Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “hardware accelerators”

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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
NASA NTRS2013

Scheduling Operations for Massive Heterogeneous Clusters

High-performance computing (HPC) programming has become increasingly difficult with the advent of hybrid supercomputers consisting of multicore CPUs and accelerator boards such as the GPU. Manual tuning of software to achieve high performance on this type of machine has been performed by programmers. This is needlessly difficult and prone to being invalidated by new hardware, new software, or changes in the underlying code. A system was developed for task-based representation of programs, which when coupled with a scheduler and runtime system, allows for many benefits, including higher performance and utilization of computational resources, easier programming and porting, and adaptations of code during runtime. The system consists of a method of representing computer algorithms as a series of data-dependent tasks. The series forms a graph, which can be scheduled for execution on many nodes of a supercomputer efficiently by a computer algorithm. The schedule is executed by a dispatch component, which is tailored to understand all of the hardware types that may be available within the system. The scheduler is informed by a cluster mapping tool, which generates a topology of available resources and their strengths and communication costs. Software is decoupled from its hardware, which aids in porting to future architectures. A computer algorithm schedules all operations, which for systems of high complexity (i.e., most NASA codes), cannot be performed optimally by a human. The system aids in reducing repetitive code, such as communication code, and aids in the reduction of redundant code across projects. It adds new features to code automatically, such as recovering from a lost node or the ability to modify the code while running. In this project, the innovators at the time of this reporting intend to develop two distinct technologies that build upon each other and both of which serve as building blocks for more efficient HPC usage. First is the scheduling and dynamic execution framework, and the second is scalable linear algebra libraries that are built directly on the former.

Humphrey, John↗
NASA NTRS2019

Overview of NASA's Solar Electric Propulsion Project

NASA is continuing to develop and qualify a state of the art 13 kW-class Advanced Electric Propulsion System (AEPS) for NASA exploration missions through a contract with Aerojet Rocketdyne (AR). An objective of the AEPS project is accelerate the adoption of high power electric propulsion technologies by reducing the risk and uncertainty of integrating Solar Electric Propulsion (SEP) technologies into space flight systems. NASA and AR have recently initiated testing of engineering hardware including the Hall Current Thruster (HCT), Power Processing Unit (PPU), and Xenon Flow Controller (XFC) at both the component and system levels. The successful completion of these tests will provide the required information to advance the AEPS system towards Critical Design Review. In support of the AEPS contract, NASA and JPL have been performing risk reduction activities to address specific concerns of this higher power Hall thruster propulsion system. These risk reduction activities have included long duration wear testing of the Technology Demonstration Unit (TDU) Hall thruster and cathode hardware, thermal cycling of TDU cathode heaters and coils, plasma plume measurements, and performed early circuit testing of the AEPS PPU design. In addition to the propulsion system development, the SEP project is developing the Plasma Diagnostic Package (PDP) and the SEP Testbed. The PDP is designed for use in conjunction with a high-powered electric propulsion (EP) system to characterize in-space operation. The SEP Testbed system is being developed to demonstrate integrated SEP system performance. The paper presents an overview of the NASA and the AEPS contract activities and a summary of the associated NASA in-house activities.

Plasma diagnostics package↗
NASA NTRS1991

Reusable Reentry Satellite (RRS) system design study

The Reusable Reentry Satellite (RRS) is intended to provide investigators in several biological disciplines with a relatively inexpensive method to access space for up to 60 days with eventual recovery on Earth. The RRS will permit totally intact, relatively soft, recovery of the vehicle, system refurbishment, and reflight with new and varied payloads. The RRS is to be capable of three reflights per year over a 10-year program lifetime. The RRS vehicle will have a large and readily accessible volume near the vehicle center of gravity for the Payload Module (PM) containing the experiment hardware. The vehicle is configured to permit the experimenter late access to the PM prior to launch and rapid access following recovery. The RRS will operate in one of two modes: (1) as a free-flying spacecraft in orbit, and will be allowed to drift in attitude to provide an acceleration environment of less than 10(exp -5) g. the acceleration environment during orbital trim maneuvers will be less than 10(exp -3) g; and (2) as an artificial gravity system which spins at controlled rates to provide an artificial gravity of up to 1.5 Earth g. The RRS system will be designed to be rugged, easily maintained, and economically refurbishable for the next flight. Some systems may be designed to be replaced rather than refurbished, if cost effective and capable of meeting the specified turnaround time. The minimum time between recovery and reflight will be approximately 60 days. The PMs will be designed to be relatively autonomous, with experiments that require few commands and limited telemetry. Mass data storage will be accommodated in the PM. The hardware development and implementation phase is currently expected to start in 1991 with a first launch in late 1993.

