Parallel Memory-Efficient Computation of Symmetric Higher-Order Joint Moment Tensors.
Abstract not provided.
Li, Zitong↗
SEARCH · Engineering Papers
Results for “compute in memory”
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.
A Test Platform to Characterize Emerging Nonvolatile Memories for Computing
Explore the source record for details and available documents.
Agarwal, Sapan↗
A Review of Discrete Element Method (DEM) Particle Shapes and Size Distributions for Lunar Soil
As part of ongoing efforts to develop models of lunar soil mechanics, this report reviews two topics that are important to discrete element method (DEM) modeling the behavior of soils (such as lunar soils): (1) methods of modeling particle shapes and (2) analytical representations of particle size distribution. The choice of particle shape complexity is driven primarily by opposing tradeoffs with total number of particles, computer memory, and total simulation computer processing time. The choice is also dependent on available DEM software capabilities. For example, PFC2D/PFC3D and EDEM support clustering of spheres; MIMES incorporates superquadric particle shapes; and BLOKS3D provides polyhedra shapes. Most commercial and custom DEM software supports some type of complex particle shape beyond the standard sphere. Convex polyhedra, clusters of spheres and single parametric particle shapes such as the ellipsoid, polyellipsoid, and superquadric, are all motivated by the desire to introduce asymmetry into the particle shape, as well as edges and corners, in order to better simulate actual granular particle shapes and behavior. An empirical particle size distribution (PSD) formula is shown to fit desert sand data from Bagnold. Particle size data of JSC-1a obtained from a fine particle analyzer at the NASA Kennedy Space Center is also fitted to a similar empirical PSD function.
Lane, John E.↗
In situ Parallel Training of Analog Neural Network Using Electrochemical Random-Access Memory
In-memory computing based on non-volatile resistive memory can significantly improve the energy efficiency of artificial neural networks. However, accurate in situ training has been challenging due to the nonlinear and stochastic switching of the resistive memory elements. One promising analog memory is the electrochemical random-access memory (ECRAM), also known as the redox transistor. Its low write currents and linear switching properties across hundreds of analog states enable accurate and massively parallel updates of a full crossbar array, which yield rapid and energy-efficient training. While simulations predict that ECRAM based neural networks achieve high training accuracy at significantly higher energy efficiency than digital implementations, these predictions have not been experimentally achieved. In this work, we train a 3 × 3 array of ECRAM devices that learns to discriminate several elementary logic gates (AND, OR, NAND). We record the evolution of the network’s synaptic weights during parallel in situ (on-line) training, with outer product updates. Due to linear and reproducible device switching characteristics, our crossbar simulations not only accurately simulate the epochs to convergence, but also quantitatively capture the evolution of weights in individual devices. The implementation of the first in situ parallel training together with strong agreement with simulation results provides a significant advance toward developing ECRAM into larger crossbar arrays for artificial neural network accelerators, which could enable orders of magnitude improvements in energy efficiency of deep neural networks.
97 MATHEMATICS AND COMPUTING↗
Benchmarking Memory Performance with the Data Cube Operator
Data movement across a computer memory hierarchy and across computational grids is known to be a limiting factor for applications processing large data sets. We use the Data Cube Operator on an Arithmetic Data Set, called ADC, to benchmark capabilities of computers and of computational grids to handle large distributed data sets. We present a prototype implementation of a parallel algorithm for computation of the operatol: The algorithm follows a known approach for computing views from the smallest parent. The ADC stresses all levels of grid memory and storage by producing some of 2d views of an Arithmetic Data Set of d-tuples described by a small number of integers. We control data intensity of the ADC by selecting the tuple parameters, the sizes of the views, and the number of realized views. Benchmarking results of memory performance of a number of computer architectures and of a small computational grid are presented.
