Search NASA⌕ Search

SEARCH · Search NASA

Results for “HLS”

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 19 records

Young's modulus and SEM analysis of leg bones exposed to simulated microgravity by hind limb suspension (HLS)

The aim of this study was to determine composition of the leg bone tissue of rats that were exposed to simulated microgravity by Hind-Limb Suspension (HLS) by tail for one week. The leg bones were cross sectioned, cleaned of soft tissues, dried and sputter coated, and then placed horizontally on the stage of a Scanning Electron Microscope (SEM) for analysis. Interaction of a 17.5 keV electron beam, incident from the vertical direction on the sample, generated images using two detectors. X-rays emitted from the sample during electron bombardment were measured with an Energy Dispersive Spectroscopy (EDS) feature of SEM using a liquid-nitrogen cooled Si(Li) detector with a resolution of 144 eV at 5.9 keV ({sub 25}Mn K{sub {alpha}} x-ray). K{sub {alpha}}- x-rays from carbon, oxygen, phosphorus and calcium formed the major peaks in the spectrum. Relative percentages of these elements were determined using a software that could also correct for ZAF factors namely Z(atomic number), A(X-ray absorption) and F(characteristic fluorescence). The x-rays from the control groups and from the experimental (HLS) groups were analyzed on well-defined parts (femur, tibia and knee) of the leg bone. The SEM analysis shows that there are definite changes in the hydroxyl or phosphate group of the main component of the bone structure, hydroxyapatite [Ca{sub 10}(PO{sub 4}){sub 6}(OH){sub 2}], due to hind limb suspension. In a separate experiment, entire leg bones (both from HLS and control rats) were subjected to mechanical stress by mean of a variable force. The stress vs. strain graph was fitted with linear and polynomial function, and the parameters reflecting the mechanical strength of the bone, under increasing stress, were calculated. From the slope of the linear part of the graph the Young's modulus for HLS bones were calculated and found to be 2.49 times smaller than those for control bones.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Horn Location Sensors (HLS) for LBNF

The Long-Baseline Neutrino Facility (LBNF) will deliver the world's most powerful muon neutrino beam to the Deep Underground Neutrino Experiment (DUNE), initially operating at 1.2 MW and upgradeable to 2.4 MW. Ensuring the accurate direction of this beam is critical for DUNE's precision goals. This talk introduces the Horn Location Sensors (HLS) system, designed to provide precise, relative measurements of the focusing horns, targets, and beam position monitors in the neutrino beamline. The HLS system employs high-precision FSI-based hydrostatic leveling sensors to track vertical motion and tilt, achieving precision on the order of 0.1 mm. Built for minimal maintenance in radioactive environments, the HLS system ensures precise alignment of beamline components during high-power operations. This system is essential for maintaining beam accuracy and enhancing DUNE's scientific performance.

43 PARTICLE ACCELERATORS↗

Classification of Wetland Vegetation Based on NDVI Time Series from the HLS Dataset

Natural wetlands are intrinsically heterogeneous and typically composed of a mosaic of ecosystem patches with different vegetation types. Hydrological and biogeochemical processes in wetlands vary strongly among these ecosystem patches. To date, most remote sensing classification approaches for wetland vegetation either rely on coarse images that cannot capture the spatial variability of wetland vegetation or rely on very-high-resolution multi-spectral images that are detailed but very sporadic in time (less than once per year). This study aimed to use NDVI time series, generated from NASA’s HLS dataset, to classify vegetation patches. We demonstrate our approach at a temperate, coastal lake, estuarine marsh. To classify vegetation patches, a standard time series library of the four land-cover patch types was built from referencing specific locations that were identified as “pure” pixels. These were identified using a single-time high-resolution image. We calculated the distance between the HLS-NDVI time series at each pixel and the “pure”-pixel standards for each land-cover type. The resulting true-positive classified rate was >73% for all patch types other than water lily. The classification accuracy was higher in pixels of a more uniform composition. A set of vegetation maps was created for the years 2016 to 2020 at our research site to identify the vegetation changes at the site as it is affected by rapid water elevation increases in Lake Erie. Our results reveal how changes in water elevation have changed the patch distribution in significant ways, leading to the local extinction of cattail by 2019 and a continuous increase in the area cover of water lily patches.

