Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed 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.

At least 919 records · Page 51

Charged particle tracking in real-time using a full-mesh data delivery architecture and associative memory techniques

We present a flexible and scalable approach to address the challenges of charged particle track reconstruction in real-time event filters (Level-1 triggers) in collider physics experiments. The method described here is based on a full-mesh architecture for data distribution and relies on the Associative Memory approach to implement a pattern recognition algorithm that quickly identifies and organizes hits associated to trajectories of particles originating from particle collisions. We describe a successful implementation of a demonstration system composed of several innovative hardware and algorithmic elements. The implementation of a full-size system relies on the assumption that an Associative Memory device with the sufficient pattern density becomes available in the future, either through a dedicated ASIC or a modern FPGA. We demonstrate excellent performance in terms of track reconstruction efficiency, purity, momentum resolution, and processing time measured with data from a simulated LHC-like tracking detector.

47 OTHER INSTRUMENTATION↗

Reusable and Extensible High Level Data Distributions

This paper presents a reusable design of a data distribution framework for data parallel high performance applications. We are implementing the design in the context of the Chapel high productivity programming language. Distributions in Chapel are a means to express locality in systems composed of large numbers of processor and memory components connected by a network. Since distributions have a great effect on,the performance of applications, it is important that the distribution strategy can be chosen by a user. At the same time, high productivity concerns require that the user is shielded from error-prone, tedious details such as communication and synchronization. We propose an approach to distributions that enables the user to refine a language-provided distribution type and adjust it to optimize the performance of the application. Additionally, we conceal from the user low-level communication and synchronization details to increase productivity. To emphasize the generality of our distribution machinery, we present its abstract design in the form of a design pattern, which is independent of a concrete implementation. To illustrate the applicability of our distribution framework design, we outline the implementation of data distributions in terms of the Chapel language.

patterns↗

Communication Optimizations for a Wireless Distributed Prognostic Framework

Distributed architecture for prognostics is an essential step in prognostic research in order to enable feasible real-time system health management. Communication overhead is an important design problem for such systems. In this paper we focus on communication issues faced in the distributed implementation of an important class of algorithms for prognostics - particle filters. In spite of being computation and memory intensive, particle filters lend well to distributed implementation except for one significant step - resampling. We propose new resampling scheme called parameterized resampling that attempts to reduce communication between collaborating nodes in a distributed wireless sensor network. Analysis and comparison with relevant resampling schemes is also presented. A battery health management system is used as a target application. A new resampling scheme for distributed implementation of particle filters has been discussed in this paper. Analysis and comparison of this new scheme with existing resampling schemes in the context for minimizing communication overhead have also been discussed. Our proposed new resampling scheme performs significantly better compared to other schemes by attempting to reduce both the communication message length as well as number total communication messages exchanged while not compromising prediction accuracy and precision. Future work will explore the effects of the new resampling scheme in the overall computational performance of the whole system as well as full implementation of the new schemes on the Sun SPOT devices. Exploring different network architectures for efficient communication is an importance future research direction as well.

Saha, Sankalita↗

Differential memory in the earth's magnetotail

The process of 'differential memory' in the earth's magnetotail is studied in the framework of the modified Harris magnetotail geometry. It is verified that differential memory can generate non-Maxwellian features in the modified Harris field model. The time scales and the potentially observable distribution functions associated with the process of differential memory are investigated, and it is shown that non-Maxwelllian distributions can evolve as a test particle response to distribution function boundary conditions in a Harris field magnetotail model. The non-Maxwellian features which arise from distribution function mapping have definite time scales associated with them, which are generally shorter than the earthward convection time scale but longer than the typical Alfven crossing time.

Burkhart, G. R.↗

The Nature of Grand Minima and Maxima from Fully Nonlinear Flux Transport Dynamos

We aim to investigate the nature and occurrence characteristics of grand solar minimum and maximum periods, which are observed in the solar proxy records such as {sup 10}Be and {sup 14}C, using a fully nonlinear Babcock–Leighton type flux transport dynamo including momentum and entropy equations. The differential rotation and meridional circulation are generated from the effect of turbulent Reynolds stress and are subjected to back-reaction from the magnetic field. To generate grand minimum- and maximum-like periods in our simulations, we used random fluctuations in the angular momentum transport process, namely the Λ-mechanism, and in the Babcock–Leighton mechanism. To characterize the nature and occurrences of the identified grand minima and maxima in our simulations, we used the waiting time distribution analyses, which reflect whether the underlying distribution arises from a random or a memory-bearing process. The results show that, in the majority of the cases, the distributions of grand minima and maxima reveal that the nature of these events originates from memoryless processes. We also found that in our simulations the meridional circulation speed tends to be smaller during grand maximum, while it is faster during grand minimum periods. The radial differential rotation tends to be larger during grand maxima, while it is smaller during grand minima. The latitudinal differential rotation, on the other hand, is found to be larger during grand minima.

