Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computer 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.

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

At least 775 records · Page 43

The Minos Computing Library: Efficient Parallel Programming for Extremely Heterogeneous Systems

Hardware specialization has become the silver bullet to achieve efficient high performance, from Systems-on-Chip systems, where hardware specialization can be ``extreme'', to large-scale HPC systems. As the complexity of the systems increases, so does the complexity of programming such architectures in a portable way. This work introduces the Minos Computing Library (MCL), as system software, programming model, and programming model runtime that facilitate programming extremely heterogeneous systems. MCL supports the execution of several multi-threaded applications within the same compute node, performs asynchronous execution of application tasks, efficiently balances computation across hardware resources, and provides performance portability. We show that code developed on a personal desktop automatically scales up to fully utilize powerful workstations with 8 GPUs and down to power-efficient embedded systems. MCL provides up to 17.5x speedup over OpenCL on NVIDIA DGX-1 systems and up to 1.88x speedup on single-GPU systems. In multi-application workloads, MCL dynamically resource allocation provides up to 2.43x performance improvement over manual, static allocation of computing resources.

Gioiosa, Roberto↗

Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators

Software simulators play a critical role in the development of new algorithms and system architectures in any field of engineering. Neuromorphic computing, which has shown potential in building brain-inspired energy-efficient hardware, suffers a slow-down in the development cycle due to a lack of flexible and easy-to-use simulators of either neuromorphic hardware itself or of spiking neural networks (SNNs), the type of neural network computation executed on most neuromorphic systems. While there are several openly available neuromorphic or SNN simulation packages developed by a variety of research groups, they have mostly targeted computational neuroscience simulations, and only a few have targeted small-scale machine learning tasks with SNNs. Evaluations or comparisons of these simulators have often targeted computational neuroscience-style workloads. In this work, we seek to evaluate the performance of several publicly available SNN simulators with respect to non-computational neuroscience workloads, in terms of speed, flexibility, and scalability. We evaluate the performance of the NEST, Brian2, Brian2GeNN, BindsNET and Nengo packages under a common front-end neuromorphic framework. Our evaluation tasks include a variety of different network architectures and workload types to mimic the computation common in different algorithms, including feed-forward network inference, genetic algorithms, and reservoir computing. We also study the scalability of each of these simulators when running on different computing hardware, from single core CPU workstations to multi-node supercomputers. Our results show that the BindsNET simulator has the best speed and scalability for most of the SNN workloads (sparse, dense, and layered SNN architectures) on a single core CPU. However, when comparing the simulators leveraging the GPU capabilities, Brian2GeNN outperforms the others for these workloads in terms of scalability. NEST performs the best for small sparse networks and is also the most flexible simulator in terms of reconfiguration capability NEST shows a speedup of at least 2x compared to the other packages when running evolutionary algorithms for SNNs. The multi-node and multi-thread capabilities of NEST show at least 2x speedup compared to the rest of the simulators (single core CPU or GPU based simulators) for large and sparse networks. We conclude our work by providing a set of recommendations on the suitability of employing these simulators for different tasks and scales of operations. We also present the characteristics for a future generic ideal SNN simulator for different neuromorphic computing workloads.

97 MATHEMATICS AND COMPUTING↗

diffReplication - An Energy-Aware Fault Tolerance Model for Silent Error Detection and Mitigation in Heterogeneous Extreme-scale Computing Environment

At extreme scale, the frequency of silent errors – a class of errors that remain undetected by low-level error detection mechanisms – increases significantly with the computational complexity of the application and the scale of the computing infrastructure. As hardware and software advances are made to usher in the next scientific era of computing, developing new approaches to mitigate the impact of silent errors remains a challenging problem. In this work, we propose an energy-aware fault-tolerance model, referred to diffReplication to overcome silent errors. In the proposed model, the main process is associated with one replica that executes at the same rate as the main process, and one diffReplica that is executed at a fraction of the main process' execution rate. If the main and its replica reach consensus at the end of a computation phase, the state of the diffReplica is updated and computation is resumed. If the synchronization attempt results in a disagreement, however, the diffReplica increases its execution speed to complete the computation and quickly reach the synchronization barrier. Assuming a single error over any given synchronization interval, a majority voting is used to reach consensus and tolerate silent errors. To further enhance its performance, diffReplication is augmented with speculative execution, whereby the main or its fast replica is selected to continue execution without waiting for the diffReplica. The selection process is based on the previous behaviour of the main and its replica. A performance analysis study is carried out to assess the performance of diffReplication, in terms of the energy saving and time-to-completion reduction achieved by the diffReplication scheme. The experiment shows that speculative execution reduces the time to completion with additional energy, and dynamic decision-making balances the energy consumption and time to completion.

