Spaceborne memory organization, phase 1 Final report
Application of associative memories to data processing for future space vehicles
Gunderson, D. C.↗
SEARCH · Engineering Papers
Results for “memory spaces”
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.
Light flash phenomena induced by HzE particles
Astronauts and Apollo and Skylab missions have reported observing a variety of visual phenomena when their eyes are closed and adapted to darkness. These phenomena have been collectively labelled as light flashes. Visual phenomena which are similar in appearance to those observed in space have been demonstrated at the number of accelerator facilities by expressing the eyes of human subjects to beams of various types of radiation. In some laboratory experiments Cerenkov radiation was found to be the basis for the flashes observed while in other experiments Cerenkov radiation could apparently be ruled out. Experiments that differentiate between Cerenkov radiation and other possible mechanisms for inducing visual phenomena was then compared. The phenomena obtained in the presence and absence of Cerenkov radiation were designed and conducted. A new mechanism proposed to explain the visual phenomena observed by Skylab astronauts as they passed through the South Atlantic Anomaly, namely nuclear interactions in and near the sensitive layer of the retina, is covered. Also some studies to search for similar transient effects of space radiation on sensors and microcomputer memories are described.
Mcnulty, P. J.↗
An advanced, radiation hardened bulk CMOS/LSI technology
An advanced, second generation, bulk, Si-gate CMOS process is described. This process is capable of producing LSI and VLSI parts that are latch-up free and hardened to total dose levels in excess of 2 x 10 to the 5th rad-Si for applications in space and weapons radiation environments. Two memories designed to use this process are also described. Both circuits are 4096-bit, static CMOS RAMs.
Schroeder, J. E.↗
Supporting shared data structures on distributed memory architectures
Programming nonshared memory systems is more difficult than programming shared memory systems, since there is no support for shared data structures. Current programming languages for distributed memory architectures force the user to decompose all data structures into separate pieces, with each piece owned by one of the processors in the machine, and with all communication explicitly specified by low-level message-passing primitives. A new programming environment is presented for distributed memory architectures, providing a global name space and allowing direct access to remote parts of data values. The analysis and program transformations required to implement this environment are described, and the efficiency of the resulting code on the NCUBE/7 and IPSC/2 hypercubes are described.
Koelbel, Charles↗
Fast packet switch architectures for broadband integrated services digital networks
Background information on networking and switching is provided, and the various architectures that have been considered for fast packet switches are described. The focus is solely on switches designed to be implemented electronically. A set of definitions and a brief description of the functionality required of fast packet switches are given. Three basic types of packet switches are identified: the shared-memory, shared-medium, and space-division types. Each of these is described, and examples are given.
Tobagi, Fouad A.↗
The neutrino gravitational memory from a core collapse supernova: phenomenology and physics potential
General Relativity predicts that the passage of matter or radiation from an asymmetrically-emitting source should cause a permanent change in the local space-time metric. This phenomenon, called the gravitational memory effect, has never been observed, however supernova neutrinos have long been considered a promising avenue for its detection in the future. With the advent of deci-Hertz gravitational wave interferometers, observing the supernova neutrino memory will be possible, with important implications for multimessenger astronomy and for tests of gravity. In this work, we develop a phenomenological (analytical) toy model for the supernova neutrino memory effect, which is overall consistent with the results of numerical simulations. This description is then generalized to several case studies of interest. We find that, for a galactic supernova, the dimensionless strain, h(t), is of order ~ 10 -22 - 10 -21 , and develops over a typical time scale that varies between ~ 0.1 - 10 s, depending on the time-evolution of the anisotropy of the neutrino emission. The characteristic strain, h c (f), has a maximum at a frequency f max ~ Script $\mathcal{O}$(10 -1 ) - Script $\mathcal{O}$(1) Hz. The detailed features of the time- and frequency-structure of the memory strain will inform us of the matter dynamics near the collapsed core, and allow to distinguish between different stellar collapse scenarios. Next generation gravitational wave detectors like DECIGO and BBO will be sensitive to the neutrino memory effect for supernovae at typical galactic distances and beyond; with Ultimate DECIGO exceeding a detectability distance of 10 Mpc
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Test and evaluation of bubble memories
A description is presented of a test program which has shown that well-constructed bubble memories can operate reliably over long periods of time and at low error rates. Even the relatively high error rate of one memory during burn-in can be considered acceptable if compared with tape recorder standards. No wear-out mechanism or aging could be detected. Bubble memories are now considered suitable for long-duration space missions and certainly are suitable for many military and commercial applications. It must be recognized, however, that bubble memories are complex devices and not yet fully understood. While the particular memory tested may never find practical applications, it nevertheless has provided insight into performance characteristics considered typical of bubble memories.
Bahm, E.↗
Flight software memory sizing and CPU loading estimates
Estimates of the AP101 memory and central processing unit (CPU) requirements for the space shuttle orbiter are presented. The resource estimates reflect OASCAB approved change requests for Release 18 and Release 19. Memory sizes are presented in 32 bit full words, CPU loading is listed by percentage. Memory and CPU information was obtained from actual AP101 code where available, and from estimates provided by flight software development programmers.