54 ENVIRONMENTAL SCIENCES↗

Measurement and Compensation of BPM Chamber Motion in HLS

Significant horizontal drifts in the beam orbit in the storage ring of HLS (Hefei Light Source) have been seen for many years. What leads to the motion of Beam Position Monitor (BPM) chamber is thermal expansion mainly caused by the synchrotron light. To monitor the BPM chamber motions for all BPMs, a BPM chamber motion measurement system is built in real-time. The raster gauges are used to measure the displacements. The results distinctly show the relation between the BPM chamber motion and the beam current. To suppress the effect of BPM chamber motion, a compensation strategy is implemented at HLS. The horizontal drifts of beam orbit have been really suppressed within 20{mu}m without the compensation of BPM chamber motion in the runtime.

43 PARTICLE ACCELERATORS↗

Multiscale assessment of land surface phenology from harmonized Landsat 8 and Sentinel-2, PlanetScope, and PhenoCam imagery

As the spatial and temporal resolution of remotely sensed imagery has improved over the last four decades, algorithms for monitoring and mapping seasonal changes in surface properties have evolved rapidly. Most recently, the availability of daily PlanetScope imagery has created new opportunities for monitoring the land surface phenology (LSP) of terrestrial ecosystems at high spatial resolution. However, the quality and value of LSP information from PlanetScope imagery have not been systematically examined. In this paper, we evaluate the character and quality of LSP information derived from PlanetScope by comparing time series of vegetation indices and LSP metrics from PlanetScope to corresponding time series and LSP metrics derived from Harmonized Landsat 8 and Sentinel-2 (HLS) imagery and PhenoCams at six sites that span a diverse range of land cover types and climate. Results show that vegetation index time series from all three data sources show high temporal correlation, and LSP metrics derived from HLS, PlanetScope, and PhenoCam show high agreement with negligible bias. Semi-variograms for phenometrics estimated from PlanetScope imagery indicate that the majority of spatial variance captured in PlanetScope phenometrics occurs well below the spatial resolution HLS imagery. At the same time, LSP metrics from HLS are most strongly correlated with the 50–75% quantiles of 3 m LSP metrics from PlanetScope. This indicates that HLS captures the average phenology at sub-pixel scale captured in PlanetScope imagery. Here, our results represent the first comprehensive comparison of LSP metrics estimated from PlanetScope and publicly available moderate spatial resolution imagery, and provide insights regarding: (1) the quality and character of LSP metrics derived from HLS and PlanetScope; and (2) the relative merits and trade-offs associated with the use of each data source for LSP studies.

54 ENVIRONMENTAL SCIENCES↗

Intelligent Experiments through Real-Time AI: Fast Data Processing and Autonomous Detector Control for High-Energy Nuclear Experiments

The aim of this project is to develop software and hardware for fast real-time data processing and autonomous detector control and calibration for the sPHENIX and the future EIC experiments. Below summarizes Georgia Tech team efforts in the past year: 1. We developed a real-time clustering algorithm and FPGA-based pipeline architecture for processing fired pixel data from ALPIDE sensors in sPHENIX experiments. Our Columnar Clustering Co-Design introduces a hardware-aware, stream-friendly approach that segments pixel data by column pairs using a Column Pair Clustering (CPC) strategy, followed by Cluster Stitching to merge adjacent subclusters. Implemented in Vitis HLS, the pipeline comprises five stages—read-in, subclustering, stitching, analysis, and write-out—connected by tagged HLS streams with custom end-of-event signaling for robust synchronization. We designed a pipelined dataflow model optimized for throughput, low latency, and minimal buffering, enabling scalable clustering across events of arbitrary size. Our system maintains spatial precision via center-of-mass and shape key extraction and efficiently handles edge cases such as fragmented or nested clusters. Compared against DBSCAN in both software and hardware, our approach demonstrates competitive performance under FPGA constraints. 2. We also conducted a comprehensive algorithm-to-hardware co-design of connected component analysis tailored for sPHENIX experiments, focusing on real-time, low-latency processing using FPGAs and High-Level Synthesis (HLS). Starting from a Python-based particle tracking pipeline, the team translated the core logic—graph traversal via DFS and Union-Find—into an HLS-compatible C++ model, replacing dynamic memory and recursion with static arrays and pipelined control flow. The final design includes a fully streamed and dataflow-compatible Union-Find kernel optimized across five iterations, incorporating loop pipelining, array partitioning, AXI/FIFO interface tuning, and function flattening. Experimental results show up to 14.8× speedup over the CPU baseline, reducing per-graph latency to 1.58 μs and demonstrating strong resource efficiency with only ~7k LUTs and zero BRAM usage. The design maintains functional correctness against the Python reference using a Python-based C-simulation framework and Mean Squared Error metrics. This work validates the potential of HLS-driven FPGA designs for edge-level HEP data acquisition, laying a scalable foundation for future integration with real-time detector pipelines and multi-graph processing systems.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

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.

