SEARCH · Search NASA

Results for “Machine Learning Hardware”

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 487 records · Page 27

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendations

Addressing the "Red-AI" trend of rising energy consumption by large-scale neural networks, this study investigates the measured energy consumption of training various fully connected neural network architectures. We introduce the BUTTER-E dataset, an augmentation to the BUTTER Empirical Deep Learning dataset, containing energy consumption and performance data from 41,129 individual experimental runs spanning 30,582 distinct configurations: 13 datasets, 20 sizes (trainable parameters), 8 "shapes", and 14 depths on both CPUs and GPUs using node-level watt-meters. This dataset reveals the complex relationship between dataset size, network structure, and energy use. Our analysis uncovers a surprising, hardware-mediated non-linear relationship between energy efficiency and network design, challenging the assumption that reducing the number of parameters or FLOPs is the best way to achieve greater energy efficiency. We propose a straightforward and effective energy model that accounts for network size, computing, and memory hierarchy. Highlighting the need for cache-considerate algorithm development, we suggest a codesign approach to energy efficient network, algorithm, and hardware design. This work contributes to the fields of sustainable computing and Green AI, offering practical guidance for creating more energy-efficient neural networks and promoting sustainable AI.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

A Science-Focused Artificial Intelligence (AI) Responding in Real-Time to New Information: Capability Demonstration for Ocean World Missions

Introduction: Artificial intelligence (AI) has long been considered a potential mechanism to explore increasingly challenging environments, including those with extreme temperatures and pressures, limited communication capabilities, or those with demanding terrain. We posit that missions in extreme environments could deploy an onboard AI focused on science observations and goals in order to augment a traditional concept(s) of operations (ConOps). An onboard AI capability could perform functions such as data analysis in order to make high-level decisions, including prioritized data transmission for analysis by ground-based teams or autonomously-guided follow-on analyses that maximize science return. Such a capability would empower missions to respond to scientific data of interest in real-time; a mission could make observations and perform a preliminary analysis to alert ground-based scientists to an observation of interest, enabling an informed, rapid response from Earth-based teams. Enceladus Case Study for Onboard AI: We are developing an onboard AI capability for real-time telemetry response that formulates and carries-out informed decisions in service to established mission goals, enabling increased science return of a mission. We focus our AI development for use on a constellation of SmallSats orbiting Enceladus. Our Enceladus case study tests autonomous decision-making capabilities in scenarios with complex orbital dynamics, plume ejecta, extreme cold environments, power restrictions, and a requirement to maximize science return for a potential positive detection of life, while critically evaluating the potential for false positives. Telemetry includes simulated scientific data, spacecraft onboard operational data (e.g., position, velocity, and rotation), and engineering hardware performance data. Enceladus SmallSat Constellation. Our constellation includes eight SmallSat spacecraft in an 8:35 resonant orbit-based formation, leveraging Saturn’s gravitational forces to maintain stable orbits with global coverage around Enceladus. To our knowledge, we simulate the first stable configuration of multiple spacecraft in closed orbits around Enceladus, using a full ephemeris force model (Russell and Lara, 2009). Each spacecraft’s orbit will precess, causing an eastward ground track shift (from an orbiter’s perspective) of each spacecraft for each orbit. However, all spacecraft return to their original positions relative to Enceladus after eight Enceladus revolutions around Saturn. We model communication pathways between SmallSats to understand how information would need to be transmitted across the constellation to enable AI-driven decision-making and resource allocation across the fleet. Capability Demonstration. Our simulated capability demonstration inputs position, velocity, and rotation telemetry from our Enceladus-focused constellation simulations, and mass spectrometry data collected from abiotic and biotic laboratory-analog ocean world experiments (Theiling et al., 2018; Theiling, 2021; Da Poian et al., 2023). Data from these experiments are used to simulate MS measurements and different scenarios of science observations for onboard analysis performed on each of the eight spacecraft. For these demonstrations, we integrate 24 machine learning (ML) algorithms into an onboard intelligence as a ‘knowledge base’, including algorithms evaluating data quality and those predicting (with % confidence) gas composition, ocean aqueous chemistry, and whether the sample was influenced by microbial life. The onboard AI capability is designed to use the knowledge base to come to a consensus-based decision in the interpretation of the observed data in order to request additional action outside of a pre-defined ConOps. Requested actions could include e.g., prioritized downlink to Earth (for analysis by ground-based teams) or follow-on analyses performed across the constellation. The spacecraft’s intelligent onboard planner must then determine whether sufficient resources (e.g., time, power, etc.) are available and weigh the request with mission priorities. In our simulation, the constellation is able to identify potential biosignatures using onboard ML algorithms, evaluate the confidence of that prediction, and perform follow-on analyses across the fleet to confirm the detection, in order to best prepare a transmission of these data to Earth-based teams.

