SEARCH · Search NASA

Results for “compression 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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 505 records · Page 28

All sources NASA NTRS DOE OSTI

NASA NTRS1975

Finite element computation of a viscous compressible free shear flow governed by the time dependent Navier-Stokes equations

A finite element algorithm for solution of fluid flow problems characterized by the two-dimensional compressible Navier-Stokes equations was developed. The program is intended for viscous compressible high speed flow; hence, primitive variables are utilized. The physical solution was approximated by trial functions which at a fixed time are piecewise cubic on triangular elements. The Galerkin technique was employed to determine the finite-element model equations. A leapfrog time integration is used for marching asymptotically from initial to steady state, with iterated integrals evaluated by numerical quadratures. The nonsymmetric linear systems of equations governing time transition from step-to-step are solved using a rather economical block iterative triangular decomposition scheme. The concept was applied to the numerical computation of a free shear flow. Numerical results of the finite-element method are in excellent agreement with those obtained from a finite difference solution of the same problem.

Cooke, C. H.↗

NASA NTRS2012

GPU Lossless Hyperspectral Data Compression System for Space Applications

On-board lossless hyperspectral data compression reduces data volume in order to meet NASA and DoD limited downlink capabilities. At JPL, a novel, adaptive and predictive technique for lossless compression of hyperspectral data, named the Fast Lossless (FL) algorithm, was recently developed. This technique uses an adaptive filtering method and achieves state-of-the-art performance in both compression effectiveness and low complexity. Because of its outstanding performance and suitability for real-time onboard hardware implementation, the FL compressor is being formalized as the emerging CCSDS Standard for Lossless Multispectral & Hyperspectral image compression. The FL compressor is well-suited for parallel hardware implementation. A GPU hardware implementation was developed for FL targeting the current state-of-the-art GPUs from NVIDIA(Trademark). The GPU implementation on a NVIDIA(Trademark) GeForce(Trademark) GTX 580 achieves a throughput performance of 583.08 Mbits/sec (44.85 MSamples/sec) and an acceleration of at least 6 times a software implementation running on a 3.47 GHz single core Intel(Trademark) Xeon(Trademark) processor. This paper describes the design and implementation of the FL algorithm on the GPU. The massively parallel implementation will provide in the future a fast and practical real-time solution for airborne and space applications.

Graphic Processor Units↗

NASA NTRS1988

A diagonally inverted LU implicit multigrid scheme for the 3-D Navier-Stokes equations and a two equation model of turbulence

An LU implicit multigrid algorithm is developed to calculate 3-D compressible viscous flows. This scheme solves the full 3-D Reynolds-Averaged Navier-Stokes equation with a two-equation kappa-epsilon model of turbulence. The flow equations are integrated by an efficient, diagonally inverted, LU implicit multigrid scheme while the kappa-epsilon equations are solved, uncoupled from the flow equations, by a block LU implicit algorithm. The flow equations are solved within the framework of the multigrid method using a four-grid level W-cycle, while the kappa-epsilon equations are iterated only on the finest grid. This treatment of the Reynolds-Averaged Navier-Stokes equations proves to be an efficient method for calculating 3-D compressible viscous flows.

Yokota, Jeffrey W.↗

NASA NTRS1989

A diagonally inverted LU implicit multigrid scheme for the 3-D Navier-Stokes equations and a two equation model of turbulence

Yokota, Jeffrey W.↗

NASA NTRS1992

A comparison of three SAR interference filters

Three interference filters are discussed and their ability to remove the interference while leaving target signal data is quantified. The filters are adaptive frequency-domain spike filtering; adaptive frequency-domain interference determination and masking; and interference-target correlation masking. Using Jet Propulsion Laboratory Airborne Synthetic Aperture Radar (JPL AIRSAR) data, the algorithms are applied to three data sets. The resultant compressed Stokes matrix data are compared with the normally processed interference-free image in a quantitative sense. The algorithms are evaluated by measuring the polarization signature, SNR, equivalent number of looks, and impulse response of the processed images.