97 MATHEMATICS AND COMPUTING↗

Design of Superconducting Optoelectronic Networks for Neuromorphic Computing

We have previously proposed a novel hardware platform (SOEN) for neuromorphic computing based on superconducting optoelectronics that presents many of the features necessary for information processing in the brain. Here we discuss the design and training of networks of neurons and synapses based on this technology. We present circuit models for the simplest neurons and synapses that we can use to build networks. We discuss the further abstracted integrate and fire model that we use for evolutionary optimization of small networks of these neurons. We show that we can use the TENNLab evolutionary optimization programming framework to design small networks for logic, control and classification tasks. We plan to use the results as feedback to inform our neuron design.

Buckley, Sonia↗

Long-time simulations for fixed input states on quantum hardware

Publicly accessible quantum computers open the exciting possibility of experimental dynamical quantum simulations. While rapidly improving, current devices have short coherence times, restricting the viable circuit depth. Despite these limitations, we demonstrate long-time, high fidelity simulations on current hardware. Specifically, we simulate an XY-model spin chain on Rigetti and IBM quantum computers, maintaining a fidelity over 0.9 for 150 times longer than is possible using the iterated Trotter method. Our simulations use an algorithm we call fixed state Variational Fast Forwarding (fsVFF). Recent work has shown an approximate diagonalization of a short time evolution unitary allows a fixed-depth simulation. fsVFF substantially reduces the required resources by only diagonalizing the energy subspace spanned by the initial state, rather than over the total Hilbert space. We further demonstrate the viability of fsVFF through large numerical simulations, and provide an analysis of the noise resilience and scaling of simulation errors.

97 MATHEMATICS AND COMPUTING↗

Engineering support activities for the Apollo 17 Surface Electrical Properties Experiment.

Description of the engineering support activities which were required to ensure fulfillment of objectives specified for the Apollo 17 SEP (Surface Electrical Properties) Experiment. Attention is given to procedural steps involving verification of hardware acceptability to the astronauts, computer simulation of the experiment hardware, field trials, receiver antenna pattern measurements, and the qualification test program.

Cubley, H. D.↗

An Object Oriented Extensible Architecture for Affordable Aerospace Propulsion Systems

Driven by a need to explore and develop propulsion systems that exceeded current computing capabilities, NASA Glenn embarked on a novel strategy leading to the development of an architecture that enables propulsion simulations never thought possible before. Full engine 3 Dimensional Computational Fluid Dynamic propulsion system simulations were deemed impossible due to the impracticality of the hardware and software computing systems required. However, with a software paradigm shift and an embracing of parallel and distributed processing, an architecture was designed to meet the needs of future propulsion system modeling. The author suggests that the architecture designed at the NASA Glenn Research Center for propulsion system modeling has potential for impacting the direction of development of affordable weapons systems currently under consideration by the Applied Vehicle Technology Panel (AVT). This paper discusses the salient features of the NPSS Architecture including its interface layer, object layer, implementation for accessing legacy codes, numerical zooming infrastructure and its computing layer. The computing layer focuses on the use and deployment of these propulsion simulations on parallel and distributed computing platforms which has been the focus of NASA Ames. Additional features of the object oriented architecture that support MultiDisciplinary (MD) Coupling, computer aided design (CAD) access and MD coupling objects will be discussed. Included will be a discussion of the successes, challenges and benefits of implementing this architecture.

Follen, Gregory J.↗

An Object Oriented Extensible Architecture for Affordable Aerospace Propulsion Systems

Driven by a need to explore and develop propulsion systems that exceeded current computing capabilities, NASA Glenn embarked on a novel strategy leading to the development of an architecture that enables propulsion simulations never thought possible before. Full engine 3 Dimensional Computational Fluid Dynamic propulsion system simulations were deemed impossible due to the impracticality of the hardware and software computing systems required. However, with a software paradigm shift and an embracing of parallel and distributed processing, an architecture was designed to meet the needs of future propulsion system modeling. The author suggests that the architecture designed at the NASA Glenn Research Center for propulsion system modeling has potential for impacting the direction of development of affordable weapons systems currently under consideration by the Applied Vehicle Technology Panel (AVT).

Follen, Gregory J.↗

System enhancements of Mesoscale Analysis and Space Sensor (MASS) computer system

The interactive information processing for the mesoscale analysis and space sensor (MASS) program is reported. The development and implementation of new spaceborne remote sensing technology to observe and measure atmospheric processes is described. The space measurements and conventional observational data are processed together to gain an improved understanding of the mesoscale structure and dynamical evolution of the atmosphere relative to cloud development and precipitation processes. A Research Computer System consisting of three primary computers was developed (HP-1000F, Perkin-Elmer 3250, and Harris/6) which provides a wide range of capabilities for processing and displaying interactively large volumes of remote sensing data. The development of a MASS data base management and analysis system on the HP-1000F computer and extending these capabilities by integration with the Perkin-Elmer and Harris/6 computers using the MSFC's Apple III microcomputer workstations is described. The objectives are: to design hardware enhancements for computer integration and to provide data conversion and transfer between machines.

