Search NASA⌕ Search

SEARCH · Search NASA

Results for “reconfigurable computing”

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 415 records · Page 23

MAGE: Alleviating Uncertainty in Real-Time Decision-Making as a Function of Problem Complexity

In this paper, we discuss a critical aspect of uncertainty in the operation of complex systems, such as the future air traffic: the ability of agents in the system to arrive at satisfactory decisions and the attendant actions as a function of problem complexity. Intuitively, when the problem complexity is manageable, given an appropriate decision problem formulation and solution tools, an agent (computational or human) has no trouble arriving at a solution that yields good outcomes for the agent and the system. Growing problem complexity results in progressively larger computational problems that may yield suboptimal solutions or even be intractable within required time limits or at all. We propose a measurable representation of complexity in terms of problem tractability and quality of solutions. We also propose a computational scheme, MAGE (Monitor, Anticipate, Guide, Evolve), for detecting approaching transitions from efficient decision-making states to inefficient to unsafe ones, so that operations based on decision-making can be reconfigured to forestall unfavorable transitions, returning to efficient modes when complexity diminishes. Maintaining tractable complexity reduces the uncertainty in the outcomes of decision-making. We describe the general scheme, an outline of MAGE applied to managing airspace complexity, and initial examples of investigating the tractability of problem-solving schemes.

complexity management↗

Dynamic Adaptable Asynchronous Progress Model for MPI RMA Multiphase Applications

Casper is a process-based asynchronous progress model for MPI one-sided communication on multi-and many-core architectures. The one-sided communication is not truly one-sided in most MPI implementations: the target process still relies on software progress to complete incoming operations. Casper allows the user to specify an arbitrary number of cores dedicated to background ghost processes and transparently redirects the RMA operations to ghost processes by utilizing the PMPI redirection and MPI-3 shared-memory technologies. Although Casper benefits applications that suffer from lack of asynchronous progress, the operation redirection design might not support complex multiphase applications effectively, which often involve dynamically changing communication density and computing workloads. In this paper, we present an adaptive mechanism in Casper to address the limitation of static asynchronous progress in multiphase applications. For this we exploit two adaptive strategies, a user-guided strategy and a fully transparent and automatic strategy based on self-profiling and prediction, to dynamically reconfigure the asynchronous progress in Casper according to real-time performance characteristics during multiphase execution. We evaluate the adaptive approaches in both microbenchmarks and a real quantum chemistry application suite, NWChem, on the Cray XC30 supercomputer and an Intel Omni-Path cluster.

97 MATHEMATICS AND COMPUTING↗

Mechanics and energetics modeling of ball-milled metal foil and particle structures

The reported research establishes a semi-analytical computational predictive model of fractal microstructure in ball-milled metal foils and powder particulates, with emphasis on its transformation mechanics via an energy-based approach. The evolving structure is composed of reconfigurable warped ellipsoid material domains, subjected to collisions with the ball milling impactors following Brownian motion energetics. In the first step of the model, impacts are assumed to generate ideal Hertzian elastic stress fields, with associated bulk deformations quantified as per Castigliano's strain energy methods. In the second stage of the model, elastic energies are recast to produce frictional slip and plastic yield, thus resulting in surface micro-joints. Only two parameters of the model necessitate experimental calibration, performed by comparison of joint energy with laboratory tensile measurements on ball-milled multilayer Al-Ni foils. Model predictions of evolving internal microstructure are validated against SEM micrographs of Al-Ni powder particulate samples for different ball milling durations. Results demonstrate the capability of the model to accurately capture relevant fractal measures of the microstructure of ball-milled powders.

36 MATERIALS SCIENCE↗

VecPAC: A Vectorizable and Precision-Aware CGRA

This paper proposes VecPAC -- a vectorizable and precision-aware coarse-grained reconfigurable array (CGRA) design. VecPAC integrates CGRA tiles with scalar functional units and specialized tiles with vector functional units that can trade off the number of vector lanes for the accuracy of the computation. We discuss the architecture design and present the related compilation framework. The experimental evaluation on a set of applications from three different domains (embedded, machine learning, and high-performance computing) shows that the hybrid design of VecPAC outperforms CGRAs with only scalar functional units by 1.48x, while providing higher scalability.

