Search NASA⌕ Search

SEARCH · Search NASA

Results for “Vectorized algorithm”

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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
NASA NTRS1995

Robust integration schemes for generalized viscoplasticity with internal-state variables. Part 2: Algorithmic developments and implementation

This two-part report is concerned with the development of a general framework for the implicit time-stepping integrators for the flow and evolution equations in generalized viscoplastic models. The primary goal is to present a complete theoretical formulation, and to address in detail the algorithmic and numerical analysis aspects involved in its finite element implementation, as well as to critically assess the numerical performance of the developed schemes in a comprehensive set of test cases. On the theoretical side, the general framework is developed on the basis of the unconditionally-stable, backward-Euler difference scheme as a starting point. Its mathematical structure is of sufficient generality to allow a unified treatment of different classes of viscoplastic models with internal variables. In particular, two specific models of this type, which are representative of the present start-of-art in metal viscoplasticity, are considered in applications reported here; i.e., fully associative (GVIPS) and non-associative (NAV) models. The matrix forms developed for both these models are directly applicable for both initially isotropic and anisotropic materials, in general (three-dimensional) situations as well as subspace applications (i.e., plane stress/strain, axisymmetric, generalized plane stress in shells). On the computational side, issues related to efficiency and robustness are emphasized in developing the (local) interative algorithm. In particular, closed-form expressions for residual vectors and (consistent) material tangent stiffness arrays are given explicitly for both GVIPS and NAV models, with their maximum sizes 'optimized' to depend only on the number of independent stress components (but independent of the number of viscoplastic internal state parameters). Significant robustness of the local iterative solution is provided by complementing the basic Newton-Raphson scheme with a line-search strategy for convergence. In the present second part of the report, we focus on the specific details of the numerical schemes, and associated computer algorithms, for the finite-element implementation of GVIPS and NAV models.

Li, Wei↗
NASA NTRS2012

Assessment of Polarization Effect on Efficiency of Levenberg-Marquardt Algorithm in Case of Thin Atmosphere Over Black Surface

The Levenberg-Marquardt algorithm [1, 2] provides a numerical iterative solution to the problem of minimization of a function over a space of its parameters. In our work, the Levenberg-Marquardt algorithm retrieves optical parameters of a thin (single scattering) plane parallel atmosphere irradiated by collimated infinitely wide monochromatic beam of light. Black ground surface is assumed. Computational accuracy, sensitivity to the initial guess and the presence of noise in the signal, and other properties of the algorithm are investigated in scalar (using intensity only) and vector (including polarization) modes. We consider an atmosphere that contains a mixture of coarse and fine fractions. Following [3], the fractions are simulated using Henyey-Greenstein model. Though not realistic, this assumption is very convenient for tests [4, p.354]. In our case it yields analytical evaluation of Jacobian matrix. Assuming the MISR geometry of observation [5] as an example, the average scattering cosines and the ratio of coarse and fine fractions, the atmosphere optical depth, and the single scattering albedo, are the five parameters to be determined numerically. In our implementation of the algorithm, the system of five linear equations is solved using the fast Cramer s rule [6]. A simple subroutine developed by the authors, makes the algorithm independent from external libraries. All Fortran 90/95 codes discussed in the presentation will be available immediately after the meeting from sergey.v.korkin@nasa.gov by request.

Korkin, S.↗
NASA NTRS2019

A Fast Vector Radiative Transfer Model for the Atmosphere-Ocean Coupled System

To infer atmospheric and oceanic constituent properties from polarimetric observations, an efficient and accurate retrieval algorithm is desirable. In-line radiative transfer calculations are indispensable if a large state vector, including both atmospheric profiles and surface properties, is used to improve retrieval accuracy. However, in-line radiative transfer calculations are usually not computationally efficient for remote sensing applications. Therefore, there is a pressing need to develop an accurate and fast vector radiative transfer model (RTM) to fully utilize satellite polarimetric observations. This paper reports on a fast vector RTM, referred to as TAMU-VRTM, in support of polarimetric remote sensing, which is capable of simulating the Stokes vector values observed at the top of the atmosphere and at the surface by fully considering absorption, scattering, and emission in the atmosphere and ocean. Gaseous absorption is parameterized with respect to gas concentration, temperature, and pressure, by using a regression method applicable to an inhomogeneous atmospheric path. An efficient two-component approach combining the small angle approximation and the adding-doubling method is utilized to solve the vector radiative transfer equation (RTE). The thermal emission component of the RTE solution is obtained by an efficient doubling process. The air-sea interface is treated as a wind-ruffled rough surface in the model to mimic a realistic ocean surface. Several oceanic optical property models are introduced to model ocean inherent optical properties. To demonstrate the applicability of the TAMUVRTM, simulations are compared with satellite observations, and results from other vector radiative transfer methods including benchmarks.

