SEARCH · Engineering Papers

Results for “high performance and distributed computing”

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 685 records · Page 38

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Methods and Experiences for Developing Abstractions for Data-intensive, Scientific Applications

Developing software for scientific applications that require the integration of diverse types of computing, instruments, and data present challenges that are distinct from commercial software. These applications require scale, and the need to integrate various programming and computational models with evolving and heterogeneous infrastructure. Pervasive and effective abstractions for distributed infrastructures are thus critical; however, the process of developing abstractions for scientific applications and infrastructures is not well understood. While theory-based approaches for system development are suited for well-defined, closed environments, they have severe limitations for designing abstractions for scientific systems and applications. The design science research (DSR) method provides the basis for designing practical systems that can handle real-world complexities at all levels. In contrast to theory-centric approaches, DSR emphasizes both practical relevance and knowledge creation by building and rigorously evaluating all artifacts. In this work, we show how DSR provides a well-defined framework for developing abstractions and middleware systems for distributed systems. Specifically, we address the critical problem of distributed resource management on heterogeneous infrastructure over a dynamic range of scales, a challenge that currently limits many scientific applications. We use the pilot-abstraction, a widely used resource management abstraction for high-performance, high throughput, big data, and streaming applications, as a case study for evaluating the DSR activities. For this purpose, we analyze the research process and artifacts produced during the design and evaluation of the pilot-abstraction. We find DSR provides a concise framework for iteratively designing and evaluating systems. Finally, we capture our experiences and formulate different lessons learned.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2017

Enabling Diverse Software Stacks on Supercomputers using High Performance Virtual Clusters.

While large-scale simulations have been the hallmark of the High Performance Computing (HPC) community for decades, Large Scale Data Analytics (LSDA) workloads are gaining attention within the scientific community not only as a processing component to large HPC simulations, but also as standalone scientific tools for knowledge discovery. With the path towards Exascale, new HPC runtime systems are also emerging in a way that differs from classical distributed com- puting models. However, system software for such capabilities on the latest extreme-scale DOE supercomputing needs to be enhanced to more appropriately support these types of emerging soft- ware ecosystems. In this paper, we propose the use of Virtual Clusters on advanced supercomputing resources to enable systems to support not only HPC workloads, but also emerging big data stacks. Specifi- cally, we have deployed the KVM hypervisor within Cray's Compute Node Linux on a XC-series supercomputer testbed. We also use libvirt and QEMU to manage and provision VMs directly on compute nodes, leveraging Ethernet-over-Aries network emulation. To our knowledge, this is the first known use of KVM on a true MPP supercomputer. We investigate the overhead our solution using HPC benchmarks, both evaluating single-node performance as well as weak scaling of a 32-node virtual cluster. Overall, we find single node performance of our solution using KVM on a Cray is very efficient with near-native performance. However overhead increases by up to 20% as virtual cluster size increases, due to limitations of the Ethernet-over-Aries bridged network. Furthermore, we deploy Apache Spark with large data analysis workloads in a Virtual Cluster, ef- fectively demonstrating how diverse software ecosystems can be supported by High Performance Virtual Clusters.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Variance-aware weight quantization of multi-level resistive switching devices based on Pt/LaAlO3/SrTiO3 heterostructures

Abstract Resistive switching devices have been regarded as a promising candidate of multi-bit memristors for synaptic applications. The key functionality of the memristors is to realize multiple non-volatile conductance states with high precision. However, the variation of device conductance inevitably causes the state-overlap issue, limiting the number of available states. The insufficient number of states and the resultant inaccurate weight quantization are bottlenecks in developing practical memristors. Herein, we demonstrate a resistive switching device based on Pt/LaAlO 3 /SrTiO 3 (Pt/LAO/STO) heterostructures, which is suitable for multi-level memristive applications. By redistributing the surface oxygen vacancies, we precisely control the tunneling of two-dimensional electron gas (2DEG) through the ultrathin LAO barrier, achieving multiple and tunable conductance states (over 27) in a non-volatile way. To further improve the multi-level switching performance, we propose a variance-aware weight quantization (VAQ) method. Our simulation studies verify that the VAQ effectively reduces the state-overlap issue of the resistive switching device. We also find that the VAQ states can better represent the normal-like data distribution and, thus, significantly improve the computing accuracy of the device. Our results provide valuable insight into developing high-precision multi-bit memristors based on complex oxide heterostructures for neuromorphic applications.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2016