astrobiology↗

DOE OSTI2017

Exploring performance and energy tradeoffs for irregular applications: A case study on the Tilera many-core architecture

High performance, parallel applications with irregular data accesses are becoming a critical workload class for modern systems. In particular, the execution of such workloads on emerging many-core systems is expected to be a significant component of applications in data mining, machine learning, scientific computing and graph analytics. However, power and energy constraints limit the capabilities of individual cores, memory hierarchy and on-chip interconnect of such systems, thus leading to architectural and software trade-os that must be understood in the context of the intended application’s behavior. Irregular applications are notoriously hard to optimize given their data-dependent access patterns, lack of structured locality and complex data structures and code patterns. We have ported two irregular applications, graph community detection using the Louvain method (Grappolo) and high-performance conjugate gradient (HPCCG), to the Tilera many-core system and have conducted a detailed study of platform-independent and platform-specific optimizations that improve their performance as well as reduce their overall energy consumption. To conduct this study, we employ an auto-tuning based approach that explores the optimization design space along three dimensions - memory layout schemes, GCC compiler flag choices and OpenMP loop scheduling options. We leverage MIT’s OpenTuner auto-tuning framework to explore and recommend energy optimal choices for different combinations of parameters. We then conduct an in-depth architectural characterization to understand the memory behavior of the selected workloads. Finally, we perform a correlation study to demonstrate the interplay between the hardware behavior and application characteristics. Using auto-tuning, we demonstrate whole-node energy savings and performance improvements of up to 49:6% and 60% relative to a baseline instantiation, and up to 31% and 45:4% relative to manually optimized variants.

auto tuning↗

NASA NTRSDate not supplied

A NASA Perspective on Quantum AI, Error Correction, and Beyond

Quantum computing is one of the most enticing computational paradigms with the potential to revolutionize diverse areas of future-generation computational systems. While quantum computing hardware has advanced rapidly, from tiny laboratory experiments to quantum chips that can outperform even the largest supercomputers on specialized computational tasks, these noisy-intermediate scale quantum (NISQ) processors are still too small and non-robust to be directly useful for any real-world applications. We discuss the prospects for quantum computing and AI, highlighting advances in algorithms, both near- and longer-term. Quantum error correction is critical to the realization of any such vision. The talk with touch on some recent exciting advanced in quantum error correction, particularly in dynamical codes. The talk will conclude with an example of how the combination of quantum computing and artificial intelligence can help probe fundamental aspect of quantum physics.