Source record↗
NASA NTRSDate not supplied

An Agile-Like Approach to Hardware Development: The Ejectable Data Recorder (EDR) for Orion's Ascent Abort 2 (AA-2) Test Flight

On July 2, 2019, the Ascent Abort 2 (AA-2) Flight Test Vehicle was launched from Cape Canaveral, with the goal of demonstrating the performance of Orion’s Launch Abort System (LAS) and collecting data from hundreds of sensors throughout the vehicle. The data collected during this test flight is of paramount importance, as it will be used to certify the Orion vehicle for human spaceflight. Originally, the data was to be downlinked via a single string network of antennas on the LAS, with the associated risk of potential data dropouts, as well as loss of data once the LAS was jettisoned. Thus, additional antennas were added onto the crew module (CM) to support data downlink post-LAS jettison, a buffer rebroadcast capability was added to fill in any gaps in data downlink transmissions, and an ejectable data recorder (EDR) subsystem was added to the CM as a redundant measure to collect all the instrumentation data. The EDR subsystem was added to the project about one year after the project commenced, which significantly reduced the available development time when compared with the other subsystems of the AA-2 Test Flight. The project was further accelerated by six months, around the critical design review gate. Due to the schedule compression challenge and the fact that the EDR subsystem was a backup system and not flight critical, the EDR subsystem was further challenged to find a new and more efficient way to develop hardware. Thus, the EDR subsystem experimented with different management and systems engineering processes, team sizes, communication methods, and tools. Some examples are novel uses of SharePoint as a Data-centric Project Management & Systems Engineering environment, a continuous testing approach through the lifecycle, and a Skunkworks approach to managing the team. The EDR subsystem blended Commercial Off The Shelf (COTS) hardware with in-house developed hardware and software to create a novel data retrieval capability. The capability evolved rapidly through a hardware in the loop simulation environment that enabled incremental component updates for not only the EDR subsystem but across the entire Crew Module. This paper will present an overview of how the EDR subsystem was managed and compare it to an Agile approach to managing projects. The paper will further provide a recommended approach to future Agile-like hardware development that incorporates lessons learned from the EDR experience.

Agile↗
DOE OSTI2021

Anomaly Detection in Accelerator Facilities Using Machine Learning

Synchrotron light sources are user facilities and usually run about 5000 hours per year to support many beamlines operations in parallel. Reliability is a key parameter to evaluate machine performance. Even many facilities have achieved >95% beam reliability, there are still many hours of unscheduled downtime and every hour lost is a waste of operation costs along with a big impact on individual scheduled user experiments. Preventive maintenance on subsystems and quick recovery from machine trips are the basic strategies to achieve high reliability, which heavily depends on experts’ dedication. Recently, SLAC, APS, and NSLS-II collaborated to develop machine-learning-based approaches aiming to solve both situations, hardware failure prediction and machine failure diagnosis to find the root sources. In this paper, we report our facility operation status, development progress, and plans.

Accelerator Physics↗
DOE OSTI2021

Measurement and analysis of GPU-accelerated applications with HPCToolkit

To address the challenge of performance analysis on the US DOE’s forthcoming exascale supercomputers, Rice University has been extending its HPCToolkit performance tools to support measurement and analysis of GPU-accelerated applications. To help developers understand the performance of accelerated applications as a whole, HPCToolkit’s measurement and analysis tools attribute metrics to calling contexts that span both CPUs and GPUs. To measure GPU-accelerated applications efficiently, HPCToolkit employs a novel wait-free data structure to coordinate monitoring and attribution of GPU performance. To help developers understand the performance of complex GPU code generated from high-level programming models, HPCToolkit constructs sophisticated approximations of call path profiles for GPU computations. To support fine-grained analysis and tuning, HPCToolkit uses PC sampling and instrumentation to measure and attribute GPU performance metrics to source lines, loops, and inlined code. To supplement fine-grained measurements, HPCToolkit can measure GPU kernel executions using hardware performance counters. To provide a view of how an execution evolves over time, HPCToolkit can collect, analyze, and visualize call path traces within and across nodes. Finally, on NVIDIA GPUs, HPCToolkit can derive and attribute a collection of useful performance metrics based on measurements using GPU PC samples. Here, we illustrate HPCToolkit’s new capabilities for analyzing GPU-accelerated applications with several codes developed as part of the Exascale Computing Project.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2001

