Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computational Load Balancing”

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 487 records · Page 27

Computer Modeling of Sand Transport on Mars Using a Compart-Mentalized Fluids Algorithm (CFA)

It has been postulated that aeolian transport on Mars may be significantly different from that on Earth. From laboratory experiments simulating martian grain transport [2], it has been observed that (saltating) grains striking the bed can cause hundreds of secondary reptation trajectories when impact occurs at speeds postulated for Mars. Some of the ballistically induced trajectories "die ouf' and effectively join the ranks on the creep population that is merely nudged along by impact. Many of the induced reptation trajectories, however, are sufficiently high for the grains to become part of the saltation load (it is irrelevant to the boundary layer how a grain attained its initial lift force). When these grains, in turn, strike the surface, they too are capable of inducing more reptating grains. This cascading effect has been discussed in connection with terrestrial aeolian transport in an attempt to dispel the notion that sand motion is divisible only into creep and saltation loads. On Earth, only a few grains are splashed by impact. On Mars, it may be hundreds. We developed a computer model to address this phenomenon because there are some important ramifications: First, this ratio may mean that martian aeolian transport is dominated by reptation flux rather than saltation. On Earth, the flux would be a roughly balanced mixture between reptation/creep and saltation. On Venus, there would be no transport other than by saltation. In other words, an understanding of planetary aeolian processes may not be necessarily understood by extrapolating from the "Earth case", with only gravity and atmospheric density/viscosity being considered as variables. Second, the reptation flux on Mars may be self sustaining, so that little input is required by the wind once transport has been initiated. The number of grains saturating the boundary layer near the bed may mean that average grain speed on Mars might conceivably be less than that on Earth. This would say much for models of sand comminution on Mars. A multiple-grain transport model using just the equations of grain motion describing lift and drag is impossible to develop owing to stochastic effects --the very effects we wish to model. Also, unless we were to employ supercomputing techniques and extremely complex computer codes that could deal with millions of grains simultaneously, it would also be difficult to model grain transport if we attempted to consider every grain in motion. No existing computer models were found that satisfactorily used the equations of motion to arrive at transport flux numbers for the different populations of saltation and reptation. Modeling all the grains in a transport system was an intractable problem within our resources, and thus we developed what we believe to be a new modeling approach to simulating grain transport. The CFA deals with grain populations, but considers them to belong to various compartmentalized fluid units in the boundary layer. In this way, the model circumvents the multigrain problem by dealing primarily with the consequences of grain transport --momentum transfer between air and grains, which is the physical essence of a dynamic grain-fluid mixture. We thus chose to model the aeolian transport process as a superposition of fluids. These fluids include the air as well as particle populations of various properties. The prime property distinguishing these fluids is upward and downward grain motion. In a normal saltation trajectory, a grain's downwind velocity increases with time, so a rising grain will have a smaller downwind velocity than a failing grain. Because of this disparity in rising and falling grain proper-ties, it seemed appropriate to track these as two separate grain populations within the same physical space. The air itself can be considered a separate fluid superimposed within and interacting with the various grain-cloud "fluids". Additional informaiton is contained in the original.

Marshall, J.↗

Growth Control and Disease Mechanisms in Computational Embryogeny

This paper presents novel approach to applying growth control and diseases mechanisms in computational embryogeny. Our method, which mimics fundamental processes from biology, enables individuals to reach maturity in a controlled process through a stochastic environment. Three different mechanisms were implemented; disease mechanisms, gene suppression, and thermodynamic balancing. This approach was integrated as part of a structural evolutionary model. The model evolved continuum 3-D structures which support an external load. By using these mechanisms we were able to evolve individuals that reached a fixed size limit through the growth process. The growth process was an integral part of the complete development process. The size of the individuals was determined purely by the evolutionary process where different individuals matured to different sizes. Individuals which evolved with these characteristics have been found to be very robust for supporting a wide range of external loads.

Genetic algorithm↗

Tutorial : the Zoltan toolkit.

The outline of this presentation is: (1) High-level view of Zoltan; (2) Requirements, data models, and interface; (3) Load Balancing and Partitioning; (4) Matrix Ordering, Graph Coloring; (5) Utilities; (6) Isorropia; and (7) Zoltan2.