quantum optimization algorithms and sampling↗

NASA NTRS2016

Overview of Proposed ISRU Technology Development

ISRU involves any hardware or operation that harnesses and utilizes in-situ resources (natural and discarded) to create products and services for robotic and human exploration: Assessment of physical, mineral chemical, and volatile water resources, terrain, geology, and environment (orbital and local). Production of replacement parts, complex products, machines, and integrated systems from feedstock derived from one or more processed resources. Civil engineering, infrastructure emplacement, and structure construction using materials produced from in situ resources. Radiation shields, landing pads, roads, berms, habitats, etc. Generation and storage of electrical, thermal, and chemical energy with in situ derived materials. Solar arrays, thermal wadis, chemical batteries, etc. ISRU is a disruptive capability: Enables more affordable exploration than todays paradigm. Allows more sustainable architectures to be developed. Understand the ripple effect in the other Exploration Elements: MAV: propellant selection, higher rendezvous altitude (higher DV capable with ISRU propellants). EDL: significantly reduces required landed mass. Life Support: reduce amount of ECLSS closure, reduce trash mass carried through propulsive maneuvers. Power: ISRU drives electrical requirements, reactant and regeneration for fuel cells for landers, rovers, and habitat backup. Every Exploration Element except ISRU has some flight heritage (power, propulsion, habitats, landers, life support, etc.) ISRU will require a flight demonstration mission on Mars before it will be included in the critical path. Mission needs to be concluded at least 10 years before first human landed mission to ensure lessons learned can be incorporated into final design. ISRU Formulation team has generated a (still incomplete) list of over 75 technical questions on more than 40 components and subsystems that need to be answered before the right ISRU system will be ready for this flight demo.

Mars exploration↗

DOE OSTI2022

On-policy learning-based deep reinforcement learning assessment for building control efficiency and stability

Artificial intelligence technologies have emerged as a game changer not only in specific applications such as image recognition and machine translation but also in many scientific domains. In particular, as deep reinforcement learning (DRL) has shown great success in complex control problems, DRL-based control has been considered as a potential solution to efficiently control and manage building systems. However, broad assessment of DRL-based building control is still required to characterize their pros and cons in comparison with conventional building control methods (e.g., rule-based feedback controls). In this paper, we assessed DRL-based controls with on-policy learning-based algorithms and continuous control actions for cooling control of large office buildings in the summer season to minimize whole-building energy use and occupant discomfort. We compared DRL-based control methods with two baseline control methods: (1) a pre-determined schedule with supply temperature and static pressure setpoints, and (2) advanced reset method that adjusts setpoints based on heuristic rules, i.e., ASHRAE Guideline 36. We also tested the DRL algorithms to evaluate their performances in multiple climate locations. We found that DRL-based control methods outperformed the baseline control methods in terms of energy savings while maintaining a thermal comfort. DRL reduced energy use between ~4%–22% on average compared to the baseline methods, depending on climate location. We also evaluated DRL-based control in terms of control stability and showed that DRL-based methods should address the span of hardware lifetimes in practical operations.

control stability↗

DOE OSTI2024

Super Resolving Unrolled Neural Networks for Remote Sensing

In remote sensing systems, the capabilities of the system are constrained by the complex interactions between size, weight, and power (SWAP) of potential designs. In electro-optical (EO) systems, examples of these critical parameters include the system’s sensitivity and resolution. Those parameters can be increased by ever larger optical apertures and focal planes but at the cost of more SWAP. Multi-image super resolution (MISR) techniques allow resolution to be enhanced via computation rather than more sophisticated optical hardware. These algorithms combine multiple images together into a single, higher resolution image, trading temporal resolution and computation for spatial resolution. Fielded MISR techniques, such as Drizzle, can require several hundred images to create a single super resolved image, implying reduced temporal resolution, increased data acquisition load, and limiting mission applications. Iterative techniques, such as model-based image reconstruction and compressive sensing, have been shown to create super resolved images using fewer images than Drizzle. They do this by posing an optimization problem that balances accuracy between a highly accurate physical model and an image model. In the case of super resolution, the physical model is defined by the relation between low resolution input images and the desired high resolution output image. The image model encodes some assumptions about the super resolved image. These assumptions are meant to suppress reconstruction artifacts that arise due to deterministic physical model error, stochastic measurement noise, and potential undersampling. In practice, the performance of iterative methods are limited by imaging models compatible with optimization. Deep learning-based methods can effectively learn image models of arbitrary complexity, but lack the theoretical explainability and robustness of iterative techniques. Consensus equilibrium (CE) generalizes the iterative techniques beyond optimization, enabling blackbox algorithms such as traditional and neural image denoisers to be used as the image model. CE-based approaches retain much of the explainability and robustness of iterative techniques while allowing the expressiveness of machine learning image models to be used. Additionally, by unrolling iterations of CE with an embedded image denoiser, the image denoiser can be further trained and specialized to the specific application with potentially higher quality reconstructions. Under this project, we demonstrated the feasibility of training an unrolled neural network based upon CE. While we didn’t train one, we showed that the CE process is differentiable and its gradient can be tractably computed. We also explored the usage of a variants of CE akin to generative neural works. Most importantly, we applied the CE framework to a number of problems including non-blind deconvolution, upsampling, single-image super resolution, MISR, event-based sensing, and saturated deconvolution. Our MISR prototype creates high quality reconstructions with an order of magnitude fewer images than previous approaches and, critically, produces these reconstructions fast enough for practical usage.

