Common Accounting System for Monitoring the ATLAS Distributed Computing Resources

Karavakis, E.; Andreeva, Julia; Gayazov, S.E.; Jézéquel, S.; Sáiz, Pablo; Sargsyan, L; Schovancová, J.; Ueda, I.

doi:10.1088/1742-6596/513/6/062024

Cited by 10 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High-precision modeling of the interactions of particles with media is important across many physical sciences, enabling and accelerating new findings. Similar to complex weather or cosmological modeling, the detailed simulation of subatomic particle collisions and interactions, as captured by detectors at the LHC, is a computationally demanding task, which annually requires billions of CPU hours, constituting more than half of the LHC experiments' computing resources [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters

2018

View full text Add to dashboard Cite

Physicists at the Large Hadron Collider (LHC) rely on detailed simulations of particle collisions to build expectations of what experimental data may look like under different theoretical modeling assumptions. Petabytes of simulated data are needed to develop analysis techniques, though they are expensive to generate using existing algorithms and computing resources. The modeling of detectors and the precise description of particle cascades as they interact with the material in the calorimeter are the most computationally demanding steps in the simulation pipeline. We therefore introduce a deep neural network-based generative model to enable high-fidelity, fast, electromagnetic calorimeter simulation. There are still challenges for achieving precision across the entire phase space, but our current solution can reproduce a variety of particle shower properties while achieving speedup factors of up to 100 000×. This opens the door to a new era of fast simulation that could save significant computing time and disk space, while extending the reach of physics searches and precision measurements at the LHC and beyond.

show abstract

Section: Introductionmentioning

confidence: 99%

Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters

2018

View full text Add to dashboard Cite

show abstract

“…Experiments at the LHC simulate billions of events every year, each event taking O(minutes) to simulate [37]. This results in simulation campaigns consuming up to 70% of experiment computing resources [44,53].…”

Section: Event Generationmentioning

confidence: 99%

Studying the Potential of Graphcore® IPUs for Applications in Particle Physics

Maddrell-Mander

Mohan

Marshall

et al. 2021

Comput Softw Big Sci

View full text Add to dashboard Cite

This paper presents the first study of Graphcore’s Intelligence Processing Unit (IPU) in the context of particle physics applications. The IPU is a new type of processor optimised for machine learning. Comparisons are made for neural-network-based event simulation, multiple-scattering correction, and flavour tagging, implemented on IPUs, GPUs and CPUs, using a variety of neural network architectures and hyperparameters. Additionally, a Kálmán filter for track reconstruction is implemented on IPUs and GPUs. The results indicate that IPUs hold considerable promise in addressing the rapidly increasing compute needs in particle physics.

show abstract

“…1 Each event represents the detector information on all particles produced in a single particle collision. 2 A job is one collection of programs processing the same physics process. The largest fraction of both the number of jobs and the overall CPU consumption is due to detector simulation jobs (simul).…”

Section: Introductionmentioning

confidence: 99%

“…The latter is mandatory to compare theoretical expectations to measured data [1] and requires a detailed description of both the underlying physics processes and the particle interactions in the detector. This process demands significant amounts of computing resources [2], which are provided by LHC computing centers distributed worldwide, the basis of the LHC computing Grid. As an example, in 2012, the ATLAS experiment at the Large Hadron Collider (LHC) has simulated about ten trillion events 1 stored in more than 54 PB of disk space, and more than 100 000 jobs are processed every day.…”

Section: Introductionmentioning

confidence: 99%

“…As an example, in 2012, the ATLAS experiment at the Large Hadron Collider (LHC) has simulated about ten trillion events 1 stored in more than 54 PB of disk space, and more than 100 000 jobs are processed every day. Figure 1 shows a monthly distribution of computing jobs 2 . Any error in processing this vast amount of simulation wastes CPU time and should be avoided.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online production validation in a HEP environment

et al. 2017

View full text Add to dashboard Cite

In high energy physics (HEP) event simulations, petabytes of data are processed and stored requiring millions of CPU-years. This enormous demand for computing resources is handled by centers distributed worldwide, which form part of the LHC computing grid. The consumption of such an important amount of resources demands for an efficient production of simulation and for the early detection of potential errors. In this article we present a new monitoring framework for grid environments, which polls a measure of data quality during job execution. This online monitoring facilitates the early detection of configuration errors (specially in simulation parameters), and may thus contribute to significant savings in computing resources.

show abstract

Common Accounting System for Monitoring the ATLAS Distributed Computing Resources

Cited by 10 publications

References 4 publications

Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters

Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multilayer Calorimeters

Studying the Potential of Graphcore® IPUs for Applications in Particle Physics

Online production validation in a HEP environment

Contact Info

Product

Resources

About