79 ASTRONOMY AND ASTROPHYSICS↗

Accurate, Fast and Scalable Kernel Ridge Regression on Parallel and Distributed Systems

Kernel Ridge Regression (KRR) is a fundamental method in machine learning. Given an n-by-d data matrix as input, a traditional implementation requires Θ(n2) memory to form an n-by-n kernel matrix and Θ(n3) flops to compute the final model. These time and storage costs prohibit KRR from scaling up to large datasets. For example, even on a relatively small dataset (a 520k-by-90 input requiring 357 MB), KRR requires 2 TB memory just to store the kernel matrix. Additionally, the reason is that n usually is much larger than d for real-world applications. On the other hand, weak scaling becomes a problem: if we keep d and n/p fixed as p grows (p is # machines), the memory needed grows as Θ(p) per processor and the flops as Θ(p2) per processor. In the perfect weak scaling situation, both the memory needed and the flops grow as Θ(1) per processor (i.e. memory and flops are constant). The traditional Distributed KRR implementation (DKRR) only achieved 0.32% weak scaling efficiency from 96 to 1536 processors. In this work, we propose two new methods to address these problems: the Balanced KRR (BKRR) and K-means KRR (KKRR). These methods consider alternative ways to partition the input dataset into p different parts, generating p different models, and then selecting the best model among them. Compared to a conventional implementation, KKRR2 (optimized version of KKRR) improves the weak scaling efficiency from 0.32% to 38% and achieves a 591x speedup for getting the same accuracy by using the same data and the same hardware (1536 processors). BKRR2 (optimized version of BKRR) achieves a higher accuracy than the current fastest method using less training time for a variety of datasets. For the applications requiring only approximate solutions, BKRR2 improves the weak scaling efficiency to 92% and achieves 3505x speedup (theoretical speedup: 4096x).

97 MATHEMATICS AND COMPUTING↗

Distributed Saturation

The Saturation algorithm for symbolic state-space generation, has been a recent break-through in the exhaustive veri cation of complex systems, in particular globally-asyn- chronous/locally-synchronous systems. The algorithm uses a very compact Multiway Decision Diagram (MDD) encoding for states and the fastest symbolic exploration algo- rithm to date. The distributed version of Saturation uses the overall memory available on a network of workstations (NOW) to efficiently spread the memory load during the highly irregular exploration. A crucial factor in limiting the memory consumption during the symbolic state-space generation is the ability to perform garbage collection to free up the memory occupied by dead nodes. However, garbage collection over a NOW requires a nontrivial communication overhead. In addition, operation cache policies become critical while analyzing large-scale systems using the symbolic approach. In this technical report, we develop a garbage collection scheme and several operation cache policies to help on solving extremely complex systems. Experiments show that our schemes improve the performance of the original distributed implementation, SmArTNow, in terms of time and memory efficiency.

Chung, Ming-Ying↗

Implementing efficient data compression and encryption in a persistent key-value store for HPC

Recently, persistent data structures, like key-value stores (KVSs), which are stored in a high-performance computing (HPC) system’s nonvolatile memory, provide an attractive solution for a number of emerging challenges like limited I/O performance. Data compression and encryption are two well-known techniques for improving several properties of such data-oriented systems. This article investigates how to efficiently integrate data compression and encryption into persistent KVSs for HPC with the ultimate goal of hiding their costs and complexity in terms of performance and ease of use. Our compression technique exploits deep memory hierarchy in an HPC system to achieve both storage reduction and performance improvement. Our encryption technique provides a practical level of security and enables sharing of sensitive data securely in complex scientific workflows with nearly imperceptible cost. We implement the proposed techniques on top of a distributed embedded KVS to evaluate the benefits and costs of incorporating these capabilities along different points in the dataflow path, illustrating differences in effective bandwidth, latency, and additional computational expense on Swiss National Supercomputing Centre’s Grand Tavé and National Energy Research Scientific Computing Center’s Cori.

