Posted on by DogukanT Posted in Blogs 2022, PRACE Summer of HPC 2022 — No Comments ↓

Before the Summer of HPC started, my mentor contacted us and gave us an exercise to familiarize ourselves with the MPI library and parallel programming. The exercise required us to use the domain decomposition method and at that time, I had no idea what it is. I searched the Web to learn more about it and eventually solved the exercise but it was difficult topic to learn, especially for beginners who have not experienced parallel programming before. Therefore, in this blog post, I will try to explain the domain decomposition method briefly and at the end of the post, I will leave a link to a GitHub repository that contains the exercise description and its solution. Keep in mind that I am not aiming to tell you everything about the domain decomposition but rather scratch the surface. Before further ado, let’s get started.

Why do we need domain decomposition?

The idea behind parallel programming is to split the amount of work into available processes. But we need to be careful when splitting the work among processes because we do not want to assign uneven work. For instance, assume there are 10 processes and there are 100 units of work that need to be done. Ideally, the work should be split so that each process is responsible for 10 units of work. If there was a mistake when dividing the work and some processes got 15 units and the rest got 5 units of work, the processes that got 5 units of work would finish their work early and have to wait for the other processes and that causes a performance problem. So, we have to avoid this situation altogether. That is why decomposing the domain into processes is an important task.

The image is taken from ResearchGate

How does it work?

By definition, domain decomposition, in the context of parallel computing, refers to the partitioning of computational work among multiple processors by distributing the computational domain of a problem, in other words, data associated with the problem.[1] Let’s go over an example to illustrate a simple decomposition. For the sake of simplicity, I chose the data as a matrix. Below you can see an 8×8 matrix:

Figure 1: Computational Domain

This will be our computational domain and we would like to get the result of a formula for each of its cells (a formula can be as simple as f(x) = (2x + 5)^3). As you can see from Figure 1, we have divided our domain into squares. You may ask this point “Why did we divide the domain into 4 squares and not like 10 squares?” Well, it is because we will use 4 processes to solve this domain and each process will be responsible for a 4×4 matrix. If the domain was big enough and we had enough computation resources, we would divide it into more than 4 squares of different sizes.

So far so good. Now, each process can substitute its cell value into the formula and get the result. That is it! But, wait. This scenario was quite naive because there was no communication involved and it is assumed that each process can access the data required by the equation. Unfortunately, most of the time there is an involvement of communication and that makes the domain decomposition a little bit harder.

Let’s continue the above example. However, this time let each process get the average of its current cell’s north, south, east and west neighbors and write the result on its current cell:

Figure 2: Clover of the first cell of process 4

Figure 2 illustrates what we are trying to do. The cell that is pointed by an arrow is the cell that we want to do our calculations on and the cells that have a white background are its neighbors. So, process 4 has to communicate with processes 2 and 3 to do the calculation. Assuming the communication is done and the new value is calculated and written. Now, moving on to the next cell, process 4 needs to communicate with process 2 to do the calculation:

Figure 3: Clover of the second cell of process 4

Assuming the communication and calculation is done. In the next cell, we again need to communicate with process 2 and that will continue for all the cells. As you might notice, our program starts to lack performance as the number of communication increases. We do not want it because the reason we are programming in parallel is to improve the performance of our programs. If we communicate with other processes for each cell, the program’s efficiency would be horrible, probably worse than serial processing. So, what are we going to do? We are not trying to eliminate the communication, that is impossible. We need to know the data that other processes hold. Ideally, we would like to get all the relevant data before the calculation starts. We can store the relevant data in guard cells or other words, halo cells or ghost cells. Guard cells are a local copy of the physical cells from neighbor nodes and make these values readily available. To continue with the above example, if we were to take process 1’s local data, this is how it would look like:

Figure 4: Process 1 and its local data surrounded by guard cells

Green cells are the actual data of process 1 and beige cells are guard cells which will be filled with processes 2’s and 3’s data after the communication. Note that the corners are empty. It is because we do not need to know these values. Only the data that is required by the communication is exchanged between the processes. Now, all processes have the required information locally. After the calculation is done, they can write the results to a file or send them to the master processes. And, this is the domain decomposition method in a nutshell.

Note

You may notice that the data was too perfect so that it decomposed without a problem. In the real world, it is likely that you may see uneven data, like a 101×103 matrix. So, in that case, we cannot decompose it evenly. For these cases, we need to consider different approaches that I cannot cover here. Also, you do not have to decompose the matrix into squares. It can be other geometrical shapes like rectangles and even triangles.

Conclusion

There are a bunch of things that can be learned about domain decomposition. I tried to explain it briefly but I highly recommend you to learn more about it if you find it interesting. You can check out the GitHub repository if you would like to practice and experience the domain decomposition method first-hand. Although knowing only domain decomposition is not enough to solve the exercise, I left the required topics to solve the exercise. I hope you learn something from this post. If you have any questions, please leave a comment below. Thank you for reading.

Posted on by Dominik Freinberger Posted in Blogs 2022 — 2 Comments ↓

A fluid consisting of two different species of atoms (red and blue).

In my first blog post, I briefly announced that I would be working on molecular dynamics simulations in the course of my project this summer. Now that I have already run some small simulations on the Mare Nostrum supercomputer at the Barcelona Supercomputing Center for training purposes, I would like to share my experiences made with molecular dynamics so far and also explain in this short intermezzo what molecular dynamics is all about. Further below I will show a visualization of one of my exercise examples.

What is Molecular Dynamics?

Forces and Potential Energies

Molecular dynamics refers to a (family of) computer simulation technique(s) used to compute the movements of particles, particularly atoms and molecules. It is based on Newton’s 2nd law “F = m⋅a” (yes exactly the one he used to calculate the orbits of the celestial bodies) and computes the trajectories of particles by integrating these equations of motion numerically. In order to do so, we need to know the forces acting upon each atom due to interaction with all the other atoms of the system. It is, however, not trivial at all to obtain these forces.

Fortunately, the forces can be derived from a so-called potential (the forces are actually the negative gradient of the potential), which is a key ingredient for doing molecular dynamics. The potential is a function of the positions of the nuclei and there are at least two main approaches to compute this potential (function) for use in molecular dynamics, leading to the distinction between Classical Molecular Dynamics and Ab-initio Molecular Dynamics.