Tan, Cheng↗

Logic design for dynamic and interactive recovery.

Recovery in a fault-tolerant computer means the continuation of system operation with data integrity after an error occurs. This paper delineates two parallel concepts embodied in the hardware and software functions required for recovery; detection, diagnosis, and reconfiguration for hardware, data integrity, checkpointing, and restart for the software. The hardware relies on the recovery variable set, checking circuits, and diagnostics, and the software relies on the recovery information set, audit, and reconstruct routines, to characterize the system state and assist in recovery when required. Of particular utility is a handware unit, the recovery control unit, which serves as an interface between error detection and software recovery programs in the supervisor and provides dynamic interactive recovery.

Carter, W. C.↗

Application of Reconfigurable Avionics for the Bantam Launch Vehicle

The modern market is placing increasing pressure on launch costs. This is particularly true for small university science payloads, where the cost of the experiment itself is relatively low, and the launch frequency is potentially very high. It is the stated goal of the Bantam Program to dramatically reduce the costs of launching this class of payloads. This is a goal that will require that the avionics not only be reduced in production costs, but also in maintenance and operation costs, because the Bantam vehicle is envisioned as a reusable launch system. However, the costs of avionics is a relatively small fraction of the overall cost of launching a payload, and a simple reduction in the avionics costs will not immediately realize the necessary gains. Instead, to reduce the total system launch costs, it is also necessary to improve avionics performance. Only by reducing weight, volume, and power, while enhancing computational capability can the avionics be used to address the system-level cost reduction requirements. The National Aeronautics and Space Administration is currently pursuing technology development tasks, in order to support the Bantam requirements. One technology task is to develop a low-cost, high-performance reconfigurable avionics core unit. In addition to providing low cost and high performance, the use of reconfigurability will be used to explore the options of accommodating multiple launch configurations, and addressing such areas as redundancy management, single-event upset immunity, and low maintenance. This paper will address how emerging developments in reconfigurable avionics can be used to meet these challenges.

Wallace, Shawn↗

Optically connected memory for disaggregated data centers

Recent advances in integrated photonics enable the implementation of reconfigurable, high-bandwidth, and low energy-per-bit interconnects in next-generation data centers. We propose and evaluate an Optically Connected Memory (OCM) architecture that disaggregates the main memory from the computation nodes in data centers. OCM is based on micro-ring resonators (MRRs), and it does not require any modification to the DRAM memory modules. We calculate energy consumption from real photonic devices and integrate them into a system simulator to evaluate performance. Here, our results show that (1) OCM is capable of interconnecting four DDR4 memory channels to a computing node using two fibers with 1.02 pJ energy-per-bit consumption and (2) OCM performs up to 5.5× faster than a disaggregated memory with 40G PCIe NIC connectors to computing nodes.

97 MATHEMATICS AND COMPUTING↗

A polymorphic reconfigurable emulator for parallel simulation

Microprocessor and arithmetic support chip technology was applied to the design of a reconfigurable emulator for real time flight simulation. The system developed consists of master control system to perform all man machine interactions and to configure the hardware to emulate a given aircraft, and numerous slave compute modules (SCM) which comprise the parallel computational units. It is shown that all parts of the state equations can be worked on simultaneously but that the algebraic equations cannot (unless they are slowly varying). Attempts to obtain algorithms that will allow parellel updates are reported. The word length and step size to be used in the SCM's is determined and the architecture of the hardware and software is described.

Parrish, E. A., Jr.↗

Fault tolerant architectures for integrated aircraft electronics systems, task 2

The architectural basis for an advanced fault tolerant on-board computer to succeed the current generation of fault tolerant computers is examined. The network error tolerant system architecture is studied with particular attention to intercluster configurations and communication protocols, and to refined reliability estimates. The diagnosis of faults, so that appropriate choices for reconfiguration can be made is discussed. The analysis relates particularly to the recognition of transient faults in a system with tasks at many levels of priority. The demand driven data-flow architecture, which appears to have possible application in fault tolerant systems is described and work investigating the feasibility of automatic generation of aircraft flight control programs from abstract specifications is reported.