97 MATHEMATICS AND COMPUTING↗

Concurrent Monte Carlo transport and fluence optimization with fluence adjusting scalable transport Monte Carlo

Purpose: The future of radiation therapy will require advanced inverse planning solutions to support single-arc, multiple-arc, and “4π” delivery modes, which present unique challenges in finding an optimal treatment plan over a vast search space, while still preserving dosimetric accuracy. The successful clinical implementation of such methods would benefit from Monte Carlo (MC) based dose calculation methods, which can offer improvements in dosimetric accuracy when compared to deterministic methods. The standard method for MC based treatment planning optimization leverages the accuracy of the MC dose calculation and efficiency of well-developed optimization methods, by precalculating the fluence to dose relationship within a patient with MC methods and subsequently optimizing the fluence weights. However, the sequential nature of this implementation is computationally time consuming and memory intensive. Methods to reduce the overhead of the MC precalculation have been explored in the past, demonstrating promising reductions of computational time overhead, but with limited impact on the memory overhead due to the sequential nature of the dose calculation and fluence optimization. The authors propose an entirely new form of “concurrent” Monte Carlo treat plan optimization: a platform which optimizes the fluence during the dose calculation, reduces wasted computation time being spent on beamlets that weakly contribute to the final dose distribution, and requires only a low memory footprint to function. In this initial investigation, the authors explore the key theoretical and practical considerations of optimizing fluence in such a manner. Methods: The authors present a novel derivation and implementation of a gradient descent algorithm that allows for optimization during MC particle transport, based on highly stochastic information generated through particle transport of very few histories. A gradient rescaling and renormalization algorithm, and the concept of momentum from stochastic gradient descent were used to address obstacles unique to performing gradient descent fluence optimization during MC particle transport. The authors have applied their method to two simple geometrical phantoms, and one clinical patient geometry to examine the capability of this platform to generate conformal plans as well as assess its computational scaling and efficiency, respectively. Results: The authors obtain a reduction of at least 50% in total histories transported in their investigation compared to a theoretical unweighted beamlet calculation and subsequent fluence optimization method, and observe a roughly fixed optimization time overhead consisting of ∼10% of the total computation time in all cases. Finally, the authors demonstrate a negligible increase in memory overhead of ∼7–8 MB to allow for optimization of a clinical patient geometry surrounded by 36 beams using their platform. Conclusions: This study demonstrates a fluence optimization approach, which could significantly improve the development of next generation radiation therapy solutions while incurring minimal additional computational overhead.

60 APPLIED LIFE SCIENCES↗

Modular Spiking Neural Circuits for Mapping Long Short-Term Memory on a Neurosynaptic Processor

Due to the distributed and asynchronous nature of neural computation through low-energy spikes, brain-inspired hardware systems offer high energy efficiency and massive parallelism. One such platform is the IBM TrueNorth neurosynaptic system. Recently, TrueNorth compatible representation learning algorithms have emerged, achieving close to the state-of-the-art performance in various data sets. However, its application in temporal sequence processing models, such as recurrent neural networks (RNNs), is still only at the proof of concept level. There is an inherent difficulty in capturing temporal dynamics of an RNN using spiking neurons, which is only exasperated by the hardware constraints in connectivity and synaptic weight resolution. This paper presents a design flow that overcomes these difficulties and maps a special case of recurrent networks called long short-term memory (LSTM) onto a spike-based platform. The framework utilizes various approximation techniques, such as activation discretization, weight quantization, and scaling and rounding, spiking neural circuits that implement the complex gating mechanisms, and a store-and-release technique to enable neuron synchronization and faithful storage. While the presented techniques can be applied to map LSTM to any spiking neural network (SNN) simulator/emulator, here we choose the TrueNorth chip as the target platform by adhering to its hardware constraints. Three LSTM applications, parity check, extended Reber grammar, and question classification, are evaluated. The tradeoffs among accuracy, performance, and energy tradeoffs achieved on TrueNorth are demonstrated. Finally, this is compared with the performance on an SNN platform without hardware constraints, which represents the upper bound of the achievable accuracy.