Concurrent Monte Carlo transport and fluence optimization with fluence adjusting scalable transport Monte Carlo

Purpose: The future of radiation therapy will require advanced inverse planning solutions to support single-arc, multiple-arc, and “4π” delivery modes, which present unique challenges in finding an optimal treatment plan over a vast search space, while still preserving dosimetric accuracy. The successful clinical implementation of such methods would benefit from Monte Carlo (MC) based dose calculation methods, which can offer improvements in dosimetric accuracy when compared to deterministic methods. The standard method for MC based treatment planning optimization leverages the accuracy of the MC dose calculation and efficiency of well-developed optimization methods, by precalculating the fluence to dose relationship within a patient with MC methods and subsequently optimizing the fluence weights. However, the sequential nature of this implementation is computationally time consuming and memory intensive. Methods to reduce the overhead of the MC precalculation have been explored in the past, demonstrating promising reductions of computational time overhead, but with limited impact on the memory overhead due to the sequential nature of the dose calculation and fluence optimization. The authors propose an entirely new form of “concurrent” Monte Carlo treat plan optimization: a platform which optimizes the fluence during the dose calculation, reduces wasted computation time being spent on beamlets that weakly contribute to the final dose distribution, and requires only a low memory footprint to function. In this initial investigation, the authors explore the key theoretical and practical considerations of optimizing fluence in such a manner. Methods: The authors present a novel derivation and implementation of a gradient descent algorithm that allows for optimization during MC particle transport, based on highly stochastic information generated through particle transport of very few histories. A gradient rescaling and renormalization algorithm, and the concept of momentum from stochastic gradient descent were used to address obstacles unique to performing gradient descent fluence optimization during MC particle transport. The authors have applied their method to two simple geometrical phantoms, and one clinical patient geometry to examine the capability of this platform to generate conformal plans as well as assess its computational scaling and efficiency, respectively. Results: The authors obtain a reduction of at least 50% in total histories transported in their investigation compared to a theoretical unweighted beamlet calculation and subsequent fluence optimization method, and observe a roughly fixed optimization time overhead consisting of ∼10% of the total computation time in all cases. Finally, the authors demonstrate a negligible increase in memory overhead of ∼7–8 MB to allow for optimization of a clinical patient geometry surrounded by 36 beams using their platform. Conclusions: This study demonstrates a fluence optimization approach, which could significantly improve the development of next generation radiation therapy solutions while incurring minimal additional computational overhead.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2020

Coupled Electro-Thermal Analysis of Permanent Magnet Synchronous Motor for Electric Vehicles

Permanent magnet synchronous motors (PMSM) are extensively used in electric vehicles. However, high internal heat generation and inefficient heat dissipation often limit the operational reliability, and longevity of the PMSM. Therefore, proper quantification of heat generation in electric motor and advanced embedded motor cooling techniques remain topics of immense interest. In order to accurately predict electro-magnetic performance, i.e., efficiency, component-wise heat losses and the corresponding temperature distribution of a jacket cooled machine, this paper presents a two-way iteratively coupled electro-thermal modeling framework. Finite element based software Motor-CAD has been utilized for electro-magnetic performance calculation of BMW i3 PMSM. Finite volume based computational fluid dynamics/heat transfer (CFD/HT) software ANSYS® FLUENT® has been employed to simulate the temperature distribution of the PMSM, using the electro-magnetic losses as heat input. Computed heat losses, stator, winding, rotor, and magnet temperatures are utilized as coupling parameters between the electro-magnetic and thermal models. A conventional one-way coupling algorithm has also been developed and compared to the newly proposed two-way coupling algorithm. Numerical results confirm that at high current density, one-way coupling algorithm significantly over-predicts the motor temperature compared to the two-way algorithm. A comprehensive analysis has been carried out to characterize the influences of current density, speed, and forced convection heat transfer coefficient on the heat losses, overall efficiency, and maximum temperature of the PMSM. Lastly, an efficiency map has been interpreted from the coupled electro-magnetic simulation.

