Search NASA⌕ Search

SEARCH · Search NASA

Results for “parallel 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 847 records · Page 47

Effects of symmetry and spin configuration on spin-dependent transport properties of iron-phthalocyanine-based devices

Spin-dependent transport properties of nanodevices constructed by iron-phthalocyanine (FePc) molecule sandwiched between two zigzag graphene nanoribbon electrodes are studied using first-principles quantum transport calculations. The effects of the symmetry and spin configuration of electrodes have been taken into account. It is found that large magnetoresistance, large spin polarization, dual spin-filtering, and negative differential resistance (NDR) can coexist in these devices. Our results show that 5Z-FePc system presents well conductive ability in both parallel (P) and anti-parallel (AP) configurations. For 6Z-FePc-P system, spin filtering effect and large spin polarization can be found. A dual spin filtering and NDR can also be shown in 6Z-FePc-AP. Our studies indicate that the dual spin filtering effect depends on the orbitals symmetry of the energy bands and spin mismatching of the electrodes. And all the effects would open up possibilities for their applications in spin-valve, spin-filter as well as effective spin diode devices.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Trends in data locality abstractions for HPC systems

The cost of data movement has always been an important concern in high performance computing (HPC) systems. It has now become the dominant factor in terms of both energy consumption and performance. Support for expression of data locality has been explored in the past, but those efforts have had only modest success in being adopted in HPC applications for various reasons. However, with the increasing complexity of the memory hierarchy and higher parallelism in emerging HPC systems, locality management has acquired a new urgency. Developers can no longer limit themselves to low-level solutions and ignore the potential for productivity and performance portability obtained by using locality abstractions. Fortunately, the trend emerging in recent literature on the topic alleviates many of the concerns that got in the way of their adoption by application developers. Data locality abstractions are available in the forms of libraries, data structures, languages and runtime systems; a common theme is increasing productivity without sacrificing performance. Furthermore, this paper examines these trends and identifies commonalities that can combine various locality concepts to develop a comprehensive approach to expressing and managing data locality on future large-scale high-performance computing systems.

97 MATHEMATICS AND COMPUTING↗

Parallel FFT-based Poisson Solver for Isolated Three-dimensional Systems

We describe an implementation to solve Poisson's equation for an isolated system on a unigrid mesh using FFTs. The method solves the equation globally on mesh blocks distributed across multiple processes on a distributed-memory parallel computer. Test results to demonstrate the convergence and scaling properties of the implementation are presented. The solver is offered to interested users as the library PSPFFT.

99 GENERAL AND MISCELLANEOUS↗

Development of Steady-State and Dynamic Mass and Energy Constrained Neural Networks for Distributed Chemical Systems Using Noisy Transient Data

The paper presents the development of algorithms for mass and energy constrained neural network models that can exactly conserve the overall mass and energy of distributed chemical process systems, even though the noisy transient data used for optimal model training violate the same. In contrast to approximately satisfying mass and energy balance constraints of a system by soft penalization of objective function, algorithms have been developed for solving equality-constrained nonlinear optimization problems, thus providing the guarantee of exactly satisfying the system mass and energy conservation laws. For developing dynamic mass-energy constrained network models for distributed systems, hybrid series and parallel dynamic-static neural networks have been leveraged. The developed algorithms for solving both the training and forward problems are validated using both steady-state and dynamic data in the presence of various noise characteristics. The developed data-driven algorithms are flexible to exactly satisfy mass and energy balance constraints for dynamic chemical processes if the system holdup information is available. The proposed network structures and algorithms are applied to the development of data-driven lumped and distributed models of an adiabatic superheater/reheater system, a nonisothermal continuous stirred tank reactor, as well as an electrically heated plug-flow reactor system where one form of energy gets transformed to another. It has been observed that the mass-energy constrained neural networks yield a root mean squared error of <1% with respect to the system truth for the case studies evaluated in this work.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

