to the current in-situ prototype.

We will like to expose to the web some of the visualization capabilities available in the  current 3D visualization tool.

We would also like to extend the current  tool to allow not just  on-line   monitoring of  the running simulation  but  also off line (i.e. for post-processing)  browsing of archived   time evolution of the 3D fields of biogeochemical variables like marine chlorophyll and macro-nutrients. The advanced visualization tools available in ParaView Web like iso-surface and streamlines representation will be included in the plotting options following user needs.

Datasets and model configurations will come from the real system operating in the European Copernicus service.

The new App will be integrated by means of  the in-situ approach in the parallel framework already developed or will be used in batch mode in order to explore archived data in an efficient way.
Such tool will be designed and implemented to be portable to other coupled modeling systems used at OGS and for different purposes: from the long-term, multi-decadal runs to the operational work-flow embedded in the CMEMS infrastructure.

Simulations and tests will be carried out in one of the supercomputers available at CINECA facilities.
As an added value, the tool will be then integrated within the Visual-Lab facility at OGS, and will be important for scientific outreach activities also.

Project Mentor: Dr. Paolo Lazzari

Site Co-ordinator: Dr. Massimiliano Guarrasi

Learning Outcomes:

Increase student’s skills about:

  • ParaView (Catalyst, ParaViewWeb)
  • PYTHON
  • FORTRAN
  • MPI
  • Open MP (if necessary)
  • Preprocessor directives
  • Managing resources on Tier-0 and Tier-1 systems
  • Batch scheduler (PBS)
  • Remote visualization
  • Batch visualization of scientific data (ParaViewCinema)
  • Video and 3D editing (Blender)
  • JavaScript
  • HTML5

Student Prerequisites (compulsory):

Knowledge of:

  • Python : strong
  • ParaView : good
  • Fortran or C: good (Fortran is better)

Student Prerequisites (desirable): 

Knowledge of:

  • MPI
  • openMP
  • Blender
  • Javascript
  • html5

Training Materials:

None.

Workplan:

  • Week 1: Common Training session
  • Week 2: Introduction to CINECA systems, small tutorials on parallel visualization and detailed work planning.
  • Week 3: Problem analysis and deliver final Work-plan at the end of week.
  • Week 4, 5: Production phase (A proper visualization work-flow will be implemented starting from existing outputs).
  • Week 6, 7: Final stage of production phase (Depending on the results and time-frame, the visualization scripts will be adapted to the production work-flow). Preparation of the final movie.
  • Week 8: Finishing the final movie. Write the final Report.

Final Product Description: 

The purpose of this project is to extend the  a visualization tool within the current OGSTM-BFM model work-flow. Our final product will result in a visualization web interface based on ParaView Web as well as a movie illustrating the use and the results obtained during this 2 months work period. Also a small report on the work done will be produced.

Adapting the Project: Increasing the Difficulty:

One foreseen expansion is the use of ParaViewCinema to pre-compute all relevant visualization artifacts during simulation phase  in a completely batch work-flow.

Resources:

Beside the OGSTM-BFM model that is owned by OGS and will be provided in source form under a non-disclosure agreement, all other needed software (mainly ParaView and Blender) is released open source and already available on the CINECA clusters that will be used by the students with their own provided accounts.

Organisation:
CINECA
cineca_logo

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1708

A common and very important application of HPC is that of weather forecasting. In conjunction with the UK Met Office we have developed a new, state of the art, atmospheric model which the scientific community use to simulate clouds. During the 2016 SoHPCprogramme a student developed an interactive outreach tool for setting up initial conditions such as temperature, pressure and the time of the year, then simulating this via our model running on Wee Archie (a mini supercomputer we have built out of Raspberry PIs) and visualising the development of the weather in real time.

Whilst this current demo (written in Python) is really successful for public engagement, we also believe it could be very useful for atmospheric, computational and HPC education targeted at undergraduates. The visualisation is currently split in two and the user can see both the actual weather progression and also aspects of parallelisation & performance such as the trade-off between communication and computation for each core along with the number of simulation seconds per real time second the code is achieving.