47 OTHER INSTRUMENTATION↗

NASA NTRS2007

Human Space Exploration: The Moon, Mars, and Beyond

America is returning to the Moon in preparation for the first human footprint on Mars, guided by the U.S. Vision for Space Exploration. This presentation will discuss NASA's mission, the reasons for returning to the Moon and going to Mars, and how NASA will accomplish that mission in ways that promote leadership in space and economic expansion on the new frontier. The primary goals of the Vision for Space Exploration are to finish the International Space Station, retire the Space Shuttle, and build the new spacecraft needed, to return people to the Moon and go to Mars. The Vision commits NASA and the nation to an agenda of exploration that also includes robotic exploration and technology development, while building on lessons learned over 50 years of hard-won experience. Why the Moon? Many questions about the Moon's potential resources and how its history is linked to that of Earth were spurred by the brief Apollo explorations of the 1960s and 1970s. This new venture will carry more explorers to more diverse landing sites with more capable tools and equipment for extended expeditions. The Moon also will serve as a training ground before embarking on the longer, more difficult trip to Mars. NASA plans to build a lunar outpost at one of the lunar poles, learn to live off the land, and reduce dePendence on Earth for longer missions. America needs to extend its ability to survive in hostile environments close to our home planet before astronauts will reach Mars, a planet very much like Earth. NASA has worked with scientists to define lunar exploration goals and is addressing the opportunities for a range of scientific study on Mars. In order to reach the Moon and Mars within a lifetime and within budget, NASA is building on common hardware, shared knowledge, and unique experience derived from the Apollo Saturn, Space Shuttle and contemporary commercial launch vehicle programs. The journeys to the Moon and Mars will require a variety of vehicles, including the Ares I Crew Launch Vehicle, which transports the Orion Crew Exploration Vehicle, and the Ares V Cargo Launch Vehicle, which transports the Lunar Surface Access Module. The architecture for the lunar missions will use one launch to ferry the crew into orbit, where it will rendezvous with the Lunar Module in the Earth Departure Stage, which will then propel the combination into lunar orbit. The imperative to explore space with the combination of astronauts and robots will be the impetus for inventions such as solar power and water and waste recycling. This next chapter in NASA's history promises to write the next chapter in American history, as well. It will require this nation to provide the talent to develop tools, machines, materials, processes, technologies, and capabilities that can benefit nearly all aspects of life on Earth. Roles and responsibilities are shared between a nationwide Government and industry team. The Exploration Launch Projects Office at the Marshall Space Flight Center manages the design, development, testing, and evaluation of both vehicles and serves as lead systems integrator. A little over a year after it was chartered, the Exploration Launch Projects team is testing engine components, refining vehicle designs, performing wind tunnel tests, and building hardware for the first flight test of Ares I-l, scheduled for spring 2009. The U.S. Vision for Space Exploration lays out a roadmap for a long-term venture of discovery. This endeavor will inspire and attract the best and brightest students to power this nation successfully to the Moon, Mars, and beyond. If one equates the value proposition for space with simple dollars and cents, the potential of the new space economy is tremendous, from orbital space delivery services for the International Space Station to mining and solar energy collection on the Moon and asteroids. The Vision for Space Exploration is fundamentally about bringing the resources of the solar system within the economic sphere of humaind. Given the immense size of our solar system, the amount of available material and energy within it present an enormous economic opportunity.