Hickey, J. S.↗

A versatile nondestructive evaluation imaging workstation

Ultrasonic C-scan and eddy current imaging systems are of the pointwise type evaluation systems that rely on a mechanical scanner to physically maneuver a probe relative to the specimen point by point in order to acquire data and generate images. Since the ultrasonic C-scan and eddy current imaging systems are based on the same mechanical scanning mechanisms, the two systems can be combined using the same PC platform with a common mechanical manipulation subsystem and integrated data acquisition software. Based on this concept, we have developed an IBM PC-based combined ultrasonic C-scan and eddy current imaging system. The system is modularized and provides capacity for future hardware and software expansions. Advantages associated with the combined system are: (1) eliminated duplication of the computer and mechanical hardware, (2) unified data acquisition, processing and storage software, (3) reduced setup time for repetitious ultrasonic and eddy current scans, and (4) improved system efficiency. The concept can be adapted to many engineering systems by integrating related PC-based instruments into one multipurpose workstation such as dispensing, machining, packaging, sorting, and other industrial applications.

Chern, E. James↗

Then and Now: Improving Software Portability, Productivity, and 100× Performance

The US Exascale Computing Project (ECP) has succeeded in preparing applications to run efficiently on the first reported Exascale supercomputers in the world. To achieve this, it modernized the whole leadership software stack, from libraries to simulation codes. In this article, we contrast selected leadership software before and after ECP. We discuss how sustainable research software development for leadership computing can embrace the conversation with the hardware vendors, the leadership computing facilities, the software community, and the domain scientists who are the application developers and integrators of software products. We elaborate on how software needs to take portability as a central design principle and to benefit from interdependent teams; we also demonstrate how moving to programming languages with high momentum, like modern C++, can help improve the sustainability, interoperability, and performance of research software. Finally, we showcase how cross-institutional efforts can enable algorithm advances that are beyond incremental performance optimization.

97 MATHEMATICS AND COMPUTING↗

Spherical roller bearing analysis. SKF computer program SPHERBEAN. Volume 3: Program correlation with full scale hardware tests

The results of a series of full scale hardware tests comparing predictions of the SPHERBEAN computer program with measured data are presented. The SPHERBEAN program predicts the thermomechanical performance characteristics of high speed lubricated double row spherical roller bearings. The degree of correlation between performance predicted by SPHERBEAN and measured data is demonstrated. Experimental and calculated performance data is compared over a range in speed up to 19,400 rpm (0.8 MDN) under pure radial, pure axial, and combined loads.

Kleckner, R. J.↗

CSM research: Testbed development

The Computational Structural Mechanics (CSM) Activity at Langley Research Center is developing methods for structural analysis on modern computers. To facilitate that research effort, a Testbed Development environment is being constructed. It is the purpose of the Testbed to insulate researchers from differences in the computer operating systems of modern computer systems and permit concentrated effort on the analytical problem rather than the analytical tools required to solve that problem. While modern computers enable the solution of larger problems of increasing complexity, they do so at a cost. Distributed computer environments, vector processing hardware and multiple processors dominate the current computer environment and threaten to overwhelm future analysis software. The systems software for current computers becomes more complex in order to manage the increasing complexity. The applications developer is caught between conflicting goals. They must take advantage of the computing power of new computer systems while maintaining a stable software development system. The CSM Testbed is being developed to address this problem for the computational structural analysis research community. The Langley CSM activity was initiated in October 1984. The current directions for the Testbed Development Team of the Langley CSM activity are discussed.

Gillian, Ronnie E.↗

Challenges in Securing the Interface Between the Cloud and Pervasive Systems

Cloud computing presents an opportunity for pervasive systems to leverage computational and storage resources to accomplish tasks that would not normally be possible on such resource-constrained devices. Cloud computing can enable hardware designers to build lighter systems that last longer and are more mobile. Despite the advantages cloud computing offers to the designers of pervasive systems, there are some limitations of leveraging cloud computing that must be addressed. We take the position that cloud-based pervasive system must be secured holistically and discuss ways this might be accomplished. In this paper, we discuss a pervasive system utilizing cloud computing resources and issues that must be addressed in such a system. In this system, the user's mobile device cannot always have network access to leverage resources from the cloud, so it must make intelligent decisions about what data should be stored locally and what processes should be run locally. As a result of these decisions, the user becomes vulnerable to attacks while interfacing with the pervasive system.

