SEARCH · Search NASA

Results for “Xilinx”

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.

SourceResearch connectionFrom yearThrough year

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

At least 19 records

All sources NASA NTRS DOE OSTI

DOE OSTI2026

A Single-Board Fermilab Timing Pipeline on the Xilinx KR260: Decode, Timestamp, Publish, Mirror

Full-width abstract \renewcommand{\maketitlehookd}{% \begin{abstract} \noindent Fermilab's accelerator timing links broadcast short event codes to thousands of devices at once, but the links themselves carry no absolute notion of time; that comes separately from a White Rabbit reference. This work builds the piece that ties the two together on a single board. On a Xilinx Kria KR260 (Zynq UltraScale+), the programmable logic decodes a real Fermilab TCLK link, stamps every event with an absolute White-Rabbit \{sec, ns\} UTC time, and reads the timestamped stream out over AXI4-Lite; a thin Linux process on the same die publishes each event into a Redis stream on the control network. To exercise the full chain on one board, the decoded events are re-encoded as gigabit ACLK, transmitted out an SFP+ optical port, looped back over a short fiber jumper, and decoded again on the same timeline, and are additionally mirrored as an ACLK-Lite Manchester waveform for benchtop probing. Across sustained, multi-day testing against real Fermilab TCLK, the pipeline has decoded, timestamped, and published hundreds of millions of events with practically zero loss, and folding the timestamped stream on the 60-second accelerator supercycle recovers the machine's periodic structure directly from the published data.

Rossel, Jacob [UC, Berkeley; Fermilab] (ORCID:0009↗

DOE OSTI2024

Characterization of throughput on the AXI DMA bus for burst data transfer over Ethernet

cThe Xilinx AXI Direct Memory Access (AXI DMA) module is an efficient solution for medium-speed data transfer in Xilinx SoC FPGAs, supporting data rates greater than 1000 Gbps even in very suboptimal operating modes. It facilitates direct transfer of AXI stream data into processor memory without constant software intervention, which reduces overhead and ensures consistent data logging. By utilizing the FPGA's available memory, large circular buffers (1-5 GiB) are used to buffer data and accommodate network limitations, enabling high-rate data bursts. In this study, we measured the performance of AXI DMA under conditions simulating its lowest practical data transfer speeds. The Arbitrary Length Data Sender was used to transmit AXI stream packets at 32-bit width and 100 MHz frequency, a narrow width and slow speed. Results show that the AXI DMA can transfer up to 3192.76 Mbps with large packet sizes but experiences reduced performance for smaller packets, as low as 2.6 Mbps for 4-byte packets. For Ethernet-limited applications, packet sizes between 8,000 and 16,000 bytes provided optimal transfer speeds of 874 to 1600 Mbps. These findings suggest that the AXI DMA is not the limiting factor in systems where packet sizes exceed 8,000 bytes.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Entropy Analysis of FPGA Interconnect and Switch Matrices for Physical Unclonable Functions

Random variations in microelectronic circuit structures represent the source of entropy for physical unclonable functions (PUFs). In this paper, we investigate delay variations that occur through the routing network and switch matrices of a field-programmable gate array (FPGA). The delay variations are isolated from other components of the programmable logic, e.g., look-up tables (LUTs), flip-flops (FFs), etc., using a feature of Xilinx FPGAs called dynamic partial reconfiguration (DPR). A set of partial designs is created to fix the placement of a time-to-digital converter (TDC) and supporting infrastructure to enable the path delays through the target interconnect and switch matrices to be extracted by subtracting out common-mode delay components. Delay variations are analyzed in the different levels of routing resources available within FPGAs, i.e., local routing and across-chip routing. Data are collected from a set of Xilinx Zynq 7010 devices, and a statistical analysis of within-die variations in delay through a set of the randomly-generated and hand-crafted interconnects is presented.