Levitt, K. N.↗

Open control/display system for a telerobotics work station

A working Advanced Space Cockpit was developed that integrated advanced control and display devices into a state-of-the-art multimicroprocessor hardware configuration, using window graphics and running under an object-oriented, multitasking real-time operating system environment. This Open Control/Display System supports the idea that the operator should be able to interactively monitor, select, control, and display information about many payloads aboard the Space Station using sets of I/O devices with a single, software-reconfigurable workstation. This is done while maintaining system consistency, yet the system is completely open to accept new additions and advances in hardware and software. The Advanced Space Cockpit, linked to Grumman's Hybrid Computing Facility and Large Amplitude Space Simulator (LASS), was used to test the Open Control/Display System via full-scale simulation of the following tasks: telerobotic truss assembly, RCS and thermal bus servicing, CMG changeout, RMS constrained motion and space constructible radiator assembly, HPA coordinated control, and OMV docking and tumbling satellite retrieval. The proposed man-machine interface standard discussed has evolved through many iterations of the tasks, and is based on feedback from NASA and Air Force personnel who performed those tasks in the LASS.

Keslowitz, Saul↗

Flight elements: Fault detection and fault management

Fault management for an intelligent computational system must be developed using a top down integrated engineering approach. An approach proposed includes integrating the overall environment involving sensors and their associated data; design knowledge capture; operations; fault detection, identification, and reconfiguration; testability; causal models including digraph matrix analysis; and overall performance impacts on the hardware and software architecture. Implementation of the concept to achieve a real time intelligent fault detection and management system will be accomplished via the implementation of several objectives, which are: Development of fault tolerant/FDIR requirement and specification from a systems level which will carry through from conceptual design through implementation and mission operations; Implementation of monitoring, diagnosis, and reconfiguration at all system levels providing fault isolation and system integration; Optimize system operations to manage degraded system performance through system integration; and Lower development and operations costs through the implementation of an intelligent real time fault detection and fault management system and an information management system.

Lum, H.↗

Advanced mobility avionics : a reconfigurable mirco-avionics platform for the future needs of small planetary rovers and micospacecraft

Future small and micro-missions, such as Mars Scouts and Deep Space probes, require a new look at highly integrated, re-configurable, low power avionics. This paper will present our plans for developing a scalable, configurable, and highly integrated 32-bit embedded platform capable of implementing computationally intensive signal processing and control algorithms in space flight instruments and systems. This platform is designed to service the need of both small and large spacecraft and planetary rovers that will operate within moderate radiation environments. Some of the key characteristics of this platform are its small size, low power, high performance, and flexibility. This estimated 10 fold reduction in both size and power over state-of-the-art processing platforms will enable this new product to act as the core of a low-cost mobility system for a wide range of missions.

reconfigurable↗

High Speed Computing, LANs, and WAMs

Optical fiber networks may one day offer potential capacities exceeding 10 terabits/sec. This paper describes present gigabit network techniques for distributed computing as illustrated by the CASA gigabit testbed, and then explores future all-optic network architectures that offer increased capacity, more optimized level of service for a given application, high fault tolerance, and dynamic reconfigurability.

all-optics networks terabit fiber optic networks s↗

On Representative Spaceflight Instrument and Associated Instrument Sensor Web Framework

Sensor Web-based adaptation and sharing of space flight mission resources, including those of the Space-Ground and Control-User communication segment, could greatly benefit from utilization of heritage Internet Protocols and devices applied for Spaceflight (SpaceIP). This had been successfully demonstrated by a few recent spaceflight experiments. However, while terrestrial applications of Internet protocols are well developed and understood (mostly due to billions of dollars in investments by the military and industry), the spaceflight application of Internet protocols is still in its infancy. Progress in the developments of SpaceIP-enabled instrument components will largely determine the SpaceIP utilization of those investments and acceptance in years to come. Likewise SpaceIP, the development of commercial real-time and instrument colocated computational resources, data compression and storage, can be enabled on-board a spacecraft and, in turn, support a powerful application to Sensor Web-based design of a spaceflight instrument. Sensor Web-enabled reconfiguration and adaptation of structures for hardware resources and information systems will commence application of Field Programmable Arrays (FPGA) and other aerospace programmable logic devices for what this technology was intended. These are a few obvious potential benefits of Sensor Web technologies for spaceflight applications. However, they are still waiting to be explored. This is because there is a need for a new approach to spaceflight instrumentation in order to make these mature sensor web technologies applicable for spaceflight. In this paper we present an approach in developing related and enabling spaceflight instrument-level technologies based on the new concept of a representative spaceflight Instrument Sensor Web (ISW).