There are many choices that a user of our weather model has about their simulation, from what scientific method should be used (for instance for modelling flows in the atmosphere) to what accuracy certain calculations need to be solved to (for instance when solving pressure terms) and it can be very difficult for novice scientists to appreciate and understand their decisions and the impacts that they will have. Atool where the impact of these different choices is illustrated upon their simulation in real time, both in terms of the actual progression of the weather but also the performance & scalability would be hugely useful.For instance, there are many decisions that present an accuracy vs performance trade-off, being able to actually see and experiment with these to understand what is “good enough” will be very powerful and might even be useful for experienced scientists.

Additionally, some areas of atmospheric study require very careful set up and take a while to occur in the simulation (called the model spin up.) An example of this isfog which can take many simulation hours to build up.Understanding exactly how to achieve different conditions as effectively as possible would also be another useful impact of this work.

The simulation code itself is designed for very large core counts on modern supercomputers, such as ARCHER, the UK national supercomputer. For outreach purposes we often run the model on Wee Archie, our mini supercomputer made out of Raspberry PIs, so that people can actually see where their weather will be simulated. With a slightly different focus towards education, this project will target the model running on a variety of different machines, from large supercomputers to clusters of Raspberry PIs that institutions can easily put together.

 

The first photo illustrates a top down view of cumulous clouds in the current visualisation Python code which have formed during a simulation due to evaporation from the sea. The white grid illustrates the decomposition of these across the different processor cores.

The second photo again illustrates work done during the 2016 SoHPC programme and a side on view of the simulation can be seen, it is raining from the cloud both into the sea and onto the land (with some green crops growing on the land.) The bottom bars illustrate the percentage of time spent in communication (red) and computation (green) for each core. The number on the top left (7.7 sps) is the number of simulation seconds the model is achieving every real time second.

Project Mentor: Nick Brown

Site Co-ordinator: Anne Whiting

Learning Outcomes:

This project involves working with an existing model used for real world atmospheric science. You will therefore gain an understanding of what makes up a computational model, experience with using real world supercomputers, technical skills writing Python codes (specifically for visualisation) and general software developmentpractice.

Student Prerequisites (compulsory): 

A strong programming background, with an interest in both HPC and the visualisation aspects of the field as well as a flair for design.

Some experience with using Python and Linux.

Student Prerequisites (desirable): 

More substantial experience with Python and some use of Fortran. Some exposure toVTK which we use as the visualisation framework.

Training Materials:

Tomislav’s project video (2016 SoHPC student who developed the current outreach tool) https://www.youtube.com/watch?v=yM6LM6jsYvo

We use VTK for the visualisation framework, there are plenty of tutorials & documentation on the website http://www.vtk.org/

Python is used as the implementation language https://docs.python.org/3/tutorial/

Workplan:

  • Work package 1: (1 week) – SoHPC training week
  • Work package 2: (2 weeks) –Gain experience with the existing code base, both the current visualisation tool and simulation code.Agree on exact scope of work and start preliminary implementation and experimentation towards this. Submit workplan.
  • Work package 3: (3 weeks) – Main development phase of the project where the current visualisation and interaction toolis matured and the focus brought towards education.
  • Work package 4: (2 weeks) – Final tidy up of code and interface. Produce a video demonstration of the work that has been done. Submit final report

Final Product Description: 

The final product will be an interactive visualisation tool which can be used for education in weather prediction, illustrating the impact that different scientific choices can have upon the fidelity of results and performance of the models. This will be useful to further illustrate to undergraduate students the importance of HPC & computational science and a video will be produced as part of the project which summaries the work done and will help with its dissemination. We believe that the results of this work will be of substantial interest to the UK weather and climate communities.

Adapting the Project: Increasing the Difficulty:

There are many options, for instance the user could take different “views” of the weather system (such as the temperature, pressure etc.)

Resources:

Nothing specific will be needed, the student will be given access to our supercomputers and also other machines such as Wee Archie for this work as well as access to the source code repositories.