Classical vs. Ab-initio Molecular Dynamics

In classical MD, the electrons are abstracted away, leaving only the nuclei whose relative positions are used to calculate the potential energy (surface) and thus the force field needed for integration. In ab-initio MD on the other hand, the electrons are indeed taken into account, albeit in an approximated form, which allows for more accurate but also far more computationally intensive calculations. This is usually realized by means of Density Functional Theory, DFT for short, but that is a story of its own. A relatively recent approach is to fit potentials computed by DFT using machine learning methods and to use the resulting machine-learned force fields (ML-FF) for classical MD. This allows near ab-initio accuracy at much lower computational cost.

In my project, however, I will be using classical molecular dynamics as it is better suited for the types of structures and lengths of time scales as well as temperatures that I will analyze.

Post-Processing

The last and probably most important step in molecular dynamics is post-processing: The trajectories of the particles by themselves are only a part of the whole, but in order to obtain relevant physical quantities of the system under study, it is common to calculate averages over all particles and/or time.

Simple MD Example

What you see here is a two dimensional simulation of a binary fluid (i.e. two atomic species) where the particles interact via a simple Lennard-Jones Potential. At the beginning of the simulation, the atoms are placed at two distinct regions of space, but after some time they will mix perfectly due to being allowed to interact with each other. Although this example does not represent the kinds of systems I will simulate during the Summer of HPC, as I will be dealing with materials in the solid state, to me it is still a nice visualization of how complex natural phenomena – such as diffusion – can be modeled and simulated using rather simple techniques.

Source Code for Visualization: https://lammpstutorials.github.io/tutorials/01-SimpleMolecularSimulation.html

Posted on by ErolA Posted in Participants 2022 — No Comments ↓

My name is Erol Aksoy. I was born in Ordu in Turkey. I am participating in the Summer of HPC programme under project number of 2206. The project subjects the development of parallel code in Julia to simulate a transport phenomena using Adaptive Mesh Refinement (AMR). I will be in Paris during this period of study. In the post, I will introduce my academic and personal interests and life.

I studied in my hometown Ordu during my secondary and high school years. Later on, I entered the Department of Aeronautical Engineering at Istanbul Technical University due to my interest in physics and mathematics. From the early days of the university, the field of aerodynamics began to interest me. I already knew about the complexity and timeliness of fluid physics. For this reason, I had decided before I entered the university that I would work in the field of aerodynamics or fluid dynamics. In my first year at the university, I started to work in the field of computational aerodynamics with one of the outstanding professors of our faculty. At this point, coding entered my life. I studied computational aerodynamics for about 2 years. In this process, together with my instructor and one of his assistant, we developed and revealed an aerodynamic analysis tool for small UAVs. Later, when my professor retired, I had to work with another professor for my undergraduate thesis.

At this point, I decided to study computational fluid dynamics, which I had the opportunity to deal with at the place where I did my internship, and I chose my teacher in this direction (of course, I had to be accepted by him first.). Now I started to focus more on applied mathematics and mathematical modeling of physical phenomena. Due to the personal interest of my teacher, we were working on moving mesh problems and their solutions. We were also using adaptive mesh refinement while doing these. For my undergraduate thesis, we solved the flow around a rotor using open source software and AMR. We also had the opportunity to publish a few publications on this study.

I am currently working on CFD with the same professor at Istanbul Technical University and I am doing my master’s degree. Although my master’s thesis is just to develop an algorithm to solve moving mesh and boundary problems in the compressible flow regime using the Arbitrary-Lagrangian-Eulerian (ALE) method, since my teacher’s interest in different subjects and my curiosity were encouraged a lot by him, I could be involved in many topics in the field of CFD, write different codes and had the opportunity to be intoduced with some of the problems of CFD.

Personal Interests Beyond the Academy

Up to this point of my post, I have only talked about my academic life. Under this heading, I would like to talk a little bit about my personal interests. All my life I have been interested in different areas of life. For example, I played chess in my primary school years and was also interested in theology. At the same time, I started learning baglama, one of the traditional musical instruments of my country. I started swimming when I was in high school. This process even progressed to becoming a licensed swimmer. Again in high school, my interest in mathematics and physics began to emerge. Along with my interest in theology, I started to encounter the philosophical reflections of physics problems. However, at that time, I was not interested in philosophy. I just stumbled upon it. I realized this much later.

University years were also very decisive for my intellectual life. First, my interest in philosophy increased. I started studying philosophy. Engineering problems didn’t interest me anyway. Because I always loved theory, not practice. When I grasped the close relationship between mathematics and philosophy, a very different world opened up for me to recognize and learn. While all this was going on, I added another traditional musical instrument to the baglama. That was a kamancha or “kabak kemane”.

As summary, I am currently studying, reading, thinking about philosophy, mathematics and CFD. Philosophy makes me think about being and truth. Mathematics seems to be the tool of the human mind to see and grasp the truth. CFD, on the other hand, reflects my experiences with this world, which must be explained in terms of its relation to applied mathematics.

To come back to real world after a lot of information about me, this summer event organized by PRACE has the following importance for me: I will have the opportunity to develop a parallel code for the adaptive mesh refinement technique that I have known and used before. I will also have the opportunity to get to know Paris and this culture closely. I’m so excited for both of these. Let’s see what the next two months will bring…

Posted on by Sara Sandh Posted in Participants 2022 — No Comments ↓

About me…

Hi everyone! My name is Sara Sandh, I’m 24 years old from Stockholm, Sweden. Since this introduction will be long enough as-is, I decided to present a coarse overview of my life and educational background in a timeline. This instantly became a more interesting read, didn’t it?

A quick overview of my life!

As you can see, I’m currently a student in Computational Science and Engineering at Vienna University of Technology in Austria, and have previously spent some years in France and Belgium. Although I spend most of my time studying, I can easily get lost in the kitchen for hours at a time. There’s nothing I find as therapeutic as experimenting with elaborate dishes or even cutting an onion! For the (few) remaining hours of the day, I like to spend time with friends and family, grab a drink, watch series, or go bouldering.

The road to where I am now was rarely as clear as it may seem when you look at my timeline. I have always been a curious person. Unfortunately, that means that I’ve always had a few too many areas of interest to easily make decisions on what to do, and where to go next. Lucky for me, I for once happen to know exactly where I’m about to go next: to Paris for a Summer of HPC!

…and what about SoHPC?

So why am I here? Well, towards the end of my Bachelor’s degree, I started picking up more and more software development projects. As much as I loved the puzzling and problem-solving of these projects, I realized that most projects had no real connection to the other engineering fields that sparked my interest in technology in the first place. I spent a large part of that year trying to decide whether I should continue down the software path, or try to go back to a more classical engineering field. Eventually, I found the perfect solution that allowed me to combine both interests and keep all doors open: Computational Science and HPC.

