SEARCH · Search NASA
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.
The comparison of programming languages is best seen while evaluating similar systems. The strengths and weaknesses of both languages were investigated as the scheduler was being implemented. Some features used in both languages shall be object-oriented paradigms, parallel programming, search and production heuristics, and other classical artificial intelligence implementations.
Architectures that would exploit the distinct characteristics of quantum-dot cellular automata (QCA) have been proposed for digital communication networks that connect advanced digital computing circuits. In comparison with networks of wires in conventional very-large-scale integrated (VLSI) circuitry, the networks according to the proposed architectures would be more compact. The proposed architectures would make it possible to implement complex interconnection schemes that are required for some advanced parallel-computing algorithms and that are difficult (and in many cases impractical) to implement in VLSI circuitry. The difficulty of implementation in VLSI and the major potential advantage afforded by QCA were described previously in Implementing Permutation Matrices by Use of Quantum Dots (NPO-20801), NASA Tech Briefs, Vol. 25, No. 10 (October 2001), page 42. To recapitulate: Wherever two wires in a conventional VLSI circuit cross each other and are required not to be in electrical contact with each other, there must be a layer of electrical insulation between them. This, in turn, makes it necessary to resort to a noncoplanar and possibly a multilayer design, which can be complex, expensive, and even impractical. As a result, much of the cost of designing VLSI circuits is associated with minimization of data routing and assignment of layers to minimize crossing of wires. Heretofore, these considerations have impeded the development of VLSI circuitry to implement complex, advanced interconnection schemes. On the other hand, with suitable design and under suitable operating conditions, QCA-based signal paths can be allowed to cross each other in the same plane without adverse effect. In principle, this characteristic could be exploited to design compact, coplanar, simple (relative to VLSI) QCA-based networks to implement complex, advanced interconnection schemes. The proposed architectures require two advances in QCA-based circuitry beyond basic QCA-based binary-signal wires described in the cited prior article. One of these advances would be the development of QCA-based wires capable of bidirectional transmission of signals. The other advance would be the development of QCA circuits capable of high-impedance state outputs. The high-impedance states would be utilized along with the 0- and 1-state outputs of QCA.
In this poster, a GPU-accelerated sparse multifrontal solver for structurally symmetric matrices is described. The implementation is tested on the Summit supercomputer against the current version, which is parallelized via MPI and OpenMP on CPUs. The GPU-accelerated implementation achieves significant speedup from the original code.
Choleski's method for solving banded symmetric, positive definite systems is implemented on a multiprocessor computer using three FORTRAN based parallel programming languages, the Force, PISCES and Concurrent FORTRAN. The capabilities of the language for expressing parallelism and their user friendliness are discussed, including readability of the code, debugging assistance offered, and expressiveness of the languages. The performance of the different implementations is compared. It is argued that PISCES, using the Force for medium-grained parallelism, is the appropriate choice for programming Choleski's method on the multiprocessor computer, Flex/32.
Least-squares (LS) estimations and spectral decomposition algorithms constitute the heart of modern signal processing and communication problems. Implementations of recursive LS and spectral decomposition algorithms onto parallel processing architectures such as systolic arrays with efficient fault-tolerant schemes are the major concerns of this dissertation. There are four major results in this dissertation. First, we propose the systolic block Householder transformation with application to the recursive least-squares minimization. It is successfully implemented on a systolic array with a two-level pipelined implementation at the vector level as well as at the word level. Second, a real-time algorithm-based concurrent error detection scheme based on the residual method is proposed for the QRD RLS systolic array. The fault diagnosis, order degraded reconfiguration, and performance analysis are also considered. Third, the dynamic range, stability, error detection capability under finite-precision implementation, order degraded performance, and residual estimation under faulty situations for the QRD RLS systolic array are studied in details. Finally, we propose the use of multi-phase systolic algorithms for spectral decomposition based on the QR algorithm. Two systolic architectures, one based on triangular array and another based on rectangular array, are presented for the multiphase operations with fault-tolerant considerations. Eigenvectors and singular vectors can be easily obtained by using the multi-pase operations. Performance issues are also considered.
