Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel algorithm”

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 1,711 records · Page 95

File I/O for MPI Applications in Redundant Execution Scenarios

As multi-petascale and exa-scale high-performance computing (HPC) systems inevitably have to deal with a number of resilience challenges, such as a significant growth in component count and smaller circuit sizes with lower circuit voltages, redundancy may offer an acceptable level of resilience that traditional fault tolerance techniques, such as checkpoint/restart, do not. Although redundancy in HPC is quite controversial due to the associated cost for redundant components, the constantly increasing number of cores-per-processor is tilting this cost calculation toward a system design where computation, such as for redundancy, is much cheaper and communication, needed for checkpoint/restart, is much more expensive. Recent research and development activities in redundancy for Message Passing Interface (MPI) applications focused on availability/reliability models and replication algorithms. This paper takes a first step toward solving an open research problem associated with running a parallel application redundantly, which is file I/O under redundancy. The approach intercepts file I/O calls made by a redundant application to employ coordination protocols that execute file I/O operations in a redundancy-oblivious fashion when accessing a node-local file system, or in a redundancy-aware fashion when accessing a shared networked file system. A proof-of concept prototype is presented and a number of coordination protocols are described and evaluated. The results show the performance impact for redundantly accessing a shared networked file system, but also demonstrate the capability to regain performance by utilizing MPI communication between replicas and parallel file I/O.

99 GENERAL AND MISCELLANEOUS↗

Causal explicit algorithm for heat conduction in a plasma

Hyperbolic heat conduction extends standard Spitzer-Harm heat conduction by including a term proportional to the time derivative of the heat flux. The new term arises from a kinetic derivation of the heat flux that includes higher order corrections. Here we present a causal explicit numerical algorithm for solving the nonlinear hyperbolic heat conduction equation in an unmagnetized plasma. The maximum stable timestep for the causal explicit algorithm scales linearly with the cell size, owing to the hyperbolic nature of the problem. This is in contrast to the quadratic scaling of the maximum stable timestep with the cell size for the parabolic forward time centered space algorithm. The favorable scaling of the timestep with the cell size enables a practical explicit implementation of heat conduction in high-performance massively parallel plasma codes. In particular, we have implemented the causal explicit algorithm in the laser plasma interaction code pF3D. We verify the CE algorithm and analyze its convergence rate by simulating a harmonic mode, which has an analytic solution within the context of the HHC model. We also compare simulations using the CE algorithm to those using the forward time centered space algorithm on a pair of test problems: evolution in time of a Gaussian temperature perturbation in a uniform plasma and heat transport in the presence of inverse bremsstrahlung heating by a Gaussian laser speckle.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Distributed merge trees

Improved simulations and sensors are producing datasets whose increasing complexity exhausts our ability to visualize and comprehend them directly. To cope with this problem, we can detect and extract significant features in the data and use them as the basis for subsequent analysis. Topological methods are valuable in this context because they provide robust and general feature definitions. As the growth of serial computational power has stalled, data analysis is becoming increasingly dependent on massively parallel machines. To satisfy the computational demand created by complex datasets, algorithms need to effectively utilize these computer architectures. The main strength of topological methods, their emphasis on global information, turns into an obstacle during parallelization. We present two approaches to alleviate this problem. We develop a distributed representation of the merge tree that avoids computing the global tree on a single processor and lets us parallelize subsequent queries. To account for the increasing number of cores per processor, we develop a new data structure that lets us take advantage of multiple shared-memory cores to parallelize the work on a single node. Finally, we present experiments that illustrate the strengths of our approach as well as help identify future challenges. Copyright © 2013 ACM 978-1-4503-1922-5/13/ 02...$15.00.

Morozov, D↗

Distributed Merge Trees

Improved simulations and sensors are producing datasets whose increasing complexity exhausts our ability to visualize and comprehend them directly. To cope with this problem, we can detect and extract significant features in the data and use them as the basis for subsequent analysis. Topological methods are valuable in this context because they provide robust and general feature definitions. As the growth of serial computational power has stalled, data analysis is becoming increasingly dependent on massively parallel machines. To satisfy the computational demand created by complex datasets, algorithms need to effectively utilize these computer architectures. The main strength of topological methods, their emphasis on global information, turns into an obstacle during parallelization. We present two approaches to alleviate this problem. We develop a distributed representation of the merge tree that avoids computing the global tree on a single processor and lets us parallelize subsequent queries. To account for the increasing number of cores per processor, we develop a new data structure that lets us take advantage of multiple shared-memory cores to parallelize the work on a single node. Finally, we present experiments that illustrate the strengths of our approach as well as help identify future challenges.

