Search NASA⌕ Search

SEARCH · Search NASA

Results for “Memory systems”

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 1,387 records · Page 77

Waste Heat Recovery System: Lightweight Thermal Energy Recovery (LIGHTER) System

Broad Funding Opportunity Announcement Project: GM is using shape memory alloys that require as little as a 10°C temperature difference to convert low-grade waste heat into mechanical energy. When a stretched wire made of shape memory alloy is heated, it shrinks back to its pre-stretched length. When the wire cools back down, it becomes more pliable and can revert to its original stretched shape. This expansion and contraction can be used directly as mechanical energy output or used to drive an electric generator. Shape memory alloy heat engines have been around for decades, but the few devices that engineers have built were too complex, required fluid baths, and had insufficient cycle life for practical use. GM is working to create a prototype that is practical for commercial applications and capable of operating with either air- or fluid-based heat sources. GM’s shape memory alloy based heat engine is also designed for use in a variety of non-vehicle applications. For example, it can be used to harvest non-vehicle heat sources, such as domestic and industrial waste heat and natural geothermal heat, and in HVAC systems and generators.

ARPA-E↗

IRIS-GNN: Leveraging Graph Neural Networks for Scheduling on Truly Heterogeneous Runtime Systems

The diversity of accelerators in computer systems poses significant challenges for software developers, such as managing vendor-specific compiler toolchains, code fragmentation requiring different kernel implementations, and performance portability issues. To address these, the Intelligent Runtime System (IRIS) was developed. IRIS works across various systems, from smartphones to supercomputers, enabling automatic performance scaling based on available accelerators. It introduces abstract tasks for seamless execution transitions between accelerators while ensuring memory consistency and task dependencies. Although IRIS simplifies system details, optimal dynamic scheduling still requires user input to understand workload structures. To address this, we introduce a new scheduling policy for IRIS, termed IRIS-GNN, which is the first IRIS hybrid policy that operates in conjunction with the dynamic policies. This policy employs a Graph-Neural Network (GNN) to conduct Graph Classification of any task graphs submitted to IRIS. This GNN analyzes the structure and attributes of the task graph, categorizing it as either locality, concurrency, or mixed. This classification subsequently guides the selection of the dynamic policy used by IRIS. We provide a comparison of the performance of IRIS-GNN against the complete spectrum of IRIS’s dynamic policies, assess the overhead introduced by the GNN within this scheduling framework, and ultimately explore its practical application in real-world scenarios.

Johnston, Beau↗

Synthesis, Characterization and Application Of PbS Quantum Dots

Lead Chalcogenides (PbS, PbSe, PbTe) quantum dots (QDs) are ideal for fundamental studies of strongly quantum confined systems with possible technological applications. Tunable electronic transitions at near--infrared wavelengths can be obtained with these QDs. Applications of lead chalcogenides encompass quite a good number of important field viz. the fields of telecommunications, medical electronics, optoelectronics etc. Very recently, it has been proposed that 'memristor'(Memory resistor) can be realized in nanoscale systems with coupled ionic and electronic transports. The hystersis characteristics of 'memristor' are observed in many nanoscale electronic devices including semiconductor quantum dot devices. This paper reports synthesis of PbS QDs by chemical route. The fabricated samples are characterized by UV-Vis, XRD, SEM, TEM, EDS, etc. Observed characteristics confirm nano formation. I-V characteristics of the sample are studied for investigating their applications as 'memristor'.

36 MATERIALS SCIENCE↗

Advanced information processing system: Fault injection study and results

The objective of the AIPS program is to achieve a validated fault tolerant distributed computer system. The goals of the AIPS fault injection study were: (1) to present the fault injection study components addressing the AIPS validation objective; (2) to obtain feedback for fault removal from the design implementation; (3) to obtain statistical data regarding fault detection, isolation, and reconfiguration responses; and (4) to obtain data regarding the effects of faults on system performance. The parameters are described that must be varied to create a comprehensive set of fault injection tests, the subset of test cases selected, the test case measurements, and the test case execution. Both pin level hardware faults using a hardware fault injector and software injected memory mutations were used to test the system. An overview is provided of the hardware fault injector and the associated software used to carry out the experiments. Detailed specifications are given of fault and test results for the I/O Network and the AIPS Fault Tolerant Processor, respectively. The results are summarized and conclusions are given.

