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 559 records · Page 31

A parallel dynamic load balancing algorithm for 3-D adaptive unstructured grids

Adaptive local grid refinement and coarsening results in unequal distribution of workload among the processors of a parallel system. A novel method for balancing the load in cases of dynamically changing tetrahedral grids is developed. The approach employs local exchange of cells among processors in order to redistribute the load equally. An important part of the load balancing algorithm is the method employed by a processor to determine which cells within its subdomain are to be exchanged. Two such methods are presented and compared. The strategy for load balancing is based on the Divide-and-Conquer approach which leads to an efficient parallel algorithm. This method is implemented on a distributed-memory MIMD system.

Vidwans, A.↗

Reconstructing the Hopfield network as an inverse Ising problem

We test four fast mean-field-type algorithms on Hopfield networks as an inverse Ising problem. The equilibrium behavior of Hopfield networks is simulated through Glauber dynamics. In the low-temperature regime, the simulated annealing technique is adopted. Although performances of these network reconstruction algorithms on the simulated network of spiking neurons are extensively studied recently, the analysis of Hopfield networks is lacking so far. For the Hopfield network, we found that, in the retrieval phase favored when the network wants to memory one of stored patterns, all the reconstruction algorithms fail to extract interactions within a desired accuracy, and the same failure occurs in the spin-glass phase where spurious minima show up, while in the paramagnetic phase, albeit unfavored during the retrieval dynamics, the algorithms work well to reconstruct the network itself. This implies that, as an inverse problem, the paramagnetic phase is conversely useful for reconstructing the network while the retrieval phase loses all the information about interactions in the network except for the case where only one pattern is stored. The performances of algorithms are studied with respect to the system size, memory load, and temperature; sample-to-sample fluctuations are also considered.

36 MATERIALS SCIENCE↗

LDRD final report : massive multithreading applied to national infrastructure and informatics.

Large relational datasets such as national-scale social networks and power grids present different computational challenges than do physical simulations. Sandia's distributed-memory supercomputers are well suited for solving problems concerning the latter, but not the former. The reason is that problems such as pattern recognition and knowledge discovery on large networks are dominated by memory latency and not by computation. Furthermore, most memory requests in these applications are very small, and when the datasets are large, most requests miss the cache. The result is extremely low utilization. We are unlikely to be able to grow out of this problem with conventional architectures. As the power density of microprocessors has approached that of a nuclear reactor in the past two years, we have seen a leveling of Moores Law. Building larger and larger microprocessor-based supercomputers is not a solution for informatics and network infrastructure problems since the additional processors are utilized to only a tiny fraction of their capacity. An alternative solution is to use the paradigm of massive multithreading with a large shared memory. There is only one instance of this paradigm today: the Cray MTA-2. The proposal team has unique experience with and access to this machine. The XMT, which is now being delivered, is a Red Storm machine with up to 8192 multithreaded 'Threadstorm' processors and 128 TB of shared memory. For many years, the XMT will be the only way to address very large graph problems efficiently, and future generations of supercomputers will include multithreaded processors. Roughly 10 MTA processor can process a simple short paths problem in the time taken by the Gordon Bell Prize-nominated distributed memory code on 32,000 processors of Blue Gene/Light. We have developed algorithms and open-source software for the XMT, and have modified that software to run some of these algorithms on other multithreaded platforms such as the Sun Niagara and Opteron multi-core chips.

97 MATHEMATICS AND COMPUTING↗

An Unipolar Terminal-Attractor Based Neural Associative Memory with Adaptive Threshold and Perfect Convergence

For the first time, a unipolar terminal-attractor based neural associative memory (TABAM)system with adaptive threshold and perfect convergence is presented. By adaptively setting thethreshold values for the dynamic iteration for the unipolar binary neuron states with terminal-attractors and inner-product approach, we demonstrate via computer simulation the achievement ofperfect convergence and correct retrieval. The simulation is completed with a small number of storedstates (M) and a small number of neurons (N) but a large M/N ratio. An experiment with exclusive-or logic operation using LCTV SLMs is used to show feasibility of the optoelectronic implementationof the models.