Frumkin, Michael A.↗
Design Space Exploration of Emerging Memory Technologies for Machine Learning Applications
Memory design space exploration methods study memory systems’ performances and limitations before implementation. The computer memory design space has grown exponentially because of the enormous growth of memory types, memory controllers, and application software. Computer simulators are commonly used for memory design space exploration. However, complex memory simulations take an enormous amount of time. Hence, in this paper, we proposed a machine learning-based design space exploration method for dynamic random-access memory and non-volatile memory systems. We applied our method to the CosmoGAN and LeNet applications to predict the following six memory response parameters: (i) bandwidth, (ii) power, (iii) average latency, (iv) average total latency, (v) memory reads, and (vi) memory writes. Our experimental results show that machine learning models can predict memory response parameter values faster than simulations. We used support vector machine, random forest, and gradient boosting machine learning models. We observed that the support vector machine provides better performance for bandwidth, average latency, and average total latency. The random forest model works better for memory reads and writes. The gradient boosting model provides superior prediction performance for power. We provide a detailed discussion on learning curve characteristics, error analysis, and memory type recommendation.
Hasan, S M Shamimul↗
Memory reduction through higher level language hardware.
Computer memory reduction through Fortran higher level language, discussing tradeoff between costs saved and additional logic hardware
Gellman, L.↗
Memory reduction through higher level language hardware
Computer memory reduction through Fortran higher level language, discussing tradeoff between costs saved and additional logic hardware
Gellman, L.↗
Comparison of uniform perturbation solutions and numerical solutions for some potential flows past slender bodies
Approximate solutions for potential flow past an axisymmetric slender body and past a thin airfoil are calculated using a uniform perturbation method and then compared with either the exact analytical solution or the solution obtained using a purely numerical method. The perturbation method is based upon a representation of the disturbance flow as the superposition of singularities distributed entirely within the body, while the numerical (panel) method is based upon a distribution of singularities on the surface of the body. It is found that the perturbation method provides very good results for small values of the slenderness ratio and for small angles of attack. Moreover, for comparable accuracy, the perturbation method is simpler to implement, requires less computer memory, and generally uses less computation time than the panel method. In particular, the uniform perturbation method yields good resolution near the regions of the leading and trailing edges where other methods fail or require special attention.
Wong, T. C.↗
Comparison of uniform perturbation and numerical solutions for some potential flows past slender bodies
Approximate solutions for potential flow past an axisymmetric slender body and past a thin airfoil are calculated using a uniform perturbation method and then compared with either the exact analytical solution or the solution obtained using a purely numerical method. The perturbation method is based upon a representation of the disturbance flow as the superposition of singularities distributed entirely within the body, while the numerical (panel) method is based upon a distribution of singularities on the surface of the body. It is found that the perturbation method provides very good results for small values of the slenderness ratio and for small angles of attack. Moreover, for comparable accuracy, the perturbation method is simpler to implement, requires less computer memory, and generally uses less computation time than the panel method. In particular, the uniform perturbation method yields good resolution near the regions of the leading and trailing edges where other methods fail or require special attention.
Wong, T.-C.↗
Hubble Space Telescope nickel-hydrogen battery and cell testing - An update
NASA's HST uses Ni-H2 batteries. NASA-Marshall has been conducting developmental tests of such batteries in both six-battery and 22-cell single battery arrays. Tests have recently been conducted on such batteries with a view to the possible need to free additional memory in the HST onboard computer; the electrical power system could contribute to this end by eliminating its software control charge mode capability, which requires significant computer memory capacity.