Organisation:
Edinburgh Parallel Computing Centre (University of Edinburgh)
EPCC

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1709

We house and run the UK national supercomputing service, ARCHER, which has an active user base of around 3000 users. Many different people rely on this machine as a crucial instrument in their science and there are a very wide variety of tools, technologies and communities involved with a modern HPC machine.

Not only is it desirable to be able to analyse this data and provide some visualisation to help track what is working well and what needs attention, but policy makers (and ultimately the funders) find this sort of information crucial when deciding what the future of HPC should look like.

We have large amounts of present day data, but we also have data going back around 10 years which we can take advantage of to track trends & changes in the community as time has progressed.

We have built a small prototype (http://www.archer.ac.uk/status/codes/) which is fairly basic and only takes advantage of a very small amount of the overall data, but this in itself has been of significant interest to people and will be a starting point for this project to build upon.

The interests of the student will drive the exact project and there are plenty of challenges which we could tackle, from the deep technical side of developing an advanced online visualisation tool where one can explore the data in detail, to questions around exactly how we can best illustrate the data in a way that is accessible and easy to understand.

Variety of data visualisations possible using the D3.js tool (taken from https://d3js.org/).

Project Mentor: Andy Turner

Site Co-ordinator: Anne Whiting

Learning Outcomes:

Real world data analytics and visualisation, exposure to software development techniques and web development technologies (HTML5, Javascript and common frameworks.)

Student Prerequisites (compulsory): 

Some programming background, experience of developing using HTML and javascript. A desire to pick up and learn new technologies.

Student Prerequisites (desirable): 

Existing data analytics and visualisation experience. Some experience with the D3.js javascript library.

Training Materials:

Workplan:

  • WP1 (1 week) – SoHPC training week
  • WP2 (2 weeks) – Gain experience with the existing prototype, understand the data and the potential for analytics & visualisation
  • WP3 (3 weeks) – Main development phase, extend the prototype to provide an advanced visualisation & exploration capacity for current and historical data
  • WP3 (2 weeks) – Final tidy of the code, produce a video describing the project & achievements. Write and submit final report.

Final Product Description: 

An online tool will be developed that visualises, and potentially allows one to explore, the usage data of modern HPC machines. This could then be used by other PRACE partners to help explore their own usage data. In terms of outreach, the general public find it very interesting to see what sciences take advantage of HPC machines and the tools/technologies that HPC developers routinely use.

Adapting the Project: Increasing the Difficulty:

A more advanced online visualisation where people can interactively drill down into the data and explore trends, anomalies and other factors.

Resources:

The current and historical usage data, we have this stored in house and it is managed by Andy Turner (the project mentor) who will make it available. None of the data is sensitive and it is all anonymised so there are no privacy concerns.

Organisation:
Edinburgh Parallel Computing Centre (University of Edinburgh)
EPCC

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1707

Operational earthquake forecasting is a novel scientific direction of Seismology focusing on providing real-time earthquake likelihoods during the evolution of an aftershock sequence. The moment a major earthquake occurs, decision-makers need expert advice to both support proactive actions that will minimize loss of life and property, and lead rescue operations. Although recent research advances provide a starting scientific hypothesis for aftershock triggering mechanisms, the challenge we still face is to develop and validate testable forecast models in real-time settings.

The focus of this project is developing a time-economical calculation environment that will enable seismologists to utilise the preliminary data products and provide an earthquake forecast model within few hours. Then using the early aftershock data within the first few days, we aim in validating our prediction matrix using statistical metrics, such as log-likelihood statistics.

The on-going scientific work on the subject samples a number of world-wide cases with a recent highlight the UK effort to forecast the evolving seismic hazard in Italy following the August-October devastating earthquakes. It should be noted that the work will have important societal impact since it will provide scientists the computational tools to support informed decision-making and advisories from state officials in UK. The British Geological Survey is among the NERC science centres providing emergency scientific advice in cases of evolving hazards for multiple disciplines.

Earthquake Forecast following the 2015 M=7.8 Nepal mainshock. Also shown the distribution of earthquakes within the first 5 days. Taken from Segou and Parsons (2016) article in Seismological Research Letters.