Sexton, Jeffrey D.↗

NASA NTRSDate not supplied

Highlights of NASA’s Orbital Debris Program Office In Situ and Laboratory Measurements

NASA’s Orbital Debris Program Office (ODPO) maintains various returned spacecraft materials, capabilities, and facilities used for in situ and laboratory measurements that directly support orbital debris environmental models. In situ measurements include the analysis of exposed and returned hardware surfaces. These surfaces serve as passive sensors for the small-sized micrometeoroid and orbital debris (MMOD) flux below the sensitivity of ground-based radar and optical sensors. Various instruments and techniques are used to determine the size and depth of selected impact features, and – if feasible – the composition of the projectile material. Analysis of the impactor residues enables the differentiation of MM and OD for debris below 1 mm to support modeling the OD environment. In addition, projectiles identified as OD can be further differentiated in low-, medium-, and high- density impactors based on chemical analyses. In addition to in situ measurements, the ODPO has also worked in collaboration with the U.S. Space Force Space Systems Command (formerly the U.S. Air Force Space and Missile Systems Center), the Aerospace Corporation, and the University of Florida on a laboratory-based hypervelocity impact test, DebriSat, conducted at the Air Force Arnold Engineering Development Complex in 2014. The resulting data from this impact test series are being analyzed to assess the fragments’ sizes/masses, materials/densities, shapes, and other parameters of interest. The DebriSat project provides the data needed to update NASA’s breakup models and size estimation models using the simulated orbital breakup of a modern, low Earth orbit spacecraft. Ultimately, over 200,000 fragments from this impact test will be stored at NASA Johnson Space Center (JSC) and further analyzed by the ODPO. This project will also use machine learning techniques to infer physical parameters of fragments embedded in the soft-catch foam used in the impact experiment. Applied to X-ray imagery of the foam panels, these techniques promise to minimize human-in-the-loop processes for fragment extraction and physical characterization. A brief overview of this project and data collected will be presented. Lastly, the ODPO provides various capabilities hosted at NASA JSC for optical inspections and measurements using a variety of techniques and scientific instrumentation to support both in situ and laboratory measurements. The ODPO’s Optical Measurement Center (OMC) is an advanced facility for photometric and spectroscopic laboratory measurements of targets, including fragments from the DebriSat project. The OMC simulates telescopic observations by using space-like illumination conditions and source-target-sensor orientation techniques. Additionally, the OMC is uniquely equipped to acquire pseudo-bidirectional reflectance distribution data for broadband photometric measurements, thus removing aspect angle dependencies that can affect target size estimates using the optical size estimation model. Narrow-band surface material characterization using spectroscopic instrumentation gives insight into how the albedo parameter – also important in the optical size estimation model – may vary depending on the state of the material. The OMC also performs simulations of photometric measurements using optical ray-tracing software to model the OMC optical throughput. In addition to the OMC, the ODPO houses a start-of-the-art Fragment Analysis Facility that uses multiple microscopic inspection instruments to support in situ measurements and material characterization. An overview of both facilities will be highlighted in this paper.

Orbital Debris↗

NASA NTRSDate not supplied

Highlights of NASA’s Orbital Debris Program Office In Situ and Laboratory Measurements

Orbital Debris↗

DOE OSTI2024

Graph Neural Networks for Parameterized Quantum Circuits Expressibility Estimation (Rev.1)

