Engineering topics

Harris, Philip

Publications and source records attributed to Harris, Philip.

32 records · Page 2

DOE OSTI2021

GPU coprocessors as a service for deep learning inference in high energy physics

In the next decade, the demands for computing in large scientific experiments are expected to grow tremendously. During the same time period, CPU performance increases will be limited. At the CERN Large Hadron Collider (LHC), these two issues will confront one another as the collider is upgraded for high luminosity running. Alternative processors such as graphics processing units (GPUs) can resolve this confrontation provided that algorithms can be sufficiently accelerated. In many cases, algorithmic speedups are found to be largest through the adoption of deep learning algorithms. We present a comprehensive exploration of the use of GPU-based hardware acceleration for deep learning inference within the data reconstruction workflow of high energy physics. We present several realistic examples and discuss a strategy for the seamless integration of coprocessors so that the LHC can maintain, if not exceed, its current performance throughout its running.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2021

GPU-Accelerated Machine Learning Inference as a Service for Computing in Neutrino Experiments

Machine learning algorithms are becoming increasingly prevalent and performant in the reconstruction of events in accelerator-based neutrino experiments. These sophisticated algorithms can be computationally expensive. At the same time, the data volumes of such experiments are rapidly increasing. The demand to process billions of neutrino events with many machine learning algorithm inferences creates a computing challenge. We explore a computing model in which heterogeneous computing with GPU coprocessors is made available as a web service. The coprocessors can be efficiently and elastically deployed to provide the right amount of computing for a given processing task. With our approach, Services for Optimized Network Inference on Coprocessors (SONIC), we integrate GPU acceleration specifically for the ProtoDUNE-SP reconstruction chain without disrupting the native computing workflow. With our integrated framework, we accelerate the most time-consuming task, track and particle shower hit identification, by a factor of 17. This results in a factor of 2.7 reduction in the total processing time when compared with CPU-only production. For this particular task, only 1 GPU is required for every 68 CPU threads, providing a cost-effective solution.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2021

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Compressing deep neural networks on FPGAs to binary and ternary precision with hls4ml

We present the implementation of binary and ternary neural networks in the hls4ml library, designed to automatically convert deep neural network models to digital circuits with FPGA firmware. Starting from benchmark models trained with floating point precision, we investigate different strategies to reduce the network's resource consumption by reducing the numerical precision of the network parameters to binary or ternary. We discuss the trade-off between model accuracy and resource consumption. In addition, we show how to balance between latency and accuracy by retaining full precision on a selected subset of network components. As an example, we consider two multiclass classification tasks: handwritten digit recognition with the MNIST data set and jet identification with simulated proton-proton collisions at the CERN Large Hadron Collider. The binary and ternary implementation has similar performance to the higher precision implementation while using drastically fewer FPGA resources.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2020

FPGAs-as-a-Service Toolkit (FaaST)

Computing needs for high energy physics are already intensive and are expected to increase drastically in the coming years. In this context, heterogeneous computing, specifically as-a-service computing, has the potential for significant gains over traditional computing models. Although previous studies and packages in the field of heterogeneous computing have focused on GPUs as accelerators, FPGAs are an extremely promising option as well. A series of workflows are developed to establish the performance capabilities of FPGAs as a service. Multiple different devices and a range of algorithms for use in high energy physics are studied. For a small, dense network, the throughput can be improved by an order of magnitude with respect to GPUs as a service. For large convolutional networks, the throughput is found to be comparable to GPUs as a service. This work represents the first open-source FPGAs-as-a-service toolkit.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Fast inference of Boosted Decision Trees in FPGAs for particle physics

We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process. Thanks to its fully on-chip implementation, hls4ml performs inference of Boosted Decision Tree models with extremely low latency. With a typical latency less than 100 ns, this solution is suitable for FPGA-based real-time processing, such as in the Level-1 Trigger system of a collider experiment. These developments open up prospects for physicists to deploy BDTs in FPGAs for identifying the origin of jets, better reconstructing the energies of muons, and enabling better selection of rare signal processes.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2019

FPGA-Accelerated Machine Learning Inference as a Service for Particle Physics Computing

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that potentially requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave by Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) ms with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600–700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2019

Long-lived particles at the energy frontier: the MATHUSLA physics case

In this review, we examine the theoretical motivations for long-lived particle (LLP) signals at the LHC in a comprehensive survey of standard model (SM) extensions. LLPs are a common prediction of a wide range of theories that address unsolved fundamental mysteries such as naturalness, dark matter, baryogenesis and neutrino masses, and represent a natural and generic possibility for physics beyond the SM (BSM). In most cases the LLP lifetime can be treated as a free parameter from the m scale up to the Big Bang Nucleosynthesis limit of m. Neutral LLPs with lifetimes above 100 m are particularly difficult to probe, as the sensitivity of the LHC main detectors is limited by challenging backgrounds, triggers, and small acceptances. MATHUSLA is a proposal for a minimally instrumented, large-volume surface detector near ATLAS or CMS. It would search for neutral LLPs produced in HL-LHC collisions by reconstructing displaced vertices (DVs) in a low-background environment, extending the sensitivity of the main detectors by orders of magnitude in the long-lifetime regime. We study the LLP physics opportunities afforded by a MATHUSLA-like detector at the HL-LHC, assuming backgrounds can be rejected as expected. We develop a model-independent approach to describe the sensitivity of MATHUSLA to BSM LLP signals, and compare it to DV and missing energy searches at ATLAS or CMS. We then explore the BSM motivations for LLPs in considerable detail, presenting a large number of new sensitivity studies. While our discussion is especially oriented towards the long-lifetime regime at MATHUSLA, this survey underlines the importance of a varied LLP search program at the LHC in general. By synthesizing these results into a general discussion of the top–down and bottom-up motivations for LLP searches, it is our aim to demonstrate the exceptional strength and breadth of the physics case for the construction of the MATHUSLA detector.