99 GENERAL AND MISCELLANEOUS↗

Aerodynamic measurements on a finite wing with simulated ice

The effect of a simulated glaze ice accretion on the aerodynamic performance of a three-dimensional straight and swept wing is studied experimentally. A semispan wing of effective aspect ratio five was mounted from the sidewall of the UIUC subsonic wind tunnel. The model uses an NACA 0012 airfoil section on a rectangular planform with interchangeable tip and root sections to allow for 0- and 30-deg sweep. A sidewall suction system is used to minimize the tunnel boundary-layer interaction with the model. A three-component sidewall balance has been designed, built and used to measure lift, drag and pitching moment on the clean and iced model. Fluorescent oil flow visualization has been performed on the iced model and reveals extensive spanwise flow in the separation bubble aft of the upper surface horn. These results are compared to computational results for the surface pressures, span loads and surface oil flow.

Bragg, M. B.↗

Full-Span Tiltrotor Aeroacoustic Model (TRAM) Overview and 40- by 80-Foot Wind Tunnel Test

Most helicopter data trends cannot be extrapolated to tiltrotors because blade geometry and aerodynamic behavior, as well as rotor and fuselage interactions, are significantly different for tiltrotors. A tiltrotor model has been developed to investigate the aeromechanics of tiltrotors, to develop a comprehensive database for validating tiltrotor analyses, and to provide a research platform for supporting future tiltrotor designs. The Full-Span Tiltrotor Aeroacoustic Model (FS TRAM) is a dual-rotor, powered aircraft model with extensive instrumentation for measurement of structural and aerodynamic loads. This paper will present the Full-Span TRAM test capabilities and the first set of data obtained during a 40- by 80-Foot Wind Tunnel test conducted in late 2000 at NASA Ames Research Center. The Full-Span TRAM is a quarter-scale representation of the V-22 Osprey aircraft, and a heavily instrumented NASA and U.S. Army wind tunnel test stand. Rotor structural loads are monitored and recorded for safety-of-flight and for information on blade loads and dynamics. Left and right rotor balance and fuselage balance loads are monitored for safety-of-flight and for measurement of vehicle and rotor aerodynamic performance. Static pressure taps on the left wing are used to determine rotor/wing interactional effects and rotor blade dynamic pressures measure blade airloads. All of these measurement capabilities make the FS TRAM test stand a unique and valuable asset for validation of computational codes and to aid in future tiltrotor designs. The Full-Span TRAM was tested in the NASA Ames Research Center 40- by 80-Foot Wind Tunnel from October through December 2000. Rotor and vehicle performance measurements were acquired in addition to wing pressures, rotor acoustics, and Laser Light Sheet (LLS) flow visualization data. Hover, forward flight, and airframe (rotors off) aerodynamic runs were performed. Helicopter-mode data were acquired during angle of attack and thrust sweeps for a variety of tunnel speeds. Wake geometry images were acquired using LLS photographs and suggest dual tip vortex formation at low thrust conditions. The full paper will include comparisons to isolated-rotor TRAM data acquired at the Duits-Nederlandse Windtunnel (DNW) in 1998. The FS TRAM has been established as a valuable national asset for tiltrotor research. Data reduction and analysis of the 40- by 80-Foot Wind Tunnel test results are underway. Follow-on testing of the FS TRAM is currently being planned for the NASA Ames 80- by 120-Foot Wind Tunnel in late 2001.

McCluer, Megan S.↗

Design Principles for Sparse Matrix Multiplication on the GPU

We implement two novel algorithms for sparse-matrix dense-matrix multiplication (SpMM) on the GPU. Our algorithms expect the sparse input in the popular compressed-sparse-row (CSR) format and thus do not require expensive format conversion. While previous SpMM work concentrates on thread-level parallelism, we additionally focus on latency hiding with instruction-level parallelism and load-balancing. We show, both theoretically and experimentally, that the proposed SpMM is a better fit for the GPU than previous approaches. We identify a key memory access pattern that allows efficient access into both input and output matrices that is crucial to getting excellent performance on SpMM. By combining these two ingredients---(i) merge-based load-balancing and (ii) row-major coalesced memory access---we demonstrate a 4.1x peak speedup and a 31.7% geomean speedup over state-of-the-art SpMM implementations on real-world datasets.