Associative↗

Development of a Computer Architecture to Support the Optical Plume Anomaly Detection (OPAD) System

The NASA OPAD spectrometer system relies heavily on extensive software which repetitively extracts spectral information from the engine plume and reports the amounts of metals which are present in the plume. The development of this software is at a sufficiently advanced stage where it can be used in actual engine tests to provide valuable data on engine operation and health. This activity will continue and, in addition, the OPAD system is planned to be used in flight aboard space vehicles. The two implementations, test-stand and in-flight, may have some differing requirements. For example, the data stored during a test-stand experiment are much more extensive than in the in-flight case. In both cases though, the majority of the requirements are similar. New data from the spectrograph is generated at a rate of once every 0.5 sec or faster. All processing must be completed within this period of time to maintain real-time performance. Every 0.5 sec, the OPAD system must report the amounts of specific metals within the engine plume, given the spectral data. At present, the software in the OPAD system performs this function by solving the inverse problem. It uses powerful physics-based computational models (the SPECTRA code), which receive amounts of metals as inputs to produce the spectral data that would have been observed, had the same metal amounts been present in the engine plume. During the experiment, for every spectrum that is observed, an initial approximation is performed using neural networks to establish an initial metal composition which approximates as accurately as possible the real one. Then, using optimization techniques, the SPECTRA code is repetitively used to produce a fit to the data, by adjusting the metal input amounts until the produced spectrum matches the observed one to within a given level of tolerance. This iterative solution to the original problem of determining the metal composition in the plume requires a relatively long period of time to execute the software in a modern single-processor workstation, and therefore real-time operation is currently not possible. A different number of iterations may be required to perform spectral data fitting per spectral sample. Yet, the OPAD system must be designed to maintain real-time performance in all cases. Although faster single-processor workstations are available for execution of the fitting and SPECTRA software, this option is unattractive due to the excessive cost associated with very fast workstations and also due to the fact that such hardware is not easily expandable to accommodate future versions of the software which may require more processing power. Initial research has already demonstrated that the OPAD software can take advantage of a parallel computer architecture to achieve the necessary speedup. Current work has improved the software by converting it into a form which is easily parallelizable. Timing experiments have been performed to establish the computational complexity and execution speed of major components of the software. This work provides the foundation of future work which will create a fully parallel version of the software executing in a shared-memory multiprocessor system.

Katsinis, Constantine↗

Competing Interactions between Mesoscale Length-Scales, Order-Disorder, and Martensitic Transformation in Ferromagnetic Shape Memory Alloys

In the present study, the effects of composition and heat treatments and the resulting microstructural changes on the martensitic transformation and ferromagnetic transition have been investigated in NiCoMnIn metamagnetic shape memory alloys. In this shape memory alloy system, it is observed that upon heat treatments at a wide temperature range, the onset temperature of the martensitic transformation follows a non-monotonic behavior with respect to heat treatment time, and the nature of the non-monotonic behavior is also a function of composition. This behavior cannot be attributed to well-known factors such as precipitation, change in local composition due to the precipitation and/or global degree of order. In this work, a systematic investigation through synthesis, thermal processing and characterization via thermo-physical measurements, transmission electron microscopy and in-situ synchrotron x-ray diffraction experiments has been used to correlate the non-monotonic dependence of the martensitic transformation and ferromagnetic transition temperatures to the evolution of L2 1 domains arising from a order/disorder phase transition. A thermodynamic model for the magneto-structural transition is combined with classical nucleation theory to further ascertain the role of microstructural length-scales on the onset of the martensitic transformation. This work thus provides understanding of the thermodynamic and kinetic factors that can be controlled to tune the coupled magneto-structural transformations in NiCoMnIn metamagnetic shape memory alloys.

36 MATERIALS SCIENCE↗

Initial Kernel Timing Using a Simple PIM Performance Model

This presentation will describe some initial results of paper-and-pencil studies of 4 or 5 application kernels applied to a processor-in-memory (PIM) system roughly similar to the Cascade Lightweight Processor (LWP). The application kernels are: * Linked list traversal * Sun of leaf nodes on a tree * Bitonic sort * Vector sum * Gaussian elimination The intent of this work is to guide and validate work on the Cascade project in the areas of compilers, simulators, and languages. We will first discuss the generic PIM structure. Then, we will explain the concepts needed to program a parallel PIM system (locality, threads, parcels). Next, we will present a simple PIM performance model that will be used in the remainder of the presentation. For each kernel, we will then present a set of codes, including codes for a single PIM node, and codes for multiple PIM nodes that move data to threads and move threads to data. These codes are written at a fairly low level, between assembly and C, but much closer to C than to assembly. For each code, we will present some hand-drafted timing forecasts, based on the simple PIM performance model. Finally, we will conclude by discussing what we have learned from this work, including what programming styles seem to work best, from the point-of-view of both expressiveness and performance.