Parameterized quantum circuits (PQCs) are fundamental to quantum machine learning (QML), quantum optimization, and variational quantum algorithms (VQAs). The expressibility of PQCs is a measure that determines their capability to harness the full potential of the quantum state space. It is thus a crucial guidepost to know when selecting a particular PQC ansatz. However, the existing technique for expressibility computation through statistical estimation requires a large number of samples, which poses significant challenges due to time and computational resource constraints. This paper introduces a novel approach for expressibility estimation of PQCs using Graph Neural Networks (GNNs). We demonstrate the predictive power of our GNN model with a dataset consisting of 25,000 samples from the noiseless IBM QASM Simulator and 12,000 samples from three distinct noisy quantum backends. The model accurately estimates expressibility, with root mean square errors (RMSE) of 0.05 and 0.06 for the noiseless and noisy backends, respectively. We compare our model’s predictions with reference circuits from Sim et al. and IBM Qiskit’s hardwareefficient ansatz sets to further evaluate our model’s performance. Our experimental evaluation in noiseless and noisy scenarios reveals a close alignment with ground truth expressibility values, highlighting the model’s efficacy. Moreover, our model exhibits promising extrapolation capabilities, predicting expressibility values with low RMSE for out-of-range qubit circuits trained solely on only up to 5-qubit circuit sets. This work thus provides a reliable means of efficiently evaluating the expressibility of diverse PQCs on noiseless simulators and hardware.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Innovative Strategies for Long-Term Monitoring of Complex Groundwater Plumes at DOE’s Legacy Sites (Workshop Report)

Most remaining Department of Energy (DOE) sites will require extended periods of institutional control, especially at complex groundwater sites where attenuation-based strategies have been implemented to facilitate closure. The current practice of monitoring—obtaining and analyzing contaminant concentration in groundwater samples at numerous wells—will account for a large portion of the projected life-cycle at these DOE sites unless a new approach is adopted. State-of-the-art technologies are being developed, including in situ sensors, geophysics, radiation mapping, numerical modeling and AI/ML. These technologies can optimize monitoring strategies in space and time, provide spatially extensive information at vulnerable regions and/or provide more continuous monitoring at lower cost. As part of DOE’s Office of Environmental Management (DOE-EM’s) efforts to advance long-term monitoring systems, an in-person/virtual hybrid workshop was hosted by Savannah River National Laboratory (SRNL) on January 24 and 25, 2023, in Augusta, Georgia. Because DOE-EM’s complex sites will eventually be transferred to DOE’s Office of Legacy Management (DOE-LM), representatives of DOE-LM were important participants in the workshop. The purpose of the workshop was to identify challenges and opportunities for deploying advanced technologies for long-term monitoring at DOE sites. The key questions during the workshop were: 1) the regulatory acceptance of replacing a process that traditionally has used laboratory sampling and analysis of groundwater samples, and 2) the application of this strategy to the southwestern arid sites that include many of the remaining DOE-EM and DOE-LM complex groundwater plumes. Characteristics common to most arid sites present both limitations and opportunities for advanced technologies. DOE-EM has funded a National Laboratory team from SRNL, Lawrence Berkeley National Laboratory (LBNL), and Pacific Northwest National Laboratory (PNNL) to establish the overarching framework of long-term monitoring by systematically combining advanced hardware and software technologies. This project is titled “Advanced Long-Term Environmental Monitoring Systems (ALTEMIS)” and is sponsored by the DOE-EM Technology Development Program. The multi-laboratory team is currently developing and testing innovative monitoring strategies, including the use of in situ groundwater sensors, geophysics, drone/satellite-based remote sensing, reactive transport modeling, and artificial intelligence/machine learning (AI/ML). The project’s demonstration testbed is at the Savannah River Site (SRS) F-Area Seepage Basins, where a well-characterized complex groundwater plume composed of uranium and other radionuclides is in the latter stages of remediation. The workshop included more than 70 participants, presentations, a field visit to F-Area, breakout working groups, and large group discussion. Participants developed recommendations on five topics: in situ sensors, spatially integrative tools, challenges to regulatory acceptance, AI/ML strategies, and transitioning sites to DOE-LM.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

NASA NTRS2006

Implementing Scientific Simulation Codes Highly Tailored for Vector Architectures Using Custom Configurable Computing Machines

