Search NASA⌕ Search

SEARCH · Search NASA

Results for “Parallel processors”

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 145 records · Page 8

Transient finite element computations on the transputer system

The aim was to study the solution of transient finite element problems on the Transputer system of parallel processors. The central difference time integration rule was used so that no equation solving was necessary. Also investigated was subcycling time integration which uses different time steps in different subdomains of the finite element mesh. A one-dimensional bar problem was analyzed using the parallel time integration algorithm. This involves subdividing the bar into subproblems which are assigned to different processors. Results show that the significant speed-up can be obtained through parallel processing. Also subcycling can give an additional speed-up in certain classes of problems. A two-dimensional problem was also examined to evaluate the effect of the communication to computation ratio on solution time.

Smolinski, Patrick J.↗

CMOS VLSI Layout and Verification of a SIMD Computer

A CMOS VLSI layout and verification of a 3 x 3 processor parallel computer has been completed. The layout was done using the MAGIC tool and the verification using HSPICE. Suggestions for expanding the computer into a million processor network are presented. Many problems that might be encountered when implementing a massively parallel computer are discussed.

Zheng, Jianqing↗

On the Degradation of the Effectiveness of Nonlinear Diffusion Acceleration with Parallel Block Jacobi Splitting

MOOSE's radiation transport module Rattlesnake comprises a first order S N solver that can be accelerated with a flexible Nonlinear Diffusion Acceleration. At each NDA iteration, the streaming and collision operator of the S{sub N} equations are (approximately) inverted using a transport sweep. When executed on multiple processors parallel block Jacobi (PBJ) splitting is utilized lagging the processor sub-domain's incoming angular fluxes making the implemented method asynchronous, i.e. the convergence properties of NDA become dependent on the number of concurrent tasks and details of the partitioning. Within this work, we study the NDA convergence properties for the two-dimensional C5G7 benchmark problem PBJ with p = 1, 2, 4, 8, 12, 16, 24, 32, 48, 60, 72, 96 and 144 concurrent tasks. Rosa studied the convergence properties of PBJ splitting methods with and without transport synthetic acceleration (TSA) in slab geometry and two-dimensional Cartesian geometry, respectively. Rosa's iteration scheme lags both the incoming angular fluxes and the scattering source making it very similar to the method described here. Rosa found by means of Fourier analysis that convergence of unaccelerated PBJ can degrade for optically thin subdomains, i.e. for a large number of processors given a fixed domain size. Depending on the choice of parameters application of TSA can lead to an effective algorithm. In contrast to Rosa's work, this work focuses on PBJ splitting for NDA accelerated solution of the multigroup eigenvalue problem. Later, Zerr and Anistratov used their integral transport matrix method in conjunction with PBJ. This iteration scheme is different as it does not lag the scattering source. Nevertheless, Fourier analysis with Diamond Difference spatial discretization showed that the method degrades with increasing the overall size of the spatial domain while keeping the sub-domain size constant. In the case of an infinite medium, the observed spectral radius becomes unity. These references establish the iterative performance of PBJ for one-group fixed source problems discretized on rectangular cells, but for the Rattlesnake first order NDA method, an emphasis lies on multigroup eigenvalue problems. In this setting, the additional complication arises that the low order equations are not exactly inverted, but only to some iterative criterion. Further, as the low order problem is solved using Jacobian-Free Newton Krylov methods, a suitable preconditioner for the GMRES iterations is required. As the effectiveness of the preconditioners may decrease when more concurrent processes are used, we expect the low order solve to impact the overall effectiveness of the NDA method in parallel execution as well. Therefore, this work focuses on the question of how detrimental the asynchronicity of the high and low order iterative solutions is for the effectiveness of NDA solutions of realistic, unstructured grid, multigroup eigenvalue problems. The iterative convergence properties of Rattlesnake's NDA method for multigroup eigenvalue problems are studied for varying number of concurrent processes. Rattlesnake's NDA method is asynchronous because the high order transport sweep uses PBJ splitting and because the low order solve's preconditioners, algebraic multigrid and additive Schwarz, are asynchronous. We found that up to 144 processes the number of Picard iterations increases by a factor of 2-3 affecting but not destroying NDA's parallel performance for the C5G7 benchmark problem, a representative LWR (light water reactor) configuration. The solution of the NDA low order eigenvalue problem posed greater problems than expected for the solvers currently available in Rattlesnake mainly because of problems to effectively precondition the modified low-order problem. As a matter of fact, the low order problem becomes an advection-diffusion problem. Non-robustness was observed for the AMG preconditioned coarse mesh acceleration for more than 60 concurrent processes, which was fixed by increasing the number of permissible V-cycles per AMG call. For fine mesh acceleration AMG proved to be ineffective and we resorted to ASM. For both AMG and ASM, increasing number of linear iterations per nonlinear are observed when increasing the number of processes, but for ASM this problem appears to be worse. The results from this work also indicate that initial development efforts should be diverted from implementation of a high-order parallel sweeping algorithm to the effective and robust iterative solution of the low order NDA multigroup eigenvalue problem. (authors)

