Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Field programmable gate array”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 505 records · Page 28
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Accelerating Transformer-based Deep Learning Models on FPGAs using Column Balanced Block Pruning

Although Transformer-based language representations achieve state-of-the-art accuracy on various natural language processing (NLP) tasks, the large model size has been challenging the resource constrained computing platforms. Weight pruning, as a popular and effective technique in reducing the number of weight parameters and accelerating the Transformer, has been investigated on GPUs. However, the Transformer acceleration using weight pruning on field-programmable gate array (FPGAs) remains unexplored. This paper investigates the column balanced block-wise pruning on Transformer and designs an FPGA acceleration engine to customize the balanced blockwise matrix multiplication. We implement the Transformer model with proper hardware scheduling, and the experiments show that the Transformer inference on FPGA achieves 10.35 ms latency with the batch size of 32, which is 10.96 × speed up comparing to CPU platform and 2.08 × speed up comparing to GPU platform.

Peng, Hongwu↗
DOE OSTI2021

Shareable FPGA compute engine

Systems, apparatuses, and methods for sharing an field programmable gate array compute engine are disclosed. A system includes one or more processors and one or more FPGAs. The system receives a request, generated by a first user process, to allocate a portion of processing resources on a first FPGA. The system maps the portion of processing resources of the first FPGA into an address space of the first user process. The system prevents other user processes from accessing the portion of processing resources of the first FPGA. Later, the system detects a release of the portion of the processing resources on the first FPGA by the first user process. Then, the system receives a second request to allocate the first FPGA from a second user process. In response to the second request, the system maps the first FPGA into an address space of the second user process.

Kegel, Andrew G.↗
DOE OSTI2021

Cycle accurate and cycle reproducible memory for an FPGA based hardware accelerator

A method, system and computer program product are disclosed for using a Field Programmable Gate Array (FPGA) to simulate operations of a device under test (DUT). The DUT includes a device memory having a number of input ports, and the FPGA is associated with a target memory having a second number of input ports, the second number being less than the first number. In one embodiment, a given set of inputs is applied to the device memory at a frequency Fd and in a defined cycle of time, and the given set of inputs is applied to the target memory at a frequency Ft. Ft is greater than Fd and cycle accuracy is maintained between the device memory and the target memory. In an embodiment, a cycle accurate model of the DUT memory is created by separating the DUT memory interface protocol from the target memory storage array.

Asaad, Sameh W.↗
DOE OSTI2021

Companion Assisted Software Based Remote Attestation in SCADA Networks

Critical infrastructure such as power generation and water distribution systems have become a priority target in cyber warfare because of their recent computerization and introduction to the internet. As a result, Supervisory Control and Data Acquisition (SCADA) system security has become a hot topic in academic and industrial research. Among these topics, Remote Attestation is a security method intended to detect the presence of fileless malware in remote devices as they continue to operate. This allows for the detection of malware in the absence of long-term storage artifacts before symptoms of compromise begin to appear. In general, a trusted device (the verifier) makes a request for evidence of innocence from the untrusted device (the prover). In software-based schemes, the verifier can then measure the delay between its request and the prover’s response. If this delay is greater than the known computational time of the evidence gathering algorithm performed by the prover, then evidence may have been forged. Multi-hop networks often introduce too much network jitter to allow accurate measurement of prover response time, which limits the effectiveness of software based Remote Attestation in a real-world setting. In this work, we introduce a companion device that the verifier can trust to perform a subset of attestation, thereby removing any network jitter. This device is a Field Programmable Gate Array (FPGA) that is physically connected to the prover. We provide a communication protocol between the verifier, prover, and companion. To evaluate our scheme, we simulate it in a common SCADA network environment under normal and heavy traffic loads. Our simulations are performed in the discrete event network simulator NS-3, and we perform statistical analysis over our results to show that our scheme allows for tight timing constraints to be placed on the prover such that the verifier can more easily determine the validity of the evidence that it receives.

