Computational marathon matches the efficiency of existing platform with the power of new supercomputer

It took about 20 hours and a variety of espresso for a group of scientists from the Swiss Nationwide Heart of Competence in Analysis NCCR MARVEL to finish a computational marathon that showcased each the ability of Switzerland’s foremost supercomputing facility, and the extent of maturity achieved by Swiss-made software program instruments for computational supplies science.

The Alps supercomputer, which simply turned operational with its official inauguration on September 14, 2024, is likely one of the world’s strongest supercomputers. It’s managed by the Swiss Nationwide Supercomputing Heart (CSCS) and it consists of a geo-distributed infrastructure primarily positioned within the Lugano knowledge heart.

Through the acceptance section, CSCS allowed entry to Alps to chose analysis teams, and among the many first with this chance had been members of the NCCR MARVEL, particularly Giovanni Pizzi’s group, a part of the Laboratory for Supplies Simulation (LMS) at PSI headed by Nicola Marzari, that makes use of computational strategies to search for new supplies for a lot of functions.

Over the course of someday and one evening on July 17 and 18, a group together with Marnik Bercx, Michail Minotakis and Timo Reents, all from Pizzi’s group, launched into what computational specialists name a “hero run”—a time slot when a supercomputing machine is fully reserved for a single person, to make use of the total energy of your complete machine to advance their very own analysis, and show their functionality of effectively exploiting the immense computational energy of the total system.

The PSI group wished to match the ability of the Alps supercomputer with AiiDA, an open-source instrument that helps supplies scientists automate the lengthy and sophisticated calculations required to simulate the properties of supplies—both present ones or these nonetheless ready to be found.

Specifically, they interfaced AiiDA and Alps to run high-throughput calculations, the place hundreds of various supplies constructions saved in a database are calculated in parallel. It’s the sort of computational experiment that enables, for instance, the choice of potential new battery supplies out of hundreds of recognized chemical compounds, serving to experimentalists to focus their efforts on essentially the most promising ones.

“We wished to point out that AiiDA can replenish all of the nodes of a supercomputer with near-exascale efficiency for a lot of hours and absolutely exploit the ability of the machine whereas dealing with, operating and sustaining many separate workflows concurrently, which is critical for high-throughput computations,” explains Bercx.

The run was managed remotely, with the AiiDA software program put in on a PSI server, and used to organize all enter recordsdata of the calculations to be carried out. The precise computations had been executed utilizing an enhanced model of the extensively used Quantum ESPRESSO computed code for supplies simulations, powered by the Sirius library—developed inside NCCR MARVEL at CSCS—that enables for the optimum exploitation of the nice computing energy offered by graphical processing models (GPUs) of Alps, and implements novel algorithms to considerably enhance the simulation success charge.

When the scientists obtained the inexperienced gentle from the CSCS workers round midday on the chosen date, they began sending enter recordsdata to the Alps machine, the place they had been submitted to a scheduling software program that distributed the roles among the many 2033 NVIDIA Grace Hopper nodes (together with 8,132 GPUs and 585,504 CPU cores) that had been granted for the hero run and queued them. On the opposite aspect of the connection, AiiDA was monitoring every job so that when it was completed, the recordsdata might be retrieved, parsed, and saved in AiiDA, and new calculations might be then submitted.

In a short time after beginning the run, AiiDA may fill the entire Alps supercomputer with jobs, absolutely exploiting its excellent computational capabilities. Round 3 AM, the group understandably wanted a brief nap, and relied on AiiDA to proceed making ready and submitting new jobs of their absence. The run efficiently ended round 9 AM on the second day.

“All went easily, and the variety of out there nodes was remarkably secure throughout your complete hero run, which speaks to the standard of the infrastructure” says Bercx. The 99.96% utilization of a near-exascale machine is completely outstanding and fairly unprecedented—very a lot attaining the objectives of the MARVEL NCCR devoted to computational supplies discovery enabled by such capabilities and infrastructure.

In the long run, the group managed to finish virtually 100,000 calculations, akin to single runs of Quantum ESPRESSO, in nearly 16 hours. Extra particularly, the calculations had been concerning the properties of round 20,000 crystal constructions taken from the AiiDA database.

“We selected medium-sized constructions, as a result of Alps is so highly effective that small constructions wouldn’t use the computational energy effectively,” explains Minotakis. “We began with constructions made out of 40 atoms, after which in subsequent submissions added barely smaller and barely bigger constructions.”

The computations had been meant to calculate the digital properties of the supplies of their floor state, discover whether or not they had been magnetic or not, and calculate their ground-state geometric configuration.

“We additionally had new pseudopotentials that we wished to check, so we up to date the calculations for a big fraction of the constructions within the database and checked the variations with earlier calculations” says Reents. All the outcomes will quickly be revealed as FAIR and open knowledge, and uploaded to the Supplies Cloud, the net knowledge sharing platform of NCCR MARVEL, to broaden the MC3D database of inorganic 3D crystal constructions.

Along with the nice scientific worth of those simulations, the run demonstrated the effectivity and stability of AiiDA, which may seamlessly fill your complete capability of an exascale machine.

“The efficiency of the brand new Alps machine is excellent, much more so when mixed with the high-throughput capabilities of AiiDA. It’s spectacular that we may compress in lower than a day the equal computing energy granted for one full 12 months to massive supercomputing tasks at CSCS, equal to roughly 800,000 GPU hours of computation on the previous-generation CSCS supercomputer Daint,” says Pizzi.

Supplied by
Nationwide Centre of Competence in Analysis (NCCR) MARVEL