Kizhner, Semion↗

Method and system for environmentally adaptive fault tolerant computing

A method and system for adapting fault tolerant computing. The method includes the steps of measuring an environmental condition representative of an environment. An on-board processing system's sensitivity to the measured environmental condition is measured. It is determined whether to reconfigure a fault tolerance of the on-board processing system based in part on the measured environmental condition. The fault tolerance of the on-board processing system may be reconfigured based in part on the measured environmental condition.

Copenhaver, Jason L.↗

Flexible silicon photonic architecture for accelerating distributed deep learning

The increasing size and complexity of deep learning (DL) models have led to the wide adoption of distributed training methods in datacenters (DCs) and high-performance computing (HPC) systems. However, communication among distributed computing units (CUs) has emerged as a major bottleneck in the training process. In this study, we propose Flex-SiPAC, a flexible silicon photonic accelerated compute cluster designed to accelerate multi-tenant distributed DL training workloads. Flex-SiPAC takes a co-design approach that combines a silicon photonic hardware platform with a tailored collective algorithm, optimized to leverage the unique physical properties of the architecture. The hardware platform integrates a novel wavelength-reconfigurable transceiver design and a micro-resonator-based wavelength-reconfigurable switch, enabling the system to achieve flexible bandwidth steering in the wavelength domain. The collective algorithm is designed to support reconfigurable topologies, enabling efficient all-reduce communications that are commonly used in DL training. The feasibility of the Flex-SiPAC architecture is demonstrated through two testbed experiments. First, an optical testbed experiment demonstrates the flexible routing of wavelengths by shuffling an array of input wavelengths using a custom-designed spatial-wavelength selective switch. Second, a four-GPU testbed running two DL workloads shows a 23% improvement in job completion time compared to a similarly sized leaf-spine topology. We further evaluate Flex-SiPAC using large-scale simulations, which show that Flex-SiPAC is able to reduce the communication time by 26% to 29% compared to state-of-the-art compute clusters under representative collective operations.

Wu, Zhenguo (ORCID:0000000322847985)↗

A fault-tolerant neutral-atom architecture for universal quantum computation

Quantum error correction (QEC) is essential for the realization of large-scale quantum computers. However, owing to the complexity of operating on the encoded ‘logical’ qubits, understanding the physical principles for building fault-tolerant quantum devices and combining them into efficient architectures is an outstanding scientific challenge. Here we use reconfigurable arrays of up to 448 neutral atoms to implement the key elements of a universal, fault-tolerant quantum processing architecture and experimentally explore their underlying working mechanisms. We first use surface codes to study how repeated QEC suppresses errors, demonstrating 2.14(13)x below-threshold performance in a four-round characterization circuit by leveraging atom loss detection and machine learning decoding. We then investigate logical entanglement using transversal gates and lattice surgery and extend it to universal logic through transversal teleportation with three-dimensional [[15,1,3]] codes, enabling arbitrary-angle synthesis with polylogarithmic overhead. Finally, we develop mid-circuit qubit reuse16, increasing experimental cycle rates by two orders of magnitude and enabling deep-circuit protocols with dozens of logical qubits and hundreds of logical teleportations with [[7,1,3]] and high-rate [[16,6,4]] codes while maintaining constant internal entropy. Our experiments show key principles for efficient architecture design, involving the interplay between quantum logic and entropy removal, judiciously using physical entanglement in logic gates and magic state generation, and leveraging teleportations for universality and physical qubit reset. These results establish foundations for scalable, universal error-corrected processing and its practical implementation in neutral atom systems.

atomic and molecular physics↗