radiative transfer in coupled atmosphere-ocean sys↗
NASA NTRS1993

MeV Gamma Ray Detection Algorithms for Stacked Silicon Detectors

By making use of the signature of a gamma ray event as it appears in N = 5 to 20 lithium-drifted silicon detectors and applying smart selection algorithms, gamma rays in the energy range of 1 to 8 MeV can be detected with good efficiency and selectivity. Examples of the types of algorithms used for different energy regions include the simple sum mode, the sum-coincidence mode used in segmented detectors, unique variations on sum-coincidence for an N-dimensional vector event, and a new and extremely useful mode for double escape peak spectroscopy at pair-production energies. The latter algorithm yields a spectrum similar to that of the pair spectrometer, but without the need of the dual external segments for double escape coincidence, and without the large loss in efficiency of double escape events. Background events due to Compton scattering are largely suppressed. Monte Carlo calculations were used to model the gamma ray interactions in the silicon, in order to enable testing of a wide array of different algorithms on the event N-vectors for a large-N stack.

McMurray, Robert E. Jr.↗
NASA NTRS2018

Applications of the Dynamic N-Dimensional K-Vector

The n-dimensional k-vector (NDKV) is an appealing alternative to binary tress for resolving complex queries in large relational databases. The method has excelled in several applications involving static databases. The present paper extends the theory supporting the NDKV to handle dynamic databases, where the data is updated frequently. This includes deleting records, adding new entries, or editing existing elements. The merit of this new version of the NDKV, the dynamic n-dimensional k-vector (DNDKV), is that it is no longer necessary to recompute the entire k-vector (the main structure that indexes the data) every time a record changes. The algorithm updates the four constituents of the standard NDKV on the fly: the database, sorted database, index, and k-vector tables. As a result, the DNDKV becomes comparable in terms of capabilities and flexibility to stateof-the-art storage engines relying on structured query languages (SQL). The performance of the DNDKV is assessed by running typical read/write operations on a database that contains millions of pre-computed missions to celestial bodies. This database requires frequent updates whenever an orbit solution is refined or new bodies are discovered. The DNDKV is faster than rebuilding the k-vector tables completely, provided that the number of elements being added or removed is not excessively large. Direct runtime comparisons with MySQL suggest that the DNDKV is several times faster for reading but might be slower for writing and updating the database. One limit of the technique is the elements being added must be within the range of the current k-vector tables. If this is not the case, the technique cannot be used and the k-vector tables must be rebuilt from scratch.

Mortari, Daniele↗
NASA NTRS2018

Optimal Control Prediction Method for Control Allocation

This paper proposes a novel prediction method for online optimal control allocation that extends the volume of moments achievable with the Moore-Penrose generalized inverse to the entire Attainable Moment Set. This method formulates the control allocation problem using selected basis vectors and associated gains which reduces the optimization problem dimensions and provides physical insight into the resulting optimal solutions. The proposed algorithm finds the entire family of unique optimal control solutions along the desired moment vector from the origin to the boundary of the Attainable Moment Set. Numerical results for the Moore-Penrose prediction method show that the unique minimal controls obtained yield the desired moment with near machine precision accuracy while maintaining control effectors within specified position limits. This method has been fully validated against the unique solution obtained on the boundary of the Attainable Moment Set using the Durham Direct Allocation method. Minimal control solutions obtained for moments in the interior of the Attainable Moment Set, similarly yield the desired moment to near machine precision while providing control solutions that are smaller (i.e. 2-norm) than solutions found with traditional control allocation algorithms (e.g. interior point methods) applied to the minimal control problem. Numerical simulations using a Matlab® autocoded executable (MEX) for the representative real world problem of 3-moments with 20 individual control effectors and prescribed control position limits show a mean computation speed of approximately 125 Hz which is sufficient to enable real-time flight allocation.