Chapman, B.↗

NASA NTRS1982

Computer program for solving laminar, transitional, or turbulent compressible boundary-layer equations for two-dimensional and axisymmetric flow

A numerical algorithm and computer program are presented for solving the laminar, transitional, or turbulent two dimensional or axisymmetric compressible boundary-layer equations for perfect-gas flows. The governing equations are solved by an iterative three-point implicit finite-difference procedure. The software, program VGBLP, is a modification of the approach presented in NASA TR R-368 and NASA TM X-2458, respectively. The major modifications are: (1) replacement of the fourth-order Runge-Kutta integration technique with a finite-difference procedure for numerically solving the equations required to initiate the parabolic marching procedure; (2) introduction of the Blottner variable-grid scheme; (3) implementation of an iteration scheme allowing the coupled system of equations to be converged to a specified accuracy level; and (4) inclusion of an iteration scheme for variable-entropy calculations. These modifications to the approach presented in NASA TR R-368 and NASA TM X-2458 yield a software package with high computational efficiency and flexibility. Turbulence-closure options include either two-layer eddy-viscosity or mixing-length models. Eddy conductivity is modeled as a function of eddy viscosity through a static turbulent Prandtl number formulation. Several options are provided for specifying the static turbulent Prandtl number. The transitional boundary layer is treated through a streamwise intermittency function which modifies the turbulence-closure model. This model is based on the probability distribution of turbulent spots and ranges from zero to unity for laminar and turbulent flow, respectively. Several test cases are presented as guides for potential users of the software.

Harris, J. E.↗

DOE OSTI2021

True Load Balancing for Matricized Tensor Times Khatri-Rao Product

MTTKRP is the bottleneck operation in algorithms used to compute the CP tensor decomposition. For sparse tensors, utilizing the compressed sparse fibers (CSF) storage format and the CSF-oriented MTTKRP algorithms is important for both memory and computational efficiency on distributed-memory architectures. Existing intelligent tensor partitioning models assume the computational cost of MTTKRP to be proportional to the total number of nonzeros in the tensor. However, this is not the case for the CSF-oriented MTTKRP on distributed-memory architectures. We outline two deficiencies of nonzero-based intelligent partitioning models when CSF-oriented MTTKRP operations are performed locally: failure to encode processors' computational loads and increase in total computation due to fiber fragmentation. We focus on existing fine-grain hypergraph model and propose a novel vertex weighting scheme that enables this model encode correct computational loads of processors. We also propose to augment the fine-grain model by fiber nets for reducing the increase in total computational load via minimizing fiber fragmentation. In this way, the proposed model encodes minimizing the load of the bottleneck processor. In conclusion, parallel experiments with real-world sparse tensors on up to 1024 processors prove the validity of the outlined deficiencies and demonstrate the merit of our proposed improvements in terms of parallel runtimes.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

Compressing unstructured mesh data from simulations using machine learning

The amount of data output from a computer simulation has grown to terabytes and petabytes as increasingly complex simulations are being run on massively parallel systems. As we approach exaflop computing in the next decade, it is expected that the I/O subsystem will not be able to write out these large volumes of data. In this paper, we explore the use of machine learning to compress the data before it is written out. Despite the computational constraints that limit us to using very simple learning algorithms, our results show that machine learning is a viable option for compressing unstructured data. Furthermore, we demonstrate that by simply using a better sampling algorithm to generate the training set, we can obtain more accurate results compared to random sampling, but at no extra cost. Further, by carefully selecting and incorporating points with high prediction error, we can improve reconstruction accuracy without sacrificing the compression rate.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1991

Diagonal implicit multigrid solution of compressible turbulent flows

The Caughey (1988) multigrid diagonal implicit algorithm for Euler equations is extended to solve the two-dimensional thin layer Navier-Stokes equations for turbulent transonic flows. To further accelerate convergence to a steady state, the implicit scheme is used within the multigrid method. Results are presented for transonic flows past airfoils, and the flow-field results are compared with other computational data and experiments demonstrating the accuracy of the method.

Varma, R. R.↗

DOE OSTI2018

Video Compression Routines Final Report CRADA No. TSB-1183-95

The purpose of this CRADA was to establish a framework for LLNL and NOVA Management, Inc. to Cooperatively develop video compression routines to be used to condense maintenance documentation provided on computers issued to Army mechanics to help them diagnose and repair equipment faults. In the past, paper technical manuals were the only means of communicating fault isolation, diagnostics and repair action information to maintenance personnel. The need for this information was at the weapon system itself as well as at the maintenance depot. This project addressed the need for means of efficient storage and retrieval of video (bandwidth issue) by maintenance personnel as they moved through the diagnostic procedures. Several research and development projects have employed interactive stored video as a means of providing maintenance information to the soldier. The problem with this approach was the massive data storage requirement. The overall objective of the project was to develop fast decompression and playback routines for full motion, coIor video. A survey was done of existing standards and potential new routines and techniques for video compression and playback to determine which were suitable for use on the CTS. Playback speeds were preferred to beat 30 frames per second on the target architecture. Compression ratios were expected to store several minutes of synchronized video in 1 MB. Playback routines were Windows 3.1 compatible. Identification of any hardware upgrades associated with playback were made when necessary. A demonstration of existing LLNL algorithms for still frame decompression which represented a current benchmark of data compression performance was completed. NOVA Management and LLNL used some of the compression technologies developed or currently being developed at LLNL to address the requirements of this SBIR. LLNL started by evaluating current compression technologies or combinations thereof to estimate the best compression ratio LLNL could achieve at this stage. LLNL ported some of our software from the SUN workstation environment to the PC or equivalent environment (e.g., MAC) so as to closely match the computer environment suggested by the Army. Finally, LLNL designed and outlined new algorithms to meet the desired video compression of CTS.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1983