Johnson, William A.↗
DOE OSTI2021

Architecture Of A Multi-channel Data Streaming Device With An Fpga As A Coprocessor

The design of a data acquisition system often involves the integration of a Field Programmable Gate Array (FPGA) with analog front-end components to achieve precise timing and control. Reuse of these hardware systems can be difficult since they need to be tightly coupled to the communications interface and timing requirements of the specific ADC used. A hybrid design exploring the use of FPGA as a coprocessor to a traditional CPU in a dataflow architecture is presented. Reduction in the volume of data and gradual transitioning of data processing away from a hard real-time environment are both discussed. Chief design concerns, including data throughput and precise synchronization with external stimuli, are addressed. The discussion is illustrated by the implementation of a multi-channel digital integrator, a device based entirely on commercial off-the-shelf (COTS) equipment.

Nogiec, Jerzy M.↗
DOE OSTI2022

Efficient Implementation of Artificial Neural Networks for Sensor Data Analysis Based on a Genetic Algorithm

The reliability of many industrial processes depends on the sensor system. However, these sensors can be affected by noise, perturbations and failures. Hence, sensor monitoring and diagnosis are fundamental to guarantee the quality of an industrial process. Nowadays, artificial neural networks (ANN) are widely used in sensor signal processing and diagnosis. However, those ANNs usually require many artificial neurons, being difficult to implement in software and hardware due to their high computational costs. This paper presents an optimized implementation of artificial neurons in ANNs for sensor data analysis using a Genetic Algorithm (GA). The objective of GA is to find an adequate segmentation to reduce the activation function approximation error. One of the advantages of the proposed approach is that the cost function used in GA considers the effect of factors such as the ANN architecture or the number of bits used in arithmetic operations. The proposed ANN implementation technique aims to get the best possible approximation for a specific ANN architecture, making easier its implementation in software and hardware. Simulation and experimental results using FPGA (Field Programmable Gate Array) prove the advantages of the proposed approach for implementing sensor data analysis systems based on ANNs.

D estefani, André↗
DOE OSTI2022

Open-source FPGA-ML codesign for the MLPerf Tiny Benchmark

We present our development experience and recent results for the MLPerf Tiny Inference Benchmark on field-programmable gate array (FPGA) platforms. We use the open-source hls4ml and FINN workflows, which aim to democratize AI-hardware codesign of optimized neural networks on FPGAs. We present the design and implementation process for the keyword spotting, anomaly detection, and image classification benchmark tasks. The resulting hardware implementations are quantized, configurable, spatial dataflow architectures tailored for speed and efficiency and introduce new generic optimizations and common workflows developed as a part of this work. The full workflow is presented from quantization-aware training to FPGA implementation. The solutions are deployed on system-on-chip (Pynq-Z2) and pure FPGA (Arty A7-100T) platforms. The resulting submissions achieve latencies as low as 20 $\mu$s and energy consumption as low as 30 $\mu$J per inference. We demonstrate how emerging ML benchmarks on heterogeneous hardware platforms can catalyze collaboration and the development of new techniques and more accessible tools.

Borras, Hendrik↗
DOE OSTI2022

FPGA-based computing system for processing data in size, weight, and power constrained environments

Technologies that are well-suited for use in size, weight, and power (SWAP)-constrained environments are described herein. A host controller dispatches data processing instructions to hardware acceleration engines (HAEs) of one or more field programmable gate arrays (FPGAs) and further dispatches data transfer instructions to a memory controller, such that the HAEs perform processing operations on data stored in local memory devices of the HAEs in parallel with other data being transferred from external memory devices coupled to the FPGA(s) to the local memory devices.

Napier, Matthew↗
DOE OSTI2023

Machine Learning 5G Attack Detection in Programmable Logic

Machine learning-assisted network security may significantly contribute to securing 5G components. However, machine learning network security inference speeds generally require tens to hundreds of milliseconds thereby introducing significant latency in 5G operations. The inference latency can be reduced by deploying the machine learning model to programmable logic in a field programmable gate array (FPGA) at the cost of a small loss in accuracy. In order to quantify this loss, as well as to establish baseline performance inference speeds for programmable logic implementations, this work explores an autoencoder and a ß-variational autoencoder deployed on two different FPGA evaluation boards and compares accuracy and performance against an NVIDIA A100 GPU implementation. A publicly available 5G dataset containing 10 types of attacks along with normal traffic is introduced as part of the evaluation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

OpenACC unified programming environment for GPU and FPGA multi-hybrid acceleration