Burkhardt, Laura F.↗

Microstructure-sensitive mechanical behavior of an additively manufactured psuedoelastic shape memory alloy

The additive manufacturing of shape memory alloys into complex geometries enables fabrication of advanced functional systems across a variety of fields and domains. This work presents results focused on the mechanical behavior of additively manufactured shape memory pseudoelastic NiTi. The deformation induced solid state phase transformation from austenite to martensite allows this system to accommodate large recoverable strains. This deformation behavior is fundamentally driven by crystal-scale transformation physics. Laser powder bed fusion processing reveals that the resulting microstructure, both grain morphology and crystallographic texture, is strongly dependent on the manufacturing processing history. Exhaustive mechanical testing demonstrates that these microstructural factors strongly impact both tensile and cyclic stress–strain behavior. Cyclic dissipative behavior, however, is similar across all tested microstructures following an initial transient period. Remarkably, analysis of spatial strain fields during tensile loading reveals two distinctly different localization “modes”. The first is initiation of localized deformation bands which continuously propagate through the tensile bar during loading. In the second mode localization is observed but lacks propagation; instead additional localization cites nucleate during subsequent loading. The latter phenomena is suspected to be driven by grain-scale deformation physics as the localized band morphologies coincide with grain morphologies. These phenomena strongly impact the resulting aggregate stress–strain behavior. Hence, manufacturers and designers of psuedoelastic functional components must at the very least consider the potential variability in properties when considering additive manufacturing processing. More ideally the process–structure–property relations can be used to further tailor and optimize final functional performance.

Additive manufacturing↗

Low cost automated precise time measurement system

The Aerospace Guidance and Metrology Center (AGMC) has the responsibility for the dissemination of Precise Time and Time Interval (PTTI) to Air Force timing systems requiring microsecond time. In order to maintain traceability to the USNO Master Clock in Washington D.C., and accomplish efficient logging of time and frequency data on individual precision clocks, a simple automatic means of acquiring precise time has been devised. The Automatic Time Interval Measurement System (ATIMS) consists of a minicomputer (8K Memory), teletype terminal, electronic counter, Loran C receiver, time base generator and locally-manufactured relay matrix panel. During the measurement process, the computer controls the relay matrix which selects for comparison 13 atomic clocks against a reference clock and the reference versus Loran C. Through use of the system teletype, the operator is able to set the system clock (hours, minutes and seconds), examine and/or modify all clock data and constants, and set measurement intervals. This is done in a conversational manner. A logic flow diagram, system schematic, source listing and software components are included in the presentation.

Alpert, A.↗

Digital Instrumentation Analysis and Navigation System (DIANS) for system identification

Hardware, software, and performance features of the Digital Instrumentation and Navigation System (DIANS) designed for NASA research to collect flight data as a strap-down system are detailed. The support software for the system has a cross compiler, a linkage editor, and cross assembler, extended communication capabilities, postflight processing applications, and compilers for PASCAL, FORTRAN, CBASIC and MT. The DIANS microcomputer has a 1 Mbyte RAM module, a fast floating point processor board, a 68000 monoboard computer with 64 RAM, a 128 Kbyte bubble memory card, and a navigation radio. The system also carries a battery for full system operation for over an hour. The support software is also stored on a host mainframe computer, which has a CP/M operating system. Pitch, roll, and heading data are gathered from the on-board system, and communication is possible between the airborne and ground-based computer.