97 MATHEMATICS AND COMPUTING↗

Implementation of the barotropic vorticity equation on the MPP

A finite difference version of the equations governing two-dimensional, non-divergent flow on a sphere is implemented and integrated on the Massively Parallel Processor (MPP). The MPP's performance is then compared with the Cyber's. The feasibility of using a massively parallel architecture to solve the hydrodynamic equations as they are used in numerical weather prediction (NWP) are described.

Suarez, Max J.↗

Algorithms and programming tools for image processing on the MPP, introduction

The programming tools and parallel algorithms created for the Massively Parallel Processor (MPP) located at the NASA Goddard Space Center are discussed. A user-friendly environment for high level language parallel algorithm development was developed. The issues involved in implementing certain algorithms on the MPP were researched. The expected results were compared with the actual results.

Source record↗

Navier-Stokes Computations on Commodity Computers

In this paper we discuss and demonstrate the feasibility of solving high-fidelity, nonlinear computational fluid dynamics (CFD) problems of practical interest on commodity machines, namely Pentium Pro PC's. Such calculations have now become possible due to the progress in computational power and memory of the off-the-shelf commodity computers, along with the growth in bandwidth and communication speeds of networks. A widely used CFD code known as TLNS3D, which was developed originally on large shared memory computers was selected for this effort. This code has recently been ported to massively parallel processor (MPP) type machines, where natural partitioning along grid blocks is adopted in which one or more blocks are distributed to each of the available processors. In this paper, a similar approach is adapted to port this code to a cluster of Pentium Pro computers. The message passing among the processors is accomplished through the use of standard message passing interface (MPI) libraries. Scaling studies indicate fairly high level of parallelism on such clusters of commodity machines, thus making solutions to Navier-Stokes equations for practical problems more affordable.

Vatsa, Veer N.↗

A Queue Simulation Tool for a High Performance Scientific Computing Center

The NASA Center for Computational Sciences (NCCS) at the Goddard Space Flight Center provides high performance highly parallel processors, mass storage, and supporting infrastructure to a community of computational Earth and space scientists. Long running (days) and highly parallel (hundreds of CPUs) jobs are common in the workload. NCCS management structures batch queues and allocates resources to optimize system use and prioritize workloads. NCCS technical staff use a locally developed discrete event simulation tool to model the impacts of evolving workloads, potential system upgrades, alternative queue structures and resource allocation policies.

Spear, Carrie↗

A nonrecursive order N preconditioned conjugate gradient: Range space formulation of MDOF dynamics

While excellent progress has been made in deriving algorithms that are efficient for certain combinations of system topologies and concurrent multiprocessing hardware, several issues must be resolved to incorporate transient simulation in the control design process for large space structures. Specifically, strategies must be developed that are applicable to systems with numerous degrees of freedom. In addition, the algorithms must have a growth potential in that they must also be amenable to implementation on forthcoming parallel system architectures. For mechanical system simulation, this fact implies that algorithms are required that induce parallelism on a fine scale, suitable for the emerging class of highly parallel processors; and transient simulation methods must be automatically load balancing for a wider collection of system topologies and hardware configurations. These problems are addressed by employing a combination range space/preconditioned conjugate gradient formulation of multi-degree-of-freedom dynamics. The method described has several advantages. In a sequential computing environment, the method has the features that: by employing regular ordering of the system connectivity graph, an extremely efficient preconditioner can be derived from the 'range space metric', as opposed to the system coefficient matrix; because of the effectiveness of the preconditioner, preliminary studies indicate that the method can achieve performance rates that depend linearly upon the number of substructures, hence the title 'Order N'; and the method is non-assembling. Furthermore, the approach is promising as a potential parallel processing algorithm in that the method exhibits a fine parallel granularity suitable for a wide collection of combinations of physical system topologies/computer architectures; and the method is easily load balanced among processors, and does not rely upon system topology to induce parallelism.