The motivation for this work comes from an observation that amidst the push for Massively Parallel (MP) solutions to high-end computing problems such as numerical physical simulations, large amounts of legacy code exist that are highly optimized for vector supercomputers. Because re-hosting legacy code often requires a complete re-write of the original code, which can be a very long and expensive effort, this work examines the potential to exploit reconfigurable computing machines in place of a vector supercomputer to implement an essentially unmodified legacy source code. Custom and reconfigurable computing resources could be used to emulate an original application's target platform to the extent required to achieve high performance. To arrive at an architecture that delivers the desired performance subject to limited resources involves solving a multi-variable optimization problem with constraints. Prior research in the area of reconfigurable computing has demonstrated that designing an optimum hardware implementation of a given application under hardware resource constraints is an NP-complete problem. The premise of the approach is that the general issue of applying reconfigurable computing resources to the implementation of an application, maximizing the performance of the computation subject to physical resource constraints, can be made a tractable problem by assuming a computational paradigm, such as vector processing. This research contributes a formulation of the problem and a methodology to design a reconfigurable vector processing implementation of a given application that satisfies a performance metric. A generic, parametric, architectural framework for vector processing implemented in reconfigurable logic is developed as a target for a scheduling/mapping algorithm that maps an input computation to a given instance of the architecture. This algorithm is integrated with an optimization framework to arrive at a specification of the architecture parameters that attempts to minimize execution time, while staying within resource constraints. The flexibility of using a custom reconfigurable implementation is exploited in a unique manner to leverage the lessons learned in vector supercomputer development. The vector processing framework is tailored to the application, with variable parameters that are fixed in traditional vector processing. Benchmark data that demonstrates the functionality and utility of the approach is presented. The benchmark data includes an identified bottleneck in a real case study example vector code, the NASA Langley Terminal Area Simulation System (TASS) application.

Rutishauser, David↗

DOE OSTI2018

Accurate, Fast and Scalable Kernel Ridge Regression on Parallel and Distributed Systems

Kernel Ridge Regression (KRR) is a fundamental method in machine learning. Given an n-by-d data matrix as input, a traditional implementation requires Θ(n2) memory to form an n-by-n kernel matrix and Θ(n3) flops to compute the final model. These time and storage costs prohibit KRR from scaling up to large datasets. For example, even on a relatively small dataset (a 520k-by-90 input requiring 357 MB), KRR requires 2 TB memory just to store the kernel matrix. Additionally, the reason is that n usually is much larger than d for real-world applications. On the other hand, weak scaling becomes a problem: if we keep d and n/p fixed as p grows (p is # machines), the memory needed grows as Θ(p) per processor and the flops as Θ(p2) per processor. In the perfect weak scaling situation, both the memory needed and the flops grow as Θ(1) per processor (i.e. memory and flops are constant). The traditional Distributed KRR implementation (DKRR) only achieved 0.32% weak scaling efficiency from 96 to 1536 processors. In this work, we propose two new methods to address these problems: the Balanced KRR (BKRR) and K-means KRR (KKRR). These methods consider alternative ways to partition the input dataset into p different parts, generating p different models, and then selecting the best model among them. Compared to a conventional implementation, KKRR2 (optimized version of KKRR) improves the weak scaling efficiency from 0.32% to 38% and achieves a 591x speedup for getting the same accuracy by using the same data and the same hardware (1536 processors). BKRR2 (optimized version of BKRR) achieves a higher accuracy than the current fastest method using less training time for a variety of datasets. For the applications requiring only approximate solutions, BKRR2 improves the weak scaling efficiency to 92% and achieves 3505x speedup (theoretical speedup: 4096x).

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Parametric Optimization of Rigid Wheels for Planetary Surface Mobility Applications

Design-Build-Test approaches for spaceflight hardware are time and cost intensive, which can result in suboptimal mechanism designs. Optimization-based approaches that utilize high-fidelity models and physics simulation could overcome these limitations while simultaneously speeding up the mechanical design process and reducing cost. In this work, we present a toolchain that enables the multi-objective optimization of rigid rover wheels for planetary surface mobility applications. The toolchain uses Chrono’s Continuous Representation Model (CRM) functionality to simulate granular soil and performs multi-objective parametric optimization on candidate rover wheels to meet a desired performance criterion. The resulting wheel design is then evaluated experimentally using a single-wheel testbed. We end with a discussion of how the toolchain can be extended to simultaneously co-optimize other system parameters, such as system power consumption and feedback control gains.