Acheson, Michael J.↗
NASA NTRS2002

Ground Operations of the ISS GNC Babb-Mueller Atmospheric Density Model

The ISS GNC system was updated recently with a new software release that provides onboard state determination capability. Prior to this release, only the Russian segment maintained and propagated the onboard state, which was periodically updated through Russian ground tracking. The new software gives the US segment the capability for maintaining the onboard state, and includes new GPS and state vector propagation capabilities. Part of this software package is an atmospheric density model based on the Babb-Mueller algorithm. Babb-Mueller efficiently mimics a full analytical density model, such as the Jacchia model. While lacchia is very robust and is used in the Mission Control Center, it is too computationally intensive for use onboard. Thus, Babb-Mueller was chosen as an alternative. The onboard model depends on a set of calibration coefficients that produce a curve fit to the lacchia model. The ISS GNC system only maintains one set of coefficients onboard, so a new set must be uplinked by controllers when the atmospheric conditions change. The onboard density model provides a real-time density value, which is used to calculate the drag experienced by the ISS. This drag value is then incorporated into the onboard propagation of the state vector. The propagation of the state vector, and therefore operation of the BabbMueller algorithm, will be most critical when GPS updates and secondary state vector sources fail. When GPS is active, the onboard state vector will be updated every ten seconds, so the propagation error is irrelevant. When GPS is inactive, the state vector must be updated at least every 24 hours, based on current protocol. Therefore, the Babb-Mueller coefficients must be accurate enough to fulfill the state vector accuracy requirements for at least one day. A ground operations concept was needed in order to manage both the on board Babb-Mueller density model and the onboard state quality. The Babb-Mueller coefficients can be determined operationally in two ways. The first method is to calibrate the coefficients in real-time, where a set of custom coefficients is generated for the real-time atmospheric conditions. The second approach is to generate pre-canned sets of coefficients that encompass the expected atmospheric conditions over the lifetime of the vehicle. These predetermined sets are known as occurrences. Even though a particular occurrence will not match the true atmospheric conditions, the error will be constrained by limiting the breadth of each occurrence. Both methods were investigated and the advantages and disadvantages of each were considered. The choice between these implementations was a trade-off between the additional accuracy of the real-time calibration and the simpler development for the approach using occurrences. The operations concept for the frequency of updates was also explored, and depends on the deviation in solar flux that still achieves the necessary accuracy of the coefficients. This was determined based on historical solar flux trends. This analysis resulted in an accurate and reliable implementation of the Babb-Mueller coefficients and how flight controllers use them during realtime operations.

Brogan, Jonathan↗
NASA NTRS1990

Parallel processors and nonlinear structural dynamics algorithms and software

Techniques are discussed for the implementation and improvement of vectorization and concurrency in nonlinear explicit structural finite element codes. In explicit integration methods, the computation of the element internal force vector consumes the bulk of the computer time. The program can be efficiently vectorized by subdividing the elements into blocks and executing all computations in vector mode. The structuring of elements into blocks also provides a convenient way to implement concurrency by creating tasks which can be assigned to available processors for evaluation. The techniques were implemented in a 3-D nonlinear program with one-point quadrature shell elements. Concurrency and vectorization were first implemented in a single time step version of the program. Techniques were developed to minimize processor idle time and to select the optimal vector length. A comparison of run times between the program executed in scalar, serial mode and the fully vectorized code executed concurrently using eight processors shows speed-ups of over 25. Conjugate gradient methods for solving nonlinear algebraic equations are also readily adapted to a parallel environment. A new technique for improving convergence properties of conjugate gradients in nonlinear problems is developed in conjunction with other techniques such as diagonal scaling. A significant reduction in the number of iterations required for convergence is shown for a statically loaded rigid bar suspended by three equally spaced springs.