97 MATHEMATICS AND COMPUTING↗

Theoretical Plasma Physics

Lattice Boltzmann algorithms are a mesoscopic method to solve problems in nonlinear physics which are highly parallelized – unlike the direction solution of the original problem. These methods are applied to both fluid and magnetohydrodynamic turbulence. By introducing entropic constraints one can enforce the positive definiteness of the distribution functions and so be able to simulate fluids at high Reynolds numbers without numerical instabilities. By introducing a vector distribution function for the magnetic field one can enforce the divergence free condition on the magnetic field automatically, without the need of divergence cleaning as needed in most direct numerical solutions of the resistive magnetohydrodynamic equations. The principal reason for the high parallelization of lattice Boltzmann codes is that they consist of a kinetic collisional relaxation step (which is purely local) followed by a simple shift of the relaxed data to neighboring lattice sites. In large eddy simulations, the closure schemes are highly nonlocal – the most famous of these schemes is that due to Smagorinsky. Under a lattice Boltzmann representation the Smagorinsky closure is purely local – being simply a particular moment on the perturbed distribution fucntions. After nonlocal fluid moment models were discovered to represent Landau damping, it was found possible to model these fluid models using an appropriate lattice Boltzmann algorithm. The close to ideal parallelization of the lattice Boltzmann codes permitted us to be Gordon Bell finalists on using the Earth Simulation in Japan. We have also been involved in the radio frequency propagation of waves into a tokamak and into a spherical overdense tokamak plasma. Initially we investigated the use of a quasi-optical grill for the launching of lower hybrid waves into a tokamak. It was found that the conducting walls do not prevent the rods from being properly irradiated, the overloading of the quasi-optical grill is not severe with the electric field only being about three times higher than in the ideal case. Moreover, the quasi-optical grill was significantly fewer structural elements that the multijunction grill. Nevertheless there has not been much interest from experimental fusion groups to implementing these structures. Hence we have returned to optimizing the multijunction grill so that the large number of coupling matrix elements can be efficiently evaluated using symmetry arguments. In overdense plasmas, the standard electromagnetic waves cannot propagate into the plasma center, but are reflected at the plasma edge. By optimizing mode conversion processes (in particular, the O-X-B wave propagation of Ordinary Mode converting to an Extraordinary mode which then converts into an electrostatic Bernstein wave) one can excite within the plasma an electrostatic Bernstein wave that does not suffer density cutoffs and is absorbed on the electron cyclotron harmonics. Finally we have started looking at other mesoscopic lattice algorithms that involve unitary collision and streaming steps. Because these algorithms are unitary they can be run on quantum computers when they become available – unlike their computational cousin of lattice Boltzmann which is a purely classical code. These quantum lattice gas algorithms have been tested successfully on exact analytic soliton collision solution. These calculations are hoped to be able to study Bose Einstein condensed atomic gases and their ground states in an optical lattice.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Efficient Distributed Optimization of Wind Farms Using Proximal Primal-Dual Algorithms: Preprint

This paper presents a distributed approach to perform real-time optimization of large wind farms. Wind turbines in a wind farm typically operate individually to maximize their own performance regardless of the impact of aerodynamic interactions on neighboring turbines. This paper optimizes the overall power produced by a wind farm by formulating and solving a nonconvex optimization problem where the yaw angles are optimized to allow some turbines to operate in misaligned conditions and shape the aerodynamic interactions in a favorable way. The solution of the nonconvex smooth problem is tackled using a proximal primal-dual gradient method, which provably identifies a first-order stationary solution in a global sublinear manner. By adding auxiliary optimization variables for every pair of turbines that are coupled aerodynamically and properly adding consensus constraints into the underlying problem, a distributed algorithm with turbine-to-turbine message passing is obtained; this allows for turbines to be optimized in parallel using local information rather than information from the whole wind farm. This algorithm is computationally light, as it involves closed-form updates. This approach is demonstrated on a large wind farm with 60 turbines. The results indicate that similar performance can be achieved as with finite-difference gradient-based optimization at a fraction of the computational time and thus approach real-time control/optimization.