97 MATHEMATICS AND COMPUTING↗

DeStager: feature guided in-situ data management in distributed deep memory hierarchies

In-situ analytics have been increasingly adopted by leadership scientific applications to gain fast insights into massive output data of simulations. With the current practice, systems buffer the output data in DRAM for analytics processing, constraining it to DRAM capacity un-used by the simulation. The rapid growth of data size requires alternative approaches to accommodating data-rich analytics, such as using solid-state disks to increase effective memory capacity. For this purpose, this paper explores software solutions for exploring the deep memory hierarchies expected on future high-end machines. Leveraging the fact that many analytics are sensitive to data features (regions-of-interest) hidden in the data being processed, the approach incorporates the knowledge of the data features into in-situ data management. It uses adaptive index creation/refinement to reduce the overhead of index management. In addition, it uses data features to predict data skew and improve load balance through controlling data distribution and placement on distributed staging servers. The experimental results show that such feature-guided optimizations achieve substantial improvements over state-of-the-art approaches for managing output data in-situ.

Computer Science↗

SIERRA Multimechanics Module: Aria User Manual – Version 4.40

Aria is a Galerkin finite element based program for solving coupled-physics problems described by systems of PDEs and is capable of solving nonlinear, implicit, transient and direct-to-steady state problems in two and three dimensions on parallel architectures. The suite of physics currently supported by Aria includes thermal energy transport, species transport, and electrostatics as well as generalized scalar, vector and tensor transport equations. Additionally, Aria includes support for manufacturing process flows via the incompressible Navier-Stokes equations specialized to a low Reynolds number (Re < 1) regime. Enhanced modeling support of manufacturing processing is made possible through use of either arbitrary Lagrangian- Eulerian (ALE) and level set based free and moving boundary tracking in conjunction with quasi-static nonlinear elastic solid mechanics for mesh control. Coupled physics problems are solved in several ways including fully-coupled Newton’s method with analytic or numerical sensitivities, fully-coupled Newton- Krylov methods and a loosely-coupled nonlinear iteration about subsets of the system that are solved using combinations of the aforementioned methods. Error estimation, uniform and dynamic ℎ-adaptivity and dynamic load balancing are some of Aria’s more advanced capabilities. Aria is based upon the Sierra Framework.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Local Power Impact Experiment Design for a New Fuel Type for use in the Advanced Test Reactor

The Advanced Test Reactor (ATR), and complimentary zero-power ATR Critical (ATRC) reactor, located at Idaho National Labs (INL), are undergoing conversion from Highly Enriched Uranium (HEU) to Low Enriched Uranium (LEU). Both have a variety of testing locations that can receive large variations in flux due to its unique serpentine design, consisting of five lobes (see Figure 1). Initial criticality and power distribution throughout the core are controlled by core-external outer shim control cylinders (OSCCs). Distinct test loops allow for testing at specific temperatures, pressures, and irradiation conditions. The ATR is one of the key nuclear engineering research and testing facilities within the DOE National Laboratory Complex, and the ATRC supports its operation [1]. Currently, the Office of Material Management and Minimization (M3) within the National Nuclear Security Administration of the DOE is working to convert the remaining research reactors, including the ATR, from 93% HEU fuel to 19.75% LEU fuel (LEU) to support non-proliferation [2]. Extensive materials testing at INL and internationally has demonstrated that a high-density uranium molybdenum (U 10Mo) alloy can meet the performance requirements of the remaining high powered research reactors. However, there are many technical challenges to address before the conversion to LEU can be successful, including the accurate characterization of the reactor core physics with LEU fuel. Reactor physics safety evaluations currently use Monte Carlo for the 21st Century (MC21), a continuous-energy Monte Carlo radiation transport code [3]. Existing MC21 models of the ATR and ATRC cores have a validation basis for use in neutronics analyses with HEU fuel. The models are used to support safety analyses that include comparisons to the safety requirements for the reactors. However, the use of the LOWE element in the ATR and ATRC is not currently covered by the current model validation basis. To deploy the new fuel type, extensive computational reactor physics support is necessary to support the use of LOWE in the ATR and ATRC. Therefore, LOWE requires a rigorous validation basis, aligned with that of HEU fuel, that takes advantage of the existing software tools and processes currently used for the ATR and ATRC. The experiment to validate of the MC21 models for determining power, the Power Impact Validation Experiment, will consist of two flux runs in the ATRC, one with fully HEU loading and one with a single LOWE element. Both flux runs will be instrumented with 20 sets of azimuthal fission wires and 3 sets of axial fission wires, as shown in Figure 4. Standard flux run methodology will be used [4]. Power Impact Validation Experiment data will be compared against MC21 calculated data, both for absolute fission rate accuracy and to determine the relative change in fission rates between the two runs. The results of the Power Impact Validation Experiment and subsequent evaluations will provide the validation basis for MC21 for use with LOWE elements. Key features of the Power Impact Validation Experiment include: (1) Two flux runs to allow for LOWE perturbed measurements to be compared to already validated measurements taken from a full core of HEU fuel, (2) Optimization of instrumentation to balance analytical needs with practical considerations (e.g., limited time window to count beta particles from fission products), and (3) Standard ATRC core loading, including both driver positions and flux traps, to minimize cost while remaining representative of typical ATR core loading.