It’s my mixed interests in programming, engineering, and scientific applications that lead me to PRACE and Summer of HPC. In this internship, I’m looking to challenge myself with a very interesting project in a completely new field. Besides the technical skills and training, I hope to gain some insight into what a career in HPC may look like. Ideally, I would also like to prove to myself that it’s possible to apply my skills and knowledge to any new discipline – that even when I’m specializing in a topic, it doesn’t necessarily mean that I’m closing doors to other opportunities and fields!

So what will I actually do this summer? I will be hosted at CentraleSupélec in Paris to implement an advanced stability condition of a high-order Spectral Element Method (a special type of Finite Element Method) for an HPC wave propagation solver called SEM3D. What this means in detail, I will leave as a great cliffhanger for my future blog posts, so be sure to come back in a few weeks!

A few pictures from my first few days at CentraleSupélec. Don’t be fooled by the beautifully bright and open architecture – this place is a maze! My goal is to before the end of the summer complete one day without getting lost.

Posted on by ArdaE Posted in Participants 2022 — No Comments ↓

Hello everyone! My name is Arda Erbasan, and I am 25 years old. I completed my Physics Bachelor at Middle East Technical University in Türkiye. Currently, I am studying for a Master’s in Physics at the same university. From the beginning of my Bachelor’s, I could not keep myself away from the good textbooks that show unique pieces of scientific developments. Whenever I comprehended a specific perspective related to a natural phenomenon, I could sense the exquisite details of nature and years of struggles to figure out how it works. Only then I sincerely was to admire science itself, and I decided to step up for new research experiences. Since then, I have been working on research projects!

I started my active research phase by running Density Functional Theory simulations to investigate the Single-Atom Catalysts(SACs) on metal oxide surfaces. Currently, I am exploring the Liquid Phase Metal Catalysts with Density Functional Theory and Molecular Dynamics.

I heard about the PRACE Summer of HPC within the extended application due period due to the transition to the hybrid system. As soon as I dived into the projects and format of the program, they had me with the project “Computational modeling of atomic-scale damage in irradiated metal“. I thought we were the perfect match regarding both my Physics background and research experience in Materials Science. I applied to the program and got accepted very soon. 

After the general training week on HPC, MPI, OpenMP and GPU programming, we started meeting with our supervisors, Julio and Mary Kate. They are extremely friendly, considerate, and knowledgeable researchers in their fields. They have already arranged our accounts for Barcelona Supercomputing Center, and they started to teach us LAMMPS, which we will be using throughout the project.

Keep in touch to learn more about the details of the project!

Posted on by TanyaK Posted in Participants 2022 — 1 Comment ↓
During my visit at the University of Bern in 2021. At the back is the city of fountains, Bern, Switzerland.
During my summer internship in 2021 at the Leiden University. The photo is taken at the city center of the Hague, Netherlands.

My delightful journey from New Delhi to …

Hello and welcome to the first blog post of my life! I am Tanya Kushwahaa from the capital of India, New Delhi. I am 22 years old. I have just finished my Master and looking forward to start my PhD, starting October. Let me tell you how it all started. I was always into science and basic questions about the origin, existence and end of different objects were intriguing for me. It started with a Venus flytrap and photosynthesis process in the third standard and I ended up in studying the different processes in the stars and the Universe, by the final year of my high school. My interest in astronomy and aim to be an astronaut are the reasons I chose to study Physics, Chemistry and Mathematics in high school.

I finished my high school in the year 2017, and went to Hungary for my Bachelors in Physics. During my Bachelors, I was taught many courses but what really grabbed all my interest were the two semesters of C programming course. It was the very first time I learnt about coding and enjoyed coding so much, that soon felt, coding is the thing I would like to include in my future studies and projects. Keeping this in mind, I applied for Master programs which consisted of a major part in both Physics and Programming. In 2020, I started my Master degree in Physics and Computational Physics in Besançon, France. During the two years of my Masters, I developed my coding skills in Python, FORTRAN and Matlab. My favourite courses among all were the Machine Learning and Artificial Intelligence courses. I started as a beginner and now I consider myself an intermediate Python and FORTRAN programmer, who may not be able to solve a problem immediately but know how to think and proceed to find solution of a problem. My coding skills have opened many opportunities for me and I expanded my network with different astronomy groups in Hungary, France, Germany, the Netherlands and Switzerland. This has connected me to different people, cultures, languages and cuisines. I believe Science is a great tool to bring humankind together. On the way to explore one new culture, I will start my PhD in October 2022 on “Exploiting GAIA data and understanding the galaxies’ past histories with machine learning” at the Cardiff University in the UK.

Well, I do not have any specific hobby, The most I like is to be around people because that’s when I learn the most. Besides this, I like cooking, playing, dancing, and everything in short. I have always loved sharing my culture and learning different cultural practices.

Why SoHPC 2022?

After finishing my Masters, I was looking for summer internships. One day my Master coordinator sent us an email with the SoHPC 2022 program. The email was in French and I was too lazy to translate from French to English but automatic Google translate did its magic and translated the email. I thought it is a French program and did not plan to apply. Soon after reading about the program and its projects, I realised that I have found my summer internship for this year. I liked several projects but unfortunately most projects required C/C++ as pre-requisite. One project which took my attention was Neural networks in chemistry – search for potential drugs for COVID-19. I enjoyed AI course so much that I decided to keep this project as my first preference. This project is basically the application of Neural Networks on the SARS-CoV-2 molecules to select potential drugs for COVID-19. The subject is very new for me and I hope to learn many things during the SoHPC 2022 about which I will update you in my next blog.

What are my expectations from SoHPC 2022?

I have a lot of expectations from the program and from myself as I want to learn advanced computational skills, increase networking with PRACE and learn about the future projects. But let’s be realistic, the most I expect from my participation in the program is to improve my coding skills and write efficient codes, learn coding with MPI and GPU programming, and learn to use computer clusters, which would help me greatly in my PhD research. Other than this, I would like to connect more people, especially females to join HPC, SoHPC, and STEM (Science, Technology, Engineering and Mathematics), in general. I would like to spread the motive of SoHPC, i.e., to inform, engage, and inspire everyone, especially the youth, to work more towards advanced computing and STEM, through my blog posts.

So, here is the end of my first blog post. Feel free to ask any questions about my journey, the SoHPC 2022 program or my ongoing work in the comment section, at the bottom of the page. See you in the next blog post with interesting results on my SoHPC 2022 project!

Posted on by AhmedSI Posted in Participants 2022 — 12 Comments ↓

Greetings to you all.