Smyth, R. K.↗

Scalable Cloning on Large-Scale GPU Platforms with Application to Time-Stepped Simulations on Grids

Cloning is a technique to efficiently simulate a tree of multiple what-if scenarios that are unraveled during the course of a base simulation. However, cloned execution is highly challenging to realize on large, distributed memory computing platforms, due to the dynamic nature of the computational load across clones, and due to the complex dependencies spanning the clone tree. In this paper, we present the conceptual simulation framework, algorithmic foundations, and runtime interface of CloneX, a new system we designed for scalable simulation cloning. It efficiently and dynamically creates whole logical copies of a dynamic tree of simulations across a large parallel system without full physical duplication of computation and memory. The performance of a prototype implementation executed on up to 1,024 graphical processing units of a supercomputing system has been evaluated with three benchmarks—heat diffusion, forest fire, and disease propagation models—delivering a speed up of over two orders of magnitude compared to replicated runs. Finally, the results demonstrate a significantly faster and scalable way to execute many what-if scenario ensembles of large simulations via cloning using the CloneX interface.

97 MATHEMATICS AND COMPUTING↗

Concurrent Image Processing Executive (CIPE)

The design and implementation of a Concurrent Image Processing Executive (CIPE), which is intended to become the support system software for a prototype high performance science analysis workstation are discussed. The target machine for this software is a JPL/Caltech Mark IIIfp Hypercube hosted by either a MASSCOMP 5600 or a Sun-3, Sun-4 workstation; however, the design will accommodate other concurrent machines of similar architecture, i.e., local memory, multiple-instruction-multiple-data (MIMD) machines. The CIPE system provides both a multimode user interface and an applications programmer interface, and has been designed around four loosely coupled modules; (1) user interface, (2) host-resident executive, (3) hypercube-resident executive, and (4) application functions. The loose coupling between modules allows modification of a particular module without significantly affecting the other modules in the system. In order to enhance hypercube memory utilization and to allow expansion of image processing capabilities, a specialized program management method, incremental loading, was devised. To minimize data transfer between host and hypercube a data management method which distributes, redistributes, and tracks data set information was implemented.

Lee, Meemong↗

Concurrent Image Processing Executive (CIPE). Volume 1: Design overview

The design and implementation of a Concurrent Image Processing Executive (CIPE), which is intended to become the support system software for a prototype high performance science analysis workstation are described. The target machine for this software is a JPL/Caltech Mark 3fp Hypercube hosted by either a MASSCOMP 5600 or a Sun-3, Sun-4 workstation; however, the design will accommodate other concurrent machines of similar architecture, i.e., local memory, multiple-instruction-multiple-data (MIMD) machines. The CIPE system provides both a multimode user interface and an applications programmer interface, and has been designed around four loosely coupled modules: user interface, host-resident executive, hypercube-resident executive, and application functions. The loose coupling between modules allows modification of a particular module without significantly affecting the other modules in the system. In order to enhance hypercube memory utilization and to allow expansion of image processing capabilities, a specialized program management method, incremental loading, was devised. To minimize data transfer between host and hypercube, a data management method which distributes, redistributes, and tracks data set information was implemented. The data management also allows data sharing among application programs. The CIPE software architecture provides a flexible environment for scientific analysis of complex remote sensing image data, such as planetary data and imaging spectrometry, utilizing state-of-the-art concurrent computation capabilities.

Lee, Meemong↗

Scalability Analysis of Gleipnir: A Memory Tracing and Profiling Tool, on Titan

Application performance is hindered by a variety of factors but most notably driven by the well know CPU-memory speed gap (also known as the memory wall). Understanding application s memory behavior is key if we are trying to optimize performance. Understanding application performance properties is facilitated with various performance profiling tools. The scope of profiling tools varies in complexity, ease of deployment, profiling performance, and the detail of profiled information. Specifically, using profiling tools for performance analysis is a common task when optimizing and understanding scientific applications on complex and large scale systems such as Cray s XK7. This paper describes the performance characteristics of using Gleipnir, a memory tracing tool, on the Titan Cray XK7 system when instrumenting large applications such as the Community Earth System Model. Gleipnir is a memory tracing tool built as a plug-in tool for the Valgrind instrumentation framework. The goal of Gleipnir is to provide fine-grained trace information. The generated traces are a stream of executed memory transactions mapped to internal structures per process, thread, function, and finally the data structure or variable. Our focus was to expose tool performance characteristics when using Gleipnir with a combination of an external tools such as a cache simulator, Gl CSim, to characterize the tool s overall performance. In this paper we describe our experience with deploying Gleipnir on the Titan Cray XK7 system, report on the tool s ease-of-use, and analyze run-time performance characteristics under various workloads. While all performance aspects are important we mainly focus on I/O characteristics analysis due to the emphasis on the tools output which are trace-files. Moreover, the tool is dependent on the run-time system to provide the necessary infrastructure to expose low level system detail; therefore, we also discuss any theoretical benefits that can be achieved if such modules were present.