42 ENGINEERING↗

NASA NTRS1986

Optical processing for future computer networks

In the development of future data management systems, such as the NASA Space Station, a major problem represents the design and implementation of a high performance communication network which is self-correcting and repairing, flexible, and evolvable. To obtain the goal of designing such a network, it will be essential to incorporate distributed adaptive network control techniques. The present paper provides an outline of the functional and communication network requirements for the Space Station data management system. Attention is given to the mathematical representation of the operations being carried out to provide the required functionality at each layer of communication protocol on the model. The possible implementation of specific communication functions in optics is also considered.

Husain, A.↗

DOE OSTI2017

Thermal-hydraulics modeling for prototype testing of the W7-X high heat flux scraper element

The long-pulse operation of the Wendelstein 7-X (W7-X) stellarator experiment is scheduled to begin in 2020. This operational phase will be equipped with water-cooled plasma facing components to allow for longer pulse durations. Certain simulated plasma scenarios have been shown to produce heat fluxes that surpass the technological limits on the edges of the divertor target elements during steady-state operation. In order to reduce the heat load on the target elements, the addition of a “scraper element” (SE) is under investigation. The SE is composed of 24 water-cooled carbon fiber reinforced carbon composite monoblock units. Multiple full-scale prototypes have been tested in the GLADIS high heat flux test facility. Previous computational studies revealed discrepancies between the simulations and experimental measurements. In this work, single-phase thermal-hydraulics modeling was performed in ANSYS CFX to identify potential causes for such discrepancies. Possible explanations investigated were the effects of a non-uniform thermal contact resistance and a potential misalignment of the monoblock fibers. And while the difference between the experimental and computational results was not resolved by a non-uniform thermal contact resistance, the computational results provided insight into the potential performance of a W7-X monoblock unit. Circumferential temperature distributions highlighted the expected boiling regions of such a unit. Finally, simulations revealed that modest angles of fiber misalignment in the monoblocks result in asymmetries at the unit edges and provide temperature differences similar to the experimental results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

NASA NTRS1999

Engineering Overview of a Multidisciplinary HSCT Design Framework Using Medium-Fidelity Analysis Codes

An objective of the HPCC Program at NASA Langley has been to promote the use of advanced computing techniques to more rapidly solve the problem of multidisciplinary optimization of a supersonic transport configuration. As a result, a software system has been designed and is being implemented to integrate a set of existing discipline analysis codes, some of them CPU-intensive, into a distributed computational framework for the design of a High Speed Civil Transport (HSCT) configuration. The proposed paper will describe the engineering aspects of integrating these analysis codes and additional interface codes into an automated design system. The objective of the design problem is to optimize the aircraft weight for given mission conditions, range, and payload requirements, subject to aerodynamic, structural, and performance constraints. The design variables include both thicknesses of structural elements and geometric parameters that define the external aircraft shape. An optimization model has been adopted that uses the multidisciplinary analysis results and the derivatives of the solution with respect to the design variables to formulate a linearized model that provides input to the CONMIN optimization code, which outputs new values for the design variables. The analysis process begins by deriving the updated geometries and grids from the baseline geometries and grids using the new values for the design variables. This free-form deformation approach provides internal FEM (finite element method) grids that are consistent with aerodynamic surface grids. The next step involves using the derived FEM and section properties in a weights process to calculate detailed weights and the center of gravity location for specified flight conditions. The weights process computes the as-built weight, weight distribution, and weight sensitivities for given aircraft configurations at various mass cases. Currently, two mass cases are considered: cruise and gross take-off weight (GTOW). Weights information is obtained from correlations of data from three sources: 1) as-built initial structural and non-structural weights from an existing database, 2) theoretical FEM structural weights and sensitivities from Genesis, and 3) empirical as-built weight increments, non-structural weights, and weight sensitivities from FLOPS. For the aeroelastic analysis, a variable-fidelity aerodynamic analysis has been adopted. This approach uses infrequent CPU-intensive non-linear CFD to calculate a non-linear correction relative to a linear aero calculation for the same aerodynamic surface at an angle of attack that results in the same configuration lift. For efficiency, this nonlinear correction is applied after each subsequent linear aero solution during the iterations between the aerodynamic and structural analyses. Convergence is achieved when the vehicle shape being used for the aerodynamic calculations is consistent with the structural deformations caused by the aerodynamic loads. To make the structural analyses more efficient, a linearized structural deformation model has been adopted, in which a single stiffness matrix can be used to solve for the deformations under all the load conditions. Using the converged aerodynamic loads, a final set of structural analyses are performed to determine the stress distributions and the buckling conditions for constraint calculation. Performance constraints are obtained by running FLOPS using drag polars that are computed using results from non-linear corrections to the linear aero code plus several codes to provide drag increments due to skin friction, wave drag, and other miscellaneous drag contributions. The status of the integration effort will be presented in the proposed paper, and results will be provided that illustrate the degree of accuracy in the linearizations that have been employed.