My name is Ahmed Senior Ismail, and I’m a Nigerian. Hitherto, my educational studies were in Nigeria. However, just about a year ago, specifically at the end of my first master’s degree in mathematics, which I undertook at the University of Ilorin, Nigeria. A congratulatory mail landed in my mailbox which conveyed the news of my selection for the InterMaths & Mathmods double degree program. Lo and behold, I saw this as an impetus with which I could leverage towards broadening my mental horizon as well as satiating my curiosity in the field of Applied Mathematics, which without hesitation I accepted the admission offer.

Confessedly, I became an European student afterwards. I have just completed the first year of my program in mathematical engineering at the University of L’Aquila, Italy. It will be worthy to remark that the final phase of my program will be at the University of Silesia, Katowice, Poland, which I am obligated to be at come September.

Conversely, I was a high school mathematics educator back in Nigeria. Additionally, I have held several leadership positions, besides, I’m currently an editor-in-chief of a blog page named Unilorin Voice, an educational research platform, with about ten thousand subscribers. Nevertheless, I am a lover of numbers, an exciting fan of technological innovations and other concepts that pose to facilitate human task (s). I also love to engage in sporting activities during my leisure, in fact I used to be a sport analyst on broadcast station in my hometown.

What led to HPC?

My interest in high performance computing  sprouted recently, precisely during my first course on parallel computing taken by Professor Antonio Cicone and Professor Denato Pera. This course exposed me to the fundamentals of high performance computing explaining its concepts and motivations of supercomputer, ranging from the ability to handle large dataset, multitasking which enhance high speed of computation, fault tolerance and more flexibility in the deployment models. Knowing the integrability of this field into other fields makes it more valuable to me. Undoubtedly, the high performance computation has come to play a significant role in the future technological advancement.

Here comes SoHPC; What is SoHPC and what are its aims?

The summer of HPC (SoHPC) PRACE Program was timely as I was willing to further on the already learned basics. Thanks to my vibrant lecturer Professor Antonio Cicone who shared the information regarding the PRACE Summer of HPC 2022 to all his students. The summer of HPC program offers students with the opportunity to learn while working on practical projects with experts across the Europe during the summer at HPC centers in a PRACE Partner country. The main goal of the program is to encourage all students in their path to become the next generation of HPC users.

Would you’d like to know the brain behind this great program? I guess yes!

PRACE is Not for Profit Association under the Belgian law, with its seat in Brussels. Her mission is to enable world-class scientific research through large scale simulation.  PRACE has partners in twenty-five countries with five hosting members which include France, Germany, Italy, Spain, and Switzerland and has two observers Croatia and Latvia.

Here is how my journey with SoHPC started!

From among several excellent diverge projects offered this year, I chose to select project number 2208 optimization of neural networks to predict the results of mechanical models, which I find more interesting and relevant to my background and future endeavors. Though, I was doubtful at some point concerning the successful outcome due to the competitiveness of the program, but, obviously the committee found me most worthy to be granted the opportunity and which is one of many key reasons I shall put in my usual dedication and studious attitude towards the achievement of the project goals.  The main motivation for my choice of selection boils down to the zeal I have for machine learning concepts, and mathematical optimization where I had my first publication titled ‘’On the characterization of optimal control model of whooping cough’’ https://doi.org/10.34198/ejms.8122.175188.

The program started proper with virtual training week, with explanation of the overview of some important areas of high performance computing. Thanks to all the revered persons who made it a success, starting from Leon Kos, Pavel Tomsic, Alenka Maffi, Claudia Blass-Schenner, Moritz Siegel, Matic Bank, Leon Bogdanovic, the technical staff, and my wonderful colleagues.

Conclusively, it was a pleasure joining my mentors this week at Capgemini Engineering Company Toulouse, France. I am enthused and optimistic about the task ahead with a strong believe of producing a standard report leveraging the available resources. Until then, I say goodbye for now but stay tuned for the upcoming updates in a few weeks.

Feel free to drop your comments….

Posted on by PierreP Posted in Participants 2022 — No Comments ↓

A brief introduction

Hello there! My name is Pierre POLLET, a French engineering student from Nancy, a small town near Strasbourg. I discovered computer science at the beginning of high school, and I fell in love with the subject.

After two years of intense learning in preparatory classes I joined Telecom SudParis an engineering school near Paris. Always fascinated by how deep the field is, I have studied programming paradigm, how compilation works, what’s inside an operating system, parallelization problems…
On the side, I have always liked discovering new programming languages (like Rust) / paradigm through creating videogames / small program prototype. Apart from computers, I do like multiplayer videogames and anime series and movies.

How I started programming

In high school I joined a group of student to participate in MathEnJeans where I tried to solve problems given by a researcher using maths and computer science.

Figure 1 : An example of problem in MathEnJeans about how to generate a random image with spots, and how to fill with rectangle whose vertices are on the same color

After high school I joined a preparatory classes to enter an engineering school. During these years I heard of metaheuristic and tried to create an ant colony algorithm.

Figure 2 : Pheromones of an ant colony algorithm (the thickness of each line corresponds to the level of pheromones on the path)

At some point I tried machine learning stuff using tensorflow, learning about how it works… but I ended up not being attracted to this field as I like programming more than data collection and processing. I like programs and the challenge to program stuffs.

My Summer of HPC

In my actual school, I joined the coding club, and this is where I met someone who told me about the Summer of HPC. After one year on working on a parallelization problem I thought it could be fun to fill this summer.

I enrolled in a project without physics nor machine learning (because I am either bad or I don’t like it). I’ll work on data visualization for system administrators to help them manage supercomputers like the Marconi 100.

Posted on by FilippoB Posted in Participants 2022 — No Comments ↓

Hello everyone! I’m Filippo, I’m 22 and I’m currently in the middle of my master’s degree in Computer Science and Engineering at the University of Bologna, Italy. I have always been curious about parallel and concurrent programming and, after attending the High-Performance Computing course during the third year of my bachelor’s degree, I discovered my passion. During that course, prof. Moreno Marzolla taught me MPI, OpenMP and CUDA but my preferred one is by far the last one due to it being more down-to-the-metal than the others. That’s also the reason why I developed my bachelor’s thesis project in CUDA.

What are my interests?

I have always been interested in algorithms, especially non-polynomial ones, and the correlated data structures. Lately, as my passion for parallel programming grew, I tried to combine the two and ended up with numerical algorithms.

What is my project about?