Attached accelerators have been frequently used in recent High Per- formance Computing (HPC) systems because of their high performance/power ratio. In particular, the Graphics Processing Unit (GPU) is the most popu- lar accelerator owing to its high peak FLOPS performance and high memory bandwidth supported by HBM2, etc. However, the performance of GPU depends highly on a large degree of SIMD parallelism and has difficulty sustaining a high performance on programs with frequent branch operations or a partially low degree of parallelism.By contrast, a Field Programmable Gate Array (FPGA) has received attention as a different type of accelerator than GPU as a fully reconfigurable processor fitting the target applications. The high performance of FPGA is mainly provided by a pipelined operation and optimized circuit suitable for any operation even with frequent conditional branches. We have been focusing on the flexibility of FPGA to compensate for the weakness of GPU. We believe that the coupling of GPU with FPGA can result in one of the most powerful accelerating platforms available.However, the program coding of GPU and FPGA coupling can be quite difficult for application users. Traditionally, CUDA by NVIDIA has been the most popular programming language with the largest share of GPUs used in HPC, whereas a hardware description language such as Verilog HDL has been used in FPGA programming. OpenCL coding has recently become available even on high-end FPGAs. Moreover, several recent studies have also enabled the OpenACC coding for use in FPGA. In this study, we provide a unified programming system based on OpenACC for a platform equipped with both GPU and FPGA aiming at the next-generation accelerated supercomputer framework. Our programming environment is called Multi-Hybrid OpenACC Translator (MHOAT), and in this paper, we describe the basic concept and prototype system of MHOAT based on an evaluation on the amount of coding required and the performance of a hybrid multi-device accelerated system.

Tsunashima, Ryuta↗
DOE OSTI2023

High-bandwidth reconfigurable data acquisition card

A reconfigurable data acquisition card including at least one field programmable gate array (FPGA) and a configurable bus switch coupled with the FPGA. The bus switch forms at least first and second ports used by the FPGA, the bus switch being adaptable for insertion into a connection having a number of lanes at least equal to a combined number of lanes in the first and second ports. The data acquisition card further includes multiple optical transmitters and optical receivers. Each optical transmitter and optical receiver is coupled with a corresponding transceiver in the FPGA via at least one optical fiber having multiple communication links. Timing circuitry in the data acquisition card is coupled with clock generation and distribution circuitry in the FPGA and is configured to distribute clock and timing signals to detector front-ends with fixed latency and to synchronize input/output links with a system clock generated by the FPGA.

Chen, Kai↗
DOE OSTI2023

Modbus RTU for Embedded Cyber Secure Inverter Controller

The Modbus communication protocol is a widely adopted communication standard in industrial control systems. This communication protocol is known for being reliable and straightforward to implement while being versatile in terms of its operating parameters while supporting multiple formats over various hardware infrastructures and architectures. Many intelligent devices such as Programmable Logic Controllers (PLCs), Human-Machine Interfaces (HMIs), Internet-of-Things (IoT), and various Operational Technologies (OT) utilize Modbus for their communication systems. These types of systems must communicate with each other through a standardized and central communication process. To support the integration of these modular systems, a Field-Programmable Gate Array (FPGA) can act as an embedded central routing fabric for this communication to take place. Embedded systems are versatile enough to interface with various devices and systems to accomplish various goals. Additionally, embedded systems require relatively small physical designs to minimize the required resources to facilitate the intended application by providing low-level system access. This minimization of system resources goes hand in hand with reducing the financial cost of a proposed solution or system. As remotely collaborating researchers often use FPGAs to prototype designs that are required to have a method for data transmission among systems, it is imperative to provide a baseline standard for communications among devices and systems. A typical method of implementing the Modbus RTU communication protocol in an embedded environment is using integrated logic architectures within the FPGA called “Intellectual Property (IP) cores.” IP cores can be designed using integrated logic or circuit designs to function as an embedded processor. These IP cores can then perform the required computational actions to support the Modbus RTU communication protocol by utilizing high-level programming languages such as the C programming language. The hardware description language of Very High-Speed Integrated Circuit Hardware Description Language (VHDL) allows for the control of real hardware at the logic gate and signal level. These logic gates and signals can be designed and controlled to perform desired actions based on the system design. Programming an FPGA using VHDL allows an individual to access the lowest abstraction level of the system during FPGA development. This level of abstraction is referred to as the register-transfer level (RTL), which gives access to manipulating values and variables at the register level. This register-level manipulation provides precision over creating the logical circuit within the FPGA, thus minimizing the required code to perform desired operations. The Modbus RTU communication protocol can be implemented within an FPGA using VHDL programming to establish a standardized and embedded serial communication pathway. This implementation provides a standardized communication protocol to streamline research efforts among researchers, thus increasing the efficiency of research efforts. Additionally, this Modbus RTU implementation requires fewer resources when compared to typical communication protocol implementations that utilize an IP core, reducing the hardware requirement for effective research efforts.