Janjusic, Tommy↗

Fast and Scalable Sparse Triangular Solver for Multi-GPU Based HPC Architectures

Designing efficient and scalable sparse linear algebra kernels on modern multi-GPU based HPC systems is a daunting task due to significant irregular memory references and workload imbalance across the GPUs. This is particularly the case for \textit{Sparse Triangular Solver (SpTRSV)} which introduces additional two-dimensional computation dependencies among subsequent computation steps. Dependency information is exchanged and shared among GPUs, thus warrant for efficient memory allocation, data partitioning, and workload distribution as well as fine-grained communication and synchronization support. In this work, we demonstrate that directly adopting unified memory can adversely affect the performance of SpTRSV on multi-GPU architectures, despite linking via fast interconnect like NVLinks and NVSwitches. Alternatively, we employ the latest NVSHMEM technology based on Partitioned Global Address Space programming model to enable efficient fine-grained communication and drastic synchronization overhead reduction. Furthermore, to handle workload imbalance, we propose a malleable task-pool execution model which can further enhance the utilization of GPUs. By applying these techniques, our experiments on the NVIDIA multi-GPU supernode V100-DGX-1 and DGX-2 systems demonstrate that our design can achieve on average 3.53x (up to 9.86x) speedup on a DGX-1 system and 3.66x (up to 9.64x) speedup on a DGX-2 system with 4-GPUs over the Unified-Memory design. The comprehensive sensitivity and scalability studies also show that the proposed zero-copy SpTRSV is able to fully utilize the computing and communication resources of the multi-GPU system.

Xie, Chenhao↗

Contrasting advantages of learning with random weights and backpropagation in non-volatile memory neural networks

Recently, a Cambrian explosion of novel, non-volatile memory (NVM) devices known as memristive devices have inspired effort in building hardware neural networks that learn like the brain. Early experimental prototypes built simple perceptrons from nanosynapses, and recently, fully-connected multi-layer perceptron (MLP) learning systems have been realized. However, while backpropagating learning systems pair well with high-precision computer memories and achieve state-of-the-art performances, this typically comes with a massive energy budget. For future Internet of Things/peripheral use cases, system energy footprint will be a major constraint, and emerging NVM devices may fill the gap by sacrificing high bit precision for lower energy. In this work, we contrast the well known MLP approach with the Extreme Learning Machine (ELM) or NoProp approach, which uses a large layer of random weights to improve the separability of high-dimensional tasks, and is usually considered inferior in a software context. However, we find that when taking device non-linearity into account, NoProp manages to equal hardware MLP system in terms of accuracy. While also using a sign-based adaptation of the delta rule for energy-savings, we find that NoProp can learn effectively with four to six ’bits’ of device analog capacity, while MLP requires eight bit capacity with the same rule. This may allow the requirements for memristive devices to be relaxed in the context of online learning. By comparing the energy footprint of these systems for several candidate nanosynapses, as well as realistic peripherals, we confirm that memristive NoProp systems save energy compared to MLP systems. Lastly, we show that ELM/NoProp systems can achieve better generalization abilities than nanosynaptic MLP systems when paired with pre-processing layers (which do not require backpropagated error). Collectively, these advantages make such systems worthy of consideration in future accelerators or embedded hardware.

