Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “quantization”

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 1,207 records · Page 67
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Errant Beam Detection Using the AMD Versal ACAP and Vitis AI

The prevalence of ML and AI-powered solutions along with the slowing of Moore's Law has given rise to novel hardware platforms aimed at accelerating ML and AI. While programming these hardware platforms can be difficult, particularly for non-hardware experts, hardware vendors provide high-level tooling in an effort to address this difficulty. The Versal ACAP is an SoC designed by AMD that combines CPU cores, FPGA fabric, and a tiled, vector architecture called an AI engine all on the same socket. In an effort to more easily program this heterogeneous system, AMD has provided the Vitis AI development stack. In this work, we leverage Vitis AI to program a Versal ACAP to perform errant beam detection in the Spallation Neutron Source at Oak Ridge National Laboratory. Our initial work shows that after quantization and compilation of the model for the Versal ACAP, the classification accuracy, as measured by the AUC metric, is over 95% accurate while achieving this accuracy in 46 microseconds on average.

Cabrera, Anthony↗
DOE OSTI2024

Neuro-Spark: A Submicrosecond Spiking Neural Networks Architecture for In-Sensor Filtering

Neuro-Spark, which is a new neuromorphic architecture with a field-programmable gate array (FPGA) implementation for ultrafast spiking neural network (SNN) inference at the edge, facilitates smart-pixel in-sensor filtering for high-energy physics experiments at the Large Hadron Collider (LHC). Utilizing the evolutionary optimization for neuromorphic systems (EONS) training method, we generate compact SNN models with 91% signal efficiency, akin to convolutional neural networks but with half the parameters. However, deploying near the detector poses a challenge because the SNN must handle a sustained input data rate exceeding 1013 GB/s. To overcome this, we propose a novel hardware architecture that uses high-level synthesis to construct a tuned architecture for the EONS-trained SNN. In addition to the analysis and validation with an AMD Xilinx Artix-A7 FPGA, our solution consumes only ç24% of FPGA LUT and flipflops. We also introduce an innovative quantization method that reduces FPGA resource utilization by ç15% without compromising accuracy. Our FPGA implementation achieves computing latency of ç10 ns for smart-pixel application inference on an edge FPGA.

Miniskar, Narasinga Rao↗
DOE OSTI2018

Modular Spiking Neural Circuits for Mapping Long Short-Term Memory on a Neurosynaptic Processor

Due to the distributed and asynchronous nature of neural computation through low-energy spikes, brain-inspired hardware systems offer high energy efficiency and massive parallelism. One such platform is the IBM TrueNorth neurosynaptic system. Recently, TrueNorth compatible representation learning algorithms have emerged, achieving close to the state-of-the-art performance in various data sets. However, its application in temporal sequence processing models, such as recurrent neural networks (RNNs), is still only at the proof of concept level. There is an inherent difficulty in capturing temporal dynamics of an RNN using spiking neurons, which is only exasperated by the hardware constraints in connectivity and synaptic weight resolution. This paper presents a design flow that overcomes these difficulties and maps a special case of recurrent networks called long short-term memory (LSTM) onto a spike-based platform. The framework utilizes various approximation techniques, such as activation discretization, weight quantization, and scaling and rounding, spiking neural circuits that implement the complex gating mechanisms, and a store-and-release technique to enable neuron synchronization and faithful storage. While the presented techniques can be applied to map LSTM to any spiking neural network (SNN) simulator/emulator, here we choose the TrueNorth chip as the target platform by adhering to its hardware constraints. Three LSTM applications, parity check, extended Reber grammar, and question classification, are evaluated. The tradeoffs among accuracy, performance, and energy tradeoffs achieved on TrueNorth are demonstrated. Finally, this is compared with the performance on an SNN platform without hardware constraints, which represents the upper bound of the achievable accuracy.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

On the Convergence of the Inexact Running Krasnosel'skii-Mann Method

This letter leverages a framework based on averaged operators to tackle the problem of tracking fixed points associated with maps that evolve over time. In particular, this letter considers the Krasnosel'skii-Mann (KM) method in a settings where: 1) the underlying map may change at each step of the algorithm, thus leading to a 'running' implementation of the KM method, and 2) an imperfect information of the map may be available. An imperfect knowledge of the maps can capture cases where processors feature a finite precision or quantization errors, or the case where (part of) the map is obtained from measurements. The analytical results are applicable to inexact running algorithms for solving optimization problems, whenever the algorithmic steps can be written in the form of (a composition of) averaged operators; examples are provided for inexact running gradient methods and the forward-backward splitting method. Convergence of the average fixed-point residual is investigated for the non-expansive case; linear convergence to a unique fixed-point trajectory is showen in the case of inexact running algorithms emerging from contractive operators.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Enhanced Machine-Learning Flow for Microwave-Sensing Systems for Contaminant Detection in Food

