Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Graphics”

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 1,765 records · Page 98
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

Fully Robotic Hot Cell Crane for Target Hall Operations at Isotope Research Facility - 18329

There are many types of equipment used in high radiation environments, but the super-sized and high precision lifting requirements for an isotope research facility in the USA called for one of the largest fully robotic cranes in the US. The 20 Ton Remote Handling Bridge Crane provided by PaR Systems met many challenging requirements for accuracy, repeatability and unique lifting motions in the radiation-shielded target hall of this facility. This robotic system was designed to address four main issues. The first is that the crane needed to be operated remotely due to high radioactivity during the time when it is needed most. Second is that high precision is needed due to the complex fit of multiple heavy shielding blocks. Third problem is that automated routines and exclusion areas were needed due to the remote operation of the system around high capital cost equipment. Lastly is the survivability of the equipment due to the high radiation environment. The facility robotic crane is an overhead top running multiple girder hot cell bridge crane (hereafter referred to as the system). The system is intended to be used in either manually operated or automated operation under computer control. Under automated control, the system provides highly accurate motion control in three linear axes as well as hook rotation. Using motion control programming, this highly accurate system ensures safe, remote movement of in-cell components. The system was designed to be remotely operated by a technician from the remote handling control room in the facility. This is facilitated by computer control using the System Graphical User Interface with feedback from a facility supplied video system. It can also be operated using a wireless hand held controller. The system will be used to place sensitive components with high precision in locations that will be difficult to observe directly. In order to accomplish this, it is critical that the system be capable of moving its payload with minimal swing, and with high accuracy, repeatability and reliability. The system will be operating in an environment where it will be exposed to both high energy neutrons and gamma radiation. Under beam-off conditions, the target hall will be hands-on accessible to accommodate crane maintenance. The system was installed and tested in early 2017 in advance of the live operations of the facility. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2020

VENTSAR V3.0: A Python GUI for Estimating Contaminant Concentrations on or Near Buildings Due to Building Effects and Plume Rise and For Calculating Inhalation and Plume Shine Doses

VENTSAR: Originated as VENTAX (Smith and Weber 1983) on the IBM Mainframe at the Savannah River Site (SRS) as a Fortran program. Updated to VENTSAR XL V1.0 (Simpkins 1997) as a spreadsheet version using macros created in Microsoft Excel. Later updated to VENTSAR XL V2.0 (Dixon 2018) as a spreadsheet executing a modified version of the original VENTAX Fortran code. Estimates contaminant concentrations on or near a building from a release at a nearby location. Calculates concentrations for a given meteorological exceedance probability or for a given stability and wind speed combination. Can model a single building with or without a penthouse on top or a ground location from either a stack or ground release. Plume rise can be considered. Contaminant releases can be chemical or radioactive with downwind concentrations determined at user-specified distances. Wind passing over and around buildings creates a complicated dispersion pattern. Air-intake vents may be located on building roofs or near the ground downwind of a release source. An estimation of pollutant concentrations on or near a structure is important in determining expected pollutant levels. Meteorological data are selected based on a specific area of the site. Fortran-based VENTAX able to make fast, complex mathematical calculations. Not user-friendly VENTSAR XL V1.0 no longer supported due to obsolete Excel macros. VENTSAR XL V2.0 an interim solution using an Excel spreadsheet to interface with the modified VENTAX Fortran code. Requires user to have Microsoft Excel. Not an intuitive interface for someone unfamiliar with VENTSAR. Does not perform dose calculations. VENTSAR V3.0 goal to combine the strengths of previous versions of VENTSAR into a single, powerful yet user-friendly program with a Graphical User Interface (GUI). Not dependent upon a specific program or plug-ins. Self-contained package to be used on any computer running Microsoft Windows. User-friendly, intuitive GUI created in Python for parameter input. Executes same modified VENTAX Fortran code as VENTSAR XL V2.0. Outputs formatted text file of completed calculations for easy review and dissemination. Performs inhalation and plume shine dose calculations for up to 11 user-selected nuclides from a nuclide dose factor library of almost 500 nuclides. 12 test cases were created for verification of V1.0 and V2.0. Same test cases run in V3.0 to verify correct performance. V3.0 produced similar results to V1.0. Confirmed GUI did not alter calculations in any way. Comparisons of the test case results confirm the V3.0 GUI does not influence the VENTSAR calculations. Simply passes same input parameters to VENTAX Fortran code for execution. Provides end user an easy-to-use, intuitive tool to quickly make building effect and plume rise calculations, as well as, inhalation and plume shine dose calculations. No experience with or working knowledge of Fortran, Excel, command line, or macros required. Self-contained package allows VENTSAR be deployed to any Windows computer without the need for specific programs or plug-ins.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2018