42 ENGINEERING↗

Enabling topography-resolving structural dynamic contact simulation

Damping of structures and systems is often dominated by frictional dissipation in connections, the prediction of which remains a longstanding scientific challenge. Previous studies have shown that the actual topography of contact interfaces may have a strong effect, especially in the partial slip/liftoff regime. We recently proposed a multi-scale method, which couples finite element and boundary element modeling. The primary benefit of this approach is that it permits to analyze the effect of the actual contact topography on the dynamics of jointed structures. While this multi-scale modeling method was initially developed for quasi-static analysis, we demonstrate herein how it can be used for time step integration and Harmonic Balance analysis. We cross-verify those fully dynamic analysis methods against each other and quasi-static results, for the S4 Beam benchmark. We compare the multi-scale method against state-of-the-art full-FE analysis, in terms of numerical damping and computational performance. Some discrepancy is found to be of physical origin. Depending on the load history, it is shown that the system settles to a slightly different equilibrium. Finally, transient multi-scale simulations enable the prediction of this interesting phenomenon, for the first time, for a structure with bolted joints.

Frictional-unilateral contact↗

A Robust and Scalable Software Library for Parallel Adaptive Refinement on Unstructured Meshes

The design and implementation of Pyramid, a software library for performing parallel adaptive mesh refinement (PAMR) on unstructured meshes, is described. This software library can be easily used in a variety of unstructured parallel computational applications, including parallel finite element, parallel finite volume, and parallel visualization applications using triangular or tetrahedral meshes. The library contains a suite of well-designed and efficiently implemented modules that perform operations in a typical PAMR process. Among these are mesh quality control during successive parallel adaptive refinement (typically guided by a local-error estimator), parallel load-balancing, and parallel mesh partitioning using the ParMeTiS partitioner. The Pyramid library is implemented in Fortran 90 with an interface to the Message-Passing Interface (MPI) library, supporting code efficiency, modularity, and portability. An EM waveguide filter application, adaptively refined using the Pyramid library, is illustrated.

Lou, John Z.↗

Dynamic Time-Variant Connection Management for PGAS Models on InfiniBand

InfiniBand (IB) has established itself as a promising network infrastructure for high-end cluster computing systems as evidenced by its usage in the Top500 supercomputers today. While the IB standard describes multiple communication models (including reliable-connection (RC), and unreliable datagram (UD)), most of its promising features such as remote direct memory access (RDMA), hardware atomics and network fault tolerance are only available for the RC model which requires connections between communicating process pairs. In the past, several researchers have proposed on-demand connection management techniques that establish connections when there is a need to communicate, and not before. While such techniques work well for algorithms and applications that only communicate with a small set of processes in their life-time, there exists a broad set of applications that do not follow this trend. For example, applications that perform dynamic load balancing and adaptive work stealing have a small set of communicating neighbors at any given time, but over time the total number of neighbors can be very high; in some cases, equal to the entire system size. In this paper, we present a dynamic time-variant connection management approach that establishes connections on-demand like previous approaches, but further intelligently tears down some of the unused connections as well. While connection tear-down itself is relevant for any programming model, different models have different complexities. In this paper, we study the Global Arrays (GA) PGAS model for two reasons: (1) the simple one-sided communication primitives provided by GA and other PGAS models ensure that connection requests are always initiated by the origin process without explicit synchronization with the target process---this makes connection tear-down simpler to handle; and (2) GA supports several applications that demonstrate this behavior making it an obvious first target for the proposed enhancements. We evaluate our proposed approach using several micro-benchmarks as well as the NWChem computational chemistry application on more than 6000 processes, and show that our approach can significantly reduce the memory requirements of the communication library while maintaining its performance. To the best of our knowledge, this is the first design, implementation and evaluation of connection tear-down protocols over InfiniBand.