97 MATHEMATICS AND COMPUTING↗

Integrating an object system into CLIPS: Language design and implementation issues

This paper describes the reasons why an object system with integrated pattern-matching and object-oriented programming facilities is desirable for CLIPS and how it is possible to integrate such a system into CLIPS while maintaining the run-time performance and the low memory usage for which CLIPS is known. The requirements for an object system in CLIPS that includes object-oriented programming and integrated pattern-matching are discussed and various techniques for optimizing the object system and its integration with the pattern-matcher are presented.

Auburn, Mark↗

Boundary element analysis on vector and parallel computers

Boundary element analysis (BEA) can be characterized as a numerical technique that generally shifts the computational burden in the analysis toward numerical integration and the solution of nonsymmetric and either dense or blocked sparse systems of algebraic equations. Researchers have explored the concept that the fundamental characteristics of BEA can be exploited to generate effective implementations on vector and parallel computers. In this paper, the results of some of these investigations are discussed. The performance of overall algorithms for BEA on vector supercomputers, massively data parallel single instruction multiple data (SIMD), and relatively fine grained distributed memory multiple instruction multiple data (MIMD) computer systems is described. Some general trends and conclusions are discussed, along with indications of future developments that may prove fruitful in this regard.

Kane, J. H.↗

Network-Attached Solid-State Recorder Architecture

A document discusses placing memory modules on the high-speed serial interconnect, which is used by a spacecraft s computer elements for inter-processor communications, to allow all multiple computer system architectures to access the spacecraft data storage at the same time. Each memory board is identical electrically and receives its bus ID upon connection to the system. The computer elements are configured in a similar fashion. The architecture allows for multiple memory boards to be accessed simultaneously by different computer elements, and results in a scalable, strong, fault-tolerant system. The IEEE-1393 ring bus can be routed so that multiple card failures can occur and the mass memory storage will still function.

Cox, Brian↗

Distributed out-of-memory NMF on CPU/GPU architectures

We propose an efficient distributed out-of-memory implementation of the non-negative matrix factorization (NMF) algorithm for heterogeneous high-performance-computing systems. The proposed implementation is based on prior work on NMFk, which can perform automatic model selection and extract latent variables and patterns from data. In this work, we extend NMFk by adding support for dense and sparse matrix operation on multi-node, multi-GPU systems. The resulting algorithm is optimized for out-of-memory problems where the memory required to factorize a given matrix is greater than the available GPU memory. Memory complexity is reduced by batching/tiling strategies, and sparse and dense matrix operations are significantly accelerated with GPU cores (or tensor cores when available). Input/output latency associated with batch copies between host and device is hidden using CUDA streams to overlap data transfers and compute asynchronously, and latency associated with collective communications (both intra-node and inter-node) is reduced using optimized NVIDIA Collective Communication Library (NCCL) based communicators. Benchmark results show significant improvement, from 32X to 76x speedup, with the new implementation using GPUs over the CPU-based NMFk. Good weak scaling was demonstrated on up to 4096 multi-GPU cluster nodes with approximately 25,000 GPUs when decomposing a dense 340 Terabyte-size matrix and an 11 Exabyte-size sparse matrix of density 10 -6 .

97 MATHEMATICS AND COMPUTING↗

An advanced programmable/reconfigurable color graphics display system for crew station technology research

The hardware configuration, software organization, and applications software for the NASA IKONAS color graphics display system are described. The systems were created at the Langley Research Center Display Device Laboratory to develop, evaluate, and demonstrate advanced generic concepts, technology, and systems integration techniques for electronic crew station systems of future civil aircraft. A minicomputer with 64K core memory acts as a host for a raster scan graphics display generator. The architectures of the hardware system and the graphics display system are provided. The applications software features a FORTRAN-based model of an aircraft, a display system, and the utility program for real-time communications. The model accepts inputs from a two-dimensional joystick and outputs a set of aircraft states. Ongoing and planned work for image segmentation/generation, specialized graphics procedures, and higher level language user interface are discussed.

Montoya, R. J.↗