A time-split finite-volume algorithm for three-dimensional flow-field simulation

A general finite-volume algorithm is developed for solving three-dimensional, time-dependent, compressible Navier-Stokes equations for high Reynolds number flows over an arbitrary geometry. This algorithm adapts MacCormack's (1982) explicit-implicit scheme to a time-split, three-dimensional finite-volume concept in a general coordinate system. It is shown that the thin-layer approximation in all three spatial directions significantly reduces the evaluation of viscous terms and allows the algorithm to solve more complicated geometries with all boundaries in two or all three directions. The calculated results using this method are found to be in good agreement with the experimental measurements of a blunt-fin induced shock wave and boundary-layer interaction problems. Observations of the existence of peak pressure, primary horseshoe and secondary vortices, and reversed supersonic zones show that computational fluid dynamics can effectively supplement the wind tunnel tests for aerodynamic design as well as for understanding basic fluid dynamics.

Hung, C. M.↗

NASA NTRS1991

Flux-vector splitting algorithm for chain-rule conservation-law form

A flux-vector splitting algorithm with Newton-Raphson iteration was developed for the 'full compressible' Navier-Stokes equations cast in chain-rule conservation-law form. The algorithm is intended for problems with deforming spatial domains and for problems whose governing equations cannot be cast in strong conservation-law form. The usefulness of the algorithm for such problems was demonstrated by applying it to analyze the unsteady, two- and three-dimensional flows inside one combustion chamber of a Wankel engine under nonfiring conditions. Solutions were obtained to examine the algorithm in terms of conservation error, robustness, and ability to handle complex flows on time-dependent grid systems.

Shih, T. I.-P.↗

NASA NTRS1984

Simulation of transonic separated airfoil flow by finite difference viscous-inviscid interaction

A finite difference viscous inviscid interaction program has been developed for simulating the separated transonic flow about lifting airfoils, including the wake. In contrast to most interaction programs, this code combines a finite difference boundary layer algorithm with the inviscid program. The recently developed finite difference boundary layer code efficiently simulates attached and reversed compressible boundary layer and wake flows. New viscous inviscid interaction algorithms were also developed to couple the boundary layer code with the inviscid transonic full potential program. Transonic cases with shock induced and trailing edge separation are computed and compared with experimental and Navier-Stokes results.

Vandalsem, W. R.↗

NASA NTRS1987

Details of the computed flowfield over a circular cylinder at Reynolds number 1200

The application of an upwind-biased implicit approximate factorization Navier-Stokes algorithm to the unsteady impulsive start-up flow over a circular cylinder at Reynolds number 1200 is described. The complete form of the compressible Navier-Stokes equations is used, and the algorithm is second-order accurate in both space and time. The development with time of the shape and size of the separated vortical flow region is computed, as well as the time-variation of several boundary layer parameters and profile shapes. Computations, in general, show excellent agreement with experiment, although the present method predicts a more rapid onset of reversed flow on the cylinder than evidenced in experiment. The changes that the vortical region behind the cylinder undergoes as the symmetric flow transitions to periodic vortex shedding are discussed. The flow becomes periodic with a Strouhal frequency of 0.222, which compares well with the experimental value of approximately 0.21. The effect of grid density on the development of the unsteady flow is also shown.