99 GENERAL AND MISCELLANEOUS↗

High-Performance Parallel Analysis of Coupled Problems for Aircraft Propulsion

Applications are described of high-performance computing methods to the numerical simulation of complete jet engines. The methodology focuses on the partitioned analysis of the interaction of the gas flow with a flexible structure and with the fluid mesh motion driven by structural displacements. The latter is treated by a ALE technique that models the fluid mesh motion as that of a fictitious mechanical network laid along the edges of near-field elements. New partitioned analysis procedures to treat this coupled three-component problem were developed. These procedures involved delayed corrections and subcycling, and have been successfully tested on several massively parallel computers, including the iPSC-860, Paragon XP/S and the IBM SP2. The NASA-sponsored ENG10 program was used for the global steady state analysis of the whole engine. This program uses a regular FV-multiblock-grid discretization in conjunction with circumferential averaging to include effects of blade forces, loss, combustor heat addition, blockage, bleeds and convective mixing. A load-balancing preprocessor for parallel versions of ENG10 was developed as well as the capability for the first full 3D aeroelastic simulation of a multirow engine stage. This capability was tested on the IBM SP2 parallel supercomputer at NASA Ames.

Felippa, C. A.↗

Accelerating DNA analysis applications on GPU clusters

DNA analysis is an emerging application of high performance bioinformatic. Modern sequencing machinery are able to provide, in few hours, large input streams of data which needs to be matched against exponentially growing databases known fragments. The ability to recognize these patterns effectively and fastly may allow extending the scale and the reach of the investigations performed by biology scientists. Aho-Corasick is an exact, multiple pattern matching algorithm often at the base of this application. High performance systems are a promising platform to accelerate this algorithm, which is computationally intensive but also inherently parallel. Nowadays, high performance systems also include heterogeneous processing elements, such as Graphic Processing Units (GPUs), to further accelerate parallel algorithms. Unfortunately, the Aho-Corasick algorithm exhibits large performance variabilities, depending on the size of the input streams, on the number of patterns to search and on the number of matches, and poses significant challenges on current high performance software and hardware implementations. An adequate mapping of the algorithm on the target architecture, coping with the limit of the underlining hardware, is required to reach the desired high throughputs. Load balancing also plays a crucial role when considering the limited bandwidth among the nodes of these systems. In this paper we present an efficient implementation of the Aho-Corasick algorithm for high performance clusters accelerated with GPUs. We discuss how we partitioned and adapted the algorithm to fit the Tesla C1060 GPU and then present a MPI based implementation for a heterogeneous high performance cluster. We compare this implementation to MPI and MPI with pthreads based implementations for a homogeneous cluster of x86 processors, discussing the stability vs. the performance and the scaling of the solutions, taking into consideration aspects such as the bandwidth among the different nodes.