BRIEFING CHARTS↗

Method and apparatus for front end gather/scatter memory coalescing

A system for processing gather and scatter instructions can implement a front-end subsystem, a back-end subsystem, or both. The front-end subsystem includes a prediction unit configured to determine a predicted quantity of coalesced memory access operations required by an instruction. A decode unit converts the instruction into a plurality of access operations based on the predicted quantity, and transmits the plurality of access operations and an indication of the predicted quantity to an issue queue. The back-end subsystem includes a load-store unit that receives a plurality of access operations corresponding to an instruction, determines a subset of the plurality of access operations that can be coalesced, and forms a coalesced memory access operation from the subset. A queue stores multiple memory addresses for a given load-store entry to provide for execution of coalesced memory accesses.

97 MATHEMATICS AND COMPUTING↗

Method and apparatus for back end gather/scatter memory coalescing

A system for processing gather and scatter instructions can implement a front-end subsystem, a back-end subsystem, or both. The front-end subsystem includes a prediction unit configured to determine a predicted quantity of coalesced memory access operations required by an instruction. A decode unit converts the instruction into a plurality of access operations based on the predicted quantity, and transmits the plurality of access operations and an indication of the predicted quantity to an issue queue. The back-end subsystem includes a load-store unit that receives a plurality of access operations corresponding to an instruction, determines a subset of the plurality of access operations that can be coalesced, and forms a coalesced memory access operation from the subset. A queue stores multiple memory addresses for a given load-store entry to provide for execution of coalesced memory accesses.

97 MATHEMATICS AND COMPUTING↗

Modeling and measuring multiprogramming and system overheads on a shared-memory multiprocessor - Case study

The present discussion of methods for quantifying multiprogramming (MP) overhead on a computer system illustrates two such techniques, respectively for quantifying MP overheads' lower bound and determining the MP overload of real workloads, in light of the percentage of parallel processing time that is consumed by MP overhead on Alliant multiprocessors. Kernel lock spinning is found to be a major factor in MP overhead, which accounts for more than half of total system overhead. It is noted that parallel environments' MP overhead is not statistically dependent on the number of parallel jobs undergoing multiprogramming.

Dimpsey, Robert T.↗

Reducing the Time to Tune Parallel Dense Linear Algebra Routines with Partial Execution and Performance Modeling

We present a modeling framework to accurately predict time to run dense linear algebra calculation. We report the framework’s accuracy in a number of varied computational environments such as shared memory multicore systems, clusters, and large supercomputing installations with tens of thousands of cores. We also test the accuracy for various algorithms, each of which having a different scaling properties and tolerance to low-bandwidth/high-latency interconnects. The predictive accuracy is very good and on the order of measurement accuracy which makes the method suitable for both dedicated and non-dedicated environments. We also present a practical application of our model to reduce the time required to tune and optimize large parallel runs whose time is dominated by linear algebra computations. We show practical examples of how to apply the methodology to avoid common pitfalls and reduce the influence of measurement errors and the inherent performance variability.

Linear systems↗

High Order Anchoring and Reinitialization of Level Set Function for Simulating Interface Motion

A second order interface anchoring method has been developed and used with fast sweeping algorithm for reinitialization of a level set function. The algebraic anchoring formulation ensures that the location of the actual interface is preserved, leading to better mass conservation property. It also provides high order accurate algebraic constraint for solving the Eikonal equation on a finite difference grid. Geometric properties of the interface such as surface normal and curvature are subsequently computed from the reinitialized distance function. Various analytical functions for modeling distortion in level set field are considered and accuracy of reinitialization is evaluated using first and second order anchoring schemes. It is also shown that accurate computation of interface curvature requires a high order anchor in addition to a high order fast sweeping method. Mass conservation property of reinitialization is also analyzed by considering test problems from literature including the classic Rider–Kothe single vortex problem. The formulation is suitable for efficient parallelization for both distributed memory and on-node shared memory parallel systems. In conclusion, scalability and performance of the reinitialization scheme on multiple architectures are demonstrated.