Source record↗
Privateer
Privateer is a general-purpose data store that optimizes the tradeoff between storage space utilization and I/O performance. Privateer uses memory-mapped I/O with private mapping and an optimized writeback mechanism to maximize write parallelism and eliminate redundant writes; it also uses contentaddressable storage to optimize storage space via de-duplication.
Iwabuchi, Keita↗
Extrusion-based Additive Manufacturing of Regolith-Filled Shape Memory Vitrimer Composite for Lunar Construction
The National Aeronautics and Space Administration (NASA) is visiting the moon again. This time, the objective is to explore establishing a permanent lunar base. To achieve both longterm human habitation on the moon and future deep space travel, it is crucial to make the most of the in-situ resources and build autonomous systems on the moon to support the construction of a lunar habitat. NASA’s In-situ Resource Utilization (ISRU) program aims to minimize the need to ship heavy prefabricated structures, reducing cost and enhancing sustainability. Here, we developed an economical extrusion method for printing lunar regolith-based composites using shape memory vitrimer as a binder. A rheological study is conducted to determine the extrudability of the composite with different regolith weight percentages. Several characterizations were conducted on the composites. The as-printed composites exhibited compressive and flexural strengths of 73.32 MPa and 156.59 MPa, respectively, and good impact tolerance. The composite maintained 57.92% of its mechanical properties even after the second crack healing cycle. The composites also exhibit shape fixity ratio of 90.02% and shape recovery ratio of 83.46%. The simple synthesis method, sustainability, and good thermomechanical properties make the 3D printed composite an ideal material for lunar construction applications.
Kingsley Yeboah Gyabaah↗
The effects of mental representation on performance in a navigation task
In three experiments, we investigated the mental representations employed when instructions were followed that involved navigation in a space displayed as a grid on a computer screen. Performance was affected much more by the number of instructional units than by the number of words per unit. Performance in a three-dimensional space was independent of the number of dimensions along which participants navigated. However, memory for and accuracy in following the instructions were reduced when the task required mentally representing a three-dimensional space, as compared with representing a two-dimensional space, although the words used in the instructions were identical in the two cases. These results demonstrate the interdependence of verbal and spatial memory representations, because individuals' immediate memory for verbal navigation instructions is affected by their mental representation of the space referred to by the instructions.
Imagination↗
GASNet-EX Memory Kinds: Support for Device Memory in PGAS Programming Models
There is an emerging need for adaptive, lightweight communication in irregular HPC applications at exascale, where GPU accelerators provide the majority of available compute cycles. To address this need, Lawrence Berkeley National Lab is developing a programming system to support distributed-memory HPC application development using the Partitioned Global Address Space (PGAS) model. This work includes two major components: UPC++ and GASNet-EX. UPC++ is a C++ template library providing Remote Memory Access (RMA) and Remote Procedure Call (RPC) communication interfaces. GASNet-EX is a portable, high-performance communication middleware library, used by the implementations of UPC++ and many other PGAS programming models. We describe recent advances in GASNet-EX to efficiently implement zero-copy Remote Memory Access (RMA) communication to and from memory on accelerator devices such as GPUs. We demonstrate performance improvements via benchmark results from UPC++ (on Summit) and the Legion programming system (on DGX-1), both using GASNet-EX for communication.
Hargrove, Paul H↗
RTSJ Memory Areas and Their Affects on the Performance of a Flight-Like Attitude Control System
The two most important factors in improving performance in any software system, but especially a real-time, embedded system, are knowing which components are the low performers and knowing what can be done to improve their performance. The word performance with respect to a real-time, embedded system does not necessarily mean fast execution, which is the common definition when discussing non real-time systems. It also includes meeting all of the specified execution dead-lines and executing at the correct time without sacrificing non real-time performance. Using a Java prototype of an existing control system used on Deep Space 1[1], the effects from adding memory areas are measured and evaluated with respect to improving performance.
Real-time Specification for Java2 (RTSJ)↗
pnnl/memgaze
MemGaze is a memory analysis toolset that combines high-resolution trace analysis and low overhead measurement, both with respect to time and space. It provides high-resolution by collecting world-level memory access traces, where the highest resolution supported is back-to-back sequences. It achieves low-overhead in space and time by leveraging sampling and various methods of hardware support for collecting traces. Its post-mortem trace processing provides multiresolution analysis for locations vs. operations; accesses vs. spatio-temporal reuse, and reuse (distance, rate, volume) vs. access patterns.