The mechanisms of electron heating and acceleration during magnetic reconnection

The heating of electrons in collisionless magnetic reconnection is explored in particle-in-cell simulations with non-zero guide fields so that electrons remain magnetized. In this regime, electric fields parallel to B accelerate particles directly, while those perpendicular to B do so through gradient-B and curvature drifts. The curvature drift drives parallel heating through Fermi reflection, while the gradient B drift changes the perpendicular energy through betatron acceleration. We present simulations in which we evaluate each of these mechanisms in space and time in order to quantify their role in electron heating. For a case with a small guide field (20% of the magnitude of the reconnecting component), the curvature drift is the dominant source of electron heating. However, for a larger guide field (equal to the magnitude of the reconnecting component) electron acceleration by the curvature drift is comparable to that of the parallel electric field. In both cases, the heating by the gradient B drift is negligible in magnitude. It produces net cooling because the conservation of the magnetic moment and the drop of B during reconnection produce a decrease in the perpendicular electron energy. Heating by the curvature drift dominates in the outflow exhausts where bent field lines expand to relax their tension and is therefore distributed over a large area. In contrast, the parallel electric field is localized near X-lines. This suggests that acceleration by parallel electric fields may play a smaller role in large systems where the X-line occupies a vanishing fraction of the system. The curvature drift and the parallel electric field dominate the dynamics and drive parallel heating. A consequence is that the electron energy spectrum becomes extremely anisotropic at late time, which has important implications for quantifying the limits of electron acceleration due to synchrotron emission. An upper limit on electron energy gain that is substantially higher than earlier estimates is obtained by balancing reconnection drive with radiative loss.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Multigrid Reduction in Time for Chaotic and Hyperbolic Problems (Final Report)

The coming massive parallelism of exascale computing presents a pressing challenge for the many DOE simulations of time-dependent partial differential equations (PDEs), which typically use traditional sequential time stepping methods. Since this traditional approach is inherently serial, it presents a sequential bottleneck when moving to exascale computing, because future performance gains will come through greater concurrency, not faster clock speeds. Thus, the goal of this work is to research parallelism in time, i.e., methods that compute multiple time values simultaneously, not sequentially. The focus will be on hyperbolic and chaotic problems of interest to DOE, with the goal of enabling scalable simulations of time-dependent hyperbolic and chaotic problems on future architectures. The chosen methodology for solving these problems parallel-in-time is multigrid, because multigrid (when it works) is a powerful, optimal, and scalable solver for discretized PDEs. Multigrid is already commonly used in many DOE simulations for scalably and optimally solving space-only PDE problems. The areas of hyperbolic and chaotic problems are chosen because of their relevance to problems of programmatic interest to DOE. However, these problems are also well-known to be difficult for parallelin-time methods, with the most common method, parareal, diverging in many cases. The current state-of-the-art for parallel-in-time at LLNL is the multigrid reduction in time (MGRIT) XBraid package, which also struggles for such problems, while still showing some improvement over parareal. In summary, new methods are needed for an efficient parallel-in-time scheme for hyperbolic and chaotic problems, and this work shall research promising new multigrid methods in this area. In particular, this work shall continue researching the directions from the current collaboration with Dr. Falgout, which are laid out in the work Toward Parallel in Time for Chaotic Dynamical Systems and showed the first known results of a parallel-in-time speedup for a chaotic problem. This work outlines two key improvements to XBraid for chaotic problems, the so-called “theta” and “delta-correction” methods. Here, these two improvements will be implemented in a high-performance but general way in XBraid and explored for more complicated problems. We will additionally research, as time allows, improvements to these techniques, as well as multigrid relaxation techniques based on Least Squares Shadowing (LSS by Wang) and a nonintrusive block tridiagonal solver based on MGRIT, called TriMGRIT.