Belytschko, Ted↗
NASA NTRS2015

A Vehicle Management End-to-End Testing and Analysis Platform for Validation of Mission and Fault Management Algorithms to Reduce Risk for NASAs Space Launch System

The engineering development of the National Aeronautics and Space Administration's (NASA) new Space Launch System (SLS) requires cross discipline teams with extensive knowledge of launch vehicle subsystems, information theory, and autonomous algorithms dealing with all operations from pre-launch through on orbit operations. The nominal and off-nominal characteristics of SLS's elements and subsystems must be understood and matched with the autonomous algorithm monitoring and mitigation capabilities for accurate control and response to abnormal conditions throughout all vehicle mission flight phases, including precipitating safing actions and crew aborts. This presents a large and complex systems engineering challenge, which is being addressed in part by focusing on the specific subsystems involved in the handling of off-nominal mission and fault tolerance with response management. Using traditional model-based system and software engineering design principles from the Unified Modeling Language (UML) and Systems Modeling Language (SysML), the Mission and Fault Management (M&FM) algorithms for the vehicle are crafted and vetted in Integrated Development Teams (IDTs) composed of multiple development disciplines such as Systems Engineering (SE), Flight Software (FSW), Safety and Mission Assurance (S&MA) and the major subsystems and vehicle elements such as Main Propulsion Systems (MPS), boosters, avionics, Guidance, Navigation, and Control (GNC), Thrust Vector Control (TVC), and liquid engines. These model-based algorithms and their development lifecycle from inception through FSW certification are an important focus of SLS's development effort to further ensure reliable detection and response to off-nominal vehicle states during all phases of vehicle operation from pre-launch through end of flight. To test and validate these M&FM algorithms a dedicated test-bed was developed for full Vehicle Management End-to-End Testing (VMET). For addressing fault management (FM) early in the development lifecycle for the SLS program, NASA formed the M&FM team as part of the Integrated Systems Health Management and Automation Branch under the Spacecraft Vehicle Systems Department at the Marshall Space Flight Center (MSFC). To support the development of the FM algorithms, the VMET developed by the M&FM team provides the ability to integrate the algorithms, perform test cases, and integrate vendor-supplied physics-based launch vehicle (LV) subsystem models. Additionally, the team has developed processes for implementing and validating the M&FM algorithms for concept validation and risk reduction. The flexibility of the VMET capabilities enables thorough testing of the M&FM algorithms by providing configurable suites of both nominal and off-nominal test cases to validate the developed algorithms utilizing actual subsystem models such as MPS, GNC, and others. One of the principal functions of VMET is to validate the M&FM algorithms and substantiate them with performance baselines for each of the target vehicle subsystems in an independent platform exterior to the flight software test and validation processes. In any software development process there is inherent risk in the interpretation and implementation of concepts from requirements and test cases into flight software compounded with potential human errors throughout the development and regression testing lifecycle. Risk reduction is addressed by the M&FM group but in particular by the Analysis Team working with other organizations such as S&MA, Structures and Environments, GNC, Orion, Crew Office, Flight Operations, and Ground Operations by assessing performance of the M&FM algorithms in terms of their ability to reduce Loss of Mission (LOM) and Loss of Crew (LOC) probabilities. In addition, through state machine and diagnostic modeling, analysis efforts investigate a broader suite of failure effects and associated detection and responses to be tested in VMET to ensure reliable failure detection, and confirm responses do not create additional risks or cause undesired states through interactive dynamic effects with other algorithms and systems. VMET further contributes to risk reduction by prototyping and exercising the M&FM algorithms early in their implementation and without any inherent hindrances such as meeting FSW processor scheduling constraints due to their target platform - the ARINC 6535-partitioned Operating System, resource limitations, and other factors related to integration with other subsystems not directly involved with M&FM such as telemetry packing and processing. The baseline plan for use of VMET encompasses testing the original M&FM algorithms coded in the same C++ language and state machine architectural concepts as that used by FSW. This enables the development of performance standards and test cases to characterize the M&FM algorithms and sets a benchmark from which to measure their effectiveness and performance in the exterior FSW development and test processes. This paper is outlined in a systematic fashion analogous to a lifecycle process flow for engineering development of algorithms into software and testing. Section I describes the NASA SLS M&FM context, presenting the current infrastructure, leading principles, methods, and participants. Section II defines the testing philosophy of the M&FM algorithms as related to VMET followed by section III, which presents the modeling methods of the algorithms to be tested and validated in VMET. Its details are then further presented in section IV followed by Section V presenting integration, test status, and state analysis. Finally, section VI addresses the summary and forward directions followed by the appendices presenting relevant information on terminology and documentation.