I’m really excited to participate in PRACE’s Summer School of HPC 2022. This will be a great experience (to say the least) both for working and for studying. My project is the 2221, “Designing Scientific Applications on GPUs”; I will be working with Mr. Ezhilmathi Krishnasamy at the University of Luxembourg on the LibRSB library. LibRSB makes available some common operations for sparse matrices for the Recursive Sparse Blocks (RSB) format, which is its main feature, and for the Sparse BLAS standard. This library is designed to work on shared memory architectures, but can be compiled serially if needed, so it features OpenMP parallelism. My job will be to make it work work with NVIDIA GPUs, but CUDA is not a full fledged programming language like C or C++, it’s more similar to a framework, so I will actually have to implement many functions of this library in order to make it work with CUDA while maintaining the same C API. In order to assess the performance of my implementations and its scalability, I will be granted access to the IRIS HPC cluster of the University of Luxembourg (you can find its technical specifications here) which features 96 really expensive CUDA-capable GPUs: NVIDIA Tesla V100 SXM2. It will be a pleasure, and surely a unique experience, to develop on this monster of a computer and I will update you with my work in the next post so stay tuned!

Posted on by Victor Muya Posted in Participants 2022 — 18 Comments ↓

Hi there!

My name is Victor Njenga Muya, and I am participating in this year’s edition of the Summer of High-Performance Computing (SoHPC) research internship. This blog post is the first in a series where I will be sharing what I am learning, my experience, and the project I am working on.

Background

Currently 23 years of age, I was born and raised in Kenya, but I moved to Turkey four years ago to study Electrical & Electronics Engineering at Osmangazi University. My interest in programming computers to solve problems started with a C programming class and a robotics project I worked on during my first semester at the university. Consequently, I set out to learn more and more about programming and computing.

I learned about PRACE Summer of HPC through a friend who participated in the program last year. The program appealed to me because it avails training and resources for High-Performance Computing to university students, for them to solve complex, interesting problems in a 2-month research project in the summer. I was intrigued.

When I learned that the applications for the 2022 edition of the Summer of HPC were open sometime in March this year, I sent in my application. And in mid-May, I received an email informing me that I had been selected to do one of the 22 projects available this year.

Project 2201

I am working on Project 2201: Leveraging High-Performance Computing to test the quality and scalability of a genetic analysis tool. The team at the Comparative Genomics Lab of the Barcelona Supercomputing Center, where I am conducting my research, is developing an algorithm, JLOH, that analyzes genome data to test for loss of heterozygosity (LOH). Under the supervision of Toni Gabaldón and Matteo Schiavinato, I will be testing the algorithm’s scalability and ability to handle different genetic and data properties using HPC. More information about the project is available here.

Training week

I am writing this fresh out of a rigorous virtual training week hosted at the University of Ljubljana’s LeCAD Lab where we learned about the various parallel and distributed computing tools such as MPI and OpenMP in addition to GPU programming using CUDA. The sessions were well structured and hands-on; we were allowed to program on the LeCAD Lab HPCFS Supercomputing cluster. This made the learning curve a little less steep and the training a bit fun. Moreover, I got to meet some of the program’s mentors and the other like-minded participants with whom I will be working for the next couple of weeks.

That is all I am going to share in today’s blog post. Feel free to leave any questions that you may have in the comment section below, and I will get back to you. Thank you for reading and see you in the next one!

Posted on by BrunoRC Posted in Participants 2022 — No Comments ↓

A bit about me

Hello everyone! My name is Bruno, and I am 27 years old . I did a bachelor’s degree in mechatronics engineering at the National Autonomous University of Mexico, Mexico City. Currently, I am in my second year of my master’s degree in computational science and engineering at the École Polytechnique Fédérale de Lausanne (EPFL), Switzerland, and doing my internship at the Swiss Supercomputing Center (CSCS), Switzerland. The latter, in general terms, related to computing the tiled Cholesky factorization on a NVIDIA GPU using the computational power of the GPU efficiently.

My interest on the PRACE HPC program

Regarding my master’s studies, I have been taking courses from different fields such as molecular physics, data science, machine learning, and mathematics. I believe that by having and getting to know more areas, I would have much more tools to tackle a given problem. Similarly, I feel fascinated by how simple Monte Carlo methods are -they are basically a simple arithmetic mean- and how complicated they can become depending on what resources or information of the problem we have available. Fortunately, I have worked with Monte Carlo methods before and I am familiar with their advantages and disadvantages over other numerical schemes.

I am interested in participating in and collaborating with the project ‘Scaling HMC on large multi-CPU and/or multi-GPGPUs architectures’ during the PRACE Summer of HPC since I would like to learn how to and work on scaling and implementing Monte Carlo simulations on a GPU, and how an existing code can be tailored such that it can run on a GPU. Besides, this projects is aligned with two of my interests for my future career: scientific computing on GPUs and stochastic processes; hopefully a mix of both.

Goals for this project

My main goals for this project are to collaborate with and learn from my mentor and my teammates, to hand over a useful and well-done piece of code, and to fulfill what it is expected from this summer project. I am quite excited to work on this project and with my team, and will do my best to achieve valuable results.

Greetings!!

Posted on by Ezgi SAMBUR Posted in Participants 2022 — No Comments ↓

About Me ;

Hello, I'm Ezgi. I'm 24 years old. Currently, I am continuing my Master's degree 'In Tissue Eng. and Regenerative Medicine' program at Bahçeşehir University (full scholarship). At the same time, as an Vice-Specialist in Prof. Dr. Serdar DURDAĞI's team, I take part in the 'Software Based Pharmaceutical Design' project. (durdagilab.com). 
I was born and raised in a region called Thrace in Turkey. My family is Turks who immigrated to Turkey from Greece, Bulgaria, and Macedonia. They call us Balkan Turks. I completed my high school education at Edirne-Keşan Science High School (96.8 honors degree)
I completed my bachelor degree in Molecular Biology and Genetics at Muğla Sıtkı Koçman University (3.02/4.00). I completed my summer internships at the Faculty of Medicine and Engineering by participating in various research in the field of Neuroscience and Cancer at Wetlab.
I completed my undergraduate thesis in Neuroscience with the study 'MiRNA Signature of Prion-induced Neurodegeneration'.
Center of Supercomputer VSC-4 
Computational Drug Design, MD Simulations, Genetic Engineering, Molecular Simulations , GPUs, CPUs and more in here !

What are my research projects about ?