97 MATHEMATICS AND COMPUTING↗

An enhanced Ada run-time system for real-time embedded processors

An enhanced Ada run-time system has been developed to support real-time embedded processor applications. The primary focus of this development effort has been on the tasking system and the memory management facilities of the run-time system. The tasking system has been extended to support efficient and precise periodic task execution as required for control applications. Event-driven task execution providing a means of task-asynchronous control and communication among Ada tasks is supported in this system. Inter-task control is even provided among tasks distributed on separate physical processors. The memory management system has been enhanced to provide object allocation and protected access support for memory shared between disjoint processors, each of which is executing a distinct Ada program.

Sims, J. T.↗

A generalized massively parallel ultra-high order FFT-based Maxwell solver

Dispersion-free ultra-high order FFT-based Maxwell solvers have recently proven to be paramount to a large range of applications, including the high-fidelity modeling of high-intensity laser–matter interactions with Particle-In-Cell (PIC) codes. To enable a massively parallel scaling of these solvers, a novel parallelization technique was recently proposed, which consists in splitting the simulation domain into several processor sub-domains, with guard regions appended at each sub-domain boundary. Maxwell's equations are advanced independently on each sub-domain using local shared-memory FFTs (instead of a single distributed global FFT). This implies small truncation errors at sub-domain boundaries, the amplitude of which depends on guard regions sizes and order of the Maxwell solver. For moderate guard region sizes, this ’local’ technique proved to be highly scalable on up to a million cores and notably enabled the 3D modeling of so-called plasma mirrors, for which 8 guard cells only were enough to prevent truncation error growth. Yet, for other applications, the required number of guard cells might be much higher, which would severely limit the parallel efficiency of this technique due to the large volume of guard cells to be exchanged between sub-domains. In this context, we propose a novel parallelization technique that ensures very good scaling of FFT-based solvers with an arbitrarily high number of guard cells. Our ’hybrid’ technique consists in performing distributed FFTs on local groups of processors with guard regions now appended to boundaries of each group of processors. It uses a dual domain decomposition method for the Maxwell solver and other parts of the PIC cycle to keep the simulation load-balanced. This ’hybrid’ technique was implemented in the open source exascale library PICSAR. Benchmarks show that for a large number of guard cells (>16), the ’hybrid’ technique offers up to ×3 speed-up and ×8 memory savings compared to the ’local’ one.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Distribution of nanoscale nuclei in the amorphous dome of a phase change random access memory

The nanoscale crystal nuclei in an amorphous Ge{sub 2}Sb{sub 2}Te{sub 5} bit in a phase change memory device were evaluated by fluctuation transmission electron microscopy. The quench time in the device (∼10 ns) afforded more and larger nuclei in the melt-quenched state than in the as-deposited state. However, nuclei were even more numerous and larger in a test structure with a longer quench time (∼100 ns), verifying the prediction of nucleation theory that slower cooling produces more nuclei. It also demonstrates that the thermal design of devices will strongly influence the population of nuclei, and thus the speed and data retention characteristics.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

A simple and efficient random walk solution of multi-rate mobile/immobile mass transport equations

We extend the particle-tracking method to simulate general multi-rate mass transfer (MRMT) equations. Previous methods for single-rate equations used two-state Markov chains and found that the time a par- ticle spends in the mobile state between waiting time epochs is random and exponentially distributed. Using Bochner's subordination technique for Markov processes, we find that the random mobile times are still exponential for the stochastic process that corresponds to the MRMT equations. The random times in the immobile phase have a distribution that is directly related to the memory function of the MRMT equation. This connection allows us to interpret the MRMT memory function as the rate at which particles of a certain age, measured by residence time in the immobile zone, exit to become mobile once again. Because the exact distributions of mobile and immobile times are known from the MRMT equa- tions, they can be simulated very simply and efficiently using random walks.

58 GEOSCIENCES↗

Experimental investigation of the residues produced in the {sup 136}Xe+Pb and {sup 124}Xe+Pb fragmentation reactions at 1A GeV

The nuclide cross sections and longitudinal velocity distributions of residues produced in the reactions of {sup 136}Xe and {sup 124}Xe at 1A GeV in a lead target were measured at the high-resolution magnetic spectrometer, the fragment separator (FRS) of GSI. The data cover a broad range of isotopes of the elements between Z=3 and Z=56 for {sup 136}Xe and between Z=5 and Z=55 for {sup 124}Xe, reaching down to cross sections of a few microbarns. The velocity distributions exhibit a Gaussian shape for masses above A=20, while more complex behavior is observed for lighter masses. The isotopic distributions for both reactions preserve a memory on the projectile N/Z ratio over the whole residue mass range.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Dark matter transfer function: Free streaming, particle statistics, and memory of gravitational clustering

