MareNostrum 5, a supercomputer in which Portugal, through the Foundation for Science and Technology, holds a 5% stake, financed by the Recovery and Resilience Plan, is about to enter the production phase.
Those interested in submitting expressions of interest to access the production phase of MN5 must complete and submit the simplified form, available at Expression of interest form, by September 9th.
Before this phase, 11 national users with previous experience were sent to the Barcelona Supercomputing Center, where MareNostrum 5 is located. They were pioneers in testing and optimizing their projects on the 2 largest partitions of this supercomputer.
Thales Silva, a researcher at the Lasers and Plasmas Group of the Institute of Plasmas and Nuclear Fusion, belonging to the Instituto Superior Técnico, was one of the first to use the supercomputer , through the experimental access still in pre-production.
At a time when this opportunity is opening up to other projects, the researcher with 7 years of experience using high-performance computing, who has already used 10 different supercomputers in Europe, shares his testimony about MareNostrum 5.
Before this supercomputer, Thales had access to the predecessor MareNostrum 4, which he describes as his "favorite supercomputer to date". On this machine, he highlights the short time the computer is not accessible, the clear communication with users when there are problems, the agility and usefulness when user support is needed and the organization of the software stack".
"All the systems I've used have responded well to most of these aspects, but few have compared to MareNostrum 4. As for MareNostrum 5, my perception is that this quality has been maintained," he says.
1. How would you describe your experience with Marenostrum 5 and what resources did you use?
The experience was very positive, especially as it was an experimental access with the machine still in pre-production.
I used resources from the general partition (focused on CPUs) and the partition that uses accelerators (GPUs) for a total of 2 million core hours on CPU and 100,000 gpu hours on GPU.
2. What are the projects you used Marenostrum 5 for?
Our primary objective was to test the OSIRIS code for plasma simulations. Our group has been one of the co-developers of this code for over 20 years, together with groups from the University of California Los Angeles and, more recently, the University of Michigan.
The code is used by dozens of groups and universities around the world and is recognized by the scientific community as the benchmark for plasma simulations, so it is important that we test its performance on new machines to ensure that it is using all the resources of the most modern architectures.
These tests give the OSIRIS community confidence in using the code in MareNostrum 5, and allow us to extrapolate the expected performance to other systems with similar architecture and processing units, and thus help other OSIRIS users who are preparing requests for computing time on other computers.
OSIRIS also has a newer version that uses GPUs to speed up the most demanding part of the code. The opportunity to test this version, especially in a context where we can use hundreds of GPUs in parallel to check the scalability of the code, was one of the objectives we were able to achieve.
In addition, our project has a highly relevant scientific component in plasma physics. Plasma is the fourth state of matter, in which temperatures are so high that the image of an atom as electrons trapped around ions (nucleus) no longer exists: the particles are so energetic that there are no direct links between electrons and the nucleus. The Sun, for example, is in this state of matter. While on Earth it is not a common state, the truth is that more than 99% of (visible) matter in the universe is in the plasma state.
There are many fundamental questions still open on this subject, namely how the energy contained in the plasma is distributed among its different particles. We have been collaborating on this subject with the University of Oxford, and have carried out large-scale simulations on MareNostrum 5 to corroborate theoretical results that explain these patterns in the distribution of energy.
Another scientific component in which we used MareNostrum 5 is related to the emission of coherent radiation by plasmas. Plasmas are disorganized and the radiation emitted is not coherent (each particle emits independently of the others). However, there are processes that can lead plasma particles to emit high-intensity coherent radiation. Our group, as part of the doctoral thesis of student Pablo Bilbao, is preparing a series of papers that make a connection between the radiation observed on Earth and coherent emission by astrophysical plasmas.
Another parallel work, in which I used the resources of MareNostrum 5, consists of creating conditions analogous to those of these astrophysical plasmas that can emit coherent radiation in the laboratory. In this way, we can better understand the connection between the radiation we observe on Earth and the coherent radiation emitted by these plasmas. A highly relevant point in this work is the combination of two technologies: ultra-intense lasers and high-performance computing.
3. What are the benefits of using the capacity of this supercomputer for your projects?
On the scientific side, we will be able to run the large-scale simulations for the projects mentioned above efficiently.
One unique factor was that MareNostrum 5 also allowed us to test the GPU version of OSIRIS on H100 GPUs for the first time. This was very useful for comparing the results and the pros and cons against the A100 GPUs that are more common in supercomputers today.
4. What improvements would you like to see implemented?
Maybe some small details, like showing how much computing time and storage the project has used or is using on the login screen.
There are other features (some commands that can be useful for checking the computer's status, how many nodes are idle in the partition, etc.) that are disabled for now, but I think that's because it's in pre-production.
5. What did you think of the application process and how would you like to apply again?
The application was very simple and convenient. MareNostrum 5 will probably always be at the top of my list in the coming years as the supercomputer I intend to use and prepare applications for. The same also applies to Deucalion.
Having both computers available through national competitions is extremely important for our group, which needs these advanced computing resources for a significant part of our research. In the last RNCA competition, our group obtained three projects with computing time on Deucalion and MareNostrum.
6. Would you recommend this experience to other researchers?
Without a doubt, and I've already done it: Prof. Jorge Vieira applied for MareNostrum 5 in the last RNCA competition after I told him that I was using the computer in that pre-production period and that the performance of our code (OSIRIS) was excellent.
More information about the application for the production phase of MareNostrum 5 at https://rnca.fccn.pt/marenostrum-5/