While doing my master's degree, I took part in the 'Software Based Covid Drug Development – Discovery of Paxlovid Analogs as SARS-CoV-2 Main-Protease Inhibitors' at Durdagilab (durdagilab.com). The results of this project are about to end. I use Schrödinger/Maestro in my work. Cov-Dock (Covalent Docking) is the area I particularly focus on in my work. Specifically, i am interested in Protein-Ligand Interactions. I am applying Covalent Docking strategies to obtain Protein-Ligand complexes, where ligands are attached to specific residues at the Binding Pocket of the Protein via Covalent bonds. After ranking ligands based on their interaction energies with the target protein, I am planning to proceed end-state free energy calculatins using MM/GBSA method.
Simultaneously, I am currently continuing my search for more than 2 million molecules  from 5 different libraries for a protein associated with Bruton Tyrosine Kinases and Leukemia.

Now, What am I doing with the SoHPC program?

I have lost many of my family members because of Cancer. When people are seriously ill, they can take medicine to relieve their pain. I would love to be able to make discoveries in the field of medicine so that people can continue their lives painlessly. Of course, I want this to be done with the least harm to nature. I think the solution to every problem is hidden in nature. That’s why I want to move forward by being inspired by nature.

With the training I will receive with SoHPC 

First of all, I was very happy to be selected for the Vienna Technical University-VSC Research Center as I work in the field of Software Based Drug Development. In this direction, I will learn to use Linux commands and AMBER.

My Project Number is 2222 ; Derived Affinity Enhancement of Antiviral Drugs

SoHPC Project aims to carry out HPC based computational screening for novel variants of the TAT-I24 peptide with improved binding affinity to ds-DNA.

HPC-based computational screening for novel variants of the TAT-I24 peptide with improved binding affinity to ds-DNA. A particular class of well-tolerated drugs is formed by small peptides because their building blocks are simply the 20 naturally occurring amino acids – the most fundamental constituents of any living cell. To transform such peptidic compounds into effective medical drugs, high-affinity binding to the target must be accomplished (and is usually the outcome of a tedious and long-lasting optimization process).

Consequently, the next simple step to further enhance drug efficacy was to change any of the 22 amino acids and examine the effect for improved or impaired binding strength.
Regarding the methods, the MM-PBSA technique can be applied. This computational approach allows semi-quantitative estimates of binding free energies (∆G) using standard tools in contemporary biophysical/biochemical research.

Computational Biology , Drug Design and Drug Repurposing,AMBER, Linux Commands, GPU Architectures, HPC, summer of HPC 2022

Computational Drug Design, AMBER, HPC

life is beautiful as you discover.. 

Ezgi ..

Posted on by ErselH Posted in Participants 2022 — No Comments ↓

My name is Ersel Hengirmen. This year, I will be remotely participating in my project, “Chitchat, Gossip & Chatter – How to efficiently deal with communication,” at JSC-Jülich Supercomputing Centre with Ignacio Encinas Rubio. It is an amazing opportunity for every one of us. I am pretty excited to be a part of Prace Summer of HPC and more than ready to start my project, even though it would have been much more fascinating to be there and see the supercomputer up close.

Why am I here

Me last month in Mersin/Turkey getting ready for soHPC

I was born in Gaziantep/Turkey, and this September, I will be a fourth-year computer engineering student at Middle East Technical University(METU). I have always got fascinated by even the simplest of algorithms. I fell in love with computer science when I was implementing a basic program that plays the “guess the number” game. In the “guess the number” game, one player tries to find the picked number that must be between 1 to 1000 in at most ten tries. The guaranteed approach is to halve the remaining numbers constantly. It was a fascinating game I liked to play as a kid, but it turns out it was a fairly known algorithm known as binary search. 

As for parallel programming, it was the genius that was behind the broadcast operation that made me fall in love this time. The algorithm used the theory behind binary search in reverse; by using the processes that received data to multiply sent data at every iteration. The weird part was that it didn’t matter if it was a ring, a hypercube, or any mesh topologies; the method always gave the same log(p) complexity.

As another weird anecdote: To be accepted to the Prace Summer of HPC we were given a task of finding error rates in pi calculation. To solve it I used a reversed version of binary search to find the interval of the solution and then used binary search to find the real solution. So binary search helped me get accepted to here.

Chitchat, Gossip & Chatter – How to efficiently deal with communication

Everyone ready for chitchat and gossip

Out of all the 22 projects, Chitchat, Gossip & Chatter was the one that spoke to me. In my college classes, we generally focused on the theoretical side and how some functions like broadcast and reduce work in the background. I chose Chitchat, Gossip & Chatter to put this theoretical knowledge to the test. In the following months, I plan to use and increase my knowledge in the theoretical territory while improving my skill in implementing this knowledge simultaneously, thus improving both aspects.

The project is about optimization. We will start with scaling up the Fast Multiple Method(FMM) for a large number of nodes to create a model that works better than naive point-to-point approaches. After this point, we will move according to our results. One of the important problems will be minimizing the overhead of communication, which can impede the speedup of the solver as the problem scales up. I believe that we will show you something we can be proud of at the end of this project. To learn more about it you can check the link here.

Who should apply

If you are interested in HPC, apply; that’s really it. It would be great if you knew about the subjects, but even if you don’t, the classes and resources our excellent instructors and mentors give you will be much more than enough. Just come here, look at the projects, find one that spokes to your heart, apply and see the fantastic world of HPC where everything you know can be done better. This field needs brilliant people like you, so come on in.

Posted on by Konstantinos Kellaris Posted in Participants 2022 — No Comments ↓

About me

Hello everyone! My name is Konstantinos Kellaris and I am 23 years old. I was born and grew up in Kiato, a small town in Greece. Right now, I’m in the fifth and final year of my undergraduate studies in Mechanical Engineering at the National Technical University of Athens and expect to graduate in October. My focus is on air and ground transportation vehicles, but I also have a strong interest in energy and environmental applications.

Summer of HPC motivation and expectations

Since I was young, I have wanted to know how and why things work and this led me to engineering. As an aspiring engineer, I learned early in my studies the value of Computational Methods and their applications in getting insight into challenging technical problems. Due to this, I have taken many courses and subsequently, work on plenty of projects that utilize methods such as the Finite Element Method or the Finite Volume Method in engineering. Furthermore, my Diploma Thesis dissertation is about Data Assimilation in Computational Fluid Dynamics using open-source software.

All of the above led me to really appreciate the value HPC systems provide in scientific and engineering computing in general. So when my supervisor informed me about the Summer of HPC opportunity PRACE provides and I saw that there were projects about Computational Fluid Dynamics I applied with excitement and thankfully I was selected.

I believe this opportunity will really help me get accustomed to HPC systems and I will be able to see how my simulations scale when utilizing lots of computational power.

