Search NASA⌕ Search

SEARCH · Search NASA

Results for “data parallel algorithms”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRS1990

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composite data structure by allocating one processor (at least conceptually) per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of the operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum-cost way to evaluate an expression, for several different data parallel architectures. This algorithm applies to any architecture in which the metric describing the cost of moving an array is robust. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes. Remarks are made on several variations of the problem, some of which are solved and some of which remain open.

Gilbert, John R.↗
NASA NTRS1990

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composite data structure by allocating one processor per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum cost way to evaluate an expression, for several different data parallel architectures. The algorithm applies to any architecture in which the metric describing the cost of moving an array has a property called robustness. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes.

Gilbert, J. R.↗
NASA NTRS1991

Optimal expression evaluation for data parallel architectures

A data parallel machine represents an array or other composits data structure by allocating one processor per data item. A pointwise operation can be performed between two such arrays in unit time, provided their corresponding elements are allocated in the same processors. If the arrays are not aligned in this fashion, the cost of moving one or both of them is part of the cost of operation. The choice of where to perform the operation then affects this cost. If an expression with several operands is to be evaluated, there may be many choices of where to perform the intermediate operations. An efficient algorithm is given to find the minimum cost way to evaluate an expression, for several different data parallel architectures. The algorithm applies to any architecture in which the metric describing the cost of moving an array has a property called robustness. This encompasses most of the common data parallel communication architectures, including meshes of arbitrary dimension and hypercubes.

Gilbert, John R.↗
NASA NTRS1984

Acoustooptic linear algebra processors - Architectures, algorithms, and applications

Architectures, algorithms, and applications for systolic processors are described with attention to the realization of parallel algorithms on various optical systolic array processors. Systolic processors for matrices with special structure and matrices of general structure, and the realization of matrix-vector, matrix-matrix, and triple-matrix products and such architectures are described. Parallel algorithms for direct and indirect solutions to systems of linear algebraic equations and their implementation on optical systolic processors are detailed with attention to the pipelining and flow of data and operations. Parallel algorithms and their optical realization for LU and QR matrix decomposition are specifically detailed. These represent the fundamental operations necessary in the implementation of least squares, eigenvalue, and SVD solutions. Specific applications (e.g., the solution of partial differential equations, adaptive noise cancellation, and optimal control) are described to typify the use of matrix processors in modern advanced signal processing.

Casasent, D.↗
NASA NTRS1990

Assignment Of Finite Elements To Parallel Processors

Elements assigned approximately optimally to subdomains. Mapping algorithm based on simulated-annealing concept used to minimize approximate time required to perform finite-element computation on hypercube computer or other network of parallel data processors. Mapping algorithm needed when shape of domain complicated or otherwise not obvious what allocation of elements to subdomains minimizes cost of computation.

Salama, Moktar A.↗
NASA NTRS2001

The Computational Complexity, Parallel Scalability, and Performance of Atmospheric Data Assimilation Algorithms

The computational complexity of algorithms for Four Dimensional Data Assimilation (4DDA) at NASA's Data Assimilation Office (DAO) is discussed. In 4DDA, observations are assimilated with the output of a dynamical model to generate best-estimates of the states of the system. It is thus a mapping problem, whereby scattered observations are converted into regular accurate maps of wind, temperature, moisture and other variables. The DAO is developing and using 4DDA algorithms that provide these datasets, or analyses, in support of Earth System Science research. Two large-scale algorithms are discussed. The first approach, the Goddard Earth Observing System Data Assimilation System (GEOS DAS), uses an atmospheric general circulation model (GCM) and an observation-space based analysis system, the Physical-space Statistical Analysis System (PSAS). GEOS DAS is very similar to global meteorological weather forecasting data assimilation systems, but is used at NASA for climate research. Systems of this size typically run at between 1 and 20 gigaflop/s. The second approach, the Kalman filter, uses a more consistent algorithm to determine the forecast error covariance matrix than does GEOS DAS. For atmospheric assimilation, the gridded dynamical fields typically have More than 10(exp 6) variables, therefore the full error covariance matrix may be in excess of a teraword. For the Kalman filter this problem can easily scale to petaflop/s proportions. We discuss the computational complexity of GEOS DAS and our implementation of the Kalman filter. We also discuss and quantify some of the technical issues and limitations in developing efficient, in terms of wall clock time, and scalable parallel implementations of the algorithms.

