Engineering Papers⌕ Search

SEARCH · Engineering Papers

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 433 records · Page 24

Grid Data Access on Widely Distributed Worker Nodes Using Scalla and SRM

Facing the reality of storage economics, NP experiments such as RHIC/STAR have been engaged in a shift of the analysis model, and now heavily rely on using cheap disks attached to processing nodes, as such a model is extremely beneficial over expensive centralized storage. Additionally, exploiting storage aggregates with enhanced distributed computing capabilities such as dynamic space allocation (lifetime of spaces), file management on shared storages (lifetime of files, pinning file), storage policies or a uniform access to heterogeneous storage solutions is not an easy task. The Xrootd/Scalla system allows for storage aggregation. We will present an overview of the largest deployment of Scalla (Structured Cluster Architecture for Low Latency Access) in the world spanning over 1000 CPUs co-sharing the 350 TB Storage Elements and the experience on how to make such a model work in the RHIC/STAR standard analysis framework. We will explain the key features and approach on how to make access to mass storage (HPSS) possible in such a large deployment context. Furthermore, we will give an overview of a fully 'gridified' solution using the plug-and-play features of Scalla architecture, replacing standard storage access with grid middleware SRM (Storage Resource Manager) components designed for space management and will compare the solution with the standard Scalla approach in use in STAR for the past 2 years. Integration details, future plans and status of development will be explained in the area of best transfer strategy between multiple-choice data pools and best placement with respect of load balancing and interoperability with other SRM aware tools or implementations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Recent Progress on the Parallel Implementation of Moving-Body Overset Grid Schemes

Viscous calculations about geometrically complex bodies in which there is relative motion between component parts is one of the most computationally demanding problems facing CFD researchers today. This presentation documents results from the first two years of a CHSSI-funded effort within the U.S. Army AFDD to develop scalable dynamic overset grid methods for unsteady viscous calculations with moving-body problems. The first pan of the presentation will focus on results from OVERFLOW-D1, a parallelized moving-body overset grid scheme that employs traditional Chimera methodology. The two processes that dominate the cost of such problems are the flow solution on each component and the intergrid connectivity solution. Parallel implementations of the OVERFLOW flow solver and DCF3D connectivity software are coupled with a proposed two-part static-dynamic load balancing scheme and tested on the IBM SP and Cray T3E multi-processors. The second part of the presentation will cover some recent results from OVERFLOW-D2, a new flow solver that employs Cartesian grids with various levels of refinement, facilitating solution adaption. A study of the parallel performance of the scheme on large distributed- memory multiprocessor computer architectures will be reported.

Wissink, Andrew↗

Exploring Fine-Grained Task-based Execution on Multi-GPU Systems

Many-core Graphics Processing Units (GPUs) have been utilized as the computation engine in many scientific fields due to the high peak performance, cost effectiveness, and the availability of user friendly programming environments, e.g., NVIDIA CUDA. However, the conventional data parallel GPU programming paradigm cannot satisfactorily address issues such as load balancing and GPU resource utilization due to the irregular and unbalanced workload patterns exhibited in some applications. In this paper, we explore the design space of task-based solutions for multi-GPU systems. By employing finer-grained tasks than what is supported in the current CUDA, and allowing task sharing, our solutions enable dynamic load balancing. We evaluate our solutions with a Molecular Dynamics application with different atom distributions (from uniform distribution to highly non-uniform distribution). Experimental results obtained on a 4-GPU system show that, for non-uniform distributed systems, our solutions achieve excellent speedup, and significant performance improvement over other solutions based on the standard CUDA APIs.

99 GENERAL AND MISCELLANEOUS↗

System Finds Horizontal Location of Center of Gravity

An instrumentation system rapidly and repeatedly determines the horizontal location of the center of gravity of a laboratory vehicle that slides horizontally on three air bearings (see Figure 1). Typically, knowledge of the horizontal center-of-mass location of such a vehicle is needed in order to balance the vehicle properly for an experiment and/or to assess the dynamic behavior of the vehicle. The system includes a load cell above each air bearing, electronic circuits that generate digital readings of the weight on each load cell, and a computer equipped with software that processes the readings. The total weight and, hence, the mass of the vehicle are computed from the sum of the load-cell weight readings. Then the horizontal position of the center of gravity is calculated straightforwardly as the weighted sum of the known position vectors of the air bearings, the contribution of each bearing being proportional to the weight on that bearing. In the initial application for which this system was devised, the center- of-mass calculation is particularly simple because the air bearings are located at corners of an equilateral triangle. However, the system is not restricted to this simple geometry. The system acquires and processes weight readings at a rate of 800 Hz for each load cell. The total weight and the horizontal location of the center of gravity are updated at a rate of 800/3 approx. equals 267 Hz. In a typical application, a technician would use the center-of-mass output of this instrumentation system as a guide to the manual placement of small weights on the vehicle to shift the center of gravity to a desired horizontal position. Usually, the desired horizontal position is that of the geometric center. Alternatively, this instrumentation system could be used to provide position feedback for a control system that would cause weights to be shifted automatically (see Figure 2) in an effort to keep the center of gravity at the geometric center.