17 WIND ENERGY↗

Efficient Distributed Optimization of Wind Farms Using Proximal Primal-Dual Algorithms

This paper presents a distributed approach to performing real-time optimization of large wind farms. Wind turbines in a wind farm typically operate individually to maximize their own performance regardless of the impact of aerodynamic interactions on neighboring turbines. This paper optimizes the overall power produced by a wind farm by formulating and solving a nonconvex optimization problem where the yaw angles are optimized to allow some turbines to operate in misaligned conditions and shape the aerodynamic interactions in a favorable way. The solution of the nonconvex smooth problem is tackled using a proximal primal-dual gradient method, which provably identifies a first-order stationary solution in a global sublinear manner. By adding auxiliary optimization variables for every pair of turbines that are coupled aerodynamically, and properly adding consensus constraints into the underlying problem, a distributed algorithm with turbine-to-turbine message passing is obtained; this allows for turbines to be optimized in parallel using local information rather than information from the whole wind farm. This algorithm is computationally light, as it involves closed-form updates. This approach is demonstrated on a large wind farm with 60 turbines. The results indicate that similar performance can be achieved as with finite-difference gradient-based optimization at a fraction of the computational time and thus approaching real-time control/optimization.

17 WIND ENERGY↗

ZEUS: An Efficient GPU Optimization Method Integrating PSO, BFGS, and Automatic Differentiation

We introduce a novel, efficient computational method, ZEUS, for numerical optimization, and provide an open-source implementation. It has four key ingredients: (1) particle swarm optimization (PSO), (2) the use of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) method, (3) automatic differentiation (AD), and (4) GPUs. Our approach addresses the computational challenges inherent in high-dimensional, non-convex optimization problems. In the first phase of the algorithm, we get a potentially good set of starting points using PSO. Thereafter, we run BFGS independently in parallel from these starting points. BFGS is one of the best-performing algorithms for numerical optimization. However, it requires the gradient of the function being optimized. ZEUS integrates automatic differentiation into BFGS thus avoiding the need for the user to calculate derivatives explicitly. The use of GPUs allows ZEUS to speed up the calculations substantially. We carry out systematic studies to explore the trade-offs between the number of PSO iterations taken, starting points, and BFGS iteration depth. We show that a handful of iterations of PSO can improve global convergence when combined with BFGS. We also present performance studies using common test functions. The source code can be found at https://github.com/fnal-numerics/global-optimizer-gpu.

Soos, Dominik [Old Dominion U.]↗

Bayesian inference of nonlinear unsteady aerodynamics from aeroelastic limit cycle oscillations

A Bayesian model selection and parameter estimation algorithm is applied to investigate the influence of nonlinear and unsteady aerodynamic loads on the limit cycle oscillation (LCO) of a pitching airfoil in the transitional Reynolds number regime. At small angles of attack, laminar boundary layer trailing edge separation causes negative aerodynamic damping leading to the LCO. The fluid–structure interaction of the rigid, but elastically mounted, airfoil and nonlinear unsteady aerodynamics is represented by two coupled nonlinear stochastic ordinary differential equations containing uncertain parameters and model approximation errors. Several plausible aerodynamic models with increasing complexity are proposed to describe the aeroelastic system leading to LCO. The likelihood in the posterior parameter probability density function (pdf) is available semi-analytically using the extended Kalman filter for the state estimation of the coupled nonlinear structural and unsteady aerodynamic model. The posterior parameter pdf is sampled using a parallel and adaptive Markov Chain Monte Carlo (MCMC) algorithm. The posterior probability of each model is estimated using the Chib–Jeliazkov method that directly uses the posterior MCMC samples for evidence (marginal likelihood) computation. The Bayesian algorithm is validated through a numerical study and then applied to model the nonlinear unsteady aerodynamic loads using wind-tunnel test data at various Reynolds numbers.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Improving the Performance Scalability of the Community Atmosphere Model

The Community Atmosphere Model (CAM), which serves as the atmosphere component of the Community Climate System Model (CCSM), is the most computationally expensive CCSM component in typical configurations. On current and next-generation leadership class computing systems, the performance of CAM is tied to its parallel scalability. Improving performance scalability in CAM has been a challenge, due largely to algorithmic restrictions necessitated by the polar singularities in its latitude-longitude computational grid. Nevertheless, through a combination of exploiting additional parallelism, implementing improved communication protocols, and eliminating scalability bottlenecks, we have been able to more than double the maximum throughput rate of CAM on production platforms. We describe these improvements and present results on the Cray XT5 and IBM BG/P. The approaches taken are not specific to CAM and may inform similar scalability enhancement activities for other codes.