FOS: Computer and information sciences↗

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↗

Inter-Procedural Resource Sharing in High Level Synthesis through Function Proxies

Modular design is becoming increasingly important in High Level Synthesis (HLS) flows. Current HLS flows generate hierarchical and modular designs that mimic the structure and call graph of input specification translating functions into modules. Function calls are translated instantiating the callee module in the data-path of its caller, allowing for resource sharing when the same function is called multiple times. However, if two different callers invoke the same function, current HLS flows cannot share the instance of the module between the two callers, even if they invoke the function in a mutually exclusive way. In this paper, we propose a methodology that enables sharing of (sub)modules across modules boundaries. Sharing is obtained through function proxies, which act as forwarders of function calls in the original specification to shared modules without adding performance penalties. Building on the concept of function proxies, we propose a methodology and the related components to perform HLS of function calls through function pointers, without requiring complete static knowledge of the alias set (point-to set). We show that module sharing through function proxies provides valuable area savings without significant impacts on the execution delays, and that our synthesis approach for function pointers enables dynamic polymorphism.

HLS, function proxy, FPGA, modular HLS,↗

MLIR loop optimizations for High-Level Synthesis: a case study

High-Level Synthesis (HLS) tools simplify the design of hardware accelerators by automatically generating Verilog/VHDL code starting from a general purpose software programming language. They include a wide range of optimization techniques in the process, most of them performed on a low-level intermediate representation (IR) of the code. Introducing optimizations on a higher level of abstraction could significantly contribute to the automated design process results; for example, polyhedral techniques for the manipulation of loops could have a significant impact on the generated accelerators when applied on a specialized IR. We use loop pipelining as a case study to explore the introduction of compiler-based transformations on top of an existing HLS process. We leverage the Multi-Level Intermediate Representation (MLIR) framework and an external scheduler to implement the required transformations, and couple them with existing HLS tools to evaluate the improvements that loop pipelining brings to the performance of generated accelerators. The proposed approach can be integrated with other high-level transformations on the MLIR representation, combining different techniques to obtain pre-optimized inputs for HLS that do not have to rely on a specific backend tool.

Curzel, Serena↗

Evaluation of the FIR Example using Xilinx Vivado High-Level Synthesis Compiler

Compared to central processing units (CPUs) and graphics processing units (GPUs), field programmable gate arrays (FPGAs) have major advantages in reconfigurability and performance achieved per watt. This development flow has been augmented with high-level synthesis (HLS) flow that can convert programs written in a high-level programming language to Hardware Description Language (HDL). Using high-level programming languages such as C, C++, and OpenCL for FPGA-based development could allow software developers, who have little FPGA knowledge, to take advantage of the FPGA-based application acceleration. This improves developer productivity and makes the FPGA-based acceleration accessible to hardware and software developers. Xilinx Vivado HLS compiler is a high-level synthesis tool that enables C, C++ and System C specification to be directly targeted into Xilinx FPGAs without the need to create RTL manually. The white paper [1] published recently by Xilinx uses a finite impulse response (FIR) example to demonstrate the variable-precision features in the Vivado HLS compiler and the resource and power benefits of converting floating point to fixed point for a design. To get a better understanding of variable-precision features in terms of resource usage and performance, this report presents the experimental results of evaluating the FIR example using Vivado HLS 2017.1 and a Kintex Ultrascale FPGA. In addition, we evaluated the half-precision floating-point data type against the double-precision and single-precision data type and present the detailed results.

97 MATHEMATICS AND COMPUTING↗

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗

Horn Location Sensors for LBNF

The Horn Location Sensor (HLS) system—named for the magnetic focusing horns it monitors, along with other critical beamline elements – is a high-precision alignment system developed for the Long-Baseline Neutrino Facility (LBNF) to support the Deep Underground Neutrino Experiment (DUNE). With minimal maintenance, the HLS can operate reliably in environments with high radiation, and it ensures that key components such as the protective baffle, focusing horns, and beam position monitors are aligned correctly – each essential for maintaining one of the world’s most intense muon-neutrino beams. A high-precision hydrostatic level sensor, a linear variable differential transformer, and INVAR rods are all used in the system to monitor vertical motion and tilt with sub-millimeter accuracy. A novel Sweep Tracker interferometer enhances calibration fidelity by correcting for non-linearities in laser wavelength and scan rate in real time. A critical part of DUNE’s precision alignment and flux prediction requirements, the HLS system initially supports beam power of up to 1.2 MW and can be upgraded to 2.4 MW.