 

Project Mentor: Amy Krause

Site Co-ordinator: Anne Whiting

Learning Outcomes:

The student will work with geo-science and computer science on forecast models. They will translate hazard earthquake models previously developed in Matlab into a real-time data streaming application, and learn about Python-based streaming tools, for example Apache Spark.

 Student Prerequisites (compulsory): 

A strong programming background, with an interest in HPC, parallel programming and real-time data processing and data streaming.

Student Prerequisites (desirable): 

Experience in Python or Matlab, parallel programming techniques, big data engineering and/or the willingness to learn these technologies

Training Materials:

These will be provided to the successful student once they accept the placement.

Workplan:

  • Week 1: Familiarise with the existing Matlab based models, and the streaming tools and development environment (Python, Apache Spark)
  • Week 2&3: Design the port of existing models from Matlab to a stream-based architecture, in consultation with geo-scientists from BGS (British Geological Survey)
  • Week 4,5,6,7: Develop the earthquake hazard models as outlined in the design phase. Testing & documentation.
  • Week 8: Final report

Final Product Description: 

The final product will be a forecast model in real-time settings.

Adapting the Project: Increasing the Difficulty:

The implementation could be tested against many models, and a real-time test scenario with large datasets could be run.

Resources:

Nothing specific, just a desktop/laptop machine capable of running the development tools.

Organisation:
Edinburgh Parallel Computing Centre (University of Edinburgh)
EPCC

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1711

The project aims to familiarise the successful candidate to use efficiently the High Performance Computing system ARIS in GRNET and optimize his/her application in the field of regional climate modelling. A hindcast regional climate simulations will be performed over the European domain in coarse resolution (0.44 degrees) with the use of the regional climate model WRF (Weather Research and Forecasting model).

Mean winter (DJF) temperature for the time period from 1990 to 2008 as simulated by the regional climate model WRF.

Project Mentor: Dr Eleni Katragkou

Site Co-ordinator: Ioannis Liabotis

Learning Outcomes:

The successful candidate will have the opportunity to learn how to use the GRNET HPC system ARIS. The awarded computational time for the project will be used for the performance of regional climate model simulations.

Student Prerequisites (compulsory): 

Good experience in the use  of WRF software.

Student Prerequisites (desirable): 

Background in natural sciences (atmospheric physics) and basic use of visualization tools (e.g. IDL, matlab, R etc)

 Training Materials:

http://www2.mmm.ucar.edu/wrf/users/supports/tutorial.html

Workplan:

Week 1: basic training

Week 2: training in the use of WRF in HPC GRNET

Week 3-7: performance of regional climate model simulations – including benchmarking

Week 8:Final report

Final Product Description: 

The final product will be a dataset of regional climate simulations (netcdf format) and some associated graphical representation of it that will be created in collaboration with the student undertaking the second proposed  project.

Adapting the Project: Increasing the Difficulty:

A set of benchmarking simulations will be performed to investigate the potential of the model to optimize in ARIS HPC.

Resources:

The required software is the numerical model (WRF) which is already installed in HPC.ARIS. Post processing tools and libraries are as well available (cdo, netcdfetc).

Organisation:

Aristotle University of Thessaloniki


Greek Research and Technology Network and Biomedical Research Foundation
project_1611_logo-grnet

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1710

The project aims to  familiarise the successful candidate to use output data from regional climate models  and apply advance  visualization tools to present climate and climate change data in a user-friendly manner (e.g. contour maps, time-series, animated gifs etc). The project will include intensive post-processing of climate output.

Temporal  Taylor plots for surface  temperature averaged over Europe for summer and winter 1990-2008. Source: Katragkou et al., Regional climate hindcast simulations within EURO-CORDEX: evaluation of a WRF multi-physics ensemble, Geoscientific Model Development, 8, 603-618, 2015.

 Project Mentor: Dr Eleni Katragkou

Site Co-ordinator: Ioannis Liabotis

Learning Outcomes:

The successful candidate will learn how to post-process raw climatic output to produce advanced visualization products.

