Search NASA⌕ Search

Engineering topics

Pedro, Kevin

Publications and source records attributed to Pedro, Kevin.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Using containers to speed up development, to run integration tests and to teach about distributed systems

GlideinWMS is a workload manager provisioning resources for many experiments including CMS and DUNE. The software is distributed both as native packages and specialized production containers. Following an approach used in other communities like web development we built our workspaces, system-like containers to ease development and testing. Developers can change the source tree or check out a different branch and quickly reconfigure the services to see the effect of their changes. In this paper, we’ll talk about what differentiates workspaces from other containers. We’ll describe our base system composed of three containers. A one-node cluster including a compute element and a batch system. A GlideinWMS Factory controlling pilot jobs. And a scheduler and Frontend, to submit jobs and provision resources. Additional containers can be used for optional components. This system can easily run on a laptop and we’ll share our evaluation of different container runtimes, with an eye for ease of use and performance. Finally, we’ll talk about our experience as developers and with students. The GlideinWMS workspaces are easily integrated with IDEs like VS Code, simplifying debugging and allowing development and testing of the system also when offline. They simplified the training and onboarding of new team members and Summer interns. And they were useful in workshops where students could have first-hand experience with the mechanisms and components that, in production, run millions of jobs.

Mambelli, Marco↗
DOE OSTI2024

Simulating the CMS High Granularity Calorimeter with ML

Detector simulation is a key component of physics analysis and related activities in CMS. In the upcoming High Luminosity LHC era, simulation will be required to use a smaller fraction of computing in order to satisfy resource constraints. At the same time, CMS will be upgraded with the new High Granularity Calorimeter (HGCal), which requires significantly more resources to simulate than the existing CMS calorimeters. This computing challenge motivates the use of generative machine learning models as surrogates to replace full physics-based simulation. We study the application of state-of-the-art diffusion models to simulate particle showers in the CMS HGCal. We will discuss methods to overcome the challenges posed by the high-dimensional, irregular geometry of the HGCal. The quality of the showers produced by the diffusion model will be assessed by comparison to the full GEANT4-based simulation. The increase in simulation throughput will be quantified and methods to accelerate the diffusion model inference will also be discussed.

Amram, Oz↗
DOE OSTI2024

Refining Fast Simulation Using Machine Learning

A growing reliance on the fast Monte Carlo (FastSim) will accompany the high luminosity and detector granularity expected in Phase 2. FastSim is roughly 10 times faster than equivalent GEANT4-based full simulation (FullSim). However, reduced accuracy of the FastSim affects some analysis variables and collections. To improve its accuracy, FastSim is refined using regression-based neural networks trained with ML. The status of FastSim refinement is presented. The results show improved agreement with the FullSim output and an improvement in correlations among output observables and external parameters.

Güngördü, Acelya Deniz↗
DOE OSTI2024

Deployment of inference as a service at the US CMS Tier-2 data centers

Coprocessors, especially GPUs, will be a vital ingredient of data production workflows at the HL-LHC. At CMS, the GPU-as-a-service approach for production workflows is implemented by the SONIC project (Services for Optimized Network Inference on Coprocessors). SONIC provides a mechanism for outsourcing computationally demanding algorithms, such as neural network inference, to remote servers, where requests from multiple clients are intelligently distributed across multiple GPUs by a load-balancing service. This talk highlights the recent progress in deploying SONIC at selected U.S. CMS Tier-2 data centers. Using realistic CMS Run3 data processing workflows, such as those containing transformer-based algorithms, we demonstrate how SONIC is integrated into the production-like environment to enable accelerated inference offloading. We will present developments from both the client and server sides, including production job and data center configurations for NVIDIA and AMD GPUs. We will also present performance scaling benchmarks and discuss the challenges of operating SONIC in CMS production, such as server discovery, GPU saturation, fallback server logic, etc.