Hubble Space Telescope Servicing Mission 3A Rendezvous Operations

The Hubble Space Telescope (HST) hardware complement includes six gas bearing, pulse rebalanced rate integrating gyros, any three of which are sufficient to conduct the science mission. After the loss of three gyros between April 1997 and April 1999 due to a known corrosion mechanism, NASA decided to split the third HST servicing mission into SM3A, accelerated to October 1999, and SM3B, scheduled for November 2001. SM3A was developed as a quick turnaround 'Launch on Need' mission to replace all six gyros. Loss of a fourth gyro in November 1999 caused HST to enter Zero Gyro Sunpoint (ZGSP) safemode, which uses sun sensors and magnetometers for attitude determination and momentum bias to maintain attitude stability during orbit night. Several instances of large attitude excursions during orbit night were observed, but ZGSP performance was adequate to provide power-positive sun pointing and to support low gain antenna communications. Body rates in ZGSP were estimated to exceed the nominal 0.1 deg/sec rendezvous limit, so rendezvous operations were restructured to utilize coarse, limited life, Retrieval Mode Gyros (RMGs) under Hardware Sunpoint (HWSP) safemode. Contingency procedures were developed to conduct the rendezvous in ZGSP in the event of RMGA or HWSP computer failure. Space Shuttle Mission STS-103 launched on December 19, 1999 after a series of weather and Shuttle-related delays. After successful rendezvous and grapple under HWSP/RMGA, the crew changed out all six gyros. Following deploy and systems checkout, HST returned to full science operations.

Lee, S.↗
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

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]↗
NASA NTRS1999

Aerospace Safety Advisory Panel

This report covers the activities of the Aerospace Safety Advisory Panel (ASAP) for calendar year 1998-a year of sharp contrasts and significant successes at NASA. The year opened with the announcement of large workforce cutbacks. The slip in the schedule for launching the International Space Station (ISS) created a five-month hiatus in Space Shuttle launches. This slack period ended with the successful and highly publicized launch of the STS-95 mission. As the year closed, ISS assembly began with the successful orbiting and joining of the Functional Cargo Block (FGB), Zarya, from Russia and the Unity Node from the United States. Throughout the year, the Panel maintained its scrutiny of NASA's safety processes. Of particular interest were the potential effects on safety of workforce reductions and the continued transition of functions to the Space Flight Operations Contractor. Attention was also given to the risk management plans of the Aero-Space Technology programs, including the X-33, X-34, and X-38. Overall, the Panel concluded that safety is well served for the present. The picture is not as clear for the future. Cutbacks have limited the depth of talent available. In many cases, technical specialties are 'one deep.' The extended hiring freeze has resulted in an older workforce that will inevitably suffer significant departures from retirements in the near future. The resulting 'brain drain' could represent a future safety risk unless appropriate succession planning is started expeditiously. This and other topics are covered in the section addressing workforce. The major NASA programs are also limited in their ability to plan property for the future. This is of particular concern for the Space Shuttle and ISS because these programs are scheduled to operate well into the next century. In the case of the Space Shuttle, beneficial and mandatory safety and operational upgrades are being delayed because of a lack of sufficient present funding. Likewise, the ISS has little flexibility to begin long lead-time items for upgrades or contingency planning. For example, the section on computer hardware and software contains specific findings related to required longer range safety-related actions. NASA can be proud of its accomplishments this past year, but must remain ever vigilant, particularly as ISS assembly begins to accelerate. The Panel will continue to focus on both the short- and long-term aspects of risk management and safety planning. This task continues to be made manageable and productive by the excellent cooperation the Panel receives from both NASA and its contractors. Particular emphasis will continue to be directed to longer term workforce and program planning issues as well as the immediate risks associated with ISS assembly and the initial flights of the X-33 and X-34. Section 2 of this report presents specific findings and recommendations generated by ASAP activities during 1998. Section 3 contains more detailed information in support of these findings and recommendations. Appendix A is a current roster of Panel members, consultants, and staff. Appendix B contains NASA's response to the findings and recommendations from the 1997 ASAP Annual Report. Appendix C details the fact-finding activities of the Panel in 1998. During the year, Mr. Richard D. Blomberg was elected chair of the Panel and Vice Admiral (VADM) Robert F Dunn was elected deputy chair. VADM Bernard M. Kauderer moved from consultant to member. Mr. Charles J. Donlan retired from the Panel after many years of meritorious service. Ms. Shirley C. McCarty and Mr. Robert L. ('Hoot') Gibson joined the Panel as consultants.