Lyster, Peter M.↗
NASA NTRS1988

Fast Fourier Transform algorithm design and tradeoffs

The Fast Fourier Transform (FFT) is a mainstay of certain numerical techniques for solving fluid dynamics problems. The Connection Machine CM-2 is the target for an investigation into the design of multidimensional Single Instruction Stream/Multiple Data (SIMD) parallel FFT algorithms for high performance. Critical algorithm design issues are discussed, necessary machine performance measurements are identified and made, and the performance of the developed FFT programs are measured. Fast Fourier Transform programs are compared to the currently best Cray-2 FFT program.

Kamin, Ray A., III↗
NASA NTRS1990

An efficient data dependence analysis for parallelizing compilers

A novel algorithm, called the lambda test, is presented for an efficient and accurate data dependence analysis of multidimensional array references. It extends the numerical methods to allow all dimensions of array references to be tested simultaneously. Hence, it combines the efficiency and the accuracy of the both approaches. This algorithm has been implemented in PARAFRASE, a FORTRAN program parallelization restructurer developed at the University of Illinois at Urbana-Champaign. Some experimental results are presented to show its effectiveness.

Li, Zhiyuan↗
NASA NTRS2009

Aerodynamic Interference Due to MSL Reaction Control System

An investigation of effectiveness of the reaction control system (RCS) of Mars Science Laboratory (MSL) entry capsule during atmospheric flight has been conducted. The reason for the investigation is that MSL is designed to fly a lifting actively guided entry with hypersonic bank maneuvers, therefore an understanding of RCS effectiveness is required. In the course of the study several jet configurations were evaluated using Langley Aerothermal Upwind Relaxation Algorithm (LAURA) code, Data Parallel Line Relaxation (DPLR) code, Fully Unstructured 3D (FUN3D) code and an Overset Grid Flowsolver (OVERFLOW) code. Computations indicated that some of the proposed configurations might induce aero-RCS interactions, sufficient to impede and even overwhelm the intended control torques. It was found that the maximum potential for aero-RCS interference exists around peak dynamic pressure along the trajectory. Present analysis largely relies on computational methods. Ground testing, flight data and computational analyses are required to fully understand the problem. At the time of this writing some experimental work spanning range of Mach number 2.5 through 4.5 has been completed and used to establish preliminary levels of confidence for computations. As a result of the present work a final RCS configuration has been designed such as to minimize aero-interference effects and it is a design baseline for MSL entry capsule.

Dyakonov, Artem A.↗
NASA NTRS1989

A fast sorting algorithm for a hypersonic rarefied flow particle simulation on the connection machine

The data parallel implementation of a particle simulation for hypersonic rarefied flow described by Dagum associates a single parallel data element with each particle in the simulation. The simulated space is divided into discrete regions called cells containing a variable and constantly changing number of particles. The implementation requires a global sort of the parallel data elements so as to arrange them in an order that allows immediate access to the information associated with cells in the simulation. Described here is a very fast algorithm for performing the necessary ranking of the parallel data elements. The performance of the new algorithm is compared with that of the microcoded instruction for ranking on the Connection Machine.

Dagum, Leonardo↗
NASA NTRS1991

Three-dimensional direct particle simulation on the Connection Machine

This paper presents the algorithms necessary for an efficient data parallel implementation of a 3D particle simulation. In particular, a general master/slave algorithm and a fast sorting algorithm are described and the use of these algorithms in a particle simulation is outlined. A particle simulation using these algorithms has been implemented on a 32768 processor Connection Machine that is capable of simulating over 30 million particles at an average rate of 2.4-microsec/particle/step. Results are presented from the simulation of flow over an Aeroassisted Flight Experiment geometry at 100 km altitude.