The spectral method provides an efficient algorithm for solving the 3D incompressible Navier-Stokes equations in periodic boundaries. Most people, so far, have used vectorized machines, such as the CRAY-2, to implement fast Fourier transformations and time integrations in the spectral calculations. In this paper, new results are presented using the spectral calculations on the Connection Machine-2 with a parallel algorithm. The large memory of the Connection Machine-2 and the parallel algorithm allows, of the first time, to implement a 512-cubed mesh resolution for high Reynolds number flows. The computational speed of the present code is about 30 percent faster than the fastest CRAY-2 simulations with four processors. Parallel machines, such as the Connection Machine-2, will possibly provide new computational power for understanding the intermittency and cascade mechanism in fluid turbulence.
Integration of Shift-and-Invert Parallel spectral transformation (SIPs) eigensolver (as implemented in the SLEPc library) into an ab initio molecular dynamics package, SIESTA, is described. The effectiveness of the code is demonstrated on applications to polyethylene chains, boron nitride sheets, and bulk water clusters. For problems with the same number of orbitals, the performance of the SLEPc eigensolver depends on the sparsity of the matrices involved, favoring reduced dimensional systems such as polyethylene or boron nitride sheets in comparison to bulk systems like water clusters. For all problems investigated, performance of SIESTA-SIPs exceeds the performance of SIESTA with default solver (ScaLAPACK) at the larger number of cores and the larger number of orbitals. A method that improves the load-balance with each iteration in the self-consistency cycle by exploiting the emerging knowledge of the eigenvalue spectrum is demonstrated
This chapter describes the implementation and benchmarking of a new software code for nonorthogonal configuration interaction calculations. GronOR is named after the University of Groningen and Oak Ridge National Laboratory, the two institutions that are collaborating on the development of this code for the largest massively parallel supercomputers for open science. The basic implementation approach is described and preliminary benchmarking results are given as obtained from early access to Summit, the next Oak Ridge Leadership Computing Facility's supercomputer with 200 PFlop.
We describe the development, operation, and application of the 4D Camera—a 576 by 576 pixel active pixel sensor for scanning/transmission electron microscopy which operates at 87,000 Hz. The detector generates data at ~480 Gbit/s which is captured by dedicated receiver computers with a parallelized software infrastructure that has been implemented to process the resulting 10–700 Gigabyte-sized raw datasets. The back illuminated detector provides the ability to detect single electron events at accelerating voltages from 30 to 300 kV. Through electron counting, the resulting sparse data sets are reduced in size by 10--300× compared to the raw data, and open-source sparsity-based processing algorithms offer rapid data analysis. The high frame rate allows for large and complex scanning diffraction experiments to be accomplished with typical scanning transmission electron microscopy scanning parameters.
A new class of distance-two interpolation methods for algebraic multigrid (AMG) that can be formulated in terms of sparse matrix-matrix multiplications is presented and analyzed. Compared with similar distance-two prolongation operators, the proposed algorithms exhibit improved efficiency and portability to various computing platforms, since they allow one to easily exploit existing high-performance sparse matrix kernels. The new interpolation methods have been implemented in hypre, a widely used parallel multigrid solver library. With the proposed interpolations, the overall time of hypre's BoomerAMG setup can be considerably reduced, while sustaining equivalent, sometimes improved, convergence rates. Numerical results for a variety of test problems on parallel machines are presented that support the superiority of the proposed interpolation operators over the existing ones in hypre.
