skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Nanosecond anomaly detection with decision trees and real-time application to exotic Higgs decays
Abstract We present an interpretable implementation of the autoencoding algorithm, used as an anomaly detector, built with a forest of deep decision trees on FPGA, field programmable gate arrays. Scenarios at the Large Hadron Collider at CERN are considered, for which the autoencoder is trained using known physical processes of the Standard Model. The design is then deployed in real-time trigger systems for anomaly detection of unknown physical processes, such as the detection of rare exotic decays of the Higgs boson. The inference is made with a latency value of 30 ns at percent-level resource usage using the Xilinx Virtex UltraScale+ VU9P FPGA. Our method offers anomaly detection at low latency values for edge AI users with resource constraints.  more » « less
Award ID(s):
2209370
PAR ID:
10502426
Author(s) / Creator(s):
; ; ; ; ; ;
Publisher / Repository:
Nature Publishing Group
Date Published:
Journal Name:
Nature Communications
Volume:
15
Issue:
1
ISSN:
2041-1723
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ; ; et al (, Frontiers in Big Data)
    null (Ed.)
    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. 
    more » « less
  2. ; ; ; ; ; (, ACM Transactions on Reconfigurable Technology and Systems)
    Convolutional neural network (CNN)-based object detection has achieved very high accuracy; e.g., single-shot multi-box detectors (SSDs) can efficiently detect and localize various objects in an input image. However, they require a high amount of computation and memory storage, which makes it difficult to perform efficient inference on resource-constrained hardware devices such as drones or unmanned aerial vehicles (UAVs). Drone/UAV detection is an important task for applications including surveillance, defense, and multi-drone self-localization and formation control. In this article, we designed and co-optimized an algorithm and hardware for energy-efficient drone detection on resource-constrained FPGA devices. We trained an SSD object detection algorithm with a custom drone dataset. For inference, we employed low-precision quantization and adapted the width of the SSD CNN model. To improve throughput, we use dual-data rate operations for DSPs to effectively double the throughput with limited DSP counts. For different SSD algorithm models, we analyze accuracy or mean average precision (mAP) and evaluate the corresponding FPGA hardware utilization, DRAM communication, and throughput optimization. We evaluated the FPGA hardware for a custom drone dataset, Pascal VOC, and COCO2017. Our proposed design achieves a high mAP of 88.42% on the multi-drone dataset, with a high energy efficiency of 79 GOPS/W and throughput of 158 GOPS using the Xilinx Zynq ZU3EG FPGA device on the Open Vision Computer version 3 (OVC3) platform. Our design achieves 1.1 to 8.7× higher energy efficiency than prior works that used the same Pascal VOC dataset, using the same FPGA device, but at a low-power consumption of 2.54 W. For the COCO dataset, our MobileNet-V1 implementation achieved an mAP of 16.8, and 4.9 FPS/W for energy-efficiency, which is ∼ 1.9× higher than prior FPGA works or other commercial hardware platforms. 
    more » « less
  3. ; ; ; (, GLSVLSI '23: Proceedings of the Great Lakes Symposium on VLSI 2023)
    As multi-tenant FPGA applications continue to scale in size and complexity, their need for resilience against environmental effects and malicious actions continues to grow. To ensure continuously correct computation, faults in the compute fabric must be identified, isolated, and suppressed in the nanosecond to microsecond range. In this paper, we detail a circuit and system-level methodology to detect compute failure conditions due to on-FPGA voltage attacks. Our approach rapidly suppresses incorrect results and regenerates potentially-tainted results before they propagate, allowing time for an attacker to be suppressed. Instrumentation includes voltage sensors to detect error conditions induced by attackers. This analysis is paired with focused remediation approaches involving data buffering, fault suppression, results recalculation, and computation restart. Our approach has been demonstrated using an RSA encryption circuit implemented on a Stratix 10 FPGA. We show that a voltage attack using on-FPGA power wasters can be effectively detected and computation halted in 15 ns, preventing the injection of timing faults. Potentially tainted results are successfully regenerated, allowing for fault-free circuit operation. A full characterization of the latency and resource overheads of fault detection and recovery is provided. 
    more » « less
  4. ; ; ; (, IEEE)
    Description / Abstract: In order to effectively provide INaaS (Inference-as-a-Service) for AI applications in resource-limited cloud environments, two major challenges must be overcome: achieving low latency and providing multi-tenancy. This paper presents EIF (Efficient INaaS Framework), which uses a heterogeneous CPU-FPGA architecture to provide three methods to address these challenges (1) spatial multiplexing via software-hardware co-design virtualization techniques, (2) temporal multiplexing that exploits the sparsity of neural-net models, and (3) streaming-mode inference which overlaps data transfer and computation. The prototype EIF is implemented on an Intel PAC (shared-memory CPU-FPGA) platform. For evaluation, 12 types of DNN models were used as benchmarks, with different size and sparsity. Based on these experiments, we show that in EIF, the temporal multiplexing technique can improve the user density of an AI Accelerator Unit from 2$$\times$$ to 6$$\times$$, with marginal performance degradation. In the prototype system, the spatial multiplexing technique supports eight AI Accelerators Unit on one FPGA. By using a streaming mode based on a Mediated Pass-Through architecture, EIF can overcome the FPGA on-chip memory limitation to improve multi-tenancy and optimize the latency of INaaS. To further enhance INaaS, EIF utilizes the MapReduce function to provide a more flexible QoS. Together with the temporal/spatial multiplexing techniques, EIF can support 48 users simultaneously on a single FPGA board in our prototype system. In all tested benchmarks, cold-start latency accounts for only approximately 5\% of the total response time. 
    more » « less
  5. ; ; ; ; ; ; ; ; ; (, Journal of Instrumentation)
    Abstract The Global Event Processor (GEP) FPGA is an area-constrained, performance-critical element of the Large Hadron Collider's (LHC) ATLAS experiment. It needs to very quickly determine which small fraction of detected events should be retained for further processing, and which other events will be discarded. This system involves a large number of individual processing tasks, brought together within the overall Algorithm Processing Platform (APP), to make filtering decisions at an overall latency of no more than 8ms. Currently, such filtering tasks are hand-coded implementations of standard deterministic signal processing tasks.In this paper we present methods to automatically create machine learning based algorithms for use within the APP framework, and demonstrate several successful such deployments. We leverage existing machine learning to FPGA flows such ashls4mlandfwXto significantly reduce the complexity of algorithm design. These have resulted in implementations of various machine learning algorithms with latencies of 1.2 μs and less than 5% resource utilization on an Xilinx XCVU9P FPGA. Finally, we implement these algorithms into the GEP system and present their actual performance.Our work shows the potential of using machine learning in the GEP for high-energy physics applications. This can significantly improve the performance of the trigger system and enable the ATLAS experiment to collect more data and make more discoveries. The architecture and approach presented in this paper can also be applied to other applications that require real-time processing of large volumes of data. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email