97 MATHEMATICS AND COMPUTING↗

Multigrid Reduction in Time for Chaotic and Hyperbolic Problems (Final Report)

The coming massive parallelism of exascale computing presents a pressing challenge for the many DOE simulations of time-dependent partial differential equations (PDEs), which typically use traditional sequential time stepping methods. Since this traditional approach is inherently serial, it presents a sequential bottleneck when moving to exascale computing, because future performance gains will come through greater concurrency, not faster clock speeds. Thus, the goal of this work is to research parallelism in time, i.e., methods that compute multiple time values simultaneously, not sequentially. The focus will be on hyperbolic and chaotic problems of interest to DOE, with the goal of enabling scalable simulations of time-dependent hyperbolic and chaotic problems on future architectures. The chosen methodology for solving these problems parallel-in-time is multigrid, because multigrid (when it works) is a powerful, optimal, and scalable solver for discretized PDEs. Multigrid is already commonly used in many DOE simulations for scalably and optimally solving space-only PDE problems. The areas of hyperbolic and chaotic problems are chosen because of their relevance to problems of programmatic interest to DOE. However, these problems are also well-known to be difficult for parallel-in-time methods, with the most common method, parareal, diverging in many cases. The current state of-the-art for parallel-in-time at LLNL is the multigrid reduction in time (MGRIT) XBraid package, which also struggles for such problems, while still showing some improvement over parareal. In summary, new methods are needed for an efficient parallel-in-time scheme for hyperbolic and chaotic problems, and this work shall research promising new multigrid methods in this area. In particular, this work shall continue researching the directions from the current collaboration with Dr. Falgout, which are laid out in the work Toward Parallel in Time for Chaotic Dynamical Systems and showed the first known results of a parallel-in-time speedup for a chaotic problem. This work outlines two key improvements to XBraid for chaotic problems, the so-called “theta” and “delta-correction” methods. Here, these two improvements will be further researched and improved (including with a new relaxation method inspired by on Least Squares Shadowing (LSS)) and explored for more complicated problems.

97 MATHEMATICS AND COMPUTING↗

An Open Infrastructure for Scalable, Reconfigurable Analysis

Petascale systems will have hundreds of thousands of processor cores so their applications must be massively parallel. Effective use of petascale systems will require efficient interprocess communication through memory hierarchies and complex network topologies. Tools to collect and analyze detailed data about this communication would facilitate its optimization. However, several factors complicate tool design. First, large-scale runs on petascale systems will be a precious commodity, so scalable tools must have almost no overhead. Second, the volume of performance data from petascale runs could easily overwhelm hand analysis and, thus, tools must collect only data that is relevant to diagnosing performance problems. Analysis must be done in-situ, when available processing power is proportional to the data. We describe a tool framework that overcomes these complications. Our approach allows application developers to combine existing techniques for measurement, analysis, and data aggregation to develop application-specific tools quickly. Dynamic configuration enables application developers to select exactly the measurements needed and generic components support scalable aggregation and analysis of this data with little additional effort.

99 GENERAL AND MISCELLANEOUS↗

Examination of Semi-Analytical Solution Methods in the Coarse Operator of Parareal Algorithm for Power System Simulation

With continuing advances in high-performance parallel computing platforms, parallel algorithms have become powerful tools for development of faster than real-time power system dynamic simulations. In particular, it has been demonstrated in recent years that parallel-in-time (Parareal) algorithms have the potential to achieve such an ambitious goal. Here, the selection of a fast and reasonably accurate coarse operator of the Parareal algorithm is crucial for its effective utilization and performance. This paper examines semi-analytical solution (SAS) methods as the coarse operators of the Parareal algorithm and explores performance of the SAS methods to the standard numerical time integration methods. Two promising time-power series-based SAS methods were considered; Adomian decomposition method and Homotopy analysis method with a windowing approach for improving the convergence. Numerical performance case studies on 10-generator 39-bus system and 327-generator 2383-bus system were performed for these coarse operators over different disturbances, evaluating the number of Parareal iterations, computational time, and stability of convergence. All the coarse operators tested with different scenarios have converged to the same corresponding true solution (if they are convergent) and the SAS methods provide comparable computational speed, while having more stable convergence to the true solution in many cases.