Holzman, Burt↗
DOE OSTI2024

Optimizing High-Throughput Inference on Graph Neural Networks at Shared Computing Facilities with the NVIDIA Triton Inference Server

Abstract With machine learning applications now spanning a variety of computational tasks, multi-user shared computing facilities are devoting a rapidly increasing proportion of their resources to such algorithms. Graph neural networks (GNNs), for example, have provided astounding improvements in extracting complex signatures from data and are now widely used in a variety of applications, such as particle jet classification in high energy physics (HEP). However, GNNs also come with an enormous computational penalty that requires the use of GPUs to maintain reasonable throughput. At shared computing facilities, such as those used by physicists at Fermi National Accelerator Laboratory (Fermilab), methodical resource allocation and high throughput at the many-user scale are key to ensuring that resources are being used as efficiently as possible. These facilities, however, primarily provide CPU-only nodes, which proves detrimental to time-to-insight and computational throughput for workflows that include machine learning inference. In this work, we describe how a shared computing facility can use the NVIDIA Triton Inference Server to optimize its resource allocation and computing structure, recovering high throughput while scaling out to multiple users by massively parallelizing their machine learning inference. To demonstrate the effectiveness of this system in a realistic multi-user environment, we use the Fermilab Elastic Analysis Facility augmented with the Triton Inference Server to provide scalable and high-throughput access to a HEP-specific GNN and report on the outcome.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Full Simulation of CMS for Run-3 and Phase-2

In this contribution we report the status of the CMS Geant4 simulation and the prospects for Run-3 and Phase-2. Firstly, we report about our experience during the start of Run-3 with Geant4 10.7.2, the common software package DD4hep for geometry description, and VecGeom runtime geometry library. In addition, FTFP_BERT_EMM Physics List and CMS configuration for tracking in magnetic field have been utilized. For the first time, for the Grid mass production of Monte-Carlo, this combination of components is used. Further simulation improvements are under development targeting Run-3 such as the switch to the new Geant4 11.1 in production, that provides several features important for the optimization of simulation, for example the new transportation process with built-in multiple scattering, neutron general process, custom tracking manager, G4HepEm sub-library, and others. We will present evaluation of various options, validation results, and the final choice of simulation configuration for 2023 production and beyond. The performance of the CMS full simulation for Run-2 and Run-3 will also be discussed. CMS development plan for the Phase-2 Geant4 based simulation is very ambitious, and it includes a new geometry description, physics, and simulation configurations. The progress on new detector descriptions and full simulation will be presented as well as the R&D in progress to reduce compute capacity needs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Accelerating Machine Learning Inference with GPUs in ProtoDUNE Data Processing

Abstract We study the performance of a cloud-based GPU-accelerated inference server to speed up event reconstruction in neutrino data batch jobs. Using detector data from the ProtoDUNE experiment and employing the standard DUNE grid job submission tools, we attempt to reprocess the data by running several thousand concurrent grid jobs, a rate we expect to be typical of current and future neutrino physics experiments. We process most of the dataset with the GPU version of our processing algorithm and the remainder with the CPU version for timing comparisons. We find that a 100-GPU cloud-based server is able to easily meet the processing demand, and that using the GPU version of the event processing algorithm is two times faster than processing these data with the CPU version when comparing to the newest CPUs in our sample. The amount of data transferred to the inference server during the GPU runs can overwhelm even the highest-bandwidth network switches, however, unless care is taken to observe network facility limits or otherwise distribute the jobs to multiple sites. We discuss the lessons learned from this processing campaign and several avenues for future improvements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Denoising diffusion models with geometry adaptation for high fidelity calorimeter simulation

Simulation is crucial for all aspects of collider data analysis, but the available computing budget in the High Luminosity LHC era will be severely constrained. Generative machine learning models may act as surrogates to replace physics-based full simulation of particle detectors, and diffusion models have recently emerged as the state of the art for other generative tasks. Here, we introduce CaloDiffusion, a denoising diffusion model trained on the public CaloChallenge datasets to generate calorimeter showers. Our algorithm employs 3D cylindrical convolutions, which take advantage of symmetries of the underlying data representation. To handle irregular detector geometries, we augment the diffusion model with a new geometry latent mapping (GLaM) layer to learn forward and reverse transformations to a regular geometry that is suitable for cylindrical convolutions. The showers generated by our approach are nearly indistinguishable from the full simulation, as measured by several different metrics.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Optimal mass variables for semivisible jets