Student Prerequisites (compulsory): 

Good knowledge of visualization tools and techniques

Student Prerequisites (desirable): 

Experience with scripting

Training Materials:

none

Workplan:

Week 1: basic training

Week 2: training in the use of WRF in HPC GRNET

Week 3-7: building of visualization routines.

Week 8:Final report

Final Product Description: 

The final product will be a set of graphics presenting key climatic variables in various forms ( e.g. contour fields, time series, trendlines, animated gifs etc)

Adapting the Project: Increasing the Difficulty:

More complex visualization tools will be attempted (e.g. 3D animated plot etc)

Resources:

Post processing tools and libraries are available (cdo, netcdfetc) in ARIS.HPC.

Organisation:

Aristotle University of Thessaloniki


Greek Research and Technology Network and Biomedical Research Foundation
project_1611_logo-grnet

 

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1712

World Ocean is covered almost 72% of the Earth’s surface. Among all Oceans Pacific Ocean is the largest Ocean. All the Oceans are interconnected through some channels or by teleconnection through atmosphere. It is well known that Ocean, Land, Atmosphere and Ice all are connected with each other and it’s a coupled system. Many climatic oscillations are discovered. Ocean has more memory than atmosphere, similarly oceanic events have larger impact in the World. El-Nino is a climate cycle in the Pacific Ocean with a global impact on weather patterns. Climate scientists predict that these are going to be more frequent as we are entering into global warming scenarios. El-Nino is a phenomenon where West equatorial warm water pushes to central and eastern equatorial Pacific Ocean. This disturbs the atmospheric cycle and impacts Global weather. This is believed to be 2 to 7 years’ cycle. There are 19events of El-Nino recorded since 1950. Among them five are two consecutive years of El-Nino. During 1997-98 El-Nino the sea surface temperature anomaly was record high of up to2.3degree C, followed by three consecutive La-Nina (Opposite of La-Nina; abnormally cool Eastern and central equatorial Pacific). 1997/98 event is called Super El-Nino. It has caused very severe impacts over the world e.g. massive forecast fire in Indonesia, flooding in Peru and global coral bleaching. Further recent El-Nino in 2015 has again that high temperature anomaly of 2.3degree C, but surprisingly there is no followed by La-Nina. Understanding El-Nino and predicting one season before will be very helpful to farmers, industries and societies for better preparedness. With the available HPC resources around the World and the observed dataset from bottom of the Ocean to top of atmosphere through different sources, enable scientist to analyse and conclude correlations and predict future scenarios. The presentstudy will highlight all the past events of El-Nino, it’s impact on different parts of world weather and the recent prediction capability of these events one season ahead.

 

Project Mentor: Dr.Basanta Kumar Samala

Site Co-ordinator: Simon Wong

Learning Outcomes:

Details of El-Nino, its impacts over the World. Is there any periodicity in the historical events of El-Nino? How different its impact from year to year and decade to another. Are there any unnoticed correlations of El-Nino from past events? Finally, forecasting El-Nino 9 months ahead and evaluate the predictability.

Student Prerequisites (compulsory): 

Basic computer knowledge power point, plotting software. Science as a subject.

Student Prerequisites (desirable): 

Making videos, good report writing, Weather and Ocean phenomenon knowledge or interest, Linux, Scientific data knowledge

Training Materials:

www.cpc.noaa.gov

www.iri.columbia.edu

www.pmel.noaa.gov

Workplan:

Training, settling, learning El-Nino: 2 Weeks

Literature collection on historical events and its impacts: 3 Weeks

Analyse impacts, forecast and its predictability: 2 Weeks

Report, video and presentation: Last Week.

Final Product Description: 

A single video, which will explain El-Nino from history to future prediction capability and its impacts.

Adapting the Project: Increasing the Difficulty:

Need to find out other regions of World and its relationship with El-Nino using historical dataset.

Resources:

Laptop with interest in weather and Ocean processes. Any plotting / graphics software.