97 MATHEMATICS AND COMPUTING↗

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 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 OSTI2024

Compiler-Driven FPGA Virtualization with SYNERGY

FPGAs are increasingly common in modern applications, and cloud providers now support on-demand FPGA acceleration in datacenters. Applications in datacenters run on virtual infrastructure, where consolidation, multi-tenancy, and workload migration enable economies of scale that are fundamental to the provider's business. However, a general strategy for virtualizing FPGAs has yet to emerge. While manufacturers struggle with hardware-based approaches, we propose a compiler/runtime-based solution called Synergy. We show a compiler transformation for Verilog programs that produces code able to yield control to software atsub-clock-tickgranularity according to the semantics of the original program. Synergy uses this property to efficiently support core virtualization primitives: suspend and resume, program migration, and spatial/temporal multiplexing, on hardware which is availabletoday.We use Synergy to virtualize FPGA workloads across a cluster of Intel SoCs and Xilinx FPGAs on Amazon F1. The workloads require no modification, run within 3--4x of unvirtualized performance, and incur a modest increase in FPGA fabric usage.

Computer Science↗

DOE OSTI2026

wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation

As machine learning (ML) is increasingly implemented in hardware to address real-time challenges in scientific applications, the development of advanced toolchains has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as hardware synthesis, are becoming limiting factors in the rapid iteration of designs. To mitigate these emerging constraints, multiple efforts have been undertaken to develop an ML-based surrogate model that estimates resource usage of ML accelerator architectures. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of over 680,000 fully connected and convolutional neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, and the average performance across a subset of the dataset. Additionally, we introduce GNN- and transformer-based surrogate models that predict latency and resources for ML accelerators. We present the architecture and performance of the models and find that the models generally predict latency and resources for the 75% percentile within several percent of the synthesized resources on the synthetic test dataset.

Hawks, Benjamin [Fermilab] (ORCID:0000000157000288↗

DOE OSTI2025

Radio Frequency Field Programable Gate Array Implementation of Reflectometry Cable Monitoring

PNNL has developed an innovative cable testing system that leverages the Xilinx RF System-on-Chip (RFSoC) technology to create a more flexible and capable measurement tool than traditional approaches. The architecture is designed on the ZCU111 development board and takes advantage of the high-speed digital to analog converters (DAC) and analog to digital converters (ADC) to generate and capture digitally synthesized waveforms. The platform allows engineers to easily adjust power, frequency, duration and modulation on the fly rather than being locked into fixed hardware configurations

Tedeschi, Jonathan [Pacific Northwest National Lab↗

DOE OSTI2025

RFSoC based digital low level RF control firmware and software suite (mimo_llrf) v1.0

It features a framework of a firmware and software architecture in support of building a digital low-level RF control system for accelerators, where precised digital RF generation and measurement are needed across many RF channels. It primarily supports the Xilinx RFSoC chips (xczu48dr, xczu47dr, xczu29dr) and their evaluation boards (zcu208, zcu216), for a highly integrated solution enabling the need for synchronous low-level RF systems, including: multi-tile synchronization, external reference for sampling clocks, deterministic delay, aligned NCO phase for digital mixers, and built-in EPICS IOC.

Du, Qiang [Lawrence Berkeley National Laboratory (↗

DOE OSTI2024

An FPGA-based hardware accelerator supporting sensitive sequence homology filtering with profile hidden Markov models

Abstract Background Sequence alignment lies at the heart of genome sequence annotation. While the BLAST suite of alignment tools has long held an important role in alignment-based sequence database search, greater sensitivity is achieved through the use of profile hidden Markov models (pHMMs). Here, we describe an FPGA hardware accelerator, called HAVAC, that targets a key bottleneck step (SSV) in the analysis pipeline of the popular pHMM alignment tool, HMMER. Results The HAVAC kernel calculates the SSV matrix at 1739 GCUPS on a $$\sim$$ ∼ $3000 Xilinx Alveo U50 FPGA accelerator card, $$\sim$$ ∼ 227× faster than the optimized SSV implementation in nhmmer . Accounting for PCI-e data transfer data processing, HAVAC is 65× faster than nhmmer’s SSV with one thread and 35× faster than nhmmer with four threads, and uses $$\sim$$ ∼ 31% the energy of a traditional high end Intel CPU. Conclusions HAVAC demonstrates the potential offered by FPGA hardware accelerators to produce dramatic speed gains in sequence annotation and related bioinformatics applications. Because these computations are performed on a co-processor, the host CPU remains free to simultaneously compute other aspects of the analysis pipeline.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