Brewer, Jeffrey C.↗
Performance evaluation of the Engineering Analysis and Data Systems (EADS) 2
The Engineering Analysis and Data System (EADS)II (1) was installed in March 1993 to provide high performance computing for science and engineering at Marshall Space Flight Center (MSFC). EADS II increased the computing capabilities over the existing EADS facility in the areas of throughput and mass storage. EADS II includes a Vector Processor Compute System (VPCS), a Virtual Memory Compute System (CFS), a Common Output System (COS), as well as Image Processing Station, Mini Super Computers, and Intelligent Workstations. These facilities are interconnected by a sophisticated network system. This work considers only the performance of the VPCS and the CFS. The VPCS is a Cray YMP. The CFS is implemented on an RS 6000 using the UniTree Mass Storage System. To better meet the science and engineering computing requirements, EADS II must be monitored, its performance analyzed, and appropriate modifications for performance improvement made. Implementing this approach requires tool(s) to assist in performance monitoring and analysis. In Spring 1994, PerfStat 2.0 was purchased to meet these needs for the VPCS and the CFS. PerfStat(2) is a set of tools that can be used to analyze both historical and real-time performance data. Its flexible design allows significant user customization. The user identifies what data is collected, how it is classified, and how it is displayed for evaluation. Both graphical and tabular displays are supported. The capability of the PerfStat tool was evaluated, appropriate modifications to EADS II to optimize throughput and enhance productivity were suggested and implemented, and the effects of these modifications on the systems performance were observed. In this paper, the PerfStat tool is described, then its use with EADS II is outlined briefly. Next, the evaluation of the VPCS, as well as the modifications made to the system are described. Finally, conclusions are drawn and recommendations for future worked are outlined.
Debrunner, Linda S.↗
Effect of Gamma Radiation on TaOₓ ECRAM
Electrochemical random access memory (ECRAM) is an emerging three-terminal nonvolatile memory (NVM) with highly controllable channel conductance which is promising for use as an analog memory (or synapse) in analog in-memory computing (IMC) systems. Energy-efficient analog IMC computing is particularly desirable for power-constrained, high-radiation environments such as satellites. However, little is known about the suitability of ECRAM for use in a total ionizing dose (TID) environment. Here, this work investigates the effect of Co-60 gamma radiation on the channel conductance and noise—two properties critical for analog IMC systems—of a TaO x -based ECRAM up to 17.3 Mrad(SiO 2 ) for both low- and high-channel-conductance state devices. A transient increase in conductance is observed in response to radiation which consists of two elements: an immediate increase in conductivity due to photocurrent and a secondary increase in conductivity, which has a slower rise and saturation and can persist for hours after exposure. This secondary, persistent photoconductivity is attributed to charging caused by hole trapping. These transient effects would not likely occur in a space environment due to the low dose rate compared with this experiment. No permanent change is found in the low conductance state (LCS) following exposure and the minor shift in the high conductance change would be less significant than the regular retention decay in this state. A permanent increase in the random telegraph noise is observed, possibly due to increased traps created in the channel. This work demonstrates that TaO x -based ECRAM is suitable for use in spaceborne analog IMC systems that are subject to significant TID.
ECRAM↗
Machine vision for real time orbital operations
Machine vision for automation and robotic operation of Space Station era systems has the potential for increasing the efficiency of orbital servicing, repair, assembly and docking tasks. A machine vision research project is described in which a TV camera is used for inputing visual data to a computer so that image processing may be achieved for real time control of these orbital operations. A technique has resulted from this research which reduces computer memory requirements and greatly increases typical computational speed such that it has the potential for development into a real time orbital machine vision system. This technique is called AI BOSS (Analysis of Images by Box Scan and Syntax).
