Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Field Programmable Gate Arrays”

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 703 records · Page 39

High performance context switching for virtualized FPGA accelerators

A hardware context manager in a field-programmable gate array (FPGA) device includes configuration logic configured to program one or more programming regions in the FPGA device based on configuration data for implementing a target configuration of the one or more programming regions. Context management logic in the hardware context manager is coupled with the configuration logic and saves a first context corresponding to the target configuration by retrieving first state information from the set of one or more programming regions, where the first state information is generated based on the target configuration, and storing the retrieved first state information in a context memory. The context management logic restores the first context by transferring the first state information from the context memory to the one or more programming regions, and causing the configuration logic to program the one or more programming regions based on the configuration data.

42 ENGINEERING↗

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↗

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.↗

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.↗

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.↗

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.↗

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↗

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↗

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↗

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↗

Signal Processing Board for Beam Loss Monitors

This paper describes a new VME based machine protection Beam Loss Monitor (BLM) signal processing board designed at Jefferson Lab which features high sensitivity, high resolution, and low cost per channel. This double-wide VME board provides eight-channel signal processing with each channel having linear, logarithmic, and integrating amplifiers that simultaneously provide the optimal signal processing for both machine protection and beam diagnostics. Amplified signals are independently sampled by 16-bit, fast ADCs and then further processed through a Field Programmable Gate Array (FPGA). It also has features of fast shutdown interface (FSD), beam sync interface, built-in-self-test, remotely controlled bias signals, and on-board memory buffer. The initial experimental test shows that the BLM board has fast response (<< 1us) for integrating and wide dynamic range from 10 nA to 1 mA (>50 dB) for logarithmic signals. The board is suitable for signal processing from photomultiplier (PMT) and ion chamber detectors. Notice: Authored by Jefferson Science Associates, LLC under U.S. DOE Contract No. DE-AC05-06OR23177. The U.S. Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce this manuscript for U.S. Government purposes.

Yan, Jianxun↗

A Diamond Micro-strip Electron Detector for Compton Polarimetry

The Qweak experiment in Hall C at Jefferson Lab aims to measure the weak charge of the proton with a precision of 4.1{\%} by measuring the parity violating asymmetry in polarized electron-proton elastic scattering. Beam polarimetry is the largest experimental contribution to the error budget. A new Compton polarimeter was installed for a non-invasive and continuous monitoring of the electron beam polarization with a goal of 1{\%} systematic and 1{\%} per hour statistical precision. The Compton-scattered electrons are detected in four planes of diamond micro-strip detectors. These detectors are read out using custom built electronic modules that include a pre-amplifier, a pulse shaping amplifier and a discriminator for each detector micro-strip. We use Field Programmable Gate Array based general purpose logic modules for event selection and histogramming. The polarimeter was commissioned during the first run period of the Qweak experiment. We will show the preliminary results from the electron detector obtained during the first run period of Qweak experiment.

Narayan, Amrendra↗

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↗

FPGA remote update for nuclear environments

The Instituto de Plasmas e Fusao Nuclear (IPFN) has developed dedicated re-configurable modules based on field programmable gate array (FPGA) devices for several nuclear fusion machines worldwide. Moreover, new Advanced Telecommunication Computing Architecture (ATCA) based modules developed by IPFN are already included in the ITER catalogue. One of the requirements for re-configurable modules operating in future nuclear environments including ITER is the remote update capability. Accordingly, this work presents an alternative method for FPGA remote programing to be implemented in new ATCA based re-configurable modules. FPGAs are volatile devices and their programming code is usually stored in dedicated flash memories for properly configuration during module power-on. The presented method is capable to store new FPGA codes in Serial Peripheral Interface (SPI) flash memories using the PCIexpress (PCIe) network established on the ATCA back-plane, linking data acquisition endpoints and the data switch blades. The method is based on the Xilinx Quick Boot application note, adapted to PCIe protocol and ATCA based modules. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Artificial Neural Network-Based Monitoring of the Fuel Assembly Temperature Sensor and FPGA Implementation

Numerous methods have been developed around the world to model the dynamic behavior and detect a faulty operating mode of a temperature sensor. In this context, we present in this study a new method based on the dependence between the fuel assembly temperature profile on control rods positions, and the coolant flow rate in a nuclear reactor. This seems to be possible since the insertion of control rods at different axial positions and variations in flow rate of the reactor coolant results in different produced thermal power in the reactor. This is closely linked to the instant fuel rod temperature profile. In a first step, we selected parameters to be used and confirmed the adequate correlation between the chosen parameters and those to be estimated by the proposed monitoring system. In the next step, we acquired and de-noised the data of corresponding parameters, the qualified data is then used to design and train the artificial neural network. The effective data denoising was done by using the wavelet transform to remove a various kind of artifacts such as inherent noise. With the suitable choice of wavelet level and smoothing method, it was possible for us to remove all the non-required artifacts with a view to verify and analyze the considered signal. In our work, several potential mother wavelet functions (Haar, Daubechies, Bi-orthogonal, Reverse Bi-orthogonal, Discrete Meyer and Symlets) were investigated to find the most similar function with the being processed signals. To implement the proposed monitoring system for the fuel rod temperature sensor (03 wire RTD sensor), we used the Bayesian artificial neural network 'BNN' technique to model the dynamic behavior of the considered sensor, the system correlate the estimated values with the measured for the concretization of the proposed system we propose an FPGA (field programmable gate array) implementation. The monitoring system use the correlation. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Firmware development for the ATLAS TileCal sROD

TileCal is the central hadronic calorimeter of the ATLAS experiment at the Large Hadron Collider (LHC) at CERN. A main upgrade of the LHC (also called Phase-II) is planned in order to increase the instantaneous luminosity in 2022. At the TileCal level, the upgrade involves the redesign of the complete read-out architecture, affecting both the front-end and the back-end electronics. In the new read-out architecture, the front-end electronics will transmit digitized information of the full detector to the back-end system every single bunch crossing. Thus, the back-end system must provide digital calibrated information to the first level of trigger. Having all detector data per bunch crossing in the back-end will increase the precision and granularity of the trigger information, improving this way the trigger efficiencies. A reduced part of the detector, 1/256 of the total, will be equipped with the new electronics during 2014 to evaluate the proposed architecture in real conditions in the so-called 'demonstrator project'. The upgraded version of the Read-Out Driver (sROD) will be the core element of the back-end electronics in Phase-II. The sROD demonstrator is a prototype that is being developed to validate in the demonstrator project the future sROD for Phase-II. This module includes two Xilinx Series 7 Field Programmable Gate Arrays (FPGAs) for data receiving and processing and will be installed and working in an ATCA framework. A complete description of the sROD functionality in terms of firmware will be introduced. In addition, the status of the firmware development and a summary of the main milestones achieved and the future plans will be presented. (authors)

43 PARTICLE ACCELERATORS↗

Thomson Scattering Diagnostic Data Acquisition Systems for Modern Fusion Systems

Uniquely designed complex data acquisition system for Thomson scattering diagnostic was developed. It allows recording short duration (3-5 ns) scattered pulses with 2 GHz sampling rate and 10-bit total resolution in oscilloscope mode. The system consists up to 48 photo detector modules with 0- 200 MHz bandwidth, 1-48 simultaneously sampling ADC modules and synchronization subsystem. The photo detector modules are based on avalanche photodiodes (APD) and ultra-low noise trans-impedance amplifiers. ADC modules include fast analog to digital converters and digital units based on the FPGA (Field- Programmable Gate Array) for data processing and storage. The synchronization subsystem is used to form triggering pulses and to organize the simultaneously mode of ADC modules operation. (authors)

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