Central, PNNL Developer↗
A Study of Shape Memory Polymer Based Slat-Cove Filler
Aircraft noise reduction is an application of current intense interest for which smart materials show significant potential. Specifically, the aeroacoustic noise produced by the unsteady aerodynamic flow about the leading-edge high-lift device, such as leading-edge slat, of typical transport-aircraft wings is of particular interest. Concepts with the most promise to mitigate this noise source, most notably the slat-cove filler concept, have focused on highly reconfigurable structures that change shape between different phases of the flight envelope. These shape changes often involve large deformation, which has stimulated the consideration of shape memory materials. In recent years, shape memory materials (SMMs) have drawn greater interest for applications such as smart fabrics, intelligent medical devices, self-deployable space structures, morphing structures and packaging. Compared to other shape memory materials, like shape memory alloys (SMAs) or shape memory ceramics (SMCs), shape memory polymers (SMPs) have desirable advantages such as high elastic deformation to enable large shape change, broad tailorability of mechanical properties, potential biocompatibility and biodegradability, ductility, light weight and ease of processing. However, SMPs still have some critical disadvantages such as insufficient mechanical and thermal characteristics for structural applications, low recovery stress, and long response time. The new LaRC shape memory thermosetting polymer composite (LaRC-SMPC) discussed herein was synthesized with nontoxic monomers and conductive/magnetic fillers to yield enhanced thermal/mechanical characteristics and faster response times. LaRC-SMPCs with a variety of fiber reinforcements [Kevlar®, carbon fiber (standard and thin-ply), and carbon-nanotube (CNT) sheet] were fabricated to tailor the physical properties and test for suitability as a slat-cove filler (SCF). The performance of SCF prototypes fabricated with the developed LaRC-SMPCs was evaluated using a bench-top test apparatus. The SCFs made of Kevlar® fiber fabric or carbon fiber fabric infused shape memory polymer composite (SMPC) exhibited kinking during simulated deployment and stowage, which can be problematic during operation. The SCF made of CNT sheet/SMP composite did not exhibit kinking, but the deployment was sluggish compared to carbon fiber fabric/SMP composite. This report documents the evolution of designing SMPCs as slat-cove fillers for aircraft noise reduction. In the course of the investigation, several 2 approaches were investigated to address shortcomings in material characteristics based on performance requirements of operational slat-cove fillers.
Kang, Jin Ho↗
Time-series learning of latent-space dynamics for reduced-order model closure
In this work, we study the performance of long short-term memory networks (LSTMs) and neural ordinary differential equations (NODEs) in learning latent-space representations of dynamical equations for an advection-dominated problem given by the viscous Burgers equation. Our formulation is devised in a nonintrusive manner with an equation-free evolution of dynamics in a reduced space with the latter being obtained through a proper orthogonal decomposition. In addition, we leverage the sequential nature of learning for both LSTMs and NODEs to demonstrate their capability for closure in systems that are not completely resolved in the reduced space. We assess our hypothesis for two advection-dominated problems given by the viscous Burgers equation. We observe that both LSTMs and NODEs are able to reproduce the effects of the absent scales for our test cases more effectively than does intrusive dynamics evolution through a Galerkin projection. This result empirically suggests that time-series learning techniques implicitly leverage a memory kernel for coarse-grained system closure as is suggested through the Mori–Zwanzig formalism.
97 MATHEMATICS AND COMPUTING↗
SpecSims: A Scalable Speculative Tree-based Simulation Cloning Framework for Finite Memory Machines
Simulation cloning is a technique in which cloned simulations whose state spaces differ partially from their parent simulation due to intervening events are spawned at runtime and concurrently advanced. It is a powerful method to carry out what-if analysis by speculatively exploring and evaluating the impact of various permutations of intervening cascade of events. Due to the exponential growth in the number of possible clones even for a small number of distinct intervening events, the practical efficacy of the approach is often severely limited by the maximum available memory of the computing host. In this paper, we introduce a novel speculative simulation cloning framework that executes a simulation cloning campaign capable of efficiently exploring an exponentially large space of clone simulations created by permutation of intervening events under a finite memory constraint. We provide a theoretical analysis of the runtime characteristics of our proposed approach and highlight its novel advantages such as memory-aware and as-long-as-needed execution. Furthermore, in support of our analytical findings and to demonstrate its practical feasibility, we implement a prototype of the cloning framework on a shared memory system and report its performance characteristics in the context of a heat diffusion simulation, and a power grid simulation subject to cascading disruptions from geomagnetic disturbances.
Simulation framework↗
Single Event Effects in Highly Scaled Devices for Space Applications
This paper discusses single-event upset (SEU) in memories and microprocessors that are the "drivers" of highly scaled commercial integrated circuits. Despite the decrease in critical charge that occurs for highly scaled CMOS devices, recent test data has shown that SEU rates are actually somewhat lower for scaled devices compared to older devices with larger feature size. Hard errors, which are increasingly important for memories, are discussed along with conventional soft errors. Functional errors in memories and microprocessors are particularly significant, and tend to dominate the response of highly scaled devices from an application standpoint. Predictions for future devices are made using the Semiconductor Industry Roadmap along with recent modeling and radiation test results.
microelectronics↗