Strongly coupled hidden sector theories predict collider production of invisible, composite dark matter candidates mixed with standard model hadrons in the form of semivisible jets. Classical mass reconstruction techniques may not be optimal for these unusual topologies, in which the missing transverse momentum comes from massive particles and has a nontrivial relationship to the visible jet momentum. We apply the artificial event variable network, a semisupervised, interpretable machine learning technique that uses an information bottleneck, to derive superior mass reconstruction functions for several cases of resonant semivisible jet production. We demonstrate that the technique can extrapolate to unknown signal model parameter values. We further demonstrate the viability of conducting an actual search for new physics using this method, by applying the learned functions to standard model background events from quantum chromodynamics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Refining fast simulation using machine learning

At the CMS experiment, a growing reliance on the fast Monte Carlo application (FastSim) will accompany the high luminosity and detector granularity expected in Phase 2. The FastSim chain is roughly 10 times faster than the application based on the GEANT4 detector simulation and full reconstruction referred to as FullSim. However, this advantage comes at the price of decreased accuracy in some of the final analysis observables. In this contribution, a machine learning-based technique to refine those observables is presented. We employ a regression neural network trained with a sophisticated combination of multiple loss functions to provide post-hoc corrections to samples produced by the FastSim chain. The results show considerably improved agreement with the FullSim output and an improvement in correlations among output observables and external parameters. This technique is a promising replacement for existing correction factors, providing higher accuracy and thus contributing to the wider usage of FastSim.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Theory, phenomenology, and experimental avenues for dark showers: a Snowmass 2021 report

In this work, we consider the case of a strongly coupled dark/hidden sector, which extends the Standard Model (SM) by adding an additional non-Abelian gauge group. These extensions generally contain matter fields, much like the SM quarks, and gauge fields similar to the SM gluons. We focus on the exploration of such sectors where the dark particles are produced at the LHC through a portal and undergo rapid hadronization within the dark sector before decaying back, at least in part and potentially with sizeable lifetimes, to SM particles, giving a range of possibly spectacular signatures such as emerging or semi-visible jets. Other, non-QCD-like scenarios leading to soft unclustered energy patterns or glueballs are also discussed. After a review of the theory, existing benchmarks and constraints, this work addresses how to build consistent benchmarks from the underlying physical parameters and present new developments for the PYTHIA Hidden Valley module, along with jet substructure studies. Finally, a series of improved search strategies is presented in order to pave the way for a better exploration of the dark showers at the LHC.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection

In the era of big astronomical surveys, our ability to leverage artificial intelligence algorithms simultaneously for multiple datasets will open new avenues for scientific discovery. Unfortunately, simply training a deep neural network on images from one data domain often leads to very poor performance on any other dataset. Here we develop a Universal Domain Adaptation method DeepAstroUDA, capable of performing semi-supervised domain alignment that can be applied to datasets with different types of class overlap. Extra classes can be present in any of the two datasets, and the method can even be used in the presence of unknown classes. For the first time, we demonstrate the successful use of domain adaptation on two very different observational datasets (from SDSS and DECaLS). We show that our method is capable of bridging the gap between two astronomical surveys, and also performs well for anomaly detection and clustering of unknown data in the unlabeled dataset. We apply our model to two examples of galaxy morphology classification tasks with anomaly detection: 1) classifying spiral and elliptical galaxies with detection of merging galaxies (three classes including one unknown anomaly class); 2) a more granular problem where the classes describe more detailed morphological properties of galaxies, with the detection of gravitational lenses (ten classes including one unknown anomaly class).

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

CompF2: Theoretical Calculations and Simulation Topical Group Report

This report summarizes the work of the Computational Frontier topical group on theoretical calculations and simulation for Snowmass 2021. We discuss the challenges, potential solutions, and needs facing six diverse but related topical areas that span the subject of theoretical calculations and simulation in high energy physics (HEP): cosmic calculations, particle accelerator modeling, detector simulation, event generators, perturbative calculations, and lattice QCD (quantum chromodynamics). The challenges arise from the next generations of HEP experiments, which will include more complex instruments, provide larger data volumes, and perform more precise measurements. Calculations and simulations will need to keep up with these increased requirements. The other aspect of the challenge is the evolution of computing landscape away from general-purpose computing on CPUs and toward special-purpose accelerators and coprocessors such as GPUs and FPGAs. These newer devices can provide substantial improvements for certain categories of algorithms, at the expense of more specialized programming and memory and data access patterns.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ${\approx}2.3$ the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.

79 ASTRONOMY AND ASTROPHYSICS↗