Source record↗
NASA NTRS2026

NASA JSC’s Simulant Development Lab Capabilities and Artemis Testing

The Simulant Development Lab (SDL) is a multifunctional collaborative workspace that supports the development, curation, analysis, testing, and distribution of planetary regolith simulants – including lunar, Martian, asteroidal, and other granular materials. The lab provides a multidisciplinary setting for scientific characterization of simulant physical properties and for engineering evaluations conducted with simulant test beds. To enable this work, the SDL curates and maintains a stock of more than 35 metric tons of simulant material. To evaluate these materials and support testing goals, the lab is equipped with a comprehensive suite of processing tools and analytical instruments. These capabilities enable the SDL’s mission at NASA’s Johnson Space Center to distribute, develop, process, characterize, and test regolith simulants for mission relevant applications. Through controlled and repeatable testing environments that replicate the physical and compositional properties of lunar regolith, the SDL supports Artemis hardware maturation, providing safe, Earth‑based analogs for evaluating systems that must withstand regolith dust interactions, physical wear and abrasion, and operational loads. The facility’s extensive simulant inventory and integrated geological and engineering test infrastructure accelerate technology readiness for Artemis and future exploration campaigns (e.g., future crewed or robotic missions to Mars).

Simulant Development Lab↗
NASA NTRS2004

Accelerated Training at Mach 20: A Brief Communication Submitted from the International Space Station

The performance of complex tasks on the International Space Station (ISS) requires significant preflight crew training commitments and frequent skill and knowledge refreshment. This report documents a recently developed just-in-time training methodology, which integrates preflight hardware familiarization and procedure training with an on-orbit CD-ROM-based skill enhancement. This just-in-time concept was used to support real-time remote expert guidance to complete medical examinations using the ISS Human Research Facility (HRF). An American and Russian ISS crewmember received 2-hours of hands on ultrasound training 8 months prior to the on-orbit ultrasound exam. A CD-ROM-based Onboard Proficiency Enhancement (OPE) interactive multimedia program consisting of memory enhancing tutorials, and skill testing exercises, was completed by the crewmember six days prior to the on-orbit ultrasound exam. The crewmember was then remotely guided through a thoracic, vascular, and echocardiographic examination by ultrasound imaging experts. Results of the CD ROM based OPE session were used to modify the instructions during a complete 35 minute real-time thoracic, cardiac, and carotid/jugular ultrasound study. Following commands from the ground-based expert, the crewmember acquired all target views and images without difficulty. The anatomical content and fidelity of ultrasound video were excellent and adequate for clinical decision-making. Complex ultrasound experiments with expert guidance were performed with high accuracy following limited pre-flight training and CD-ROM-based in-flight review, despite a 2-second communication latency. In-flight application of multimedia proficiency enhancement software, coupled with real-time remote expert guidance, can facilitate the performance of complex demanding tasks.