Rumsey, C. L.↗

NASA NTRS2006

Low-Complexity Adaptive Lossless Compression of Hyperspectral Imagery

A low-complexity, adaptive predictive technique for lossless compression of hyperspectral imagery is described. This technique is designed to be suitable for implementation in hardware such as a field programmable gate array (FPGA); such an implementation could be used for high-speed compression of hyperspectral imagery onboard a spacecraft. The predictive step of the technique makes use of the sign algorithm, which is a relative of the least mean square (LMS) algorithm from the field of low-complexity adaptive filtering. The compressed data stream consists of prediction residuals encoded using a method similar to that of the JPEG-LS lossless image compression standard. Compression results are presented for several datasets including some raw Airborne Visible/ Infrared Imaging Spectrometer (AVIRIS) datasets and raw Atmospheric Infrared Sounder (AIRS) datasets. The compression effectiveness obtained with the technique is competitive with that of the best of previously described techniques with similar complexity.

lossless data compression↗

NASA NTRS1993

Flux-difference split parabolized Navier-Stokes algorithm for non-equilibrium chemically reacting flows

A flux-difference split explicit finite-difference algorithm is presented for solving the parabolized form of the equations governing three-dimensional nonequilibrium chemically reacting flows. The algorithm is based on an explicit noniterative, upwind space-marching scheme developed by Korte, but differs in that the unsteady Riemann problem, rather than the steady Riemann problem, is solved. The algorithm allows either a second or an approximately third-order accurate upwind treatment of the convection terms by employing the unsteady approximate Riemann solver of Roe. The source terms of the species transport equations are treated in either an explicit or implicit manner, and the species diffusion terms are modeled with either a Fickian or a multicomponent model. A validation of the algorithm is performed by comparing computational results with the 2-D Mach 14, 15 degree compression-corner data of Holden. The three-dimensional capability of the algorithm is demonstrated by computing Mach 2.7 flow over a swept wedge scramjet fuel injector, and three-dimensional reacting flow capability is demonstrated by a computing a shock-jet interaction concept for mixing and combustion enhancement.

White, J. A.↗

DOE OSTI2019

Performance optimization, modeling and analysis of sparse matrix-matrix products on multi-core and many-core processors

Sparse matrix-matrix multiplication (SpGEMM) is a computational primitive that is widely used in areas ranging from traditional numerical applications to recent big data analysis and machine learning. Although many SpGEMM algorithms have been proposed, hardware specific optimizations for multi- and many-core processors are lacking and a detailed analysis of their performance under various use cases and matrices is not available. In this work, we firstly identify and mitigate multiple bottlenecks with memory management and thread scheduling on Intel Xeon Phi (Knights Landing or KNL). Specifically targeting many-core processors, we develop a hash-table-based algorithm and optimize a heap-based shared-memory SpGEMM algorithm. We examine their performance together with other publicly available codes. Different from the literature, our evaluation also includes use cases that are representative of real graph algorithms, such as multi-source breadth-first search or triangle counting. Our hash-table and heap-based algorithms are showing significant speedups from libraries in the majority of the cases while different algorithms dominate the other scenarios with different matrix size, sparsity, compression factor and operation type. We wrap up in-depth evaluation results and make a recipe to give the best SpGEMM algorithm for target scenario. We build the performance model for hash-table and heap-based algorithms, which supports the recipe. A critical finding is that hash-table-based SpGEMM gets a significant performance boost if the nonzeros are not required to be sorted within each row of the output matrix. Finally, we integrate our implementations into a large-scale protein clustering code named HipMCL, accelerating its SpGEMM kernel by up to 10X and achieving an overall performance boost for the whole HipMCL application by 2.6X.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2018

High-Performance Sparse Matrix-Matrix Products on Intel KNL and Multicore Architectures

Sparse matrix-matrix multiplication (SpGEMM) is a computational primitive that is vastly used in areas ranging from traditional numerical applications to recent big data analysis and machine learning. While many SpGEMM algorithms have been proposed, hardware specific optimizations for multi- and many-core processors are lacking and a detailed analysis of their performance under various use cases and matrices is not available. We firstly identify and mitigate multiple bottlenecks with memory management and thread scheduling on Intel Xeon Phi (Knights Landing or KNL). Specifically targeting multi- and many-core processors, we develop a hash-table-based algorithm and optimize a heap-based shared-memory SpGEMM algorithm. We investigate their performance together with other publicly available codes. Different from the literature, our evaluation also includes use cases that are representative of real graph algorithms, such as multi-source breadth-first search or triangle counting. Our hash-table and heap-based algorithms are showing significant speedups from libraries in the majority of the cases while different algorithms dominate the other scenarios with different matrix size, sparsity, compression factor and operation type. We wrap up in-depth evaluation results and make a recipe to give the best SpGEMM algorithm for target scenario. In conclusion, a critical finding is that hash-table-based SpGEMM gets a significant performance boost if the nonzeros are not required to be sorted within each row of the output matrix.

97 MATHEMATICS AND COMPUTING↗