communication↗
DOE OSTI2023

A Real-Time ANPC Inverter Digital Twin with Integrated Design-For-Trust

The demand for renewable energy has increased over the last few years, and so has the demand for greater expectations within the energy market. This increasing trend has been accompanied by more significant usage of internet-connected devices (IoT), leading to critical electrical infrastructure being connected to the internet. Implementing internet connectivity with such devices and systems provides benefits such as improving the system's performance, facilitating irregularity and anomaly mitigation, and providing additional situational awareness for enhanced decision-making. However, enhancing the connected system with IoT introduces a drawback – a greater vulnerability to cyber-attacks. Cyber-attacks targeting critical infrastructure in the electrical sector have occurred in the United States and Ukraine. These cyber-attacks highlight and expose vulnerabilities that a system inherits when connecting to the internet. These attacks left thousands of customers without electricity for hours until operators could regain control of the electric utility grid. Therefore, to address the vulnerabilities of an internet-connected power electronic device, this work focused on the hardware layer of the system. Implementing a cyber-control system inside the hardware layer can significantly reduce the possibility of an attacker patching malicious controller firmware into a photovoltaic grid-connected inverter, thus mitigating the likelihood that the inverter becomes inactive a cyber-attack scenario. With this mitigation technique, if a cyberattack is successful and an attacker gains control of the network, a cyber-defense technique is in place to mitigate the impact of the cyber-attack. This additional protection layer was developed based on an innovative concept known as Digital Twin (DT). A DT, in this case, replicates an Active-Neutral Point Clamped (ANPC) inverter and was designed using a hardware language known as VHDL (Very High-Speed Integrated Circuit Hardware Description Language) and applied to Field-Programmable-GateArray (FPGA). The DT is embedded within the FPGA and contained in a controller board, the UCB (Unified Controller Board), developed by the University of Arkansas electrical engineering team. This UCB also contains two Digital Signal Processors (DSPs) responsible for generating associated signals to control an authentic physical inverter. These DSP signals are received and processed by the FPGA that implements the DT of an ANPC; in other words, it simulates in realtime the expected output of an actual ANPC inverter using the signals from the DSP. When a new firmware is ready to be patched, the DT provides output signals simulating behavior that a real ANPC inverter would generate with the new firmware. The new firmware is tested to check if it meets all the operational requirements established using a Design-For-Trust technique (DFTr). If the new firmware fails in at least one of the DFT tests, it is considered malicious and must be rejected. This work is divided into sections, such as Background, which explains the pieces that were used and the strategy behind this work; Process and Procedure, which explains the methodology that was adopted to prove the reliability and effectiveness of this work; Results and Discussion, where the simulations and results are described and explained; followed by Conclusion and Future work section, which concludes this work and adds possible future projects to continue this work further.

do Amaral Custodio, Paulo Vitor↗
DOE OSTI2024

Towards Automated Generation of Chiplet-Based Systems

The Software Defined Architectures (SODA) Synthesizer is an open-source compiler-based tool able to automatically generate domain-specialized systems targeting Application- Specific Integrated Circuits (ASICs) or Field Programmable Gate Arrays (FPGAs) starting from high-level programming. SODA is composed of a high-level frontend, SODA-OPT, which leverages the multilevel intermediate representation (MLIR) framework to interface with productive programming tools (e.g., machine learning frameworks), identify kernels suitable for acceleration, and perform high-level optimizations, and of a state-of-the-art high-level synthesis backend, Bambu from the PandA framework, to generate custom accelerators. One specific application of the SODA Synthesizer is the generation of accelerators to enable ultra-low latency inference and control on autonomous systems for scientific discovery (e.g., electron microscopes, sensors in particle accelerators, etc.). This talk will discuss ongoing work on the SODA synthesizer to enable no-human-in-the-loop generation and design space exploration of the chiplets for highly specialized artificial intelligence accelerators. Connecting these highly specialized chiplets to general-purpose cores or programmable accelerators will allow to quickly deploy autonomous systems for scientific discovery.