Foale, C. Michael↗
DOE OSTI2025

Introduction: Neuromorphic Materials

The explosive growth in data collection and the need to process it efficiently, as well as the desire to automate increasingly complex tasks in transportation, medical care, manufacturing, security and many other fields have motivated a growing interest in neuromorphic computing. Unlike the binary, transistorbased ON/OFF logic gates and separate logic and memory functionalities employed in digital computing, neuromorphic computing is inspired by animal brains that use interconnected synapses and neurons to perform processing, storage and transmission of information at the same location, while only consuming ~20 W or less of power. Motivated by the brain’s efficiency, adaptability, self-learning and resiliency qualities, neuromorphic computing can be broadly defined as an approach to processing and storing information using hardware and algorithms inspired by models of biological neural systems. Present research in neuromorphic computing encompasses approaches that vary significantly in their degree of neuro-inspiration, from systems that only incorporate features such as asynchronous, event-driven operation or use crossbar arrays of non-volatile memory (NVM) elements to accelerate deep neural networks (DNNs), to designs that embrace the extreme parallelism, sparsity, reconfigurability, adaptability, complexity and stochasticity observed in nervous systems. The term ‘neuromorphic’ computing is often credited to Carver Mead, who in the 1980s investigated Si-based analog electronics to replicate functions of the animal retina. Earlier important advances in this field include the work of Frank Rosenblatt, who proposed the concept of the perceptron, Bernard Widrow, who used this concept to build one of the first analog neural networks, the Adaline and many other researchers (see ref. 6 for an historical perspective on neuromorphic computing). With the recent increase in the use of artificial intelligence and large language models, and rising concerns over the associated energy costs, interest in neuromorphic hardware has expanded rapidly. According to some estimates, driven largely by the drastic growth in the training use of artificial intelligence (AI) models using the current computing architectures, the energy cost of computing is projected to reach the energy supply worldwide by 2045. Furthermore, while this is not a realistic outcome, it means that, if more efficient computing technologies are not developed -- soon -- the world will soon become one where demand for energy and market constraints limit the continued increase of societal access to AI and cloud services from data centers. Data centers used for training and use of these models consume hundreds of terawatt hours of electricity, already past 4% of the US electricity demand.

Circuits↗
NASA NTRS2002

Life-Extending Control for Aircraft Engines Studied

Current aircraft engine controllers are designed and operated to provide both performance and stability margins. However, the standard method of operation results in significant wear and tear on the engine and negatively affects the on-wing life--the time between cycles when the engine must be physically removed from the aircraft for maintenance. The NASA Glenn Research Center and its industrial and academic partners have been working together toward a new control concept that will include engine life usage as part of the control function. The resulting controller will be able to significantly extend the engine's on-wing life with little or no impact on engine performance and operability. The new controller design will utilize damage models to estimate and mitigate the rate and overall accumulation of damage to critical engine parts. The control methods will also provide a means to assess tradeoffs between performance and structural durability on the basis of mission requirements and remaining engine life. Two life-extending control methodologies were studied to reduce the overall life-cycle cost of aircraft engines. The first methodology is to modify the baseline control logic to reduce the thermomechanical fatigue (TMF) damage of cooled stators during acceleration. To accomplish this, an innovative algorithm limits the low-speed rotor acceleration command when the engine has reached a threshold close to the requested thrust. This algorithm allows a significant reduction in TMF damage with only a very small increase in the rise time to reach the commanded rotor speed. The second methodology is to reduce stress rupture/creep damage to turbine blades and uncooled stators by incorporating an engine damage model into the flight mission. Overall operation cost is reduced by an optimization among the flight time, fuel consumption, and component damages. Recent efforts have focused on applying life-extending control technology to an existing commercial turbine engine, and doing so without modifying the hardware or adding sensors. This approach makes it possible to retrofit existing engines with life-extending control technology by changing only the control software in the full-authority digital engine controller (FADEC). The significant results include demonstrating a 20- to 30-percent reduction in TMF damage to the hot section by developing and implementing smart acceleration logic during takeoff. The tradeoff is an increase, from 5.0 to 5.2 sec, in the time required to reach maximum power from ground idle. On a typical flight profile of a cruise at Mach 0.8 at an altitude of 41,000 ft, and cruise time of 104 min, the optimized system showed that a reduction in cruise speed from Mach 0.8 to 0.79 can achieve an estimated 25-to 35-percent creep/rupture damage reduction in the engine's hot section and a fuel savings of 2.1 percent. The tradeoff is an increase in flight time of 1.3 percent (1.4 min).