Trevino, Luis↗
NASA NTRS1995

A simple method for verifying the deployment of the TOMS-EP solar arrays

The Total Ozone Mapping Spectrometer-Earth Probe (TOMS-EP) mission relies upon a successful deployment of the spacecraft's solar arrays. Several methods of verification are being employed to ascertain the solar array deployment status, with each requiring differing amounts of data. This paper describes a robust attitude-independent verification method that utilizes telemetry from the coarse Sun sensors (CSS's) and the three-axis magnetometers (TAM's) to determine the solar array deployment status - and it can do so with only a few, not necessarily contiguous, points of data. The method developed assumes that the solar arrays are deployed. Telemetry data from the CSS and TAM are converted to the Sun and magnetic field vectors in spacecraft body coordinates, and the angle between them is calculated. Deployment is indicated if this angle is within a certain error tolerance of the angle between the reference Sun and magnetic field vectors. Although several other methods can indicate a non-deployed state, with this method there is a 70% confidence level in confirming deployment as well as a nearly 100% certainty in confirming a non-deployed state. In addition, the spacecraft attitude (which is not known during the first orbit after launch) is not needed for this algorithm because the angle between the Sun and magnetic field vectors is independent of the spacecraft attitude. This technique can be applied to any spacecraft with a TAM and with CSS's mounted on the solar array(s).

Koppersmith, James R.↗
NASA NTRS1980

Fast, Conservative Algorithm for Solving the Transonic Full-Potential Equation

A fast, fully implicit approximate factorization algorithm designed to solve the conservative, transonic, full-potential equation in either two or three dimensions is described. The algorithm uses an upwind bias of the density coefficient for stability in supersonic regions. This provides an effective upwind difference of the streamwise terms for any orientation of the velocity vector (i.e., rotated differencing), thereby greatly enhancing the reliability of the present algorithm. A numerical transformation is used to establish an arbitrary body-fitted, finite-difference mesh. Computed results for both airfoils and simplified wings demonstrate substantial improvement in convergence speed for the new algorithm relative to standard successive-line over-relaxation algorithms.

Holst, Terry L.↗
NASA NTRS1991

Parallel Methods on Large-Scale Structural Analysis and Physics Applications; Symposium, Hampton, VA, Feb. 5, 6, 1991, Selected Papers

Recent advances in parallel methods and algorithms integrated into large-scale codes are presented. Consideration is given to problem decomposition (substructuring), efficient matrix solution algorithms for shared memory architectures, dynamic and transient analysis algorithms for shared memory architectures, and algorithms for distributed and massively parallel architectures. Particular attention is given to partitioning of unstructured problems for parallel processing, parallel-vector computation for linear-structural analysis and nonlinear unconstraint optimization problems, a parallel-vector equation solver for unsymmetric matrices on supercomputers, parallel nonlinear finite element dynamic response, multigrid algorithms for solving structural mechanics problems on supercomputers, structural analysis on massively parallel computers, explicit finite element methods with contact-impact on SIMD computers, and the impact of mapping and sparsity on parallelized finite element method modules.

Storaasli, Olaf O.↗
NASA NTRS1994

Visualizing Flow Over Parametric Surfaces Using Line Integral Convolution

Line Integral Convolution (LIC) is a powerful technique for imaging and animating vector fields. We extend the LIC paradigm in three ways: (1) The existing technique is limited to vector fields over a regular Cartesian grid. We extend it to vector fields over parametric surfaces, such as those found in curvilinear grids, used in computational fluid dynamics simulations; (2) Periodic motion filters can be used to animate the flow visualization. When the flow lies on a parametric surface, however, the motion appears misleading. We explain why this problem arises and show how to adjust the LIC algorithm to handle it; (3) We introduce a technique to visualize vector magnitudes as well as vector direction. Cabral and Leedom have suggested a method for variable-speed animation, which is based on varying the frequency of the filter function. We develop a different technique based on kernel phase shifts which we have found to show substantially better results. Our implementation of these algorithms utilizes texture-mapping hardware to run in real time, which allows them to be included in interactive applications.