99 GENERAL AND MISCELLANEOUS↗

Algorithms and Libraries

This exploratory study initiated our inquiry into algorithms and applications that would benefit by latency tolerant approach to algorithm building, including the construction of new algorithms where appropriate. In a multithreaded execution, when a processor reaches a point where remote memory access is necessary, the request is sent out on the network and a context--switch occurs to a new thread of computation. This effectively masks a long and unpredictable latency due to remote loads, thereby providing tolerance to remote access latency. We began to develop standards to profile various algorithm and application parameters, such as the degree of parallelism, granularity, precision, instruction set mix, interprocessor communication, latency etc. These tools will continue to develop and evolve as the Information Power Grid environment matures. To provide a richer context for this research, the project also focused on issues of fault-tolerance and computation migration of numerical algorithms and software. During the initial phase we tried to increase our understanding of the bottlenecks in single processor performance. Our work began by developing an approach for the automatic generation and optimization of numerical software for processors with deep memory hierarchies and pipelined functional units. Based on the results we achieved in this study we are planning to study other architectures of interest, including development of cost models, and developing code generators appropriate to these architectures.

Dongarra, Jack↗

Optimizing temperature distributions for training neural quantum states using parallel tempering

Parametrized artificial neural networks (ANNs) can be very expressive ansatzes for variational algorithms, reaching state-of-the-art energies on many quantum many-body Hamiltonians. Nevertheless, the training of the ANN can be slow and stymied by the presence of local minima in the parameter landscape. One approach to mitigate this issue is to use parallel tempering methods, and in this work, we focus on the role played by the temperature distribution of the parallel tempering replicas. Using an adaptive method that adjusts the temperatures in order to equate the exchange probability between neighboring replicas, we show that this temperature optimization can significantly increase the success rate of the variational algorithm with negligible computational cost by eliminating bottlenecks in the replicas' random walk. Furthermore, we demonstrate this using two different neural networks, a restricted Boltzmann machine and a feedforward network, which we use to study a toy problem based on a permutation invariant Hamiltonian with a pernicious local minimum and the 𝐽 1 −𝐽 2 model on a rectangular lattice.

Neural network simulations↗

Prediction of perovskite and other ternary oxide multilayers as mirrors for soft X-rays

Highlights: • Theoretical framework to identify optimal multilayers for high x-ray reflectivity. • Perovskite oxide multilayers are proposed as soft x-ray mirrors. • High soft x-ray reflectivity up to 33% are expected in perovskite multilayers. - Abstract: We propose multilayers of perovskite and related ternary oxides with a general formula of ABO{sub 3} as high reflectivity mirrors, especially for use in water window region (2.3–4.4 nm). The high reflectivity combinations of oxide multilayers were deduced using evolutionary search algorithms such as genetic algorithms, and the calculation speed was accelerated via parallel computing methods We also propose a figure of merit for X-ray reflectivity in periodic multilayers systems, which can simplify the future efforts on identifying material combinations, and the search through this multi-dimensional parameter space. The highest reflectivity value was found to be over 33% at 3.1 nm in the water window region. The effect of interface roughness was simulated and the decrease in reflectivity was found to be modest for practically achievable roughness values. This work establishes the foundation for future experimental and theoretical studies towards achieving high reflectivity x-ray mirrors of complex oxide multilayers.

36 MATERIALS SCIENCE↗

SU-E-T-765: Treatment Planning Comparison of SFUD Proton and 4Ï€ Radiotherapy for Prostate Cases

Purpose: Single-Field Uniform Dose (SFUD) proton scanning beams and non-coplanar 4π intensity-modulated radiation therapy (IMRT) represent the most advanced treatment methods based on heavy ion and X-rays, respectively. Here we compare their performance for prostate treatment. Methods: Five prostate patients were planned using 4π radiotherapy and SFUD to an initial dose of 54Gy to a planning target volume (PTV) that encompassed the prostate and seminal vesicles, then a boost prescription dose of 25.2Gy to the prostate for a total dose of 79.2 Gy. 4π plans were created by inversely selecting and optimizing 30 beams from 1162 candidate non-coplanar beams using a greedy column generation algorithm. The SFUD plans utilized two coplanar, parallel-opposing lateral scanning beams. The SFUD plan PTV was modified to account for range uncertainties while keeping an evaluation PTV identical to that of the X-ray plans for comparison. PTV doses, bladder and rectum dose volumes (V40, V45, V60, V70, V75.6, and V80), R50, and PTV homogeneity index (D95/D5) were evaluated. Results: Compared to SFUD, 4π resulted in 6.8% lower high dose spillage as indicated by R50. Bladder and rectum mean doses were 38.3% and 28.2% lower for SFUD, respectively. However, bladder and rectum volumes receiving >70Gy were 13.1% and 12% greater using proton SFUD. Due to the parallel-opposing beam arrangement, SFUD resulted in greater femoral head (87.8%) and penile bulb doses (43.7%). 4π PTV doses were slightly more homogeneous (HI 0.99 vs. 0.98) than the SFUD dose. Conclusion: Proton is physically advantageous to reduce the irradiated normal volume and mean doses to the rectum and bladder but it is also limited in the beam orientations and entrance dose, which resulted in greater doses to the femoral heads and penile bulb, and larger volumes of rectum and bladder exposed to high dose due to the required robust PTV definition. This project is supported by Varian Medical Systems.