baryogenesis↗

DOE OSTI2019

FPGAs as a Service to Accelerate Machine Learning Inference [PowerPoint]

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC, and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave b y Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2019

Prospects for a measurement of the W boson mass in the all-jets final state at hadron colliders

Precise measurements of the mass of the W boson are important to test the overall consistency of the Standard Model of particle physics. The current best measurements of the W boson mass come from single production measurements at hadron colliders in its decay mode to a lepton (electron or muon) and a neutrino and pair production of W bosons at lepton colliders, where both the leptonic and hadronic decay modes of the W boson have been considered. In this study, prospects for a measurement of the W boson mass in the all-jet final state at hadron colliders are presented. The feasibility of this measurement takes advantage of numerous recent developments in the field of jet substructure. Compared to other methods for measuring the W mass, a measurement in the all-jets final state would be complementary in methodology and have systematic uncertainties orthogonal to previous measurements. We have estimated the main experimental and theoretical uncertainties affecting a measurement in the all-jet final state. With new trigger strategies, a statistical uncertainty for the measurement of the mass difference between the Z and W bosons of 30 MeV could be reached with HL-LHC data corresponding to 3000 fb$^{-1}$ of integrated luminosity. However, in order to reach that precision, the current understanding of non-perturbative contributions to the invariant mass of W → $ q\overline{q}^{\prime } $ and Z → $ b\overline{b} $ jets will need to be refined. Similar strategies will also allow the reach for generic boosted resonances searches in hadronic channels to be extended.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2018

Fast inference of deep neural networks in FPGAs for particle physics

Here, recent results at the Large Hadron Collider (LHC) have pointed to enhanced physics capabilities through the improvement of the real-time event processing techniques. Machine learning methods are ubiquitous and have proven to be very powerful in LHC physics, and particle physics as a whole. However, exploration of the use of such techniques in low-latency, low-power FPGA (Field Programmable Gate Array) hardware has only just begun. FPGA-based trigger and data acquisition systems have extremely low, sub-microsecond latency requirements that are unique to particle physics. We present a case study for neural network inference in FPGAs focusing on a classifier for jet substructure which would enable, among many other physics scenarios, searches for new dark sector particles and novel measurements of the Higgs boson. While we focus on a specific example, the lessons are far-reaching. A companion compiler package for this work is developed based on High-Level Synthesis (HLS) called hls4ml to build machine learning models in FPGAs. The use of HLS increases accessibility across a broad user community and allows for a drastic decrease in firmware development time. We map out FPGA resource usage and latency versus neural network hyperparameters to identify the problems in particle physics that would benefit from performing neural network inference with FPGAs. For our example jet substructure model, we fit well within the available resources of modern FPGAs with a latency on the scale of 100 ns.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2016

Thinking outside the ROCs: Designing decorrelated taggers (DDT) for jet substructure

Here, we explore the scale-dependence and correlations of jet substructure observables to improve upon existing techniques in the identification of highly Lorentz-boosted objects. Modified observables are designed to remove correlations from existing theoretically well-understood observables, providing practical advantages for experimental measurements and searches for new phenomena. We study such observables in W jet tagging and provide recommendations for observables based on considerations beyond signal and background efficiencies.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2014

Pileup per particle identification

We propose a new method for pileup mitigation by implementing “pileup per particle identification” (PUPPI). For each particle we first define a local shape α which probes the collinear versus soft diffuse structure in the neighborhood of the particle. The former is indicative of particles originating from the hard scatter and the latter of particles originating from pileup interactions. The distribution of α for charged pileup, assumed as a proxy for all pileup, is used on an event-by-event basis to calculate a weight for each particle. The weights describe the degree to which particles are pileup-like and are used to rescale their four-momenta, superseding the need for jet-based corrections. Furthermore, the algorithm flexibly allows combination with other, possibly experimental, probabilistic information associated with particles such as vertexing and timing performance. We demonstrate the algorithm improves over existing methods by looking at jet p T and jet mass. As a result, we also find an improvement on non-jet quantities like missing transverse energy.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

NASA NTRS2013

ISS Live!

International Space Station Live! (ISSLive!) is a Web application that uses a proprietary commercial technology called Lightstreamer to push data across the Internet using the standard http port (port 80). ISSLive! uses the push technology to display real-time telemetry and mission timeline data from the space station in any common Web browser or Internet- enabled mobile device. ISSLive! is designed to fill a unique niche in the education and outreach areas by providing access to real-time space station data without a physical presence in the mission control center. The technology conforms to Internet standards, supports the throughput needed for real-time space station data, and is flexible enough to work on a large number of Internet-enabled devices. ISSLive! consists of two custom components: (1) a series of data adapters that resides server-side in the mission control center at Johnson Space Center, and (2) a set of public html that renders the data pushed from the data adapters. A third component, the Lightstreamer server, is commercially available from a third party and acts as an intermediary between custom components (1) and (2). Lightstreamer also provides proprietary software libraries that are required to use the custom components. At the time of this reporting, this is the first usage of Web-based, push streaming technology in the aerospace industry.

Price, Jennifer↗