97 MATHEMATICS AND COMPUTING↗

SmartApps: Middle-ware for Adaptive Applications on Reconfigurable Platforms

There are several reasons why the performance of current distributed and heterogeneous systems is often disappointing. For example, the characteristics of the application may be input sensitive and evolve during execution causing dramatic changes in memory reference patterns, resource requirements, or degree of concurrency between different phases of the computation. Or, the system may change dynamically with nodes failing or appearing, some network links severed and other links established with different latencies and bandwidths. Another important reason for poor performance is the fairly compartmentalized approach to optimization: applications, compilers, operating systems and hardware configurations are designed and optimized in isolation and without the knowledge of instance specific information and needs of a running application. There is too little information flow across these boundaries and no global optimization is even attempted. For example, most operating systems services like paging, virtual-to-physical page mapping, I/O, or data layout in disks, provide little or no application customization. Similarly, the off-the-shelf hardware used by most commercial systems is optimized to give best average-case performance. To address this problem, we have proposed application-centric computing, or Smart Applications (SAS). In the SAS executable, the compiler embeds most run-time system services, and a performance-optimizing feedback loop that monitors the application's performance and adaptively reconfigures the application and the OS/system platform. At run-time, after incorporating the code's input and determining the system's resources and state, the SAS performs an *instance* specific optimization, which is more tractable than a global generic optimization between application, OS and system. The overriding philosophy of SAS is ``measure, compare, and adapt if beneficial.'' That is, the application will continually monitor its performance and the available resources to determine if, and by how much, performance could be improved if the application was restructured. Then, if the potential performance benefit outweighs the projected overhead costs, the application will restructure itself and the underlying system accordingly. The SAS framework includes performance monitoring and modeling components and mechanisms for performing the actual restructuring at various levels including: (i) algorithmic adaptation, (ii) run-time software optimization (e.g., input sensitivity analysis, etc.), (iii) tuning reconfigurable OS services (scheduling policy, page size, etc), and (iv) system configuration (e.g., selecting which, and how many, computational resources to use). SmartApps is being developed in the STAPL infrastructure. STAPL (the Standard Template Adaptive Parallel Library) is a framework for developing highly-optimizable, adaptable, and portable parallel and distributed applications. It consists of a relatively new and still evolving collection of generic parallel algorithms and distributed containers and a run-time system (RTS) through which the application and compiler interact with the OS and hardware.

97 MATHEMATICS AND COMPUTING↗

Parallel-in-Time Methods for Method-of-Lines Discretizations of Nonlinear Hyperbolic PDEs and Systems (Final Report)

The work for the subcontract is situated in the area of parallel-in-time integration for hyperbolic partial differential equations (PDEs). Parallel-in-time integration is an active area of research due to its ability to enable faster numerical simulations for applications throughout many areas of science. The work in this subcontract builds on a variety of results that were obtained, as part of the work performed for Subcontract No. B648355, for the Multigrid Reduction-in-Time (MGRIT) method from [1] applied to hyperbolic PDEs. This subcontract extends these results further to more efficient methods and to the case of method-of-lines discretizations for nonlinear hyperbolic PDES and systems of PDEs. The following is a summary of the research performed and results achieved during milestone periods 1, 2 and 3 by the PI (Hans De Sterck) and Postdoctoral Research Associate (Oliver Krzysik), for required tasks 1-4 (as listed in the Statement of Work): Research over the previous year has been split into three main projects: (i) solution of acoustic equation system; (ii) solution of nonlinear scalar hyperbolic PDEs; (iii) solution of nonlinear hyperbolic systems of PDEs.