Limaye, Ankur M.↗
DOE OSTI2024

A Graph Neural Network Surrogate Model for hls4ml

Recent advancements in use of machine learning (ML) techniques on field-programmable gate arrays (FPGAs) have allowed for the implementation of embedded neural networks with extremely low latency. This is invaluable for particle detectors at the Large Hadron Collider, where latency and used area are strictly bounded. The hls4ml framework is a procedure that converts trained ML model software to a synthesis result to can be used on an FPGA. However, running the pipeline is a time-consuming procedure, and there is a strong risk of failure. In particular, it may not be possible to successfully convert a model into a synthesis result, or the resource consumption of the model may exceed the resources of the target FPGA. To aid with this development, we introduce wa-hls4ml, a surrogate model using a graph neural network to emulate the structure of the source models. The goal is to estimate the chance of success and resource consumption of a given model when passed through the hls4ml pipeline, without needing to run the pipeline.

Plotnikov, Dennis↗
DOE OSTI2024

Calibration of the analog beam-signal hardware for the credited engineered beam power limit system at the Proton Power Upgrade Project at the Spallation Neutron Source

A programmable signal processor-based credited safety control that calculates pulsed beam power based on beam kinetic energy and charge was designed as part of the Proton Power Upgrade (PPU) project at the Spallation Neutron Source (SNS). The system must reliably shut off the beam if the average power exceeds 2.145 MW averaging over 60 seconds. System calibration requires pedigree in measurements, calibration setup, and calculations. This paper discusses the calibration of the analog beam signal components up to and including the Analog Digital Convertors (ADCs) for implementation into the Safety Programmable Logic Controllers (PLCs) and Field Programmable Gate Arrays (FPGAs).

Bobrek, Miljko↗
DOE OSTI2025

SQuaD: Smart Quantum Detection for Photon Recognition and Dark Count Elimination

Quantum detectors of single photons are an essential component for quantum information processing across computing, communication and networking. Today's quantum detection system, which consists of single photon detectors, timing electronics, control and data processing software, is primarily used for counting the number of single photon detection events. However, it is largely incapable of extracting other rich physical characteristics of the detected photons, such as their wavelengths, polarization states, photon numbers, or temporal waveforms. This work, for the first time, demonstrates a smart quantum detection system, SQuaD, which integrates a field programmable gate array (FPGA) with a neural network model, and is designed to recognize the features of photons and to eliminate detector dark-count. The SQuaD is a fully integrated quantum system with high timing-resolution data acquisition, onboard multi-scale data analysis, intelligent feature recognition and extraction, and feedback-driven system control. Our \name experimentally demonstrates 1) reliable photon counting on par with the state-of-the art commercial systems; 2) high-throughput data processing for each individual detection events; 3) efficient dark count recognition and elimination; 4) up to 100% accurate feature recognition of photon wavelength and polarization. Additionally, we deploy the SQuaD to an atomic (erbium ion) photon emitter source to realize noise-free control and readout of a spin qubit in the telecom band, enabling critical advances in quantum networks and distributed quantum information processing.

Linne, Karl C. [U. Chicago (main)] (ORCID:00090009↗
DOE OSTI2025

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

We present hls4ml, a free and open-source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can be integrated into full designs for field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs). With its flexible and modular design, hls4ml supports a large number of deep learning frameworks and can target HLS compilers from several vendors, including Vitis HLS, Intel oneAPI and Catapult HLS. Together with a wider eco-system for software-hardware co-design, hls4ml has enabled the acceleration of ML inference in a wide range of commercial and scientific applications where low latency, resource usage, and power consumption are critical. In this paper, we describe the structure and functionality of the hls4ml platform. The overarching design considerations for the generated HLS code are discussed, together with selected performance results.

Schulte, Jan-Frederik [Purdue U.] (ORCID:000000034↗