The presence of foreign bodies in packaged food is a serious concern for both fnal consumers (allergies, injuries, choking) and food manufacturers (reputation and economic losses). In particular, low-density plastics, glass and wood splinters are hard to detect even by the most advanced X-ray imagers. One solution is Machine-Learning-based Microwave Sensing (MLMWS): a non-invasive, contactless, and real-time method which uses a machine-learning (ML) classifer to analyze the scattered microwaves from the irradiated target object. In this paper, we want to extend our previous work about contaminant detection in cocoa-hazelnut spread jars by proposing an enhanced ML flow to increase the accuracy of the ML classifier. For the first time in this case study, we use a multi-class classifier, we train it with scattering parameters measured at multiple microwave frequencies, with a new pre-processing scaler, data augmentation, quantization-aware training and a pruning schedule. The results show a contaminant detection multi-class accuracy of 94.167% with a latency of 26 µs when targeting an AMD/Xilinx Kria K26 FPGA. Finally, we released our datasets publicly to OpenML.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2016

A Weather Radar Simulator for the Evaluation of Polarimetric Phased Array Performance

A radar simulator capable of generating time series data for a polarimetric phased array weather radar has been designed and implemented. The received signals are composed from a high-resolution numerical prediction weather model. Thousands of scattering centers, each with an independent randomly generated Doppler spectrum, populate the field of view of the radar. The moments of the scattering center spectra are derived from the numerical weather model, and the scattering center positions are updated based on the three-dimensional wind field. In order to accurately emulate the effects of the system-induced cross-polar contamination, the array is modeled using a complete set of dual-polarization radiation patterns. The simulator offers reconfigurable element patterns and positions as well as access to independent time series data for each element, resulting in easy implementation of any beamforming method. It also allows for arbitrary waveform designs and is able to model the effects of quantization on waveform performance. Simultaneous, alternating, quasi-simultaneous, and pulse-to-pulse phase coded modes of polarimetric signal transmission have been implemented. This framework allows for realistic emulation of the effects of cross-polar fields on weather observations, as well as the evaluation of possible techniques for the mitigation of those effects.

phased array↗
DOE OSTI2014

Delta Modulation Technique for Improving the Sensitivity of Monobit Subsamplers in Radar and Coherent Receiver Applications

This paper introduces a technique for improving the sensitivity of RF subsamplers in radar and coherent receiver applications. The technique, referred to herein as “delta modulation” (DM), feeds the time-average output of a monobit analog-to-digital converter (ADC) back to the ADC input, but with opposite polarity. Assuming pseudo-stationary modulation statistics on the sampled RF waveform, the feedback signal corrects for aggregate DC offsets present in the ADC that otherwise degrade ADC sensitivity. Two RF integrated circuits (RFICs) are designed to demonstrate the approach. One uses analog DM to create the feedback signal; the other uses digital DM to achieve the same result. A series of tests validates the designs. The dynamic time-domain response confirms the feedback loop’s basic operation. Measured output quantization imbalance, under noise-only input drive, significantly improves with the use of the DM circuit, even for large, deliberately induced DC offsets and wide temperature variation from -55°C to +85 °C. Examination of the corrected vs. uncorrected baseband spectrum under swept input signal-tonoise ratio (SNR) conditions demonstrates the effectiveness of this approach for realistic radar and coherent receiver applications. In conclusion, two-tone testing shows no impact of the DM technique on ADC linearity.

47 OTHER INSTRUMENTATION↗
DOE OSTI2017

Blocker-tolerant and high-sensitivity $Δ$\!$Σ$ correlation digitizer for radar and coherent receiver applications

In this study, a coherent subsampling digitizer for pulsed Doppler radar systems is proposed. Prior to transmission, the radar system modulates the RF pulse with a known pseudorandom binary phase shift keying (BPSK) sequence. Upon reception, the radar digitizer uses a programmable sample-and-hold circuit to multiply the received waveform by a properly time-delayed version of the known a priori BPSK sequence. This operation demodulates the desired echo signal while suppressing the spectrum of all in-band noncorrelated interferers, making them appear as noise in the frequency domain. The resulting demodulated narrowband Doppler waveform is then subsampled at the IF frequency by a delta-sigma modulator. Because the digitization bandwidth within the delta-sigma feedback loop is much less than the input bandwidth to the digitizer, the thermal noise outside of the Doppler bandwidth is effectively filtered prior to quantization, providing an increase in signal-to-noise ratio (SNR) at the digitizer's output compared with the input SNR. In this demonstration, a delta-sigma correlation digitizer is fabricated in a 0.18-μm CMOS technology. The digitizer has a power consumption of 1.12 mW with an IIP3 of 7.5 dBm. The digitizer is able to recover Doppler tones in the presence of blockers up to 40 dBm greater than the Doppler tone.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