Weston, R. P.↗

DOE OSTI2018

High-Performance Multi-Mode Ptychography Reconstruction on Distributed GPUs

Abstract—Ptychography is an emerging imaging technique that is able to provide wavelength-limited spatial resolution from spec-imen with extended lateral dimensions. As a scanning microscopy method, a typical two-dimensional image requires a number of data frames. As a diffraction-based imaging technique, the real-space image has to be recovered through iterative reconstruction algorithms. Due to these two inherent aspects, a ptychographic reconstruction is generally a computation-intensive and time-consuming process, which limits the throughput of this method. We report an accelerated version of the multi-mode difference map algorithm for ptychography reconstruction using multiple distributed GPUs. This approach leverages available scientific computing packages in Python, including mpi4py and PyCUDA, with the core computation functions implemented in CUDA C. We find that interestingly even with MPI collective communications, the weak scaling in the number of GPU nodes can still remain nearly constant. Most importantly, for realistic diffraction measurements, we observe a speedup ranging from a factor of 10 to 103 depending on the data size, which reduces the reconstruction time remarkably from hours to typically about 1 minute and is thus critical for real-time data processing and visualization.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2017

Multidimensional Vlasov–Poisson Simulations with High-order Monotonicity- and Positivity-preserving Schemes

We develop new numerical schemes for Vlasov–Poisson equations with high-order accuracy. Our methods are based on a spatially monotonicity-preserving (MP) scheme and are modified suitably so that the positivity of the distribution function is also preserved. We adopt an efficient semi-Lagrangian time integration scheme that is more accurate and computationally less expensive than the three-stage TVD Runge–Kutta integration. We apply our spatially fifth- and seventh-order schemes to a suite of simulations of collisionless self-gravitating systems and electrostatic plasma simulations, including linear and nonlinear Landau damping in one dimension and Vlasov–Poisson simulations in a six-dimensional phase space. The high-order schemes achieve a significantly improved accuracy in comparison with the third-order positive-flux-conserved scheme adopted in our previous study. With the semi-Lagrangian time integration, the computational cost of our high-order schemes does not significantly increase, but remains roughly the same as that of the third-order scheme. Vlasov–Poisson simulations on 128{sup 3}×128{sup 3} mesh grids have been successfully performed on a massively parallel computer.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2017

Tailoring the Properties of a Ni-Based Superalloy via Modification of the Forging Process: an ICME Approach to Fatigue Performance