EXSAN: An Interactive Version of the Nuclear Cross Section Data Handbook - 25687

Neutron cross section measurements and data files have advanced significantly since 1989 when Los Alamos published 'A Nuclear Cross Section Data Handbook', a detailed compendium of point-wise cross section plots and pie charts of relative contributions of individual reactions to the total cross section for 129 isotopes. Other compendiums with similar data and analysis tools have also been published. The intent of this work is to develop a modern, open-source application for interactive exploration and analysis of Evaluated Nuclear Data File (ENDF) libraries that also allows users to create their own 'Nuclear Cross Section Data Handbooks'. EXSAN is an easy-to-use graphical user interface application for exploring ENDF photon and neutron cross sections developed in Python. In addition to interactive plotting, EXSAN includes methods for computing rank-order lists of cross section for any energy and calculating composite cross sections for isotopic and elemental compositions and additional batch automation features. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2015

Criticality safety enhancements for SCALE 6.2 and beyond - 14648

SCALE is a widely used suite of tools for nuclear systems modeling and simulation that provides comprehensive, verified and validated, user-friendly capabilities for criticality safety, reactor physics, radiation shielding, and sensitivity and uncertainty analysis. Since 1980, regulators, industry, and research institutions around the world have relied on SCALE for nuclear safety analysis and design. SCALE 6.2 provides several new capabilities and significant improvements in many existing features for criticality safety analysis. Enhancements are realized for nuclear data; multigroup resonance self-shielding; continuous-energy Monte Carlo analysis for sensitivity/uncertainty analysis, radiation shielding, and depletion; and graphical user interfaces. An overview of these capabilities is provided in this paper, and additional details are provided in several companion papers. (authors)

42 ENGINEERING↗
DOE OSTI2024

Development of a Performance Portable Non-Equilibrium Plasma Fluid Solver on Adaptive Grids

This presentation will describe the numerical techniques, programming paradigms, verification, and performance of a non-equilibrium plasma fluid solver that can effectively utilize current and upcoming central processing and graphics processing unit (CPU+GPU) architectures. Our plasma fluid model solves the conservation equations for self-consistent electrostatic Poisson, electron and heavy species transport, and electron temperature on adaptive Cartesian grids. Our solver is written using performance portable adaptive mesh management library, AMReX (Zhang et al., JOSS, 4 (37) 1370, 2019), and can be built and run on widely available vendor specific GPU architectures (NVIDIA/AMD/Intel). We utilize a non-subcycled second order semi-implicit time-stepping method where all adaptive mesh refinement (AMR) levels are advanced with the same time step. The composite multi-level multigrid solver from within AMReX is used for each of the governing equations that are cast into a Helmholtz equation form. We have also developed a python based chemical mechanism parser framework that uses a similar format as CANTERA (Goodwin et al., Zenodo, 2018) yaml files as input. Our custom parser reads the yaml file and provides C++ files with transport and production rate functions that can be executed on both host (CPU) and device (GPU). We present verification of our solver using method of manufactured solutions that indicate formal second order accuracy with central diffusion and fifth order weighted-essentially-non-oscillatory (WENO) advection scheme. We also verify our solver with published literature on low-pressure capacitive and high-pressure streamer discharges. Our initial performance studies indicate 10X speed-up using 20 NVIDIA GPUs versus 200 CPUs for an atmospheric streamer discharge problem solved on a 512 x 1024 x 512 grid.

graphics processing units↗
DOE OSTI2017

Reproducible, Component-based Modeling with TopoFlow, A Spatial Hydrologic Modeling Toolkit