60 APPLIED LIFE SCIENCES↗

Parallel multi-time step integration on a transputer system

An algorithm which allows different nodes of the finite element mesh to be integrated with different time steps is presented for second order finite element systems. The implementation of this algorithm on a system of transputer processors is discussed and a numerical example is used to evaluate the efficiency of the algorithm.

Smolinski, P.↗

Mentat/A: Medium grain parallel processing

The objective of this project is to support the Algorithm to Architecture Mapping Model (ATAMM) firing rules using the Mentat run-time system and the Mentat Programming Language (MPL). Specifically, this required changes to (1) modify the run-time system to control queue length and inhibit actor firing until required data tokens are available and space is available in the input queues of all of the direct descendent actors, (2) disallow the specification of persistent object classes in the MPL, and (3) permit only decision free graphs in the MPL. We have been successful in implementing the spirit of the plan, although some goals changed as we came to better understand the problem. Here, we report on what we accomplished and the lessons we learned. The Mentat/A runtime system, the compiler, results for three applications, and a summary and some observations are given. Appendix A contains a list of technical reports and published papers partially supported by the grant. Appendix B contains listings for the three applications.

Grimshaw, Andrew S.↗

Mentat/A: Medium grain parallel processing

The objective of this project is to test the Algorithm to Architecture Mapping Model (ATAMM) firing rules using the Mentat run-time system and the Mentat Programming Language (MPL). A special version of Mentat, Mentat/A (Mentat/ATAMM) was constructed. This required changes to: (1) modify the run-time system to control queue length and inhibit actor firing until required data tokens are available and space is available in the input queues of all of the direct descendent actors; (2) disallow the specification of persistent object classes in the MPL; and (3) permit only decision free graphs in the MPL. We were successful in implementing the spirit of the plan, although some goals changed as we came to better understand the problem. We report on what we accomplished and the lessons we learned. The Mentat/A run-time system is discussed, and we briefly present the compiler. We present results for three applications and conclude with a summary and some observations. Appendix A contains a list of technical reports and published papers partially supported by the grant. Appendix B contains listings for the three applications.

Grimshaw, Andrew S.↗

Highly Parallel Computing Architectures by using Arrays of Quantum-dot Cellular Automata (QCA): Opportunities, Challenges, and Recent Results

There has been significant improvement in the performance of VLSI devices, in terms of size, power consumption, and speed, in recent years and this trend may also continue for some near future. However, it is a well known fact that there are major obstacles, i.e., physical limitation of feature size reduction and ever increasing cost of foundry, that would prevent the long term continuation of this trend. This has motivated the exploration of some fundamentally new technologies that are not dependent on the conventional feature size approach. Such technologies are expected to enable scaling to continue to the ultimate level, i.e., molecular and atomistic size. Quantum computing, quantum dot-based computing, DNA based computing, biologically inspired computing, etc., are examples of such new technologies. In particular, quantum-dots based computing by using Quantum-dot Cellular Automata (QCA) has recently been intensely investigated as a promising new technology capable of offering significant improvement over conventional VLSI in terms of reduction of feature size (and hence increase in integration level), reduction of power consumption, and increase of switching speed. Quantum dot-based computing and memory in general and QCA specifically, are intriguing to NASA due to their high packing density (10(exp 11) - 10(exp 12) per square cm ) and low power consumption (no transfer of current) and potentially higher radiation tolerant. Under Revolutionary Computing Technology (RTC) Program at the NASA/JPL Center for Integrated Space Microelectronics (CISM), we have been investigating the potential applications of QCA for the space program. To this end, exploiting the intrinsic features of QCA, we have designed novel QCA-based circuits for co-planner (i.e., single layer) and compact implementation of a class of data permutation matrices, a class of interconnection networks, and a bit-serial processor. Building upon these circuits, we have developed novel algorithms and QCA-based architectures for highly parallel and systolic computation of signal/image processing applications, such as FFT and Wavelet and Wlash-Hadamard Transforms.

Fijany, Amir↗