Organisation:
Irish Centre for High-End Computing
ichec_logo

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1713

The aim of this project is to create a computer render of a very simple scene using radiosity techniques.  The rate at which energy leaves a surface is called its radiosity.  This idea is the starting point for a method of near photo-realistic computer rendering.  It produces images which model soft shadows and detailed colour interactions very well.  It is determined via the ‘finite element method’ by solving a linear system of equations (i.e. an NxN matrix equation with N unknowns) which produces the radiosity of each element (polygon) in the scene.  The entries of the matrix depend on the visibility between each pair of polygons, which is how the layout/geometry of the scene enters the equation.  Once the solution is obtained, the light energy leaving each polygon is then projected to a viewing plane and the colour of each pixel in the render is determined.  The determination of the matrix coefficients (called the ‘form factors’) and solution of the matrix equation can be accelerated via HPC methods such as parallelism, and a very fine subdivision of the scene into polygons (we will use squares) should be possible.  If the number of polygons becomes very large, it may be faster to render by using a technique called ‘progressive refinement’, which gradually develops the image as light propagates.  The project will consist of training/orientation, an implementation, a rendered scene and a final report.

This image shows the ‘Cornell Box’ rendered using near-photorealistic global illumination techniques, which include radiosity.  (Copyright owner is Oisín Robinson@ICHEC)

 Project Mentor: Oisín Robinson

Site Co-ordinator: Simon Wong

Learning Outcomes:

The student will develop an understanding how a problem with a physical relevance – simulation of light interaction in an environment – can be modelled by a linear system of equations.

The student will also see how this problem can be solved more quickly by employing a standard technique of HPC – exposing parallelism.

 Student Prerequisites (compulsory): 

Familiarity with solving a linear system of equations (i.e. inverting a matrix).  Experience programming in c or c++ (not necessarily professional).

Student Prerequisites (desirable): 

Comfort with higher-level mathematics such as taught in university in first year (e.g. linear algebra).  Real vector spaces will be used to deal with geometry and it is an advantage to be familiar with this (e.g. how to compute dot product/vector products and more advanced tasks such as computing the intersection between a line and a plane).  It will also be an advantage to have already used linux.

Training Materials:

Read about radiosity online, https://www.siggraph.org/education/materials/HyperGraph/radiosity/overview_1.htm

and

https://www.siggraph.org/education/materials/HyperGraph/radiosity/overview_2.htm

(the second link gives the idea of the hemicube approximation method for determining form factors but we will go into more detail/cover the gaps).

 

Workplan:

Week 1, orientation/settle.  Week 2, training – cover theory of radiosity/some mathematics to help with geometry, and cover the basics of working with linux/g++.

Week 3 outline milestones of project with particular emphasis on calculation of form factors via the hemicube method.  We should be able to calculate the form factor Fij between any two patches Ai and Aj.

Weeks 4-7 implement algorithms in c++ and generate output, evaluating our incremental progress as we go – and finally present and write up final report in week 8.

Final Product Description: 

Photo-realistic computer graphics have universal appeal and the subject produces imagery that is both striking and well-suited to academic study.  The student can generate a number of stills that can be effectively used to showcase the project output, and the student may be able to generate a video (either a walk-through or propagation of light through the scene),encapsulating many different ideas from mathematics, physics, computer science and HPC, in the project output.

Adapting the Project: Increasing the Difficulty:

The difficulty could be increased by requiring a video to be produced as project output, either a walkthrough or showing the propagation of light.  Also, adding a box to the scene complicates form factor calculation, since we have to account for surfaces being hidden, but would produce a more detailed image.

Resources:

All software will be developed from firstprinciples using an open-source c++ compiler, g++.  Any part of the project that requires a non-trivial amount of parallelisation will be facilitated by ICHEC through the Fionn cluster.  All training will be provided by the mentor, and will be self-contained.

Organisation:
Irish Centre for High-End Computing
ichec_logo

Posted on by SoHPC Team Posted in Projects 2017 — 1 Comment ↓

Project reference: 1714

Main objective of this project is to create platform for visualization of real motion of human body based on motion capture technology. First 3D virtual model of human skeleton will be created. This model will be moving based on real human motion obtained through motion capture technology. First model will be created manually using polygons. Second moresophisticated model will be generated based on Computed Tomography (CT) images. Outcome of this project could be used not only for promotion of HPC among general public but it could be also developed into more sophisticated system which could be later used by physicians for home treatment of patients with movement problems.