My project

The project I will be working on is conveniently named Computational Fluid Dynamics. This project will be carried out in person at the University of Luxemburg. I will use the open-source finite element code FEniCS to study the 3-dimensional turbulent flow around a simple geometry.

The training week has ended and from now on I will be working full time on my project, so stay tuned for updates!

Posted on by DogukanT Posted in Participants 2022, PRACE Summer of HPC 2022 — No Comments ↓

A little about myself

My name is Doğukan Teber. I am 22 years old and am a fourth-year software engineering student at Yasar University. I met programming when I started the university and ever since I am in love with programming, software, and computation. Although I like technical stuff and I did not want to abandon my human skills such as communication skills, teamwork, leadership, and so on. Therefore, I spent my first two years of university education learning the basics of programming and doing volunteering work to improve my soft skills. After I worked on my programming skills and soft skills, I applied for a part-time job at a company near to my school. At the end of two months of internship, I got accepted and started working there. I learned the Django framework and got the opportunity to practice Python. I learned tons of new stuff there such as RabbitMQ, Redis, working with APIs, and so forth.

This summer, I will work at GET-Geosciences Environment Toulouse. My project partner is Stavros Dimou and more about the project is at the end of the blog. Now, let me talk a little about how I applied to the Summer of HPC.

How did I apply?

One of my university professors sent me the program’s flyer via e-mail. “There are interesting projects. You may be interested”, he said. So I took a look at the projects and I immediately sent my application. Just when I started to lose hope, I got an e-mail saying that “You have been selected for project number 2207 that will be running in online mode.” and here I am.

At this point, we have finished the training week and every student now is going to focus on their project. You may wonder, “What did you learn from the training week? And, how was it?”. Let me explain.

What is a training week and how did it go?

As you may understand from the name, training week is an introductory week of Summer of HPC to introduce students to parallel programming paradigms and tools. Of course, the aim is not to teach all the details about these tools but rather to teach the very basics of these concepts. The training week took 4 days and approximately 7 hours per day. Here is a brief overview of the training week:

On the first day, we learned about PRACE, its mission, and what Summer of HPC is. We also learned how to connect supercomputers and how to run our programs on supercomputers.

On the second day, we dived into technical stuff and learned the basics of the MPI library.

The last two days were kind of the same as the second day except the tools were changed. On the third day, we learned openMP. In addition to that, after the lunch break, we dived a little deeper into MPI and learned advanced topics of MPI. Finally, on the last day, we learned the basics of GPU architecture and CUDA programming.

The schedule may seem overwhelming but I can assure you that it is not. There are plenty of breaks between the topics to have a coffee or to have a nap. So, you can easily fill your battery. Besides, you do not just sit in front of your computer and listen. Most of the topics contain hands-on exercises that keep you focused on what is being taught and you do not get bored.

What will we work on?

We will perform a performance analysis with permaFoam for contrasted physical conditions and on different supercomputing systems. However, it is not just this. We also aim to develop a new tool that leverages parallel programming in permaFoam. The tool we will develop parallelizes the decomposePar utility in OpenFOAM. Now, this utility is working serially. At the end of the project, we would like our tool to do exactly the same thing that decomposePar does, but in parallel. If everything goes smoothly, we will open a pull request to OpenFOAM and contribute to this awesome open-source project.

Final remarks

We have come to the end of this blog. I am delighted to be part of this program and cannot wait to see the end result. I hope you learned something from this blog post. I will be posting my progress during the program. Thank you for reading.

Posted on by ThomasW Posted in Participants 2022 — No Comments ↓

Hi everyone! My name is Thomas and this summer I’ll be working on scaling Hamiltonian Monte Carlo (HMC) with the Hartree Centre. In this post I’ll take you through the random walk that lead me to working on this project.

Me in Paris this June

First, a little about me. I’m a Physics undergraduate at the University of Manchester with a strong interest in the application and physical limits of computation. In my spare time, I enjoy rock climbing (although I’ve yet to climb outdoors!) and playing rugby. This summer will be my first experience collaborating on code, and I’m excited to write code that other people will build upon.

Below is some of the past work I’ve done with monte carlo methods – namely simulating the propagation of neutrons through different materials. I also have experience with Linux due to my efforts to maximize cryptocurrency mining profit, which was rewarding in the sense it taught me a lot about computers. As a result of this experience, and my Physics background, I feel like this project is a great fit and I’m excited to see how far we can take it.

10 Neutrons Travelling Through Water, Lead and Graphite

The hamiltonian monte carlo method is commonly used for estimating the parameters of a distribution, as well as for generating samples from a known distribution. Fascinatingly, as the name suggests, the method takes inspiration from Physics, with ‘energy’ and ‘momentum’ playing a key role in the algorithm. It’s strange that the analogy of a hockey puck sliding over a smooth hill is so applicable to statistics.

That’s all for now – come back in 2 weeks for a better overview of hamiltonian monte carlo – and some details of the parallel implementation!

Posted on by MonikaD Posted in Participants 2022 — 2 Comments ↓

A bit personal…. 

Hello everyone! My name is Monika Das and I am 27 years old. I was born and grew up in a small city named Rangpur in Bangladesh. I did my bachelor’s in Electrical engineering at the University of Dhaka. Sometime during my bachelor’s, I developed a strong interest in physics, and in 2021, I moved to France to study physics. I am currently doing my master’s in Computational physics at Université Bourgogne-Franche-Comté. I live and study in Besançon, a beautiful city in eastern France. 

To be honest, I am a bit shy person and I love to be as near to nature as possible. But in my spare time, I also enjoy traveling to new places, meeting new people, and exploring different foods and cultures. The fact that I love music and have always had a passion for it is another significant aspect of my personality. I have been learning and practicing traditional music since my childhood. I am also very keen to experiment with new instruments and currently, I am learning to play the piano. 

How I end up with SoHPC 2022…. 

Since I started my master’s in France, I have had the opportunity to explore a diverse range of physics topics. At that time, I was getting to know quantum computing and I felt amazed. I wanted to work on a research project related to it and that opportunity came to me with the offer of SoHPC 2022. 

I started looking for a summer internship right after finishing my first semester so that I could develop some skills during the summer. One day, when I was completing job applications and preparing for interviews, my master’s coordinator sent me an email with the URL for the PRACE summer program. Several projects drew my attention, but the one truly fascinated me was, “Fundamentals of quantum algorithms and their implementation”. I applied for the project since I did not want to lose the chance to pursue my ambition. As it was highly competitive, I was not expecting too much from it. But with utter surprise, I got the selection email. Midway through May, on a beautiful morning, I began my journey with SoHPC. 

