arXiv subjects

Nhan Tran

Publications and source records attributed to Nhan Tran.

At least 73 records · Page 4Linked to original sources

arXiv2021

Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference

Efficient machine learning implementations optimized for inference in hardware have wide-ranging benefits, depending on the application, from lower inference latency to higher data throughput and reduced energy consumption. Two popular techniques for reducing computation in neural networks are pruning, removing insignificant synapses, and quantization, reducing the precision of the calculations. In this work, we explore the interplay between pruning and quantization during the training of neural networks for ultra low latency applications targeting high energy physics use cases. Techniques developed for this study have potential applications across many other domains. We study various configurations of pruning during quantization-aware training, which we term quantization-aware pruning, and the effect of techniques like regularization, batch normalization, and different pruning schemes on performance, computational complexity, and information content metrics. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task. Further, quantization-aware pruning typically performs similar to or better in terms of computational efficiency compared to other neural architecture search techniques like Bayesian optimization. Surprisingly, while networks with different training configurations can have similar performance for the benchmark application, the information content in the network can vary significantly, affecting its generalizability.

cs.LG↗

arXiv2021

A reconfigurable neural network ASIC for detector front-end data compression at the HL-LHC

Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network autoencoder model can be implemented in a radiation tolerant ASIC to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the CMS experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the neural network weights, a unique data compression algorithm can be deployed for each sensor in different detector regions, and changing detector or collider conditions. To meet area, performance, and power constraints, we perform a quantization-aware training to create an optimized neural network hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework, and was processed through synthesis and physical layout flows based on a LP CMOS 65 nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates, and reports a total area of 3.6 mm^2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. This is the first radiation tolerant on-detector ASIC implementation of a neural network that has been designed for particle physics applications.

physics.ins-det↗

arXiv2021

Fast convolutional neural networks on FPGAs with hls4ml

We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate an inference latency of $5\,μ$s using convolutional architectures, targeting microsecond latency applications like those at the CERN Large Hadron Collider. Considering benchmark models trained on the Street View House Numbers Dataset, we demonstrate various methods for model compression in order to fit the computational constraints of a typical FPGA device used in trigger and data acquisition systems of particle detectors. In particular, we discuss pruning and quantization-aware training, and demonstrate how resource utilization can be significantly reduced with little to no loss in model accuracy. We show that the FPGA critical resource consumption can be reduced by 97% with zero loss in model accuracy, and by 99% when tolerating a 6% accuracy degradation.

cs.LG↗

arXiv2021

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.

physics.comp-ph↗

arXiv2021

hls4ml: An Open-Source Codesign Workflow to Empower Scientific Low-Power Machine Learning Devices

Accessible machine learning algorithms, software, and diagnostic tools for energy-efficient devices and systems are extremely valuable across a broad range of application domains. In scientific domains, real-time near-sensor processing can drastically improve experimental design and accelerate scientific discoveries. To support domain scientists, we have developed hls4ml, an open-source software-hardware codesign workflow to interpret and translate machine learning algorithms for implementation with both FPGA and ASIC technologies. We expand on previous hls4ml work by extending capabilities and techniques towards low-power implementations and increased usability: new Python APIs, quantization-aware pruning, end-to-end FPGA workflows, long pipeline kernels for low power, and new device backends include an ASIC workflow. Taken together, these and continued efforts in hls4ml will arm a new generation of domain scientists with accessible, efficient, and powerful tools for machine-learning-accelerated discovery.

cs.LG↗

arXiv2021

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.

physics.comp-ph↗

arXiv2021

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 1$μ\mathrm{s}$ 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 $\mathtt{hls4ml}$ 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.

physics.ins-det↗

arXiv2020

Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs

We develop and study FPGA implementations of algorithms for charged particle tracking based on graph neural networks. The two complementary FPGA designs are based on OpenCL, a framework for writing programs that execute across heterogeneous platforms, and hls4ml, a high-level-synthesis-based compiler for neural network to firmware conversion. We evaluate and compare the resource usage, latency, and tracking performance of our implementations based on a benchmark dataset. We find a considerable speedup over CPU-based execution is possible, potentially enabling such algorithms to be used effectively in future computing workflows and the FPGA-based Level-1 trigger at the CERN Large Hadron Collider.

physics.ins-det↗

arXiv2020

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.

physics.comp-ph↗

arXiv2020

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.