Attached picture shows 3D virtual model of human skeleton created form Computed Tomography (CT) images

Project Mentor: Petr Strakoš Ph.D.

Site Co-ordinator: Karina Pešatová

Learning Outcomes:

Basic knowledge of processing and visualization of biomedical images, principles of motion capture and inverse kinematics

Student Prerequisites (compulsory): 

Basic programming skills in

  • C, C++
  • Python

Student Prerequisites (desirable): 

  • Image processing and segmentation
  • 3D data visualization
  • Parallel processing

Training Materials:

https://www.blender.org/support/tutorials/

http://www.creativebloq.com/3d-tips/blender-tutorials-1232739

https://www.youtube.com/user/tutor4u

Beginning Blender Open Source 3D Modeling, Animation, and Game Design, Lance Flavell, ISBN13: 978-1-4302-3126-4

Workplan:

Week 1 –Training (Blender Cycles, basics of bio-imaging)

Week 2 – 4 Creation of 3D virtual model of human skeleton

Week 5 – 7 Capturing of motion of real human through motion capture technique and applying to 3D virtual model

Week 8 – Final report completion and final presentation preparation

Final Product Description: 

Platform together with devices for motion capture could be used for real time demonstration of this technology and as a show case how HPC could be used.

Adapting the Project: Increasing the Difficulty:

Motion of the 3D virtual skeleton will be prescribed, not based on real movement of real human

Resources:

Software

  • Python
  • Blender Cycles
  • C, C++ programming environment

Hardware

  • High memory system
  • Visualisation server
  • Salomon cluster

Access to the appropriate software and hardware will be provided by the IT4Innovations National Supercomputing Center.

Organisation:
IT4Innovations national supercomputing center
project_1615_logo-it4i

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1715

Supercomputers can help speed up the drug discovery using machine learning. Within the project the student will work with our tool that deploys new programming model and scheduler for running complex pipelines in a distributed environment on an HPC cluster. The goal of the project is to bring performance information from workflow pipelines to the users. The student’s work is to bring more detailed information about performance of the pipeline to the users via own visualization or exports to a tool for performance analyses.

Attached picture shows protein and directed acyclic graph of small cross-validation example

Project Mentor: Jan Martinovič

Site Co-ordinator: Karina Pešatová

Learning Outcomes:

Basic knowledge of processing and visualization of results from performance analysis of machine learning pipelines used for  example for drug discovery

Student Prerequisites (compulsory): 

Basic programming skills in

  • C, C++
  • Python

Student Prerequisites (desirable): 

  • 2D data visualization
  • Parallel processing

Training Materials:

http://www.mcs.anl.gov/research/projects/perfvis/software/viewers/

C++: http://www.cplusplus.com/doc/tutorial/

Python: https://www.python.org/doc/

Workplan:

Week 1: Training

Week 2: Work plan setting

Week 3 – 6: Implementation of software tool for performance information extraction and visualisation from workflow pipelines by own implementation or exports to a tool for performance analyses

Week 7: Visualization of the results

Week 8: Final report completion and final presentation preparation

Final Product Description: 

visualisation from workflow pipelines

Adapting the Project: Increasing the Difficulty:

In the original setting, the project is focused on post-mortem analysis. The complexity can be increased by providing the visualization in realtime.

Resources:

 

Software

  • Python
  • C, C++ programming environment

Hardware

  • Salomon cluster

Access to the appropriate software and hardware will be provided by the IT4Innovations National Supercomputing Center.

Organisation:
IT4Innovations national supercomputing center
project_1615_logo-it4i

Posted on by SoHPC Team Posted in Projects 2017 — No Comments ↓

Project reference: 1716

Simulations of Lattice Quantum Chromodynamics (the theory of quarks and gluons) are used to study properties of strongly interacting matter and can, e.g., be used to calculate properties of the quark-gluon plasma, a phase of matter that existed a few milliseconds after the Big Bang (at temperatures larger than a trillion degrees Celsius). Such simulations take up a large fraction of the available supercomputing resources worldwide.