Quantum computing and what else? 

I assume you have already guessed that the focus of my project is quantum computing. Quantum computing with its unprecedented features has become a potential field of research nowadays. It has a lot of applications in various branches of engineering and physics. As the name suggests, quantum computing is mainly founded on the principles of quantum mechanics. While classical computers are made of transistors and can only have smallest functional units as 0 or 1, the smallest unit in quantum computers is called a qubit, which unlike bits of classical computers can be in a superposition of 0 or 1. What makes it more interesting is that, the computational power increases exponentially. Therefore, quantum computers can give effective solution to complex research problems and handle millions of data with as small as 10 or 20 qubits. There are other advantages of quantum computation over classical computing, like quantum parallelism, quantum teleportation etc.   

What is planned to achieve with this project is to explore such differences of quantum computation with the classical one. Based on a completely different and new principle of quantum computing, our target is to design the quantum circuits of our own. We also plan to test the circuits by using simulators or real quantum hardware.  

My personal goal with this project is to learn more about quantum computing and related simulation techniques. I hope the skills that I will gain through this training will help me choose a career path in this field. However, the overall impact of SoHPC is far-reaching for me. It not only just aims for developing scientific skills but also trains to build active communication and collaboration among participants. The latter is the key for successful research because it opens the door for sharing creative ideas among young researchers.  

That is all about me and my thoughts about PRACE summer of HPC. Let me know what you think and do not forget to stay tuned so that I can get back to you with interesting updates about my work in upcoming weeks.

Posted on by ChristopherK Posted in Participants 2022 — No Comments ↓

About Me

Greeting from Westmeath, Ireland, I’m Christopher Kirwan. I am 23 years old and last year graduated from Trinity College Dublin with a bachelors degree in Theoretical Physics. For as long as I could remember, I always had a passion for STEM and how the world works fundamentally. While completing my degree, I also gained an admiration for the intersection of computing and physics. Naturally, an interest in High Performance Computing (HPC) arose from those passions.

Me at my graduation

Why This Project?

Recently, I was given the wonderful news that I would be starting a PhD in Lattice Quantum Chromodynamics (Lattice QCD for short) with Trinity College Dublin, funded by IBM Research Dublin. I will be researching modern techniques, algorithmic advances and workflow optimizations in Lattice QCD in the exascale. This research is intimately tied to advances in HPC, so to get a good grounding in HPC infrastructure I applied to the PRACE Summer of HPC programme.

I was absolutely delighted when I got my first choice: High Performance Quantum Fields. It’s not often you get handed a project that aligns exactly with your research area! This project is organised/hosted by the Jülich Supercomputing Centre (JSC) and I hope to gain some excellent computing experience from them over the summer.

Initial Experience

So the first week is over – the dreaded training week. Unfortunately, along with the project, this was held remotely. As I am based in Ireland, this meant a series of early mornings to make it into the office for the 8AM start. Aside from that, the training sessions were incredibly fun and very interesting. I also had the opportunity to meet with my fellow colleague on this project Apostolos Giannousas.

Posted on by StavrosD Posted in Participants 2022 — No Comments ↓

About me.

My name is Stavros Dimou and I am 22 years old. I was born in Volos, Greece and I am currently a fourth year student at the Electrical and Computer Engineering Department of University Of Thessaly. From a young age I have always been interested in engineering and technology as well as making things work the best way possible. Being guided by my professors I learned many important facts about working and being an engineer and as the years passed I discovered differents paths of engineering and got really interested into High Performance Computing, Networking and Distributed Systems.

My involvement with SoHPC.

A few months ago after finishing the High Performance Computing course of our department, our professor informed us about this internship program. Since I really enjoyed the course, this was a really big opportunity for me to get involved even further with HPC. Thankfully i got accepted and joined my first choice project which was 2207, Assessment of the parallel performances of permaFoam up to the tens of thousands of cores and new architectures, which I find really interesting for a lot of reasons, but mainly about it’s environmental purpose combined with HPC.

Expectations and goals.

As this project is closely associated with PRACE I am sure that I will be able to learn a lot about high performance computing and parallel programming in general. I also expect to get the chance to be able to run my programs on a supercomputer which would be amazing.

As for my goals, I intend to enhance my knowledge on HPC and to make the most out of the program. Hopefully i will be able to get some interesting results at the end, and also solve the main problem that is associated with the project.

Posted on by JulenE Posted in Participants 2022 — No Comments ↓

Hello everyone! I’m Julen Expósito, I’m 24 years old and I live in San Cristobal de La Laguna, Spain. I graduated in Physics at the Public University of the Basque Country and I am currently finishing a Master in Astrophysics at the University of La Laguna, place where I discovered my passion for research and my taste for theoretical and computational work with physical models.

I have learned a lot in the master, but I have never had a real opportunity to work in collaborative projects of a certain size or with supercomputers. In my second year I learned how to program in parallel and through my contact with researchers I got a good idea of how they used to work in the field of high performance computing. As someone looking to work with simulations and big data in astrophysics in the future, I knew that I could really use some experience working with supercomputers on a real project, beyond the didactic testing ground of a master’s degree, so when one of my professors told me about Summer of HPC I was very interested, as it offered me just what I wanted before starting a PhD.

In my project I will perform High Performance Data Analysis with the results of a multi-scale simulations of plasma code. This code is being used by my mentors to simulate the interaction between the solar wind and planetary magnetospheres, and I can assure you for which I have explored of it so far that my interest in acquiring experience with large collaboratory codes is going to be fulfilled, in addition to deepening my knowledge of parallel computing. My job will be to work with and optimize the post-processing of the simulation outputs, so I hope to be up to the task and do a good job!

There is one other thing that I think this program is going to bring me. Something that is easy to consider secondary, but which is extremely important in the life of a researcher. You see, I had never left my country, nor had I ever had to speak with other people in a language other than Spanish. For this project I have had to move to Nice, France, and that has brought me to a new environment in which I have to force myself to speak English with everyone (and many times to communicate with people in the city who only speak French, a language that I do not know at all!). I find myself very much out of my comfort zone, and I admit that these first few days were very scary. I think that, for the moment, I’ve managed to get by and quickly get used to this new place. A research scientist has to get used to moving from place to place and cooperating with people from all over the world, and I am very grateful for this opportunity to gain that experience and get rid of the fear of leaving the comfortable walls within which I have always moved.

Let’s see what this experience brings me, and what I can bring to the project I will be immersed in these next few weeks. It’s time to use everything I’ve learned over the years to contribute to science!

Facebook
Twitter
Follow by Email