Dagum, Leonardo↗
NASA NTRS1984

On the impact of communication complexity on the design of parallel numerical algorithms

This paper describes two models of the cost of data movement in parallel numerical alorithms. One model is a generalization of an approach due to Hockney, and is suitable for shared memory multiprocessors where each processor has vector capabilities. The other model is applicable to highly parallel nonshared memory MIMD systems. In this second model, algorithm performance is characterized in terms of the communication network design. Techniques used in VLSI complexity theory are also brought in, and algorithm-independent upper bounds on system performance are derived for several problems that are important to scientific computation.

Gannon, D. B.↗
NASA NTRSDate not supplied

Data Science and the Knowledge Discovery Adventure

This talk will cover the important steps involved in the data science and knowledge discovery process: • Initial fact gathering (interview domain experts, review reports, articles, state-of-the-art) • Identify the problem (prediction, classification, statistical analysis, etc.) • Survey supporting data sources • Understand the data (numerical, categorical, text, sampling rate, data quality issues, etc.) • Selecting relevant features and sources • Acquire the data (set up agreements with the data stewards, APIs to download, etc.) • Merge data sources (temporal, spatial, common key, other ontologies...) • Feature Engineering (non linear domain knowledge or physics-based relationships) • Build data processing pipeline (may need to tap into data stream, develop parallel processing algorithm, federated learning etc.) • Build model and test (tune hyper-parameters, cross validation.) • Analyze/Validate results (do the results make sense. Does it answer the original question). • Deploy/Publish (Monitor and assess benefits)

Data science↗
NASA NTRS2010

Multiscale Simulations of Magnetic Island Coalescence

We describe a new interactive parallel Adaptive Mesh Refinement (AMR) framework written in the Python programming language. This new framework, PyAMR, hides the details of parallel AMR data structures and algorithms (e.g., domain decomposition, grid partition, and inter-process communication), allowing the user to focus on the development of algorithms for advancing the solution of a systems of partial differential equations on a single uniform mesh. We demonstrate the use of PyAMR by simulating the pairwise coalescence of magnetic islands using the resistive Hall MHD equations. Techniques for coupling different physics models on different levels of the AMR grid hierarchy are discussed.