Kurdila, Andrew J.↗

Compute Server Performance Results

Parallel-vector supercomputers have been the workhorses of high performance computing. As expectations of future computing needs have risen faster than projected vector supercomputer performance, much work has been done investigating the feasibility of using Massively Parallel Processor systems as supercomputers. An even more recent development is the availability of high performance workstations which have the potential, when clustered together, to replace parallel-vector systems. We present a systematic comparison of floating point performance and price-performance for various compute server systems. A suite of highly vectorized programs was run on systems including traditional vector systems such as the Cray C90, and RISC workstations such as the IBM RS/6000 590 and the SGI R8000. The C90 system delivers 460 million floating point operations per second (FLOPS), the highest single processor rate of any vendor. However, if the price-performance ration (PPR) is considered to be most important, then the IBM and SGI processors are superior to the C90 processors. Even without code tuning, the IBM and SGI PPR's of 260 and 220 FLOPS per dollar exceed the C90 PPR of 160 FLOPS per dollar when running our highly vectorized suite,

Stockdale, I. E.↗

Programming a hillslope water movement model on the MPP

A physically based numerical model was developed of heat and moisture flow within a hillslope on a parallel architecture computer, as a precursor to a model of a complete catchment. Moisture flow within a catchment includes evaporation, overland flow, flow in unsaturated soil, and flow in saturated soil. Because of the empirical evidence that moisture flow in unsaturated soil is mainly in the vertical direction, flow in the unsaturated zone can be modeled as a series of one dimensional columns. This initial version of the hillslope model includes evaporation and a single column of one dimensional unsaturated zone flow. This case has already been solved on an IBM 3081 computer and is now being applied to the massively parallel processor architecture so as to make the extension to the one dimensional case easier and to check the problems and benefits of using a parallel architecture machine.

Devaney, J. E.↗

A study of the XY model by the Monte Carlo method

The massively parallel processor is used to perform Monte Carlo simulations for the two dimensional XY model on lattices of sizes up to 128 x 128. A parallel random number generator was constructed, finite size effects were studied, and run times were compared with those on a CRAY X-MP supercomputer.

Suranyi, Peter↗

Concurrent Finite-Element Analysis On Hypercube Computers

Improved approach to execution of finite-element codes on hypercube and similar concurrent data processors increases efficiency of computation for many different types of problems. Based on flexible general model of computation on, and communication among, large-node parallel processors. Hybrid combining direct methods within subdomains and preconditioned-conjugate-gradient (PCG) iteration on remaining boundary system to obtain method of solution both robust and efficient. Preserves general structure and function of conventional sequential finite-element-method software. Generalized to both distributed- and shared-memory multicomputers, eliminating degree of machine specificity restricting general usefulness.

Lyzenga, G. A.↗

Supercomputing systems - A projection to 2000

Advances in computer architecture, computer science, computational methods, and constituent technologies are expected to lead to significant advances in the performance of scientific supercomputing system capabilities over the next decade. By the year 2000, single 1-in-sq dies are projected to incorporate four processors, each of which would be operating faster than 750 million instructions per second (MIPS) for a total on-chip processing performance in excess of 2000 MIPS. Scalable parallel processors can be expected to contain thousands of such multiple processor chips. In general, semiconductor performance advances appear to change about one order of magnitude every five years. Rotating magnetic memory and communications technology are not advancing as rapidly, with the result that the allocation of functions within the system configurations fo future supercomputer systems will require important changes. Availability of massively parallel heterogeneous processing capabilities should be a catalyst leading to new approaches for applications.

