Related papers: Extreme Scale-out SuperMUC Phase 2 - lessons learn…
Modern large language model workloads put increasing demands on parallel compute capability and on-chip memory capacity, while also stressing fine-grained data movement and synchronization. These trends motivate exploring and designing…
New challenges in Astronomy and Astrophysics (AA) are urging the need for a large number of exceptionally computationally intensive simulations. "Exascale" (and beyond) computational facilities are mandatory to address the size of…
ATLAS, a general-purpose experiment at the Large Hadron Collider (LHC), makes use of a large internationally-distributed computing infrastructure, including over $10^6$ TB of managed data on disk and tape and almost one million…
We present the design, implementation and engineering experience in building and deploying MegaScale, a production system for training large language models (LLMs) at the scale of more than 10,000 GPUs. Training LLMs at this scale brings…
The ATLAS and CMS experiments at the Large Hadron Collider (LHC) at CERN have searched for signals of new physics, in particular for supersymmetry. The data collected until 2012 at center-of-mass energies of 7 and 8 TeV and integrated…
A memory leak in an application deployed on the cloud can affect the availability and reliability of the application. Therefore, identifying and ultimately resolve it quickly is highly important. However, in the production environment…
We report on the 3-year INFN ATLAS-CMS joint research activity in collaboration with FBK, started in 2014, and aimed at the development of new thin pixel detectors for the High Luminosity LHC Phase-2 upgrades. The program is concerned with…
Memory-bound algorithms show complex performance and energy consumption behavior on multicore processors. We choose the lattice-Boltzmann method (LBM) on an Intel Sandy Bridge cluster as a prototype scenario to investigate if and how…
The CERN LHC provided proton and heavy ion collisions during its Run 2 operation period from 2015 to 2018. Proton-proton collisions reached a peak instantaneous luminosity of 2.1 $\times$ 10$^{34}$ cm$^{-2}$s$^{-1}$, twice the initial…
The energy consumption of an exascale High-Performance Computing (HPC) supercomputer rivals that of tens of thousands of people in terms of electricity demand. Given the substantial energy footprint of exascale HPC systems and the…
Data scouting, introduced by CMS in 2011, is the use of specialized data streams based on reduced event content, enabling LHC experiments to record unprecedented numbers of proton-proton collision events that would otherwise be rejected by…
A high-performance implementation of a multiphase lattice Boltzmann method based on the conservative Allen-Cahn model supporting high-density ratios and high Reynolds numbers is presented. Metaprogramming techniques are used to generate…
This paper presents the first, 15-PetaFLOP Deep Learning system for solving scientific pattern classification problems on contemporary HPC architectures. We develop supervised convolutional architectures for discriminating signals in…
After successfully completing Phase I upgrades during LHC Long Shutdown 2, the ATLAS detector is back in operation with several upgrades implemented. The most important and challenging upgrade is in the Muon Spectrometer, where the two…
Phase-change materials (PCMs) are increasingly recognised as promising platforms for tunable photonic devices due to their ability to modulate optical properties through solid-state phase transitions. Ultrathin and low-loss PCMs are highly…
We present the simulation tools developed to aid the design phase of the Cassegrain U-Band Efficient Spectrograph (CUBES) for the Very Large Telescope (VLT), exploring aspects of the system design and evaluating the performance for…
Turning the current experimental plasma accelerator state-of-the-art from a promising technology into mainstream scientific tools depends critically on high-performance, high-fidelity modeling of complex processes that develop over a wide…
The DZERO experiment located at Fermilab has recently started RunII with an upgraded detector. The RunII physics program requires the Data Acquisition to readout the detector at a rate of 1 KHz. Events fragments, totaling 250 KB, are…
Physical phenomena such as chemical reactions, bond breaking, and phase transition require molecular dynamics (MD) simulation with ab initio accuracy ranging from milliseconds to microseconds. However, previous state-of-the-art neural…
This article reports on first results of the KONWIHR-II project OMI4papps at the Leibniz Supercomputing Centre (LRZ). The first part describes Apex-MAP, a tunable synthetic benchmark designed to simulate the performance of typical…