Optical implementation of the Fukunaga-Koontz transform (FKT) and the Least-Squares Linear Mapping Technique (LSLMT) is described. The FKT is a linear transformation which performs image feature extraction for a two-class image classification problem. The LSLMT performs a transform from large dimensional feature space to small dimensional decision space for separating multiple image classes by maximizing the interclass differences while minimizing the intraclass variations. The FKT and the LSLMT were optically implemented by utilizing a coded phase optical processor. The transform was used for classifying birds and fish. After the F-K basis functions were calculated, those most useful for classification were incorporated into a computer generated hologram. The output of the optical processor, consisting of the squared magnitude of the F-K coefficients, was detected by a T.V. camera, digitized, and fed into a micro-computer for classification. A simple linear classifier based on only two F-K coefficients was able to separate the images into two classes, indicating that the F-K transform had chosen good features. Two advantages of optically implementing the FKT and LSLMT are parallel and real time processing.
It is pointed out that the two-dimensional cyclic convolution is a useful tool for many two-dimensional digital signal processing applications. Two important applications are related to spaceborne high-resolution synthetic aperture radar (SAR) processing and image processing. Nussbaumer and Quandalle (1978) showed that a radix-2 polynomial transform analogous to the conventional radix-2 FFT algorithm can be used to compute a two-dimensional cyclic convolution. On the basis of results reported by Arambepola and Rayner (1979), a radix-2 polynomial transform can be defined to compute a multidimensional cyclic convolution. Truong et al. (1981) used the considered ideas together with the Chinese Theorem to further reduce the complexity of the radix-2 fast polynomial transform (FPT). Reed et al. (1981) demonstrated that such a new FPT algorithm is significantly faster than the FFT algorithm for computing a two-dimensional convolution. In the present investigation, a parallel-pipeline architecture is considered for implementing the FPT developed by Truong et al.
The similarity between the Fast Fourier Transform and the Viterbi algorithm is exploited to develop a Concurrent Viterbi Algorithm suitable for a multiprocessor system interconnected as a hypercube. The proposed algorithm can efficiently decode large constraint length convolutional codes, using different degrees of parallelism, and is attractive for VLSI implementation.
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.
A new algorithm for the numerical solution of the Euler equations is presented. This algorithm is particularly suited to the use of unstructured triangular meshes, allowing geometric flexibility. Solutions are second-order accurate in the steady state. Implementation of the algorithm requires minimal grid connectivity information, resulting in modest storage requirements, and should enhance the implementation of the scheme on massively parallel computers. A novel form of upwind differencing is developed, and is shown to yield sharp resolution of shocks. Two new artificial viscosity models are introduced that enhance the performance of the new scheme. Numerical results for transonic airfoil flows are presented, which demonstrate the performance of the algorithm.
Techniques are described for computing matrix inverses by algorithms that are highly suited to massively parallel computation. The techniques are based on an algorithm suggested by Strassen (1969). Variations of this scheme use matrix Newton iterations and other methods to improve the numerical stability while at the same time preserving a very high level of parallelism. One-processor Cray-2 implementations of these schemes range from one that is up to 55 percent faster than a conventional library routine to one that is slower than a library routine but achieves excellent numerical stability. The problem of computing the solution to a single set of linear equations is discussed, and it is shown that this problem can also be solved efficiently using these techniques.
User does not have to add any special logic to aid in synchronization. Time Warp Operating System (TWOS) computer program is special-purpose operating system designed to support parallel discrete-event simulation. Complete implementation of Time Warp mechanism. Supports only simulations and other computations designed for virtual time. Time Warp Simulator (TWSIM) subdirectory contains sequential simulation engine interface-compatible with TWOS. TWOS and TWSIM written in, and support simulations in, C programming language.
The problem of Cholesky factorization of a sparse matrix has been very well investigated on sequential machines. A number of efficient codes exist for factorizing large unstructured sparse matrices. However, there is a lack of such efficient codes on parallel machines in general, and distributed machines in particular. Some of the issues that are critical to the implementation of sparse Cholesky factorization on a distributed memory parallel machine are ordering, partitioning and mapping, load balancing, and ordering of various tasks within a processor. Here, we focus on the effect of various partitioning schemes on the performance of sparse Cholesky factorization on the Intel iPSC/860. Also, a new partitioning heuristic for structured as well as unstructured sparse matrices is proposed, and its performance is compared with other schemes.