 These simulations require the repeated computation of solutions of extremely sparse linear systems. Different methods are being used to solve these systems,  Krylov-based solvers such as CG or FGMRES or multi-grid methods (MG), which combines a generic solver  one a fine with another solver on a coarsened grid (lattice).

Depending on personal preference, the student will be involved in tuning and scaling the most critical parts of a specific method, or attempt to optimize for a specific architecture in the algorithm space.

In the former case, the student can select among different target architectures, ranging from Intel XeonPhi (KNC/KNL), Haswell (AVX2) or GPUs (OpenPOWER), which are available in different installations at the institute. To that end, he/she will benchmark the method and identify the relevant kernels. He/she will analyse the performance of the kernels, identify performance bottlenecks, and develop strategies to solve these – if possible taking similarities between the target architectures (such as SIMD vectors) into account. He/she will optimize the kernels and document the steps taken in the optimization as well as the performance results achieved.

In the latter case, the student will, after getting familiar with the architectures, explore different methods by either implementing them or using those that have already been implemented. He/she will explore how the algorithmic properties match the hardware capabilities. He/she will test the archived total performance, and study bottlenecks e.g. using profiling tools. He/she will then test the method at different scales and document the findings.

In any case, the student is embedded in an extended infrastructure of hardware, computing, and benchmarking experts at the institute.

 

Project Mentor: Dr. Stefan Krieg

Site Co-ordinator: Ivo Kabadshow

Learning Outcomes:

The student will familiarize himself with important new HPC architectures, Intel Xeon Phi, Haswell, and OpenPOWER. He/she will learn how the hardware functions on a low level and use this knowledge to optimize software. He/she will use state-of-the art benchmarking tools to achieve optimal performance for the kernels found to be relevant in the application

Student Prerequisites (compulsory): 

  • Programming experience in C/C++

Student Prerequisites (desirable): 

  • Knowledge of computer architectures
  • Basic knowledge on numerical methods
  • Basic knowledge on benchmarking
  • Computer science, mathematics, or physics background

Training Materials:

Architectures:

https://software.intel.com/en-us/articles/optimization-and-performance-tuning-for-intel-xeon-phi-coprocessors-part-1-optimization

https://software.intel.com/en-us/articles/practical-intel-avx-optimization-on-2nd-generation-intel-core-processors

https://developer.nvidia.com/cuda-zone

http://www.openacc.org/content/education

Paper on MG with introduction to LQCD from the mathematician’s point of view:

http://arxiv.org/abs/1303.1377

Introductory text for LQCD:

http://arxiv.org/abs/hep-lat/0012005

http://arxiv.org/abs/hep-ph/0205181

Workplan:

Week – Work package

  1. Training and introduction
  2. Introduction to architectures
  3. Introductory problems
  4. Introduction to methods
  5. Optimization and benchmarking, documentation
  6. Optimization and benchmarking, documentation
  7. Optimization and benchmarking, documentation
  8. Generation of final performance results. Preparation of plots/figures. Submission of results.

Final Product Description: 

The end product will be a student educated in the basics of HPC, optimized kernel routines and/or optimized methods. These results can be easily illustrated in appropriate figures, as is routinely done by PRACE and HPC vendors. Such plots could be used by PRACE.

Adapting the Project: Increasing the Difficulty:

  1. Different kernels require different levels of understanding of the hardware and of optimization strategies. For example it may or may not be required to optimize memory access patterns to improve cache utilization. A particularly able student may work on such a kernel.
  2. Methods differ greatly in terms of complexity. A particularly able student may choose to work on more advanced algorithms.

Resources:

The student will have his own desk in an open-plan office (12 desks in total) or in a separate office (2-3 desks in total), will get access (and computation time) on the required HPC hardware for the project and have his own workplace with fully equipped workstation for the time of the program. A range of performance and benchmarking tools are available on site and can be used within the project. No further resources are required.

Organisation:
Jülich Supercomputing Centre, Forschungszentrum Jülich GmbH
JULICH

Facebook
Twitter
Follow by Email