Lundstrom, S. F.↗

Automatic partitioning of unstructured meshes for the parallel solution of problems in computational mechanics

Most of the recently proposed computational methods for solving partial differential equations on multiprocessor architectures stem from the 'divide and conquer' paradigm and involve some form of domain decomposition. For those methods which also require grids of points or patches of elements, it is often necessary to explicitly partition the underlying mesh, especially when working with local memory parallel processors. In this paper, a family of cost-effective algorithms for the automatic partitioning of arbitrary two- and three-dimensional finite element and finite difference meshes is presented and discussed in view of a domain decomposed solution procedure and parallel processing. The influence of the algorithmic aspects of a solution method (implicit/explicit computations), and the architectural specifics of a multiprocessor (SIMD/MIMD, startup/transmission time), on the design of a mesh partitioning algorithm are discussed. The impact of the partitioning strategy on load balancing, operation count, operator conditioning, rate of convergence and processor mapping is also addressed. Finally, the proposed mesh decomposition algorithms are demonstrated with realistic examples of finite element, finite volume, and finite difference meshes associated with the parallel solution of solid and fluid mechanics problems on the iPSC/2 and iPSC/860 multiprocessors.

Farhat, Charbel↗

Seasat synthetic-aperture radar data reduction using parallel programmable array processors

This paper presents a digital processing system that produces the Seasat synthetic-aperture radar (SAR) imagery. The system consists of a SEL 32/77 host minicomputer and three AP-120B array processors. The partitioning of the SAR processing functions and the design of software modules is described. The rationale for selecting the parallel array processor architecture and the methodology for developing the parallel processing scheme on this system is described. This system attains a Seasat SAR data reduction speed of 2.5 h per 25-m resolution 4-look and 100 km x 100 km image frame. A preliminary performance evaluation of this parallel processing system and potential future applications for remote sensing data reduction are described.

Wu, C.↗

Appendix E: Parallel Pascal development system

The Parallel Pascal Development System enables Parallel Pascal programs to be developed and tested on a conventional computer. It consists of several system programs, including a Parallel Pascal to standard Pascal translator, and a library of Parallel Pascal subprograms. The library includes subprograms for using Parallel Pascal on a parallel system with a fixed degree of parallelism, such as the Massively Parallel Processor, to conveniently manipulate arrays which have dimensions than the hardware. Programs can be conveninetly tested with small sized arrays on the conventional computer before attempting to run on a parallel system.

Source record↗

iHarmonizer: improving the disk efficiency of I/O-intensive multithreaded codes

Challenged by serious power and thermal constraints, and limited by available instruction-level parallelism, processor designs have evolved to multi-core architectures. These architectures, many augmented with native simultaneous multithreading, are driving software developers to use multithreaded programs to exploit thread-level parallelism. While multithreading is well-known to introduce concerns of data dependency and CPU load balance, less known is that the uncertainty of relative progress of thread execution can cause patterns of I/O requests, issued by different threads, to be effectively random and so significantly degrade hard-disk efficiency. This effect can severely offset the performance gains from parallel execution, especially for I/O-intensive programs. Retaining the benefits of multithreading while not reducing I/O efficiency is an urgent and challenging problem. We propose a user-level scheme, iHarmonizer, to streamline the servicing of I/O requests from multiple threads in OpenMP programs. Specifically, we use the compiler to insert code into OpenMP programs so that data usage can be transmitted at run time to a supporting run-time library; this library in turn prefetches data in a disk-friendly way and coordinates threads execution according to the availability of their requested data. Transparently to the programmer, iHarmonizer makes a multithreaded program I/O efficient while maintaining the benefits of parallelism. Our experiments show that iHarmonizer can significantly speed up the execution of a representative set of I/O-intensive scientific benchmarks.

97 MATHEMATICS AND COMPUTING↗

Design and Performance Analysis of a Massively Parallel Atmospheric General Circulation Model

In the 1990's computer manufacturers are increasingly turning to the development of parallel processor machines to meet the high performance needs of their customers. Simultaneously, atmospheric scientists study weather and climate phenomena ranging from hurricanes to El Nino to global warming that require increasingly fine resolution models. Here, implementation of a parallel atmospheric general circulation model (GCM) which exploits the power of massively parallel machines is described. Using the horizontal data domain decomposition methodology, this FORTRAN 90 model is able to integrate a 0.6 deg. longitude by 0.5 deg. latitude problem at a rate of 19 Gigaflops on 512 processors of a Cray T3E 600; corresponding to 280 seconds of wall-clock time per simulated model day. At this resolution, the model has 64 times as many degrees of freedom and performs 400 times as many floating point operations per simulated day as the model it replaces.

Schaffer, Daniel S.↗