97 MATHEMATICS AND COMPUTING↗

Sparse, iterative simulation methods for one-dimensional laminar flames

Sparse, iterative simulation methods for one-dimensional laminar flames are proposed. The resulting steady and unsteady flame solvers exploit approximate Jacobians to greatly reduce the computational cost associated with matrix operations. The constant, non-unity Lewis number assumption is introduced to further reduce the computational cost. The solvers are also parallelized to reduce time-to-solution on distributed memory computer systems. Computed laminar flame speeds and species profiles for a range of chemical mechanisms (from 10 to 2878 species) are compared against a well-validated commercial code and are found to be consistent within solver tolerances. The computation times of both the unsteady and steady solutions increase only linearly with the number of species, which is a significant improvement over the quadratic or cubic scaling of existing steady-state flame solvers. For the largest mechanism tested, the steady-state flame solver is two orders of magnitude faster than commonly-used codes. The use of an approximate Jacobian is shown to reduce the rate of convergence for the steady-state solver, but does not significantly affect the domain of convergence. The steady-state solver with approximate Jacobian is thus well suited for computationally efficient laminar flame speed sweeps with large kinetic mechanisms.

42 ENGINEERING↗

Multithreaded Algorithms for Graph Coloring

Graph algorithms are challenging to parallelize when high performance and scalability are primary goals. Low concurrency, poor data locality, irregular access pattern, and high data access to computation ratio are among the chief reasons for the challenge. The performance implication of these features is exasperated on distributed memory machines. More success is being achieved on shared-memory, multi-core architectures supporting multithreading. We consider a prototypical graph problem, coloring, and show how a greedy algorithm for solving it can be e*ectively parallelized on multithreaded architectures. We present in particular two di*erent parallel algorithms. The first relies on speculation and iteration, and is suitable for any shared-memory, multithreaded system. The second uses data ow principles and is targeted at the massively multithreaded Cray XMT system. We benchmark the algorithms on three di*erent platforms and demonstrate scalable runtime performance. In terms of quality of solution, both algorithms use nearly the same number of colors as the serial algorithm.

Catalyurek, Umit V↗

Energy-efficient Mott activation neuron for full-hardware implementation of neural networks

To circumvent the von Neumann bottleneck, substantial progress has been made towards in-memory computing with synaptic devices. However, compact nanodevices implementing non-linear activation functions are required for efficient full-hardware implementation of deep neural networks. Here, in this work, we present an energy-efficient and compact Mott activation neuron based on vanadium dioxide and its successful integration with a conductive bridge random access memory (CBRAM) crossbar array in hardware. The Mott activation neuron implements the rectified linear unit function in the analogue domain. The neuron devices consume substantially less energy and occupy two orders of magnitude smaller area than those of analogue complementary metal–oxide semiconductor implementations. The LeNet-5 network with Mott activation neurons achieves 98.38% accuracy on the MNIST dataset, close to the ideal software accuracy. We perform large-scale image edge detection using the Mott activation neurons integrated with a CBRAM crossbar array. Our findings provide a solution towards large-scale, highly parallel and energy-efficient in-memory computing systems for neural networks.

electrical and electronic engineering↗

Restoring universality to the pinch-off of a bubble

The pinch-off of a bubble is an example of the formation of a singularity, exhibiting a characteristic separation of length and time scales. Because of this scale separation, one expects universal dynamics that collapse into self-similar behavior determined by the relative importance of viscous, inertial, and capillary forces. Surprisingly, however, the pinch-off of a bubble in a large tank of viscous liquid is known to be nonuniversal. In this work, we show that the pinch-off dynamics of a bubble confined in a capillary tube undergo a sequence of two distinct self-similar regimes, even though the entire evolution is controlled by a balance between viscous and capillary forces. We demonstrate that the early-time self-similar regime restores universality to bubble pinch-off by erasing the system’s memory of the initial conditions. Our findings have important implications for bubble/drop generation in microfluidic devices, with applications in inkjet printing, medical imaging, and synthesis of particulate materials.

moving contact lines↗