Traditionally, material design and property modifications are usually associated with compositional changes. However, subtle changes in the manufacturing process parameters can also have a dramatic effect on the resulting material properties. In this work, an integrated computational materials engineering (ICME) framework is adopted to tailor the fatigue performance of a Ni-based superalloy, RR1000. An existing fatigue model is used to identify microstructural features that promote enhanced fatigue life, namely a uniform, fine grain size distribution, random orientation, a distinct grain boundary distribution (specifically high twin boundary density and limited low-angle grain boundaries). A deformation mechanism map and process models for grain boundary engineering of RR1000 are used to identify the optimal thermo-mechanical processing parameters to realize these desirable microstructural features. For validation, small-scale forgings of RR1000 were produced and heat-treated to attain fine grain and coarse grain microstructures that represent the conventionally processed and grain boundary engineered (GBE) conditions, respectively. For each of the four microstructural variants of RR1000, the twin density and grain size were characterized and were in agreement with the desired microstructural attributes. In order to validate the deformation mechanisms and fatigue behavior of the material, high-resolution digital image correlation was performed to generate strain maps relative to the microstructural features. The high density of twin boundaries was confirmed to inhibit the length of slip bands, which is directly attributed to extended fatigue life. Thus, this study demonstrated the successful role of models, both process and performance, in the design and manufacture of Ni-based superalloy disk forgings.

36 MATERIALS SCIENCE↗

DOE OSTI2019

Multigrid treatment of implicit continuum diffusion

Implicit treatment of diffusive terms of various differential orders common in continuum mechanics modeling, such as computational fluid dynamics, is investigated with spectral and multigrid algorithms in non-periodic 2D domains. In doubly periodic time dependent problems these terms are handled efficiently by spectral methods, but in non-periodic systems solved with distributed memory parallel computing and 2D domain decomposition, this efficiency is lost for a large number of processors. Here, we built and present here a multigrid algorithm for these types of problems that outperforms a spectral solution employing the highly optimized FFTW library. This solver is suitable for high performance computing and may be able to efficiently treat implicit diffusion of arbitrary order by introducing auxiliary equations of lower order. We test these solvers for fourth and sixth order diffusion with harmonic test functions as well as turbulent 2D magnetohydrodynamic simulations. It is also shown that an anisotropic operator without mixed-derivative terms improves model accuracy and speed, and we examine the impact that the various diffusion operators have on the energy, the enstrophy, and the qualitative aspect of a simulation.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

NASA NTRS1990

Local-Area-Network Simulator

Local Area Network Extensible Simulator (LANES) computer program provides method for simulating performance of high-speed local-area-network (LAN) technology. Developed as design and analysis software tool for networking computers on board proposed Space Station. Load, network, link, and physical layers of layered network architecture all modeled. Mathematically models according to different lower-layer protocols: Fiber Distributed Data Interface (FDDI) and Star*Bus. Written in FORTRAN 77.

Gibson, Jim↗

NASA NTRS1990

Advanced sensors and instrumentation

NASA is currently investigating the readiness of Advanced Sensors and Instrumentation to meet the requirements of new initiatives in space. The following technical objectives and technologies are briefly discussed: smart and nonintrusive sensors; onboard signal and data processing; high capacity and rate adaptive data acquisition systems; onboard computing; high capacity and rate onboard storage; efficient onboard data distribution; high capacity telemetry; ground and flight test support instrumentation; power distribution; and workstations, video/lighting. The requirements for high fidelity data (accuracy, frequency, quantity, spatial resolution) in hostile environments will continue to push the technology developers and users to extend the performance of their products and to develop new generations.

Calloway, Raymond S.↗

NASA NTRS2002

A Facility and Architecture for Autonomy Research

Autonomy is a key enabling factor in the advancement of the remote robotic exploration. There is currently a large gap between autonomy software at the research level and software that is ready for insertion into near-term space missions. The Mission Simulation Facility (MST) will bridge this gap by providing a simulation framework and suite of simulation tools to support research in autonomy for remote exploration. This system will allow developers of autonomy software to test their models in a high-fidelity simulation and evaluate their system's performance against a set of integrated, standardized simulations. The Mission Simulation ToolKit (MST) uses a distributed architecture with a communication layer that is built on top of the standardized High Level Architecture (HLA). This architecture enables the use of existing high fidelity models, allows mixing simulation components from various computing platforms and enforces the use of a standardized high-level interface among components. The components needed to achieve a realistic simulation can be grouped into four categories: environment generation (terrain, environmental features), robotic platform behavior (robot dynamics), instrument models (camera/spectrometer/etc.), and data analysis. The MST will provide basic components in these areas but allows users to plug-in easily any refined model by means of a communication protocol. Finally, a description file defines the robot and environment parameters for easy configuration and ensures that all the simulation models share the same information.