Guo, Te-Huei↗
DOE OSTI2021

ArborX

ArborX library tackles a problem of efficiently finding geometric objects that are close in space. Variations of this problem, such as finding the nearest neighbors of a point, or finding all objects within a certain distance, are inherent components of applications in many fields. The data may be large so that solving the problem efficiently may require significant computational resources, such as multiple processors or accelerators such as general purpose GPUs. ArborX' main advantage in its ability to solve large problems efficiently utilizing a combination of distributed and on-node parallelism. ArborX can be run efficiently on a wide variety of hardware, including GPUs from different vendors, which distinguishes it from other available libraries which typically choose only few of these. The other advantage is that it supports both types of user problems: spatial problems (useful for intersections and finding objects within certain distance), and nearest neighbor problems. ArborX also supports flexible interface in its interaction with a user. Particularly, it allows a user to call user's own function on a positive match, a functionality not rarely available in other libraries. ArborX implements construction and traversal algorithms using efficient tree structures, such as bounding volume hierarchy (BVH). At its core, it uses linear BVH for its low construction cost and sufficient quality. ArborX is written using C++, and is parallelized using the message passing interface (MPI) for the distributed communication, and the Kokkos library for on-node parallelism. This approach allows ArborX to be run on a wide variety of hardware, from common laptops and desktops to supercomputers while using the same codebase. ArborX also implements several advanced algorithms using geometric search, such as density-based clustering algorithm DBSCAN.

ECP↗
DOE OSTI2025

ArborX 2.0

ArborX library tackles a problem of efficiently finding geometric objects that are close in space. Variations of this problem, such as finding the nearest neighbors of a point, or finding all objects within a certain distance, are inherent components of applications in many fields. The data may be large so that solving the problem efficiently may require significant computational resources, such as multiple processors or accelerators such as general purpose GPUs. ArborX' main advantage in its ability to solve large problems efficiently utilizing a combination of distributed and on-node parallelism. ArborX can be run efficiently on a wide variety of hardware, including GPUs from different vendors, which distinguishes it from other available libraries which typically choose only few of these. The other advantage is that it supports both types of user problems: spatial problems (useful for intersections and finding objects within certain distance), and nearest neighbor problems. ArborX also supports flexible interface in its interaction with a user. Particularly, it allows a user to call user's own function on a positive match, a functionality not rarely available in other libraries. ArborX implements construction and traversal algorithms using efficient tree structures, such as bounding volume hierarchy (BVH). At its core, ArborX uses linear BVH for its low construction cost and sufficient quality. ArborX implements both spatial and nearest-neighbor traversal algorithms. ArborX also provides several clustering algorithms (minimum spanning tree, DBSCAN, HDBSCAN*), interpolation using minimum least squares and ray tracing. ArborX is written using C++, and is parallelized using the message passing interface (MPI) for the distributed communication, and the Kokkos library for on-node parallelism. This approach allows ArborX to be run on a wide variety of hardware, from common laptops and desktops to supercomputers while using the same codebase.

Prokopenko, Andrey [Oak Ridge National Laboratory ↗
DOE OSTI2025

SpacelyProject/spacely-docs

Spacely is an open-source framework for the post-silicon validation of analog, digital, and mixed-signal ASICs (Application-Specific Integrated Circuits) which maximizes the reuse of hardware and software, reducing the time taken to achieve meaningful test results. Spacely specifically addresses the needs of small, flexible ASIC design teams commonly found in academia or research institutions. Spacely was originally developed at Fermi National Accelerator Laboratory.

Quinn, Adam [Fermi National Accelerator Laboratory↗
NASA NTRS1994

A method to determine the kinematics of the lower limbs of a subject pedaling a bicycle using encoders and accelerometers

The goal of this research was to determine kinematic parameters of the lower limbs of a subject pedaling a bicycle. An existing measurement system was used as the basis to develop the model to determine position and acceleration of the limbs. The system consists of an ergometer instrumented to provide position of the pedal (foot), accelerometers to be attached to the lower limbs to measure accelerations, a recorder used for filtering, and a computer instrumented with an A/D board and a decoder board. The system is designed to read and record data from accelerometers and encoders. Software has been developed for data collection, analysis and presentation. Based on the measurement system, a two dimensional analytical model has been developed to determine configuration (position, orientation) and kinematics (velocities, accelerations). The model has been implemented in software and verified by simulation. An error analysis to determine the system's accuracy shows that the expected error is well within the specifications of practical applications. When the physical hardware is completed, NASA researchers hope to use the system developed to determine forces exerted by muscles and forces at articulations. This data will be useful in the development of countermeasures to minimize bone loss experienced by astronauts in microgravity conditions.

Liu, Shih-Ching↗