Johnston, Albert S.↗

HPC formulations of optimization algorithms for tensor completion

Tensor completion is a powerful tool used to estimate or recover missing values in multi-way data. It has seen great success in domains such as product recommendation and healthcare. Tensor completion is most often accomplished via low-rank sparse tensor factorization, a computationally expensive non-convex optimization problem which has only recently been studied in the context of parallel computing. In this work, we study three optimization algorithms that have been successfully applied to tensor completion: alternating least squares (ALS), stochastic gradient descent (SGD), and coordinate descent (CCD++). We explore opportunities for parallelism on shared- and distributed-memory systems and address challenges such as memory- and operation-efficiency, load balance, cache locality, and communication. Among our advancements are a communication-efficient CCD++ algorithm, an ALS algorithm rich in level-3 BLAS routines, and an SGD algorithm which combines stratification with asynchronous communication. Furthermore, we show that introducing randomization during ALS and CCD++ can accelerate convergence. We evaluate our parallel formulations on a variety of real datasets on a modern supercomputer and demonstrate speedups through 16384 cores. Further, these improvements reduce time-to-solution from hours to seconds on real-world datasets. We show that after our optimizations, ALS is advantageous on parallel systems of small-to-moderate scale, while both ALS and CCD++ provide the lowest time-to-solution on large-scale distributed systems.

97 MATHEMATICS AND COMPUTING↗

Scalable molecular dynamics with NAMD on the Summit system

According to the article, NAnoscale Molecular Dynamics (NAMD) is a parallel molecular dynamics application that has been used to make breakthroughs in understanding the structure and dynamics of large biomolecular complexes, such as viruses like HIV and various types of influenza. State-of-the-art biomolecular simulations often require integration of billions of timesteps, computing all interatomic forces for each femtosecond timestep. Molecular dynamics simulation of large biomolecular systems and long-timescale biological phenomena requires tremendous computing power. NAMD harnesses the power of thousands of heterogeneous processors to meet this demand. In this paper, we present algorithmic improvements and performance optimizations that enable NAMD to achieve high performance on the IBM Newell platform (with IBM POWER9 processors and NVIDIA Volta V100 GPUs), which underpins the Oak Ridge National Laboratory's Summit and Lawrence Livermore National Laboratory's Sierra supercomputers. The Top-500 supercomputers November 2018 list shows Summit at the number one spot, with 200 petaflop/s peak performance, and Sierra second with 125 petaflop/s. Optimizations for NAMD on Summit include: data layout changes for GPU acceleration and CPU vectorization, improving GPU offload efficiency, increasing performance with Parallel Active Messaging Interface support in Charm++, improving efficiency of fast Fourier transform calculations, improving load balancing, enabling better CPU vectorization and cache performance, and providing an alternative thermostat through stochastic velocity rescaling. We also present performance scaling results on early Newell systems.

Computer Science↗

Employing Nested OpenMP for the Parallelization of Multi-Zone Computational Fluid Dynamics Applications

In this paper we describe the parallelization of the multi-zone code versions of the NAS Parallel Benchmarks employing multi-level OpenMP parallelism. For our study we use the NanosCompiler, which supports nesting of OpenMP directives and provides clauses to control the grouping of threads, load balancing, and synchronization. We report the benchmark results, compare the timings with those of different hybrid parallelization paradigms and discuss OpenMP implementation issues which effect the performance of multi-level parallel applications.

Ayguade, Eduard↗

VinaMPI: Facilitating multiple receptor high-throughput virtual docking on high-performance computers

The program VinaMPI has been developed to enable massively large virtual drug screens on leadership-class computing resources, using a large number of cores to decrease the time-to-completion of the screen. VinaMPI is a massively parallel Message Passing Interface (MPI) program based on the multithreaded virtual docking program AutodockVina, and is used to distribute tasks while multithreading is used to speed-up individual docking tasks. VinaMPI uses a distribution scheme in which tasks are evenly distributed to the workers based on the complexity of each task, as defined by the number of rotatable bonds in each chemical compound investigated. VinaMPI efficiently handles multiple proteins in a ligand screen, allowing for high-throughput inverse docking that presents new opportunities for improving the efficiency of the drug discovery pipeline. VinaMPI successfully ran on 84,672 cores with a continual decrease in job completion time with increasing core count. The ratio of the number of tasks in a screening to the number of workers should be at least around 100 in order to have a good load balance and an optimal job completion time. The code is freely available and downloadable. Lastly, the instructions for downloading and using the code are provided in the Supporting Information.

