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 577 records · Page 32

Integration of Ag-CBRAM crossbars and Mott ReLU neurons for efficient implementation of deep neural networks in hardware

In-memory computing with emerging non-volatile memory devices (eNVMs) has shown promising results in accelerating matrix-vector multiplications. However, activation function calculations are still being implemented with general processors or large and complex neuron peripheral circuits. Here, we present the integration of Ag-based conductive bridge random access memory (Ag-CBRAM) crossbar arrays with Mott rectified linear unit (ReLU) activation neurons for scalable, energy and area-efficient hardware (HW) implementation of deep neural networks. We develop Ag-CBRAM devices that can achieve a high ON/OFF ratio and multi-level programmability. Compact and energy-efficient Mott ReLU neuron devices implementing ReLU activation function are directly connected to the columns of Ag-CBRAM crossbars to compute the output from the weighted sum current. We implement convolution filters and activations for VGG-16 using our integrated HW and demonstrate the successful generation of feature maps for CIFAR-10 images in HW. Our approach paves a new way toward building a highly compact and energy-efficient eNVMs-based in-memory computing system.

Mott insulators↗

Noise-induced stabilization of dynamical states with broken time-reversal symmetry

Under a high frequency drive, Josephson junctions demonstrate Shapiro steps of quantized voltage. These are dynamically stabilized states in which the phase across the junction locks to the external drive. We explore the stochastic switching between two symmetric steps at $\frac{hw}{2e}$ and –$\frac{hw}{2e}$. Surprisingly, the switching rate exhibits a pronounced nonmonotonicity as a function of temperature, violating the general expectation that transitions should become faster with temperature. As a result, we explain this behavior by realizing that the system retains memory of the dynamic state from which it is switching, thereby breaking the conventional simplifying assumptions about separations of timescales.

36 MATERIALS SCIENCE↗

Electromagnetically induced transparency with quantized fields in optocavity mechanics

We report electromagnetically induced transparency (EIT) using quantized fields in optomechanical systems. The weak probe field is a narrowband squeezed field. We present a homodyne detection of EIT in the output quantum field. We find that the EIT dip exists even though the photon number in the squeezed vacuum is at the single-photon level. The EIT with quantized fields can be seen even at temperatures on the order of 100 mK, thus paving the way for using optomechanical systems as memory elements.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Accelerating Scientific Applications With SambaNova Reconfigurable Dataflow Architecture

Here, our exploratory work finds that the SambaNova Reconfigurable Dataflow Architecture (RDA) along with the SambaFlow software stack provides for an attractive system and solution to accelerate AI for science workloads. We have observed the efficacy of using the system with a diverse set of science applications and reasoned their suitability for performance gains over traditional hardware. As the Data-Scale system provides for a very large memory capacity, the system can be used to train models that typically do not fit in a GPU. The architecture also provides for deeper integration with upcoming supercomputers at the Argonne Leadership Computing Facility (ALCF), a US Department of Energy Office of Science user facility, to help advance science insights.

97 MATHEMATICS AND COMPUTING↗

TH-E-BRE-01: A 3D Solver of Linear Boltzmann Transport Equation Based On a New Angular Discretization Method with Positivity for Photon Dose Calculation Benchmarked with Geant4

Purpose: The Linear Boltzmann Transport Equation (LBTE) solved through statistical Monte Carlo (MC) method provides the accurate dose calculation in radiotherapy. This work is to investigate the alternative way for accurately solving LBTE using deterministic numerical method due to its possible advantage in computational speed from MC. Methods: Instead of using traditional spherical harmonics to approximate angular scattering kernel, our deterministic numerical method directly computes angular scattering weights, based on a new angular discretization method that utilizes linear finite element method on the local triangulation of unit angular sphere. As a Result, our angular discretization method has the unique advantage in positivity, i.e., to maintain all scattering weights nonnegative all the time, which is physically correct. Moreover, our method is local in angular space, and therefore handles the anisotropic scattering well, such as the forward-peaking scattering. To be compatible with image-guided radiotherapy, the spatial variables are discretized on the structured grid with the standard diamond scheme. After discretization, the improved sourceiteration method is utilized for solving the linear system without saving the linear system to memory. The accuracy of our 3D solver is validated using analytic solutions and benchmarked with Geant4, a popular MC solver. Results: The differences between Geant4 solutions and our solutions were less than 1.5% for various testing cases that mimic the practical cases. More details are available in the supporting document. Conclusion: We have developed a 3D LBTE solver based on a new angular discretization method that guarantees the positivity of scattering weights for physical correctness, and it has been benchmarked with Geant4 for photon dose calculation.

97 MATHEMATICS AND COMPUTING↗

Chalcogenide phase-change material advances programmable terahertz metamaterials: a non-volatile perspective for reconfigurable intelligent surfaces

Terahertz (THz) waves have gained considerable attention in the rising 6G communication due to their large bandwidth. However, the cost and power consumption become the major constraints for the commercialization of 6G THz systems as the frequency increases. Reconfigurable intelligent surface (RIS) comprising active metasurfaces and digital controllers has been proposed for beamforming in the 6G multiple-input-multiple-output systems, showing good potential to suppress the system size, weight, and power consumption (SWaP). Currently, their controlling diodes can hardly work up to THz frequencies. Therefore, several active stimuli have been investigated as alternatives. Among them, chalcogenide phase-change material Ge 2 Sb 2 Te 5 (GST) addresses large modulation depth, picosecond switching speed, and non-volatile properties. Notably, the non-volatile GST may enable RIS systems with memory and low control power. This work briefly reviews the advances of GST-tuned THz metamaterials (MTMs), discusses the current obstacles to overcome, and gives a perspective of GST applications in the rising 6G communications.