Dorelli, John C.↗
NASA NTRS2019

InSight's Reconstructed Aerothermal Environments

The InSight Mars Lander successfully landed on the surface on November 26, 2018. This poster will describe the methodologies and margins used in developing the aerothermal environments for design of the thermal protection systems (TPS), as well as a prediction of as-flown environments based on the best estimated trajectory. The InSight mission spacecraft design approach included the effects of radiant heat flux to the aft body from the wake for the first time on a US Mars Mission, due to overwhelming evidence in ground testing for the European ExoMars mission (2009/2010) [1] and 2010 tests in the Electric Arc Shock Tube (EAST) facility [2]. The radiant energy on an aftbody was also recently confirmed via measurement on the Schiaparelli mission [3]. In addition, the InSight mission expected to enter the Mars atmosphere during the dust storm season, so the heatshield TPS was designed to accommodate the extra recession due to the potential dust impact. This poster will compare the predicted aerothermal environments using the reconstructed best estimated trajectory to the design environments. Design Approach: The InSight spacecraft was planned to be a near-design-to-print copy of the Phoenix spacecraft. The determination of the heatshield TPS requirements was approached as if it was a new design due to the new requirement of flying through a dust storm. The baseline for aftbody was build-to-print, and all analyses focused on ensuring adequate margin. This proved to be a challenge because the Phoenix aftbody was designed to withstand only convective heating and the InSight aftbody was evaluated for both convective and radiative heating. Aerothermal environments were predicted using the Langley Aerothermodynamic Upwind Relaxation Algorithm (LAURA) and the Data Parallel Line Relaxation (DPLR) CFD codes, and the Nonequilibrium Radiative Transport and Spectra Program (NEQAIR) utilizing bounding design trajectories derived from Monte Carlo analyses from the Program to Optimize Simulated Trajectories II (POST2). In all cases, super-catalytic flowfields were assigned to ensure the most conservative heating results. Two trajectories were evaluated: 1) the trajectory with the maximum heat flux was utilized to determine the flowfield characteristics and the viability of the selection of TPS materials; and 2) the trajectory with the maximum heat load was used to determine the required thicknesses of the TPS materials. Evaluation of the MEDLI data [4], along with ground test data [5] led to the determination of whether or not the flow would transition from laminar to turbulent on the heatshield, which also determined the TPS sizing location for the heatshield. Aerothermal margins were added for the convective heating and developed for the radiative heating. TPS material sizing was determined with the Reaction Kinetic Ablation Program (REKAP) and the Fully Implicit Ablation and Thermal Analysis program (FIAT) using a three-branched approach to account for aerothermal, material response, and material properties uncertainties. In addition, the heatshield recession was augmented by an analysis of the effect of entry through a potential dusty atmosphere using a methodology developed in References [6] and [7]. These analyses resulted in an increase to the Phoenix heatshield TPS thickness. Reconstruction Efforts: Once the best estimated trajectory is reconstructed by the team, the LAURA/HARA (High-Temperature Aerothermo-dynamic Radiation model) and DPLR/NEQAIR code pairs will be used to predict the as-flown aerothermal conditions. In these runs, fully-catalytic flowfields will be assigned because it is a more physically accurate description of the chemistry in the flow. Once again, determination of the onset of turbulence on the heatshield will be evaluated. The as-flown aerothermal environments will then be compared to the design environments.

Beck, R. A.↗
NASA NTRS1978

An alternating direction implicit method for the Control Data STAR-100 vector computer

An implementation of the alternating direction implicit (ADI) method for the Control Data STAR-100 computer is presented and analyzed. Two parallel algorithms, both of which are most efficient when used to solve many independent tridiagonal systems of equations, are discussed relative to their usefulness in an ADI implementation on the STAR-100 computer. It is shown that it may be desirable to alternate between the parallel algorithms as the direction of implicitness is alternated in order to eliminate the data rearrangement which would otherwise be required. The applicability of the two parallel tridiagonal solvers to several other numerical algorithms is also discussed.

Lambiotte, J. J., Jr.↗
NASA NTRS1989

Configuration space representation in parallel coordinates

By means of a system of parallel coordinates, a nonprojective mapping from R exp N to R squared is obtained for any positive integer N. In this way multivariate data and relations can be represented in the Euclidean plane (embedded in the projective plane). Basically, R squared with Cartesian coordinates is augmented by N parallel axes, one for each variable. The N joint variables of a robotic device can be represented graphically by using parallel coordinates. It is pointed out that some properties of the relation are better perceived visually from the parallel coordinate representation, and that new algorithms and data structures can be obtained from this representation. The main features of parallel coordinates are described, and an example is presented of their use for configuration space representation of a mechanical arm (where Cartesian coordinates cannot be used).

Fiorini, Paolo↗
NASA NTRS1988

Parallel algorithms for interactive manipulation of digital terrain models

Interactive three-dimensional graphics applications, such as terrain data representation and manipulation, require extensive arithmetic processing. Massively parallel machines are attractive for this application since they offer high computational rates, and grid connected architectures provide a natural mapping for grid based terrain models. Presented here are algorithms for data movement on the massive parallel processor (MPP) in support of pan and zoom functions over large data grids. It is an extension of earlier work that demonstrated real-time performance of graphics functions on grids that were equal in size to the physical dimensions of the MPP. When the dimensions of a data grid exceed the processing array size, data is packed in the array memory. Windows of the total data grid are interactively selected for processing. Movement of packed data is needed to distribute items across the array for efficient parallel processing. Execution time for data movement was found to exceed that for arithmetic aspects of graphics functions. Performance figures are given for routines written in MPP Pascal.

Davis, E. W.↗