The transfer function T(k) of dark matter (DM) perturbations during matter domination is obtained by solving the linearized collisionless Boltzmann-Vlasov equation. We provide an exact expression for T(k) for arbitrary distribution functions of decoupled particles and initial conditions, which can be systematically expanded in a Fredholm series. An exhaustive numerical study of thermal relics for different initial conditions reveals that the first two terms in the expansion of T(k) provide a remarkably accurate and simple approximation valid on all scales of cosmological relevance for structure formation in the linear regime. The natural scale of suppression is the free-streaming wave vector at matter-radiation equality, k{sub fs}(t{sub eq})=[4{pi}{rho}{sub 0M}/[<V-vector{sup 2}>(1+z{sub eq})]]{sup 1/2}. An important ingredient is a nonlocal kernel determined by the distribution functions of the decoupled particles which describes the memory of the initial conditions and gravitational clustering and yields a correction to the fluid description. This correction is negligible at large scales k<<k{sub fs}(t{sub eq}) but it becomes important at small scales k{>=}k{sub fs}(t{sub eq}). Distribution functions that favor the small momentum region yield longer-range memory kernels and lead to an enhancement of power at small scales k>k{sub fs}(t{sub eq}). Fermi-Dirac and Bose-Einstein statistics lead to long-range memory kernels, with longer-range for bosons, both resulting in enhancement of T(k) at small scales. For DM thermal relics that decoupled while ultrarelativistic we find k{sub fs}(t{sub eq}){approx_equal}0.003(g{sub d}/2){sup 1/3} (m/keV) [kpc]{sup -1}, where g{sub d} is the number of degrees of freedom at decoupling. For WIMPS we obtain k{sub fs}(t{sub eq})=5.88(g{sub d}/2){sup 1/3} (m/100 GeV){sup 1/2} (T{sub d}/10 MeV){sup 1/2} [pc]{sup -1}. For k<<k{sub fs}(t{sub eq}), T(k){approx}1-C[k/k{sub fs}(t{sub eq})]{sup 2} where C=O(1) and independent of statistics for thermal relics. We provide simple and accurate fits for T(k) in a wide range of small scales k>k{sub fs}(t{sub eq}) for thermal relics and different initial conditions. The numerical and analytic results for arbitrary distribution functions and initial conditions allow an assessment of DM candidates through their impact on structure formation.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Multiplexed color centers in a silicon photonic cavity array

Entanglement distribution is central to the modular scaling of quantum processors and establishing quantum networks. Color centers with telecom-band transitions and long spin coherence times are suitable candidates for long-distance entanglement distribution. However, high-bandwidth memory-enhanced quantum communication is limited by high-yield, scalable creation of efficient spin-photon interfaces. Here, we develop a silicon photonics platform consisting of arrays of bus-coupled cavities. The coupling to a common bus waveguide enables simultaneous access to individually addressable cavity-enhanced T center arrays. We demonstrate frequency-multiplexed operation of two T centers in separate photonic crystal cavities. In addition, we investigate the cavity enhancement of a T center through hybridized modes formed between physically distant cavities. Our results show that bus-coupled arrays of cavity-enhanced color centers could enable efficient on-chip and long-distance entanglement distribution.

Komza, Lukasz↗

Theory and modeling of atmospheric turbulence, part 1

The cascade transfer which is the only function to describe the mode coupling as the result of the nonlinear hydrodynamic state of turbulence is discussed. A kinetic theory combined with a scaling procedure was developed. The transfer function governs the non-linear mode coupling in strong turbulence. The master equation is consistent with the hydrodynamical system that describes the microdynamic state of turbulence and has the advantages to be homogeneous and have fewer nonlinear terms. The modes are scaled into groups to decipher the governing transport processes and statistical characteristics. An equation of vorticity transport describes the microdynamic state of two dimensional, isotropic and homogeneous, geostrophic turbulence. The equation of evolution of the macrovorticity is derived from group scaling in the form of the Fokker-Planck equation with memory. The microdynamic state of turbulence is transformed into the Liouville equation to derive the kinetic equation of the singlet distribution in turbulence. The collision integral contains a memory, which is analyzed with pair collision and the multiple collision. Two other kinetic equations are developed in parallel for the propagator and the transition probability for the interaction among the groups.

Source record↗