6G↗

MC-15: Next Generation Neutron Multiplicity Detector FY12 Annual Report

The MC-15 project finished its second year of a three year project. The objective of this $5.5 million dollar project is to develop (jointly with LANL, LLNL and SNL) the next generation neutron multiplicity detector to improve neutron diagnostics capabilities for early emergency response activities. Major activities completed this year include the agreement of a final detector design by all three labs. Also completed was the mechanical design with fabrication of parts starting this year. Significant improvements were made to the onboard memory storage and USB memory transfer system. The “stop work” imposed upon this project has delayed finalizing the analog electronics. This delay will affect the original project schedule, but we still hope to have two prototype detectors built by the end of FY13. Field testing will be pushed back to FY14.

Instrumentation Related to Nuclear Science & Techn↗

Techniques for Automated Performance Analysis

The performance of a particular HPC code depends on a multitude of variables, including compiler selection, optimization flags, OpenMP pool size, file system load, memory usage, MPI configuration, etc. As a result of this complexity, current predictive models have limited applicability, especially at scale. We present a formulation of scientific codes, nodes, and clusters that reduces complex performance analysis to well-known mathematical techniques. Building accurate predictive models and enhancing our understanding of scientific codes at scale is an important step towards exascale computing.

97 MATHEMATICS AND COMPUTING↗

Reducing Communication Costs for Sparse Matrix Multiplication within Algebraic Multigrid

We consider the sequence of sparse matrix-matrix multiplications performed during the setup phase of algebraic multigrid. In particular, we show that the most commonly used parallel algorithm is often not the most communication-efficient one for all of the matrix-matrix multiplications involved. By using an alternative algorithm, we show that the communication costs are reduced (in theory and practice), and we demonstrate the performance benefit for both model (structured) and more realistic unstructured problems on large-scale distributed-memory parallel systems. Our theoretical analysis shows that we can reduce communication by a factor of up to 5.4 for a model problem, and we observe in our empirical evaluation communication reductions of factors up to 4.7 for structured problems and 3.7 for unstructured problems. These reductions in communication translate to run-time speedups of up to factors of 2.3 and 2.5, respectively.

97 MATHEMATICS AND COMPUTING↗

Data storage, image tube type

Method and apparatus for the storage of digital or analog electrical signals are provided by a memory storage system employing a conventional vidicon tube. At the beginning of an operating cycle, the vidicon is conditioned to accept electrical data input by exposing its photosensitive target to a short, high intensity light flash. A first electron beam scan of the photosensitive surface then sets up a charge pattern on the photosensitive target. A second electron beam scan of the photosensitive surface by an unmodulated electron beam then develops an output signal across an output resistor by using capacitive currents. The conditioning and scanning steps are operated repetitively at high speed using conventional television camera scan, sync, and power supply circuitry to provide a low cost data storage system.

Lipoma, P. C.↗

Prevention of design flaws in multicomputer systems

Report summarizes research on failure mode analysis for multicomputer systems where two or more computers may serve as redundant set. Failure modes such as data bus monopolization, shutdown due to transients, loss of control system equalization, memory alteration, and software errors are discussed.

Romberg, J. M.↗

NASTRAN computer resource management for the matrix decomposition modules

Detailed computer resource measurements of the NASTRAN matrix decomposition spill logic were made using a software input/output monitor. These measurements showed that, in general, job cost can be reduced by avoiding spill. The results indicated that job cost can be minimized by using dynamic memory management. A prototype memory management system is being implemented and evaluated for the CDC Cyber computer.

Bolz, C. W.↗

On the impact of communication complexity in the design of parallel numerical algorithms

This paper describes two models of the cost of data movement in parallel numerical algorithms. One model is a generalization of an approach due to Hockney, and is suitable for shared memory multiprocessors where each processor has vector capabilities. The other model is applicable to highly parallel nonshared memory MIMD systems. In the second model, algorithm performance is characterized in terms of the communication network design. Techniques used in VLSI complexity theory are also brought in, and algorithm independent upper bounds on system performance are derived for several problems that are important to scientific computation.

Gannon, D.↗

On the impact of communication complexity on the design of parallel numerical algorithms

This paper describes two models of the cost of data movement in parallel numerical alorithms. One model is a generalization of an approach due to Hockney, and is suitable for shared memory multiprocessors where each processor has vector capabilities. The other model is applicable to highly parallel nonshared memory MIMD systems. In this second model, algorithm performance is characterized in terms of the communication network design. Techniques used in VLSI complexity theory are also brought in, and algorithm-independent upper bounds on system performance are derived for several problems that are important to scientific computation.

Gannon, D. B.↗

Partitioning problems in parallel, pipelined and distributed computing

The problem of optimally assigning the modules of a parallel program over the processors of a multiple computer system is addressed. A Sum-Bottleneck path algorithm is developed that permits the efficient solution of many variants of this problem under some constraints on the structure of the partitions. In particular, the following problems are solved optimally for a single-host, multiple satellite system: partitioning multiple chain structured parallel programs, multiple arbitrarily structured serial programs and single tree structured parallel programs. In addition, the problems of partitioning chain structured parallel programs across chain connected systems and across shared memory (or shared bus) systems are also solved under certain constraints. All solutions for parallel programs are equally applicable to pipelined programs. These results extend prior research in this area by explicitly taking concurrency into account and permit the efficient utilization of multiple computer architectures for a wide range of problems of practical interest.

Bokhari, S.↗