97 MATHEMATICS AND COMPUTING↗

A universal TagModule collection for parallel genetic analysis of microorganisms

Systems-level analyses of non-model microorganisms are limited by the existence of numerous uncharacterized genes and a corresponding overreliance on automated computational annotations. One solution to this challenge is to disrupt gene function using DNA tag technology, which has been highly successful in parallelizing reverse genetics in Saccharomyces cerevisiae and has led to discoveries in gene function, genetic interactions and drug mechanism of action. To extend the yeast DNA tag methodology to a wide variety of microorganisms and applications, we have created a universal, sequence-verified TagModule collection. A hallmark of the 4280 TagModules is that they are cloned into a Gateway entry vector, thus facilitating rapid transfer to any compatible genetic system. Here, we describe the application of the TagModules to rapidly generate tagged mutants by transposon mutagenesis in the metal-reducing bacterium Shewanella oneidensis MR-1 and the pathogenic yeast Candida albicans. Our results demonstrate the optimal hybridization properties of the TagModule collection, the flexibility in applying the strategy to diverse microorganisms and the biological insights that can be gained from fitness profiling tagged mutant collections. The publicly available TagModule collection is a platform-independent resource for the functional genomics of a wide range of microbial systems in the post-genome era

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Ensemble models for circuit topology estimation, fault detection and classification in distribution systems

This paper presents a methodology for simultaneous fault detection, classification, and topology estimation for adaptive protection of distribution systems. The methodology estimates the probability of the occurrence of each one of these events by using a hybrid structure that combines three sub-systems, a convolutional neural network for topology estimation, a fault detection based on predictive residual analysis, and a standard support vector machine with probabilistic output for fault classification. The input to all these sub-systems is the local voltage and current measurements. A convolutional neural network uses these local measurements in the form of sequential data to extract features and estimate the topology conditions. The fault detector is constructed with a Bayesian stage (a multitask Gaussian process) that computes a predictive distribution (assumed to be Gaussian) of the residuals using the input. Since the distribution is known, these residuals can be transformed into a Standard distribution, whose values are then introduced into a one-class support vector machine. The structure allows using a one-class support vector machine without parameter cross-validation, so the fault detector is fully unsupervised. Finally, a support vector machine uses the input to perform the classification of the fault types. All three sub-systems can work in a parallel setup for both performance and computation efficiency. In conclusion, we test all three sub-systems included in the structure on a modified IEEE123 bus system, and we compare and evaluate the results with standard approaches.

24 POWER TRANSMISSION AND DISTRIBUTION↗

GASNet-EX RMA Communication Performance on Recent Supercomputing Systems

Partitioned Global Address Space (PGAS) programming models, typified by systems such as Unified Parallel C (UPC) and Fortran coarrays, expose one-sided Remote Memory Access (RMA) communication as a key building block for High Performance Computing (HPC) applications. Architectural trends in supercomputing make such programming models increasingly attractive, and newer, more sophisticated models such as UPC++, Legion and Chapel that rely upon similar communication paradigms are gaining popularity. GASNet-EX is a portable, open-source, high-performance communication library designed to efficiently support the networking requirements of PGAS runtime systems and other alternative models in emerging exascale machines. The library is an evolution of the popular GASNet communication system, building upon 20 years of lessons learned. We present microbenchmark results which demonstrate the RMA performance of GASNet-EX is competitive with MPI implementations on four recent, high-impact, production HPC systems. These results are an update relative to previously published results on older systems. The networks measured here are representative of hardware currently used in six of the top ten fastest supercomputers in the world, and all of the exascale systems on the U.S. DOE road map.

Hargrove, Paul H↗

UCX: An Open Source Framework for HPC Network APIs and Beyond, In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects

This paper presents Unified Communication X (UCX), a set of network APIs and their implementations for high throughput computing. UCX comes from the combined effort of national laboratories, industry, and academia to design and implement a high-performing and highly-scalable network stack for next generation applications and systems. UCX design provides the ability to tailor its APIs and network functionality to suit a wide variety of application domains and hardware. We envision these APIs to satisfy the networking needs of many programming models such as Message Passing Interface (MPI), OpenSHMEM, Partitioned Global Address Space (PGAS) languages, task-based paradigms and I/O bound applications. To evaluate the design we implement the APIs and protocols, and measure the performance of overhead-critical network primitives fundamental for implementing many parallel programming models and system libraries. Our results show that the latency, bandwidth, and message rate achieved by the portable UCX prototype is very close to that of the underlying driver. With UCX, we achieved a message exchange latency of 0.89 us, a bandwidth of 6138.5 MB/s, and a message rate of 14 million messages per second. As far as we know, this is the highest bandwidth and message rate achieved by any network stack (publicly known) on this hardware.