Pisanich, Greg↗

DOE OSTI2017

NPTFit: A Code Package for Non-Poissonian Template Fitting

We present NPTFit, an open-source code package, written in Python and Cython, for performing non-Poissonian template fits (NPTFs). The NPTF is a recently developed statistical procedure for characterizing the contribution of unresolved point sources (PSs) to astrophysical data sets. The NPTF was first applied to Fermi gamma-ray data to provide evidence that the excess of ∼GeV gamma-rays observed in the inner regions of the Milky Way likely arises from a population of sub-threshold point sources, and the NPTF has since found additional applications studying sub-threshold extragalactic sources at high Galactic latitudes. The NPTF generalizes traditional astrophysical template fits to allow for the ability to search for populations of unresolved PSs that may follow a given spatial distribution. NPTFit builds upon the framework of the fluctuation analyses developed in X-ray astronomy, thus it likely has applications beyond those demonstrated with gamma-ray data. The NPTFit package utilizes novel computational methods to perform the NPTF efficiently. The code is available at http://github.com/bsafdi/NPTFit and up-to-date and extensive documentation may be found at http://nptfit.readthedocs.io.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

Accelerated Coupled Monte Carlo-Thermal Hydraulic Calculations using a Hybrid GTF-Diffusion-based Prediction Block: First Results

Accurate predictions of spatial power and temperature distributions require the coupling of a neutron transport solver with a thermal-hydraulic (TH) feedback. Nowadays, Monte Carlo (MC) codes are widely coupled to TH solvers, typically via a Picard iteration (PI) method, due to the higher fidelity that such frameworks can produce. To speed up a PI, a prediction step can produce an improved initial guess for a source distribution and feed it to the MC code. Recent work [1, 2] investigated a prediction step that uses generalized transfer functions (GTFs) to predict the macroscopic cross sections’ variations following a perturbation in TH properties, such as coolant density. The previous method also relied on first order perturbation (FOP) theory to predict perturbed power profiles, rather than using an expensive MC iterate. The implemented FOP method relied on generating a fission matrix from which the forward and adjoint eigenmodes were extracted and later used to for power calculations. The generation of the fission matrix can introduce a significant computational overhead, therefore undermining the performance of the proposed hybrid technique when applied to high-dimensional problems, e.g., full core calculations. This work attempts to improve the GTF-FOP prediction step by replacing the FOP solver with a nodal diffusion solver, thus eliminating the need to calculate a fission matrix. The GTF-diffusion step was tested for various moderator density perturbations. In each case, the predicted power distribution showed good agreement with the reference case. The latter is attributed to the generally good prediction of most spatially distributed macroscopic cross sections, except the transport cross section, which will become the focus of future work.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2021

Machine Learning-enabled Scalable Performance Prediction of Scientific Codes

Hardware architectures become increasingly complex as the compute capabilities grow to exascale. Here, we present the Analytical Memory Model with Pipelines (AMMP) of the Performance Prediction Toolkit (PPT). PPT-AMMP takes high-level source code and hardware architecture parameters as input and predicts runtime of that code on the target hardware platform, which is defined in the input parameters. PPT-AMMP transforms the code to an (architecture-independent) intermediate representation, then (i) analyzes the basic block structure of the code, (ii) processes architecture-independent virtual memory access patterns that it uses to build memory reuse distance distribution models for each basic block, and (iii) runs detailed basic-block level simulations to determine hardware pipeline usage. PPT-AMMP uses machine learning and regression techniques to build the prediction models based on small instances of the input code, then integrates into a higher-order discrete-event simulation model of PPT running on Simian PDES engine. We validate PPT-AMMP on four standard computational physics benchmarks and present a use case of hardware parameter sensitivity analysis to identify bottleneck hardware resources on different code inputs. We further extend PPT-AMMP to predict the performance of a scientific application code, namely, the radiation transport mini-app SNAP. To this end, we analyze multi-variate regression models that accurately predict the reuse profiles and the basic block counts. We validate predicted SNAP runtimes against actual measured times.

97 MATHEMATICS AND COMPUTING↗