Design of digital acquisition for beam current monitor

As a part of the Proton Improvement Plan – II (PIP-II) at Fermilab, instrumentation systems are being modernized to take advantage of the higher speeds and ease of use offered by standardized embedded systems like MicroTCA. A rear-transition module (RTM) is being designed to interface with said embedded systems. In each of the four identical channels on the RTM, the differential signal from an alternating-current current transformer (ACCT) transimpedance amplifier will again be amplified by a differential operation-amplifier, then filtered by a low-pass topology. The conditioned signal is then digitized at a maximum of 10MS/s by an analog to digital converter (ADC) integrated circuit. After digitization, the ADC passes the data to an off the shelf AdvancedMC (AMC) Xilinx FPGA module using low voltage differential signals. This paper will describe the simulation of analog circuitry for signal conditioning, simulation of digital signal integrity based on physical design as well as verification of design characteristics critical to signal integrity. This work aims to create a methodology that can be applied to future RTMs requiring application of high-speed digital design principles.

White, R.Turner [Fermilab]↗

DOE OSTI2024

DIRECT RF SAMPLING BASED LLRF CONTROL SYSTEM FOR C-BAND LINEAR ACCELERATOR

Low Level RF (LLRF) control systems of linear accel- erators (LINACs) are typically implemented with hetero- dyne based architectures, which have complex analog RF mixers for up and down conversion. The Gen 3 Radio Fre- quency System-on-Chip (RFSoC) device from AMD Xilinx integrates data converters with maximum RF frequency of 6 GHz. This enables direct RF sampling of C-band LLRF signal typically operated at 5.712 GHz without any analogue mixers, which can significantly simplify the system architec- ture. The data converters sample RF signals in higher order Nyquist zones and then up or down convert digitally by the integrated data path in RFSoC. The closed-loop feedback control firmware implemented in FPGA integrated in RF- SoC can process the base-band signal from the ADC data path and calculate the updated phase and amplitude to be up- mixed by the DAC data path. We have developed a C-band LLRF control RFSoC platform with direct RF sampling, which targets Cool Copper Collider (𝐶3) and other C or S band LINAC research and development projects. In this paper, the architecture of the platform will be described. We have optimized the configuration of the data converter and characterized performance of them with RF pulses. The test results for some of the key performance parameters for the LLRF platform with our custom solid-state amplifier, such as phase and amplitude stability, will be discussed in this paper.

Liu, C↗

DOE OSTI2025

wa-hls4ml and lui-gnn: A benchmark and GNN-based surrogate model for hls4ml resource and latency estimation

As machine learning (ML) increasingly serves as a tool for addressing real-time challenges in scientific applications, the development of advanced tooling has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as model synthesis, are now becoming limiting factors in the rapid iteration of designs. To reduce these emerging constraints, multiple efforts are being launched toward designing an ML-based surrogate model that estimates resource usage of synthesized accelerator architectures. This model would reduce the design iteration time, especially when designing within a set of given hardware constraints. This approach shows considerable potential, but as it stands, the effort is early and would benefit from coordination and standardization to assist future work as it emerges. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of more than 100,000 fully connected neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. In addition to the resource utilization and latency data provided, the dataset includes generated artifacts and log files for many of the synthesized neural networks, in order to support future research in ML-based code generation. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, as well as the average performance across a subset of the dataset. We measure the performance of a given predictor model through multiple metrics, including $R^2$ score and SMAPE on regression tasks, as well as inference time to further characterize the estimator under test. Additionally, we introduce the latency/utilization inference graph neural network (lui-gnn), a surrogate model that uses a graph neural network to represent input architectures in the form of a directed graph. This graph representation allows for a diverse set of model architectures to all be effectively handled by a surrogate model. We present the architecture and performance of the model, as evaluated by the new proposed benchmark, including SMAPE, $R^2$ score, and inference times, and find that lui-gnn generally predicts latency and utilization for the 75\% quantile within several percent of the synthesized resources on the synthetic test dataset, indicating that this approach of estimating resource and latency via a surrogate models has promise and warrants further research.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation

As machine learning (ML) is increasingly implemented in hardware to address real-time challenges in scientific applications, the development of advanced toolchains has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as hardware synthesis, are becoming limiting factors in the rapid iteration of designs. To mitigate these emerging constraints, multipleefforts have been undertaken to develop an ML-based surrogate model that estimates resource usage of synthesized ML accelerator architectures. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of over 680 000 fully connected and convolutional neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, and the average performance across a subset of the dataset. Additionally, we introduce GNN- and transformer-based surrogate models that predict latency and resources for ML accelerators. We present the architecture and performance of the models and find that the models generally predict latency and resources for the 75% percentile within several percent of the synthesized resources on the synthetic test dataset.

Hawks, Benjamin G. [Fermilab]↗

DOE OSTI2025

Design of Digital Acquisition for Beam Current Monitor

As a part of the Proton Improvement Plan II (PIP-II) at Fermilab, instrumentation systems are being modernized to take advantage of the higher speeds and ease of use offered by standardized embedded systems like MicroTCA. A rear-transition module (RTM) is being designed to interface with said embedded systems. In each of the four identical channels on the RTM, the differential signal from an alternating-current current transformer (ACCT) transimpedance amplifier will again be amplified by a differential operation-amplifier, then filtered by a low-pass topology. The conditioned signal is then digitized at a maximum of 10MS/s by an analog to digital converter (ADC) integrated circuit. After digitization, the ADC passes the data to an off the shelf AdvancedMC (AMC) Xilinx FPGA module using low voltage differential signals. This paper will describe the simulation of analog circuitry for signal conditioning, simulation of digital signal integrity based on physical design as well as verification of design characteristics critical to signal integrity. This work aims to create a methodology that can be applied to future RTMs requiring application of high-speed digital design principles.

White, Turner [Fermilab] (ORCID:0009000348159256)↗

DOE OSTI2025

Development of BPM Electronics for PIP-II at Fermilab

This paper presents the uTCA4.0-based BPM electronics for PIP-II, featuring four 250 MSPS ADCs and a Xilinx UltraScale+ MPSoC FPGA with 10 GbE uplink. Design elements include signal conditioning, clock, and thermal management. The FPGA performs signal processing, time tagging, digital down-conversion, and phase drift compensation. Position and phase resolution, and thermal stability is validated through dedicated testing.

Liu, Shengli [Fermilab] (ORCID:0009000128436936)↗

DOE OSTI2026

White-Rabbit-Disciplined FPGA Readout for Fermilab Timing Events

Fermilab's accelerator timing links broadcast short event codes to thousands of devices at once, but the links themselves carry no absolute notion of time; that comes separately from a White Rabbit reference. This work builds the piece that ties the two together on a single board. On a Xilinx Kria KR260 (Zynq UltraScale+), the programmable logic decodes a real Fermilab TCLK link, stamps every event with an absolute White-Rabbit \{sec, ns\} UTC time, and reads the timestamped stream out over AXI4-Lite; a thin Linux process on the same die publishes each event into a Redis stream on the control network. To exercise the full chain on one board, the decoded events are re-encoded as gigabit ACLK, transmitted out an SFP+ optical port, looped back over a short fiber jumper, and decoded again on the same timeline, and are additionally mirrored as an ACLK-Lite Manchester waveform for benchtop probing. Across sustained, multi-day testing against real Fermilab TCLK, the pipeline has decoded, timestamped, and published hundreds of millions of events with practically zero loss, and folding the timestamped stream on the 60-second accelerator supercycle recovers the machine's periodic structure directly from the published data.

Rossel, Jacob [Fermilab; UC, Berkeley (main)] (ORC↗

DOE OSTI2025

Development of BPM electronics for PIP-II at Fermilab

Liu, Shengli [Fermilab] (ORCID:0009000128436936)↗