Vinz, Frank L.↗
Critical evaluation of Jet-A spray combustion using propane chemical kinetics in gas turbine combustion simulated by KIVA-2
Jet-A spray combustion has been evaluated in gas turbine combustion with the use of propane chemical kinetics as the first approximation for the chemical reactions. Here, the numerical solutions are obtained by using the KIVA-2 computer code. The KIVA-2 code is the most developed of the available multidimensional combustion computer programs for application of the in-cylinder combustion dynamics of internal combustion engines. The released version of KIVA-2 assumes that 12 chemical species are present; the code uses an Arrhenius kinetic-controlled combustion model governed by a four-step global chemical reaction and six equilibrium reactions. Researchers efforts involve the addition of Jet-A thermophysical properties and the implementation of detailed reaction mechanisms for propane oxidation. Three different detailed reaction mechanism models are considered. The first model consists of 131 reactions and 45 species. This is considered as the full mechanism which is developed through the study of chemical kinetics of propane combustion in an enclosed chamber. The full mechanism is evaluated by comparing calculated ignition delay times with available shock tube data. However, these detailed reactions occupy too much computer memory and CPU time for the computation. Therefore, it only serves as a benchmark case by which to evaluate other simplified models. Two possible simplified models were tested in the existing computer code KIVA-2 for the same conditions as used with the full mechanism. One model is obtained through a sensitivity analysis using LSENS, the general kinetics and sensitivity analysis program code of D. A. Bittker and K. Radhakrishnan. This model consists of 45 chemical reactions and 27 species. The other model is based on the work published by C. K. Westbrook and F. L. Dryer.
Nguyen, H. L.↗
NASA's Seasonal-to-Interannual Prediction Project: In Partnership With the NCCS
Researchers with NASA's Season-to-Interannual Prediction Project (NSIPP) refer to different types of memory when running models on NCCS computers: the computer memory required for their models and the memory of the atmosphere or the ocean. Because of the atmosphere's chaotic nature, its memory is short. For weather predictions, the initial information taken from atmospheric observations has a limited useful life. Currently, there is no way to take observations, initialize an atmosphere model, integrate ahead in time, and make an accurate weather forecast beyond about 2 weeks. After that, the system becomes chaotic. What conditions could be used to make predictions beyond 2 weeks? If not conditions in the atmosphere, then the memory must be found somewhere else. That place is in the oceans. Although most changes in the atmosphere vary on a short timescale, the weather being a prime example, some important large atmospheric climate variations occur over much longer timescales-month s, years, or decades. NSIPP is interested specifically in those phenomena that occur over timescales of several months to a few years, and the El Nino Southern Oscillation (ENSO) is the most significant of these.
Source record↗
Spaceborne Processor Array
A Spaceborne Processor Array in Multifunctional Structure (SPAMS) can lower the total mass of the electronic and structural overhead of spacecraft, resulting in reduced launch costs, while increasing the science return through dynamic onboard computing. SPAMS integrates the multifunctional structure (MFS) and the Gilgamesh Memory, Intelligence, and Network Device (MIND) multi-core in-memory computer architecture into a single-system super-architecture. This transforms every inch of a spacecraft into a sharable, interconnected, smart computing element to increase computing performance while simultaneously reducing mass. The MIND in-memory architecture provides a foundation for high-performance, low-power, and fault-tolerant computing. The MIND chip has an internal structure that includes memory, processing, and communication functionality. The Gilgamesh is a scalable system comprising multiple MIND chips interconnected to operate as a single, tightly coupled, parallel computer. The array of MIND components shares a global, virtual name space for program variables and tasks that are allocated at run time to the distributed physical memory and processing resources. Individual processor- memory nodes can be activated or powered down at run time to provide active power management and to configure around faults. A SPAMS system is comprised of a distributed Gilgamesh array built into MFS, interfaces into instrument and communication subsystems, a mass storage interface, and a radiation-hardened flight computer.
Chow, Edward T.↗
A generalized memory test algorithm
A general algorithm for testing digital computer memory is presented. The test checks that (1) every bit can be cleared and set in each memory work, and (2) bits are not erroneously cleared and/or set elsewhere in memory at the same time. The algorithm can be applied to any size memory block and any size memory word. It is concise and efficient, requiring the very few cycles through memory. For example, a test of 16-bit-word-size memory requries only 384 cycles through memory. Approximately 15 seconds were required to test a 32K block of such memory, using a microcomputer having a cycle time of 133 nanoseconds.
Milner, E. J.↗