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 (NN) autoencoder model can be implemented in a radiation-tolerant application-specific integrated circuit (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 Compact Muon Solenoid (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 NN 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 quantization-aware training to create an optimized NN 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 low-power (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. Furthermore, this is the first radiation-tolerant on-detector ASIC implementation of an NN that has been designed for particle physics applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2018

Efficient Lossy Compression for Scientific Data Based on Pointwise Relative Error Bound

An effective data compressor is becoming increasingly critical to today's scientific research, and many lossy compressors are developed in the context of absolute error bounds. Based on physical/chemical definitions of simulation fields or multiresolution demand, however, many scientific applications need to compress the data with a pointwise relative error bound (i.e., the smaller the data value, the smaller the compression error to tolerate). To this end, we propose two optimized lossy compression strategies under a state-of-the-art three-staged compression framework (prediction + quantization + entropy-encoding). The first strategy (called block-based strategy) splits the data set into many small blocks and computes an absolute error bound for each block, so it is particularly suitable for the data with relatively high consecutiveness in space. The second strategy (called multi-threshold-based strategy) splits the whole value range into multiple groups with exponentially increasing thresholds and performs the compression in each group separately, which is particularly suitable for the data with a relatively large value range and spiky value changes. We implement the two strategies rigorously and evaluate them comprehensively by using two scientific applications which both require lossy compression with point-wise relative error bound. Experiments show that the two strategies exhibit the best compression qualities on different types of data sets respectively. In conclusion, the compression ratio of our lossy compressor is higher than that of other state-of-the-art compressors by 17.2-618 percent on the climate simulation data and 30-210 percent on the N-body simulation data, with the same relative error bound and without degradation of the overall visualization effect of the entire data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Performance Optimization for Relative-Error-Bounded Lossy Compression on Scientific Data

Scientific simulations in high-performance computing (HPC) environments generate vast volume of data, which may cause a severe I/O bottleneck at runtime and a huge burden on storage space for postanalysis. Unlike traditional data reduction schemes such as deduplication or lossless compression, not only can error-controlled lossy compression significantly reduce the data size but it also holds the promise to satisfy user demand on error control. Pointwise relative error bounds (i.e., compression errors depends on the data values) are widely used by many scientific applications with lossy compression since error control can adapt to the error bound in the dataset automatically. Pointwise relative-error-bounded compression is complicated and time consuming. In this article, we develop efficient precomputation-based mechanisms based on the SZ lossy compression framework. Our mechanisms can avoid costly logarithmic transformation and identify quantization factor values via a fast table lookup, greatly accelerating the relative-error-bounded compression with excellent compression ratios. In addition, we reduce traversing operations for Huffman decoding, significantly accelerating the decompression process in SZ. Experiments with eight well-known real-world scientific simulation datasets show that our solution can improve the compression and decompression rates (i.e., the speed) by about 40 and 80 p, respectively, in most of cases, making our designed lossy compression strategy the best-in-class solution in most cases.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2025

End-to-End Workflow for Machine-Learning-Based Qubit Readout With QICK and hls4ml

In this article, we present an end-to-end workflow for superconducting qubit readout that embeds codesigned neural networks into the quantum instrumentation control kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx radiofrequency system-on-chip field-programmable gate arrays (FPGAs), we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workflow utilizes the hls4ml package and employs quantization-aware training to translate ML models into hardware-efficient FPGA implementations via user-friendly Python application programming interfaces. We experimentally demonstrate the design, optimization, and integration of an ML algorithm for single transmon qubit readout, achieving 96% single-shot fidelity with a latency of 32.25 ns and less than 16% FPGA lookup table resource utilization. Our results offer the community an accessible workflow to advance ML-driven readout and adaptive control in quantum information processing applications.