Modern geoscientists have online access to an abundance of different data sets and models, but these resources differ from each other in myriad ways and this heterogeneity works against interoperability as well as reproducibility. The purpose of this paper is to illustrate the main issues and some best practices for addressing the challenge of reproducible science in the context of a relatively simple hydrologic modeling study for a small Arctic watershed near Fairbanks, Alaska. This study requires several different types of input data in addition to several, coupled model components. All data sets, model components and processing scripts (e.g. for preparation of data and figures, and for analysis of model output) are fully documented and made available online at persistent URLs. Similarly, all source code for the models and scripts is open-source, version controlled and made available online via GitHub. Each model component has a Basic Model Interface (BMI) to simplify coupling and its own HTML help page that includes a list of all equations and variables used. The set of all model components (TopoFlow) has also been made available as a Python package for easy installation. Three different graphical user interfaces for setting up TopoFlow runs are described, including one that allows model components to run and be coupled as web services.

58 GEOSCIENCES↗
DOE OSTI2017

Theoretical analysis of non‐ G aussian heterogeneity effects on subsurface flow and transport

Abstract Much of the stochastic groundwater literature is devoted to the analysis of flow and transport in Gaussian or multi‐Gaussian log hydraulic conductivity (or transmissivity) fields, ( x being a position vector), characterized by one or (less frequently) a multiplicity of spatial correlation scales. Yet Y and many other variables and their (spatial or temporal) increments, Δ Y , are known to be generally non‐Gaussian. One common manifestation of non‐Gaussianity is that whereas frequency distributions of Y often exhibit mild peaks and light tails, those of increments are generally symmetric with peaks that grow sharper, and tails that become heavier, as separation scale or lag between pairs of Y values decreases. A statistical model that captures these disparate, scale‐dependent distributions of Y and in a unified and consistent manner has been recently proposed by us. This new “generalized sub‐Gaussian (GSG)” model has the form where is (generally, but not necessarily) a multiscale Gaussian random field and is a nonnegative subordinator independent of G . The purpose of this paper is to explore analytically, in an elementary manner, lead‐order effects that non‐Gaussian heterogeneity described by the GSG model have on the stochastic description of flow and transport. Recognizing that perturbation expansion of hydraulic conductivity diverges when Y is sub‐Gaussian, we render the expansion convergent by truncating Y 's domain of definition. We then demonstrate theoretically and illustrate by way of numerical examples that, as the domain of truncation expands, (a) the variance of truncated Y (denoted by Y t ) approaches that of Y and (b) the pdf (and thereby moments) of Y t increments approach those of Y increments and, as a consequence, the variogram of approaches that of . This in turn guarantees that perturbing to second order in (the standard deviation of Y t ) yields results which approach those we obtain upon perturbing to second order in even as the corresponding series diverges. Our analysis is rendered mathematically tractable by considering mean‐uniform steady state flow in an unbounded, two‐dimensional domain of mildly heterogeneous Y with a single‐scale function G having an isotropic exponential covariance. Results consist of expressions for (a) lead‐order autocovariance and cross‐covariance functions of hydraulic head, velocity, and advective particle displacement and (b) analogues of preasymptotic as well as asymptotic Fickian dispersion coefficients. We compare these theoretically and graphically with corresponding expressions developed in the literature for Gaussian Y . We find the former to differ from the latter by a factor k = ( denoting ensemble expectation) and the GSG covariance of longitudinal velocity to contain an additional nugget term depending on this same factor. In the limit as Y becomes Gaussian, k reduces to one and the nugget term drops out.

Riva, Monica↗
DOE OSTI2017

Situating Green Infrastructure in Context: A Framework for Adaptive Socio‐Hydrology in Cities

Abstract Management of urban hydrologic processes using green infrastructure (GI) has largely focused on storm water management. Thus, design and implementation of GI usually rely on physical site characteristics and local rainfall patterns, and do not typically account for human or social dimensions. This traditional approach leads to highly centralized storm water management in a disconnected urban landscape and can deemphasize additional benefits that GI offers, such as increased property value, greenspace aesthetics, heat island amelioration, carbon sequestration, and habitat for biodiversity. We propose the Framework for Adaptive Socio‐Hydrology (FrASH) in which GI planning and implementation moves from a purely hydrology‐driven perspective to an integrated sociohydrological approach. This allows for an iterative, multifaceted decision‐making process that would enable a network of stakeholders to collaboratively set a dynamic, context‐guided project plan for the installation of GI, rather than a “one‐size‐fits‐all” installation. We explain how different sectors (e.g., governance, nongovernmental organizations, communities, academia, and industry) can create a connected network of organizations that work toward a common goal. Through a graphical Chambered Nautilus model, FrASH is experimentally applied to contrasting GI case studies and shows that this multistakeholder, connected, decentralized network with a coevolving decision‐making project plan results in enhanced multifunctionality, potentially allowing for the management of resilience in urban systems at multiple scales.