97 MATHEMATICS AND COMPUTING↗

Manipulation of large objects

Remote manipulator control experiments have been conducted to investigate the problems related to the 'controlled collision' aspect of manipulation. A six degrees of freedom pantograph arm with a six-dimensional force-torque balance sensor and microprocessor-driven real-time graphics display are employed in the experiments. Among other results, it is found that the use of computer force-torque feedback loop for 'stop at contact' provides a nearly linear relation between load transfer to jigs at 'stop at contact', rate of motion, and preset force-torque threshold values for stop under limited motion and load conditions.

Bejczy, A. K.↗

Recent refinements and increased capabilities in balloon vertical performance analysis

The NASA Thermal Trajectory analysis model for predicting the vertical performance of balloons is described in terms of two critical refinements and recent results. The model employs heat-balance equations and a vertical equation of motion, and revised methods are employed to predict maximum balloon volume, balloon shape, and the continuous computation of gas loss. Also incorporated are modeling techniques for assessing the solar radiation input that can affect the load tapes, and autoballast control algorithms are employed. The model permits the evaluation of the presence of cap layers as well as the effects of small leaks and programmed venting. The revised model is shown to give good predictions of balloon performance during flight in terms of altitude changes, descent rates, gas-mass flow, and leak potential. The model is found to be more versatile due to autoballasting and leak analysis, and good prediction are possible for the float phase and descent of current balloon shapes.

Conrad, G. R.↗

Object-Oriented Implementation of the NAS Parallel Benchmarks using Charm++

This report describes experiences with implementing the NAS Computational Fluid Dynamics benchmarks using a parallel object-oriented language, Charm++. Our main objective in implementing the NAS CFD kernel benchmarks was to develop a code that could be used to easily experiment with different domain decomposition strategies and dynamic load balancing. We also wished to leverage the object-orientation provided by the Charm++ parallel object-oriented language, to develop reusable abstractions that would simplify the process of developing parallel applications. We first describe the Charm++ parallel programming model and the parallel object array abstraction, then go into detail about each of the Scalar Pentadiagonal (SP) and Lower/Upper Triangular (LU) benchmarks, along with performance results. Finally we conclude with an evaluation of the methodology used.

Krishnan, Sanjeev↗

Exploring dynamic load imbalance solutions with the CoMD proxy application

Proxy applications are developed to simplify studying parallel performance of scientific simulations and to test potential solutions for performance problems. However, proxy applications are typically too simple to allow work migration or to represent the load imbalance of their parent applications. To study the ability of load balancing solutions to balance work effectively, we enable work migration in one of the Exascale Co-design Center for Materials in Extreme Environments (ExMatEx) [1] applications, CoMD. We design a methodology to parameterize three key aspects necessary for studying load imbalance correction: (1) the granularity with which work can be migrated; (2) the initial load imbalance; (3) the dynamic load imbalance (how quickly the load changes over time). Finally, we present a study of the impact of flexibility in work migration in CoMD on load balance and the associated rebalancing costs for a wide range of initial and dynamic load imbalance scenarios.

97 MATHEMATICS AND COMPUTING↗

Modeling a Gas-Cooled Microreactor Balance of Plant for the Virtual Test Bed

High Temperature Gas-cooled Reactors (HTGRs) are one of the technology considered for microreactor designs because of their high performance and technological maturity. Several designs are being developed. These microreactor cores are connected to power conversion system (PCS) through a heat exchanger. For transient analysis, the feedback of the PCS or of the primary loop can be important, therefore, it is necessary to develop robust models for the balance of plant that can be coupled to a core model. In this work, a balance of plant model using the MOOSE Thermal Hydraulics module (THM) is presented and demonstrated for startup and load-follow transients. This model can be seamlessly coupled with any MOOSE-based multi-physics core model using the MOOSE multi-app approach.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

An enhanced SOCP-based method for feeder load balancing using the multi-terminal soft open point in active distribution networks

The integration of distributed generators (DGs) exacerbates the feeder power flow fluctuation and load unbalanced condition in active distribution networks (ADNs). The unbalanced feeder load causes inefficient use of network assets and network congestion during system operation. The flexible interconnection based on the multi-terminal soft open point (SOP) significantly benefits the operation of ADNs. The multi-terminal SOP, which is a controllable power electronic device installed to replace the normally open point, provides accurate active and reactive power flow control to enable the flexible connection of feeders. An enhanced SOCP-based method for feeder load balancing using the multi-terminal SOP is proposed in this paper. Furthermore, by regulating the operation of the multi-terminal SOP, the proposed method can mitigate the unbalanced condition of feeder load and simultaneously reduce the power losses of ADNs. Then, the original non-convex model is converted into a second-order cone programming (SOCP) model using convex relaxation. In order to tighten the SOCP relaxation and improve the computation efficiency, an enhanced SOCP-based approach is developed to solve the proposed model. Finally, case studies are performed on the modified IEEE 33-node system to verify the effectiveness and efficiency of the proposed method.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Preliminary Investigation on the Cost Reduction Potential of Optimizing Bore Fields for Commercial Ground Source Heat Pump Systems