59 BASIC BIOLOGICAL SCIENCES↗

A hybrid incremental projection method for thermal-hydraulics applications

In this paper, a new second-order accurate, hybrid, incremental projection method for time-dependent incompressible viscous flow is introduced in this paper. The hybrid finite-element/finite-volume discretization circumvents the well-known Ladyzhenskaya–Babuška–Brezzi conditions for stability, and does not require special treatment to filter pressure modes by either Rhie–Chow interpolation or by using a Petrov–Galerkin finite element formulation. The use of a co-velocity with a high-resolution advection method and a linearly consistent edge-based treatment of viscous/diffusive terms yields a robust algorithm for a broad spectrum of incompressible flows. The high-resolution advection method is shown to deliver second-order spatial convergence on mixed element topology meshes, and the implicit advective treatment significantly increases the stable time-step size. The algorithm is robust and extensible, permitting the incorporation of features such as porous media flow, RANS and LES turbulence models, and semi-/fully-implicit time stepping. A series of verification and validation problems are used to illustrate the convergence properties of the algorithm. The temporal stability properties are demonstrated on a range of problems with 2 ≤ CFL ≤ 100. The new flow solver is built using the Hydra multiphysics toolkit. The Hydra toolkit is written in C++ and provides a rich suite of extensible and fully-parallel components that permit rapid application development, supports multiple discretization techniques, provides I/O interfaces, dynamic run-time load balancing and data migration, and interfaces to scalable popular linear solvers, e.g., in open-source packages such as HYPRE, PETSc, and Trilinos.

97 MATHEMATICS AND COMPUTING↗

Preliminary report on use of Lahey clinic automated history in an idustrial complex

A questionnaire has been developed and used extensively as an aid to the appointment office in determining what department a patient should be referred to and what time for special consultations should be reserved. It has helped to maintain a balanced case load and informs the physician in advance about the patients he will see. By coordinating appointments so that the patient can visit two or more of the specialty departments in one day rather than having to return a number of times to see different doctors, it has increased efficiency. The questionnaire screens for important symptoms or trouble spots to which the computer is programmed to assign scoring values which in turn point out the clinic division or section to which the patient should initially be referred.

Leonardson, B. O.↗

Multiprocessing the Sieve of Eratosthenes

The Sieve of Eratosthenes for finding prime numbers in recent years has seen much use as a benchmark algorithm for serial computers while its intrinsically parallel nature has gone largely unnoticed. The implementation of a parallel version of this algorithm for a real parallel computer, the Flex/32, is described and its performance discussed. It is shown that the algorithm is sensitive to several fundamental performance parameters of parallel machines, such as spawning time, signaling time, memory access, and overhead of process switching. Because of the nature of the algorithm, it is impossible to get any speedup beyond 4 or 5 processors unless some form of dynamic load balancing is employed. We describe the performance of our algorithm with and without load balancing and compare it with theoretical lower bounds and simulated results. It is straightforward to understand this algorithm and to check the final results. However, its efficient implementation on a real parallel machine requires thoughtful design, especially if dynamic load balancing is desired. The fundamental operations required by the algorithm are very simple: this means that the slightest overhead appears prominently in performance data. The Sieve thus serves not only as a very severe test of the capabilities of a parallel processor but is also an interesting challenge for the programmer.

Bokhari, S.↗

A cell-centered AMR-ALE framework for 3D multi-material hydrodynamics. Part I: Lagrangian and indirect Euler AMR algorithms

Many applications of physics and engineering involve wide ranges of time and spatial scales. The numerical simulation of localized small scales such as shock waves and material interfaces requires a large number of computational cells in these regions. For these applications, Lagrangian and Arbitrary-Lagrangian-Eulerian (ALE) related methods are engaging since the moving mesh feature naturally brings mesh cells on shock discontinuities and material interfaces are carefully captured. In addition, Adaptive-Mesh-Refinement (AMR) strategies aim to optimize computational resources by concentrating finer mesh cells only in areas of interest while using coarser cells elsewhere. A key but challenging AMR requirement consists in efficiently distributing the computational effort to achieve high accuracy without the prohibitive computational costs associated with uniformly fine grids. Here, in this document, the coupling of the p4est AMR library with a cell-centered Lagrangian scheme is presented with the goal to perform reliable 3D Lagrangian-AMR and indirect Euler-AMR multi-material simulations. In particular, it is shown that starting from a 3D indirect ALE code, the memory management and load balancing requirements can be delegated to an external library (here the p4est library) to unlock ALE-AMR capabilities. First, we present a strategy to transcribe the octant-based connectivity of the 3D AMR framework with that of an unstructured mesh of polygonal cells used in Lagrangian hydrodynamics. Then, we show how refinement and coarsening operations must be adapted to the particular Lagrangian framework to ensure the conservation of volume during those steps. Finally, several numerical test cases are presented that demonstrate the capabilities of the Lagrangian-AMR and indirect Euler-AMR algorithms.

3D cell-centered Lagrangian numerical scheme↗