Forssell, Lisa↗
NASA NTRS1993

A simple parallel prefix algorithm for compact finite-difference schemes

A compact scheme is a discretization scheme that is advantageous in obtaining highly accurate solutions. However, the resulting systems from compact schemes are tridiagonal systems that are difficult to solve efficiently on parallel computers. Considering the almost symmetric Toeplitz structure, a parallel algorithm, simple parallel prefix (SPP), is proposed. The SPP algorithm requires less memory than the conventional LU decomposition and is highly efficient on parallel machines. It consists of a prefix communication pattern and AXPY operations. Both the computation and the communication can be truncated without degrading the accuracy when the system is diagonally dominant. A formal accuracy study was conducted to provide a simple truncation formula. Experimental results were measured on a MasPar MP-1 SIMD machine and on a Cray 2 vector machine. Experimental results show that the simple parallel prefix algorithm is a good algorithm for the compact scheme on high-performance computers.

Sun, Xian-He↗
NASA NTRS1990

A collision-selection rule for a particle simulation method suited to vector computers

A theory is developed for a selection rule governing collisions in a particle simulation of rarefied gas-dynamic flows. The selection rule leads to an algorithmic form highly compatible with fine grain parallel decomposition, allowing for efficient utilization of supercomputers having vector or massively parallel single instruction multiple data architectures. A comparison of shock-wave profiles obtained using both the selection rule and Bird's direct simulation Monte Carlo (DSMC) method show excellent agreement. The equation on which the selection rule is based is shown to be directly related to the time-counter procedure in the DSMC method. The results of several example simulations of representative rarefied flows are presented, for which the number of particles used ranged from 10 to the 6th to 10 to the 7th demonstrating the greatly improved computational efficiency of the method.

Baganoff, D.↗
NASA NTRS1995

A Parallel Prefix Algorithm for Almost Toeplitz Tridiagonal Systems

A compact scheme is a discretization scheme that is advantageous in obtaining highly accurate solutions. However, the resulting systems from compact schemes are tridiagonal systems that are difficult to solve efficiently on parallel computers. Considering the almost symmetric Toeplitz structure, a parallel algorithm, simple parallel prefix (SPP), is proposed. The SPP algorithm requires less memory than the conventional LU decomposition and is efficient on parallel machines. It consists of a prefix communication pattern and AXPY operations. Both the computation and the communication can be truncated without degrading the accuracy when the system is diagonally dominant. A formal accuracy study has been conducted to provide a simple truncation formula. Experimental results have been measured on a MasPar MP-1 SIMD machine and on a Cray 2 vector machine. Experimental results show that the simple parallel prefix algorithm is a good algorithm for symmetric, almost symmetric Toeplitz tridiagonal systems and for the compact scheme on high-performance computers.

Sun, Xian-He↗
NASA NTRS1991

Development of iterative techniques for the solution of unsteady compressible viscous flows

Efficient iterative solution methods are being developed for the numerical solution of two- and three-dimensional compressible Navier-Stokes equations. Iterative time marching methods have several advantages over classical multi-step explicit time marching schemes, and non-iterative implicit time marching schemes. Iterative schemes have better stability characteristics than non-iterative explicit and implicit schemes. Thus, the extra work required by iterative schemes can also be designed to perform efficiently on current and future generation scalable, missively parallel machines. An obvious candidate for iteratively solving the system of coupled nonlinear algebraic equations arising in CFD applications is the Newton method. Newton's method was implemented in existing finite difference and finite volume methods. Depending on the complexity of the problem, the number of Newton iterations needed per step to solve the discretized system of equations can, however, vary dramatically from a few to several hundred. Another popular approach based on the classical conjugate gradient method, known as the GMRES (Generalized Minimum Residual) algorithm is investigated. The GMRES algorithm was used in the past by a number of researchers for solving steady viscous and inviscid flow problems with considerable success. Here, the suitability of this algorithm is investigated for solving the system of nonlinear equations that arise in unsteady Navier-Stokes solvers at each time step. Unlike the Newton method which attempts to drive the error in the solution at each and every node down to zero, the GMRES algorithm only seeks to minimize the L2 norm of the error. In the GMRES algorithm the changes in the flow properties from one time step to the next are assumed to be the sum of a set of orthogonal vectors. By choosing the number of vectors to a reasonably small value N (between 5 and 20) the work required for advancing the solution from one time step to the next may be kept to (N+1) times that of a noniterative scheme. Many of the operations required by the GMRES algorithm such as matrix-vector multiplies, matrix additions and subtractions can all be vectorized and parallelized efficiently.

Sankar, Lakshmi N.↗