Optimization↗

DOE OSTI2022

Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml

In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network architecture, we demonstrate a fully-on-chip deployment with a latency of 4.9 ms per image, using less than 30% of the available resources on a Xilinx ZCU102 evaluation board. The latency is reduced to 3 ms per image when increasing the batch size to ten, corresponding to the use case where the autonomous vehicle receives inputs from multiple cameras simultaneously. We show, through aggressive filter reduction and heterogeneous quantization-aware training, and an optimized implementation of convolutional layers, that the power consumption and resource utilization can be significantly reduced while maintaining accuracy on the Cityscapes dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2018

Automated point mapping for building control systems: Recent advances and future research needs

Not Available

Wang, Weimin↗

DOE OSTI2024

Next-Generation, High-temperature, High-frequency, High-efficiency, High-power-density Traction System

To meet performance and reliability requirements necessary for broader adoption of electric drive vehicles, the Electrical and Electronics Technical Team of the U.S. Drive partnership has established aggressive design goals for next-generation electric vehicle drivetrains. Specifically, the 2025 roadmap stipulates a 100 kW/L power density target and a $\$$2.7/kW cost target for power electronics, in addition to high-voltage operation (i.e., greater than 800 VDC). The additional targets for traction motor and the overall system performance impose further challenges on the power electronics design. For example, many high specific power machines have reduced iron content, and therefore reduced intrinsic filtering, thus requiring the inverter to supply a low-distortion drive current. These machines also typically have a high pole count, thus requiring drive current at a higher electrical frequency. Other motors, such as brush-less dc and switch reluctance machines, require a carefully-shaped, non-sinusoidal drive current (Yang, Shang, Brown, & Krishnamurthy, 2015), (Zhang, Bowman, O'Connel, & Haran, 2018), (Anderson, et al., 2018). Two- and three-level inverter topologies are the conventional framework for the power electronics design of the drivetrain, and some demonstrations have shown recent progress towards addressing cost, power density and efficiency goals (Gurpinar & Ozpineci, 2018), (Zhu, Kim, Chen, Erickson, & Maksimović, 2018), (Deshpande, Chen, Narayanasamy, Sathyanarayanan, & Luo, 2018), (Alizadeh, et al., 2019). However, an unconventional approach may be necessary to take the dramatic leap in power density necessitated by the roadmap—while simultaneously addressing the other system needs. Therefore, this project leverages the flying capacitor multilevel (FCML) topology, together with a scalable, modular approach, to address these needs. This type of hybrid converter has several advantages: lower voltage (i.e., less than 300 V) transistors can be used, energy-dense capacitors process most of the power, and the output current waveform is multilevel and exhibits a frequency multiplying effect—in other words, the output has reduced dv/dt and filtering requirements for the same high voltage dc bus. For example, in an electric vehicle with an 800 V bus, a 10-level FCML could leverage 100 V, commercially available GaN devices switching at 115 kHz to produce a ~1 MHz switching waveform (modulated according to the motor drive requirements) with one ninth of the dv/dt of a two-level converter. Prior work has already demonstrated promising performance and gravimetric power density figures for more electric aircraft applications (Pallo, Foulkes, Modeer, Coday, & Pilawa-Podgurski, 2018). This project leverages lessons learned to achieve the volumetric power density of 100 kW/L by employing advanced liquid cooling, address the 300,000 mile reliability challenge with redundant design, topology failure studies and online health monitoring, and reduce costs to $\$$2.7/kW through the use of low-cost GaN devices, modular converter assemblies, and modest modifications to traditional manufacturing methods. The project involved several hardware designs, each achieving increasing performance. At the conclusion of the project, a volumetric power density of 380 kW/L was achieved, in a 800V dc-ac converter, greatly surpassing even the aggressive target goal.

33 ADVANCED PROPULSION SYSTEMS↗