42 ENGINEERING↗
DOE OSTI2018

A Study of the Trade-off Between Reducing Precision and Reducing Resolution for Data Analysis and Visualization

There presently exist two dominant strategies to reduce data sizes in analysis and visualization: reducing the precision of the data, e.g., through quantization, or reducing its resolution, e.g., by subsampling. Both have advantages and disadvantages and both face fundamental limits at which the reduced information ceases to be useful. The paper explores the additional gains that could be achieved by combining both strategies. In particular, we present a common framework that allows us to study the trade-off in reducing precision and/or resolution in a principled manner. We represent data reduction schemes as progressive streams of bits and study how various bit orderings such as by resolution, by precision, etc., impact the resulting approximation error across a variety of data sets as well as analysis tasks. Additionally, we compute streams that are optimized for different tasks to serve as lower bounds on the achievable error. Scientific data management systems can use the results proposed in this paper as guidance on how to store and stream data to make efficient use of the limited storage and bandwidth in practice.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

TopoSZ: Preserving Topology in Error-Bounded Lossy Compression

Existing error-bounded lossy compression techniques control the pointwise error during compression to guarantee the integrity of the decompressed data. However, they typically do not explicitly preserve the topological features in data. When performing post hoc analysis with decompressed data using topological methods, preserving topology in the compression process to obtain topologically consistent and correct scientific insights is desirable. In this paper, we introduce TopoSZ, an error-bounded lossy compression method that preserves the topological features in 2D and 3D scalar fields. Specifically, we aim to preserve the types and locations of local extrema as well as the level set relations among critical points captured by contour trees in the decompressed data. The main idea is to derive topological constraints from contour-tree-induced segmentation from the data domain, and incorporate such constraints with a customized error-controlled quantization strategy from the SZ compressor (version 1.4). In conclusion, our method allows users to control the pointwise error and the loss of topological features during the compression process with a global error bound and a persistence threshold.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Reliable edge machine learning hardware for scientific applications

Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. This leads to unique validation challenges for VLSI implementations of ML algorithms: enabling bit-accurate functional simulations for performance validation in experimental software frameworks, verifying those ML models are robust under extreme quantization and pruning, and enabling ultra-fine-grained model inspection for efficient fault tolerance. We discuss approaches to developing and validating reliable algorithms at the scientific edge under such strict latency, resource, power, and area requirements in extreme experimental environments. We study metrics for developing robust algorithms, present preliminary results and mitigation strategies, and conclude with an outlook of these and future directions of research towards the longer-term goal of developing autonomous scientific experimentation methods for accelerated scientific discovery.

Baldi, Tommaso↗
DOE OSTI2021

Compressive Neural Representations of Volumetric Scalar Fields

Here, we present an approach for compressing volumetric scalar fields using implicit neural representations. Our approach represents a scalar field as a learned function, wherein a neural network maps a point in the domain to an output scalar value. By setting the number of weights of the neural network to be smaller than the input size, we achieve compressed representations of scalar fields, thus framing compression as a type of function approximation. Combined with carefully quantizing network weights, we show that this approach yields highly compact representations that outperform state-of-the-art volume compression approaches. The conceptual simplicity of our approach enables a number of benefits, such as support for time-varying scalar fields, optimizing to preserve spatial gradients, and random-access field evaluation. We study the impact of network design choices on compression performance, highlighting how simple network architectures are effective for a broad range of volumes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Observation of quantum oscillation of work function in ultrathin-metal/semiconductor junctions

Quantization in energy level due to confinement is generally observed for semiconductors. This property is used for various quantum devices, and it helps to improve the characteristics of conventional devices. Here, the authors have demonstrated the quantum size effects in ultrathin metal (Ni) layers sandwiched between two large band-gap materials. The metal work function is found to oscillate as a function of its thickness. The thermionic emission current bears the signature of the oscillating work function, which has a linear relationship with barrier heights. This methodology allows direct observation of quantum oscillations in metals at room temperature using a Schottky diode and electrical measurements using source-measure-units. The observed phenomena can provide additional mechanism to tune the barrier height of metal/semiconductor junctions, which are used for various electronic devices.

42 ENGINEERING↗
DOE OSTI2020

Characterization of skipper CCDs for cosmological applications

We characterize the response of a novel 250 µm thick, fully-depleted Skipper Charged-Coupled Device (CCD) to visible/near-infrared light with a focus on potential applications for astronomical observations. We achieve stable, single-electron resolution with readout noise &sigma; 0.18 e - rms/pix from 400 non-destructive measurements of the charge in each pixel. We verify that the gain derived from photon transfer curve measurements agrees with the gain calculated from the quantized charge of individual electrons to within < 1%. We also perform relative quantum efficiency measurements and demonstrate high relative quantum efficiency at optical/near- infrared wavelengths, as is expected for a thick, fully depleted detector. Finally, we demonstrate the ability to perform multiple non-destructive measurements and achieve sub-electron readout noise over configurable sub- regions of the detector. This work is the first step toward demonstrating the utility of Skipper CCDs for future astronomical and cosmological applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