97 MATHEMATICS AND COMPUTING↗

Real-Time Machine Learning Inferencing with Edge Computing Devices from Google and Intel

Machine Learning (ML) has been demonstrated to accelerate discovery and improve the accuracy of many measurements in astrophysics and high energy physics research. As an increasingly commonplace tool, we have reached a new set of challenges in the deployment of ML, at the forefront of which is their computational complexity. The goal of this project is to explore the viability of dedicated machine learning hardware, such as Google’s Coral/Edge TPU and Intel’s Movidius Myriad devices, in astrophysics and high energy physics applications. ML algorithms, while faster than traditional methods, can become the bottleneck in data processing pipelines --- which is a critical issue in systems that require low latency. Within the context of high energy physics and astrophysics, we test this hardware in an attempt to find if it is able to reduce the computational cost of machine learning. We have benchmarked some of these devices, specifically the Google Coral Dev Board and th e Google AIY Vision Kit (Containing Intel’s Movidius Myriad 2).This was done via a strong gravitational lens finding application and a known data set of lenses, simulating a realistic astrophysics application of machine learning, and compare their results to that of traditional computer hardware.

Hawks, Benjamin↗

Explore: An Advanced Computing Agenda for Competitiveness

Over the course of this three-year grant, the Council on Competitiveness (Council) hosted six meetings of its Advanced Computing Roundtable made up of experts from a broad cross section of advanced computing users and manufacturers, and four Advanced Computing for Competitiveness Regional Forums to explore issues related to advanced computing in regions, states and localities. More than two hundred experts, stakeholders and policymakers from the federal and state levels participated in this work and provided their time and expertise to help define the opportunity in advanced computing and the barriers to it reaching its full potential as a game-changing competitive advantage for the United States economy and national security. Building on the insights of the Council’s Advanced Computing Roundtable and findings and recommendations from the four U.S. Department of Energy-supported Forums, the Council has identified several broad policy objectives for the United States related to advanced computing leadership and implementation. The United States must: Compete at the high end of advanced computing. Continue investing to be a technology leader as the world moves toward exascale computing, including in hardware, software and applications. America also must lead in strategic areas like extending Moore’s Law and quantum computing. Improve the ability of HPC-using firms to leverage advanced computing. The Council recommends steps to improve computational skills, increase industry partnerships with laboratories and academia, and expand and strengthen software partnerships. Regulatory agencies also should accelerate efforts to use modeling and simulation within the regulatory process. Expand the number of HPC-using companies in America. Too few firms are able to leverage advanced computing to innovate and compete. Federal, state and local economic development efforts should be utilized to lower barriers and teach small and medium-sized firms, particularly manufacturers, to use advanced modeling, simulation and analytics. Coordinate federal action. Federal agencies should continue to act in a coordinated fashion on advanced computing challenges through the Joint Program Office for Strategic Computing. Leverage HPC to compete in strategic technologies and applications. Leadership in advanced computing is tightly linked to leadership in artificial intelligence, the Internet of Things, cybersecurity, additive manufacturing and other emerging technologies. Public and private sector leaders should collaborate on research and partnership efforts that ensure world-class computing environments for strategic technology leadership.

advanced computing↗

On-the fly scheduling of execution of dynamic hardware behaviors

Methods for dynamically executing computer code across multiple disparate processing unit architectures are disclosed. During execution of a first portion of computer code on a first processing unit, it is determined that a first dynamic hardware behavior of a plurality of dynamic hardware behaviors will occur at a subsequent point in time, based on a second dynamic hardware behavior that is occurring. The methods include determining to execute code corresponding to the first dynamic hardware behavior on a second processing unit, rather than the first processing unit, and scheduling computer program code corresponding to the first dynamic hardware behavior to execute on the second processing unit rather than the first processing unit. Upon completion of execution of the computer code corresponding to the first dynamic hardware behavior, a remaining portion of the computer code is scheduled to execute on the first processing unit.

97 MATHEMATICS AND COMPUTING↗

Non-Proprietary Companion to the Q1 CY2021 PathForward Final Assessment (WBS 2.4.1, Milestone PM-HI-1040)

The PathForward element of the Exascale Computing Project (ECP) Hardware and Integration (HI) focus area has met its goals of preparing the US industry for exascale system procurements and generally improving US competitiveness in the worldwide computing market. This report is a companion to the deliverable for the ECP milestone PM-HI-1040, Assess PathForward Impact Against Exascale Hardware Challenges, which gives a summary of the final status of each PathForward project, describes progress achieved against PathForward contract milestones, and includes a final assessment of each vendor’s progress on key exascale challenges. This companion document details the results of the PathForward research to the extent possible without disclosing proprietary information and the impact on products and US exascale systems. In addition, it captures lessons learned in order to inform future projects in general and in high-performance computing in particular.

97 MATHEMATICS AND COMPUTING↗