Publications (23)
Time-Based Roofline for Deep Learning Performance Analysis
Yunsong Wang, Charlene Yang, Steven Farrell +3
Deep learning applications are usually very compute-intensive and require a long run time for training and inference. This has been tackled by researchers from both hardware and so…
Track Seeding and Labelling with Embedded-space Graph Neural Networks
Nicholas Choma, Daniel Murnane, Xiangyang Ju +16
To address the unprecedented scale of HL-LHC data, the Exa.TrkX project is investigating a variety of machine learning approaches to particle track reconstruction. The most promisi…
Applications of Deep Learning to physics workflows
Manan Agarwal, Jay Alameda, Jeroen Audenaert +65
Modern large-scale physics experiments create datasets with sizes and streaming rates that can exceed those from industry leaders such as Google Cloud and Netflix. Fully processing…
Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation
Nabin Giri, Steven Farrell, Kristofer E. Bouchard
Multimodal models that jointly reason over protein sequences, structures, and function annotations within a unified representation hold immense potential for integrating multimodal…
Reconstruction of Large Radius Tracks with the Exa.TrkX pipeline
Chun-Yi Wang, Xiangyang Ju, Shih-Chieh Hsu +22
Particle tracking is a challenging pattern recognition task at the Large Hadron Collider (LHC) and the High Luminosity-LHC. Conventional algorithms, such as those based on the Kalm…
Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materials
Alex Morehead, Miruna Cretu, Antonia Panescu +14
General-purpose 3D modeling in chemistry encompasses molecules and materials, requiring both generative and predictive capabilities. However, most existing AI approaches are optimi…
FAIR Universe Weak Lensing ML Uncertainty Challenge: Handling Uncertainties and Distribution Shifts for Precision Cosmology
Biwei Dai, Po-Wen Chang, Wahid Bhimji +15
Weak gravitational lensing, the correlated distortion of background galaxy shapes by foreground structures, is a powerful probe of the matter distribution in our universe and allow…
Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
Xiangyang Ju, Steven Farrell, Paolo Calafiura +20
Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and…
MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems
Steven Farrell, Murali Emani, Jacob Balma +40
Scientific communities are increasingly adopting machine learning and deep learning models in their applications to accelerate scientific insights. High performance computing syste…
Novel deep learning methods for track reconstruction
Steven Farrell, Paolo Calafiura, Mayur Mudigonda +11
For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew…
Understanding the Landscape of Ampere GPU Memory Errors
Zhu Zhu, Yu Sun, Dhatri Parakal +9
Graphics Processing Units (GPUs) have become a de facto solution for accelerating high-performance computing (HPC) applications. Understanding their memory error behavior is an ess…
Accelerating the Inference of the Exa.TrkX Pipeline
Alina Lazar, Xiangyang Ju, Daniel Murnane +21
Recently, graph neural networks (GNNs) have been successfully used for a variety of particle reconstruction problems in high energy physics, including particle tracking. The Exa.Tr…
Benchmarking GPU and TPU Performance with Graph Neural Networks
xiangyang Ju, Yunsong Wang, Daniel Murnane +3
Many artificial intelligence (AI) devices have been developed to accelerate the training and inference of neural networks models. The most common ones are the Graphics Processing U…
FAIR Universe HiggsML Uncertainty Dataset and Competition
Lisa Benato, Wahid Bhimji, Paolo Calafiura +26
The FAIR Universe HiggsML Uncertainty Challenge focused on measuring the physical properties of elementary particles with imperfect simulators. Participants were required to comput…
Multi-threaded Geant4 on the Xeon-Phi with Complex High-Energy Physics Geometry
Steven Farrell, Andrea Dotti, Makoto Asai +2
To study the performance of multi-threaded Geant4 for high-energy physics experiments, an application has been developed which generalizes and extends previous work. A highly-compl…
Hierarchical Roofline Performance Analysis for Deep Learning Applications
Charlene Yang, Yunsong Wang, Steven Farrell +2
This paper presents a practical methodology for collecting performance data necessary to conduct hierarchical Roofline analysis on NVIDIA GPUs. It discusses the extension of the Em…
Graph Neural Network-based Tracking as a Service
Haoran Zhao, Andrew Naylor, Shih-Chieh Hsu +8
Recent studies have shown promising results for track finding in dense environments using Graph Neural Network (GNN)-based algorithms. However, GNN-based track finding is computati…
Fair Universe Higgs Uncertainty Challenge
Ragansu Chakkappai, Wahid Bhimji, Paolo Calafiura +16
This competition in high-energy physics (HEP) and machine learning was the first to strongly emphasise uncertainties in cross-section measurement. Parti…
The Tracking Machine Learning challenge : Throughput phase
Sabrina Amrouche, Laurent Basara, Paolo Calafiura +18
This paper reports on the second "Throughput" phase of the Tracking Machine Learning (TrackML) challenge on the Codalab platform. As in the first "Accuracy" phase, the participants…
Comprehensive Performance Modeling and System Design Insights for Foundation Models
Shashank Subramanian, Ermal Rrapaj, Peter Harrington +6
Generative AI, in particular large transformer models, are increasingly driving HPC system design in science and industry. We analyze performance characteristics of such transforme…
The Tracking Machine Learning challenge : Accuracy phase
Sabrina Amrouche, Laurent Basara, Paolo Calafiura +24
This paper reports the results of an experiment in high energy physics: using the power of the "crowd" to solve difficult experimental problems linked to tracking accurately the tr…
A Roadmap for HEP Software and Computing R&D for the 2020s
Johannes Albrecht, Antonio Augusto Alves, Guilherme Amadio +307
Particle physics has an ambitious and broad experimental programme for the coming decades. This programme requires large investments in detector hardware, either to build new facil…
Hierarchical Graph Neural Networks for Particle Track Reconstruction
Ryan Liu, Paolo Calafiura, Steven Farrell +3
We introduce a novel variant of GNN for particle tracking called Hierarchical Graph Neural Network (HGNN). The architecture creates a set of higher-level representations which corr…