cs.LG↗

arXiv2020

Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors

Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in high energy collisions and recorded with complex detector systems. Two critical applications are the reconstruction of charged particle trajectories in tracking detectors and the reconstruction of particle showers in calorimeters. These two problems have unique challenges and characteristics, but both have high dimensionality, high degree of sparsity, and complex geometric layouts. Graph Neural Networks (GNNs) are a relatively new class of deep learning architectures which can deal with such data effectively, allowing scientists to incorporate domain knowledge in a graph structure and learn powerful representations leveraging that structure to identify patterns of interest. In this work we demonstrate the applicability of GNNs to these two diverse particle reconstruction problems.

physics.ins-det↗

arXiv2020

Lepton-Nucleus Cross Section Measurements for DUNE with the LDMX Detector

We point out that the LDMX (Light Dark Matter eXperiment) detector design, conceived to search for sub-GeV dark matter, will also have very advantageous characteristics to pursue electron-nucleus scattering measurements of direct relevance to the neutrino program at DUNE and elsewhere. These characteristics include a 4-GeV electron beam, a precision tracker, electromagnetic and hadronic calorimeters with near 2$π$ azimuthal acceptance from the forward beam axis out to $\sim$40$^\circ$ angle, and low reconstruction energy threshold. LDMX thus could provide (semi)exclusive cross section measurements, with detailed information about final-state electrons, pions, protons, and neutrons. We compare the predictions of two widely used neutrino generators (GENIE, GiBUU) in the LDMX region of acceptance to illustrate the large modeling discrepancies in electron-nucleus interactions at DUNE-like kinematics. We argue that discriminating between these predictions is well within the capabilities of the LDMX detector.

hep-ph↗

arXiv2020

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.

physics.comp-ph↗

arXiv2020

Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory

Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. This poses a major challenge to goal of completely solving Optical Character Recognition (OCR) problem. Inspired by recently proposed memory-augmented neural networks (MANNs) for long-term sequential modeling, we present a new architecture dubbed Convolutional Multi-way Associative Memory (CMAM) to tackle the limitation of current CRNNs. By leveraging recent memory accessing mechanisms in MANNs, our architecture demonstrates superior performance against other CRNN counterparts in three real-world long text OCR datasets.

cs.CV↗

arXiv2019

A High Efficiency Photon Veto for the Light Dark Matter eXperiment

Fixed-target experiments using primary electron beams can be powerful discovery tools for light dark matter in the sub-GeV mass range. The Light Dark Matter eXperiment (LDMX) is designed to measure missing momentum in high-rate electron fixed-target reactions with beam energies of 4 GeV to 16 GeV. A prerequisite for achieving several important sensitivity milestones is the capability to efficiently reject backgrounds associated with few-GeV bremsstrahlung, by twelve orders of magnitude, while maintaining high efficiency for signal. The primary challenge arises from events with photo-nuclear reactions faking the missing-momentum property of a dark matter signal. We present a methodology developed for the LDMX detector concept that is capable of the required rejection. By employing a detailed GEANT4-based model of the detector response, we demonstrate that the sampling calorimetry proposed for LDMX can achieve better than $10^{-13}$ rejection of few-GeV photons. This suggests that the luminosity-limited sensitivity of LDMX can be realized at 4 GeV and higher beam energies.

physics.ins-det↗

arXiv2019

Algorithms and Statistical Models for Scientific Discovery in the Petabyte Era

The field of astronomy has arrived at a turning point in terms of size and complexity of both datasets and scientific collaboration. Commensurately, algorithms and statistical models have begun to adapt --- e.g., via the onset of artificial intelligence --- which itself presents new challenges and opportunities for growth. This white paper aims to offer guidance and ideas for how we can evolve our technical and collaborative frameworks to promote efficient algorithmic development and take advantage of opportunities for scientific discovery in the petabyte era. We discuss challenges for discovery in large and complex data sets; challenges and requirements for the next stage of development of statistical methodologies and algorithmic tool sets; how we might change our paradigms of collaboration and education; and the ethical implications of scientists' contributions to widely applicable algorithms and computational modeling. We start with six distinct recommendations that are supported by the commentary following them. This white paper is related to a larger corpus of effort that has taken place within and around the Petabytes to Science Workshops (https://petabytestoscience.github.io/).

astro-ph.IM↗

arXiv2019

FPGA-accelerated machine learning inference as a service for particle physics computing

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) 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.

physics.data-an↗

arXiv2019

Jet Substructure at the Large Hadron Collider: Experimental Review

Jet substructure has emerged to play a central role at the Large Hadron Collider, where it has provided numerous innovative ways to search for new physics and to probe the Standard Model, particularly in extreme regions of phase space. In this article we focus on a review of the development and use of state-of-the-art jet substructure techniques by the ATLAS and CMS experiments.

hep-ex↗