The high initial cost of ground heat exchangers (GHE) is a primary hurdle preventing wider adoption of ground source heat pump (GSHP) systems. GHEs used for commercial GSHP systems commonly consist of vertical boreholes installed on a grid with equal spacing between boreholes. Significant thermal loads require a large number of boreholes to be present in the field. However, due to thermal interactions among boreholes, the ground formation in the center of a bore field can, over time, become thermally saturated when the thermal load is not balanced on an annual basis. The loss of effectiveness due to thermal saturation at the center boreholes in regularly spaced borehole fields suggests that larger spacing near the center of the bore field could be more optimal, and in return reduce initial costs. Through computer simulations using the latest development of a GHE modeling tool, this study evaluates the impacts of various unconventional designs of the borehole field on the performance and cost of the GHEs of a typical commercial GSHP system. The unconventional designs include irregular spacing among boreholes with decreased spacing around the perimeter and increased spacing in the interior of the field. The unconventional bore field design shortens the total drilling length by up to 42% while giving better heat transfer performance than a conventional bore field design. The significant total bore length reduction is due to improved heat transfer effectiveness of each borehole in the unconventional bore field.

Spitler, Jeffery↗

A partitioning strategy for nonuniform problems on multiprocessors

The partitioning of a problem on a domain with unequal work estimates in different subddomains is considered in a way that balances the work load across multiple processors. Such a problem arises for example in solving partial differential equations using an adaptive method that places extra grid points in certain subregions of the domain. A binary decomposition of the domain is used to partition it into rectangles requiring equal computational effort. The communication costs of mapping this partitioning onto different microprocessors: a mesh-connected array, a tree machine and a hypercube is then studied. The communication cost expressions can be used to determine the optimal depth of the above partitioning.

Berger, M. J.↗

A partitioning strategy for nonuniform problems on multiprocessors

The partitioning of a problem on a domain with unequal work estimates in different subdomains is considered in a way that balances the work load across multiple processors. Such a problem arises for example in solving partial differential equations using an adaptive method that places extra grid points in certain subregions of the domain. A binary decomposition of the domain is used to partition it into rectangles requiring equal computational effort. The communication costs of mapping this partitioning onto different microprocessors: a mesh-connected array, a tree machine and a hypercube is then studied. The communication cost expressions can be used to determine the optimal depth of the above partitioning.

Berger, Marsha J.↗

Rollable Corrugated Tubular Booms

A promising candidate for a new class of deployable composite boom is the COrrugated ROllable TUbular Boom (COROTUB), which is to be employed on future large space structures by the National Aeronautics and Space Administration (NASA). The COROTUB’s two corrugated thin shells form a closed section, which yields high bending and torsional stiffness, allowing for high dimensional stability. The corrugation geometry that dictates the boom cross-section shape was completely defined by closed-form analytical equations given a set of key design parameters. Parametric studies of two geometric variables were used to evaluate which parameters most influence the cross-section’s area moment of inertia and torsional constant. The number of corrugations, flattened height of the boom, and concave and convex corrugation radii were varied to study the complete boom design space. Deeper corrugations increased the local buckling (crimpling) loads of the thin-shell boom but reduced the area moment of inertia and therefore the global buckling load of the beam-column member, and thus a fine balance was sought. Finite element analyses of pure bending and compression load cases for short, 1.22-m-long fully-deployed booms ofeither the same size (flattened height) or similar inertia properties, were first carried out to efficiently study this design trade-off in detail.A second computational study evaluated the boom transition shape and the structural response of a 6-m-long partially-deployed boom, where the effects of partially bracing the root of the boom were also assessed. It was found that bracing length could greatly affect the strength and stiffness of this boom.Bracing type (as in the discrete number of clamps at the root) had no effect on stiffness, but particularly impacted strength for loading cases and boundary conditions that promoted the onset of local web buckling at the root. The corrugated designs were also found to improve, by as much as 20%, the boom bending and axial strength and boom transition length from flat to deployed when compared to a state-of-the-art boom alternative of the same size, for short bracing distances, such as those that would be required by small satellite applications. In addition, they showed a comparable structural response for longer bracing supports.

Booms↗