Frequency scanning interferometry↗

Strong, ductile, and hierarchical hetero-lamellar-structured alloys through microstructural inheritance and refinement

The strength−ductility trade-off exists ubiquitously, especially in brittle intermetallic-containing multiple principal element alloys (MPEAs), where the intermetallic phases often induce premature failure leading to severe ductility reduction. Hierarchical heterogeneities represent a promising microstructural solution to achieve simultaneous strength−ductility enhancement. However, it remains fundamentally challenging to tailor hierarchical heterostructures using conventional methods, which often rely on costly and time-consuming processing. Here, we report a multiscale microstructural inheritance and refinement strategy to process “structural hierarchy precursors” in as-cast heterogeneous Al 0.7 CoCrFeNi MPEAs, which lead directly to a hierarchical hetero-lamellar structure (HLS) after simple rolling and annealing. Interestingly, it takes only 10 min of annealing time, two orders of magnitude less than that required to render the state-of-the-art properties during conventional processing of Al 0.7 CoCrFeNi, for us to achieve record-high strength−ductility combinations via the hierarchical HLS design that sequentially stimulates multiple unusual deformation and reinforcement mechanisms. In particular, the HLS-enabled high hetero-deformation-induced (HDI) internal stress triggers profuse <111>-type dislocations on over five independent slip systems in the supposedly brittle intermetallic phase and activates extensive stacking faults (SFs) and nanotwinning in the adjoining soft phase with a rather high SF energy. These unexpected, dynamically reinforcing hetero-deformation mechanisms across multiple length scales facilitate high sustained HDI strain hardening, along with a salient microcrack-mediated extrinsic ductilization effect, suggesting that the proposed microstructural inheritance and refinement strategy provides an efficient, fast, and low-cost approach to overcome the strength−ductility trade-off in a broad range of structural materials.

Science & Technology - Other Topics↗

Effective Lagrangian for low-scale technicolor

We present an effective Lagrangian for low-scale technicolor. It describes the interactions at energies < or approx. M{sub {rho}{sub T}} of the lowest-lying bound states of the lightest technifermion doublet--the spin-one {rho}{sub T}, {omega}{sub T}, a{sub T}, f{sub T}, and the corresponding technipions {pi}{sub T}. This Lagrangian is intended to put on firmer ground the technicolor straw man phenomenology used for collider searches of low-scale technicolor. The technivectors are described using the hidden local symmetry (HLS) formalism of Bando, et al. The Lagrangian is based on SU(2) x U(1) x U(2){sub L} x U(2){sub R}, where SU(2) x U(1) is the electroweak gauge group and U(2){sub L} x U(2){sub R} is the HLS gauge group. Special attention is paid to the higher-derivative standard HLS and Wess-Zumino-Witten interactions needed to describe radiative and other decays of a{sub T} and {rho}{sub T}/{omega}{sub T}, respectively.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Extending High-Level Synthesis with AI/ML Methods

Artificial Intelligence (AI) and Machine Learning (ML) methods provide significant opportunities of improving quality of results when performing high-level synthesis (HLS). For example, they can be used to model and predict metrics of the final design (e.g., area, considering aspects such as interconnect overhead for different device technologies), facilitating exploration when searching for the best design trade-offs. They can also enable identifying hidden correlations across the various phases of the synthesis and the various optimizations performed, identifying the most effective pipelines. Finally, in more general terms, bio-inspired heuristic algorithms can improve the design space exploration for the synthesis process in terms of time and quality of the result. This paper discusses opportunities and challenges to augment HLS with AI/ML using as example flow the SODA Synthesizer, an open-source hardware generation toolchain which includes SODA-OPT, a hardware/software partitioning and pre-optimization tool developed with the MLIR framework, and PandA-Bambu, a state-of-the art HLS tool. SODA interfaces with OpenROAD to provide a complete end-to-end toolchain.

artificial intelligence↗