Computer Science↗

WE-AB-BRB-09: Real Time In Vivo Scintillating Fiber Array Detector for Medical LINACS

Purpose: An in vivo transmission scintillation fiber detector was developed to monitor patient treatment in real time for the enhancement of patient safety and treatment accuracy. The detector system is capable of monitoring each pulse from a medical LINAC during treatment to determine the dose delivered as treatment progresses. Methods: The detector system consists of 60 parallel scintillating fibers coupled to fast data processing optoelectronics that can monitor the beam fluence in real time. Each 2.5mm{sup 2} square fiber is aligned with an MLC leaf pair and is long enough to capture a 40cm field. The fibers are embedded within a water equivalent polymer substrate that is secured in the LINAC accessory tray. The fibers are coupled to high speed photosensors and front end amplifiers that filter noise and pass each pulse to a high speed analog-to-digital converter. The system components are capable of detecting pulse repetition times shorter than what is delivered by a medical LINAC to ensure true real time data acquisition. Results: The system was able to capture and record the signal from each linac pulse and display the information in real time with no pulse pile up. It was found that the fiber array attenuates 2.65% of the beam which can easily be compensated for in treatment planning. The fibers responded linearly with dose, are independent of clinical beam energies, and are independent of dose rate. Calibration of the system was performed as a function of beam energy, beam size, dose rate, and monitor units to optimize beam fluence error detection. Conclusion: The detector system presented provides true real time in vivo beam monitoring to enhance patient safety and treatment delivery accuracy. Furthermore, the detector can be used for current patient specific QA.

60 APPLIED LIFE SCIENCES↗

Uncovering I/O demands on HPC platforms: Peeking under the hood of Santos Dumont

High-Performance Computing (HPC) platforms are required to solve the most diverse large-scale scientific problems in various research areas, such as biology, chemistry, physics, and health sciences. Researchers use a multitude of scientific softwares, which have different requirements. These include input and output operations, which directly impact performance due to the existing difference in processing and data access speeds. Thus, supercomputers must efficiently handle mixed workload when storing data from the applications. Understanding the set of applications and their performance running in a supercomputer is paramount to understanding the storage system's usage, pinpointing possible bottlenecks, and guiding optimization techniques. This research proposes a methodology and visualization tool to evaluate a supercomputer's data storage infrastructure's performance, taking into account the diverse workload and demands of the system over a long period of operation. As a study case, we focus on the Santos Dumont supercomputer, identifying inefficient usage, problematic performance factors, and providing guidelines on how to tackle those issues.

97 MATHEMATICS AND COMPUTING↗

A new architecture for fast ultrasound imaging

Some ultrasound imaging applications require high frame rate, for example 3D imaging and automated inspections of large components. Being the signal-processing throughput of the system the main bottleneck, parallel beamforming is required to achieve hundreds to thousands of images per second. Simultaneous A-scan line beamforming in all active channels is required to reach the intended high frame rate. To this purpose, a new parallel beamforming architecture that exploits the currently available processing resources available in state-of-the-art FPGAs is proposed. The work aims to get the optimal resource usage, high scalability and flexibility for different applications. To achieve these goals, the basic beamforming function is reformulated to be adapted to the DSP-cell architecture of state-of-the-art FPGAs. This allows performing simultaneous dynamic focusing on multiple A-scan lines. Some realistic examples are analyzed, evaluating resource requirements and maximum operating frequency. For example, a 128-channel system, with 128 scan lines and acquiring at 20 MSPS, can be built with 4 mid-range FPGAs, achieving up to 18000 frames per second, just limited by the maximum PRF. The gold standard Synthetic Transmit Aperture method (also called Total Focusing Method) can be carried out in real time at a processing rate of 140 high-resolution images per second (16 cm depth on steel)

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