Schifman, L. A.↗
DOE OSTI2020

Investigating Porous Media for Relief Printing Using Micro-Architected Materials

Advances in printed electronics are predicated on the integration of sophisticated printing technologies with functional materials. Although scalable manufacturing methods, such as letterpress and flexographic printing, have significant history in graphic arts printing, functional applications require sophisticated control and understanding of nanoscale transfer of fluid inks. In this paper, a versatile platform is introduced to study and engineer printing forms, exploiting a microscale additive manufacturing process to design micro-architected materials with controllable porosity and deformation. Building on this technology, controlled ink transfer for submicron functional films is demonstrated. The design freedom and high-resolution 3D control afforded by this method provide a rich framework for studying mechanics of fluid transfer for advanced manufacturing processes.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Illumination correction of dyed fabric based on extreme learning machine with improved ant lion optimizer

Abstract In order to eliminate the influence of scene illumination on the evaluation of the color difference of dyed fabrics, this paper proposes a dyed fabric illumination correction algorithm based on the extreme learning machine (ELM) with grey wolf optimizer (GWO)‐optimized ant lion optimizer (ALO). Firstly, the Grey Edge framework is used to extract the features of the dyed fabric image as the input vector. Then, to improve the optimization ability of the ALO algorithm, the GWO algorithm is used to provide a set of optimized initial populations to the ALO algorithm, and then the improved ALO algorithm is used to optimize the parameters of the ELM. Finally, the proposed GWO‐ALO‐ELM algorithm is used to correct the illumination of the dyed fabric, and restore the graphics to the effect display under standard illumination through the diagonal reduction model. Compared with the experimental results of GWO‐ELM, ALO‐ELM, backpropagation (BP), ELM, random vector function link (RVFL), and other algorithms, it can be seen that the GWO‐ALO‐ELM algorithm proposed in this paper has good predictive value and quasi‐bias effect, and good stability.

Zhou, Zhiyu↗
DOE OSTI2013

Performance modeling of microsecond scale biological molecular dynamics simulations on heterogeneous architectures

Performance improvements in biomolecular simulations based on molecular dynamics (MD) codes are widely desired. Unfortunately, the factors, which allowed past performance improvements, particularly the microprocessor clock frequencies, are no longer increasing. Hence, novel software and hardware solutions are being explored for accelerating performance of widely used MD codes. In this paper, we describe our efforts on porting, optimizing and tuning of Large-scale Atomic/Molecular Massively Parallel Simulator, a popular MD framework, on heterogeneous architectures: multi-core processors with graphical processing unit (GPU) accelerators. Our implementation is based on accelerating the most computationally expensive non-bonded interaction terms on the GPUs and overlapping the computation on the CPU and GPUs. This functionality is built on top of message passing interface that allows multi-level parallelism to be extracted even at the workstation level with the multi-core CPUs and allows extension of the implementation on GPU-enabled clusters. We hypothesize that the optimal benefit of heterogeneous architectures for applications will come by utilizing all possible resources (for example, CPU-cores and GPU devices on GPU-enabled clusters). Benchmarks for a range of biomolecular system sizes are provided, and an analysis is performed on four generations of NVIDIA's GPU devices. On GPU-enabled Linux clusters, by overlapping and pipelining computation and communication, we observe up to 10-folds application acceleration in multi-core and multi-GPU environments illustrating significant performance improvements. Detailed analysis of the implementation is presented that allows identification of bottlenecks in algorithm, indicating that code optimization and improvements on GPUs could allow microsecond scale simulation throughput on workstations and inexpensive GPU clusters, putting widely desired biologically relevant simulation time-scales within reach of a large user community. In order to systematically optimize simulation throughput and to enable performance prediction, we have developed a parameterized performance model that will allow developers and users to explore the performance potential of future heterogeneous systems for biological simulations.

Agarwal, Pratul K.↗
DOE OSTI2014

A scalable approach to solving dense linear algebra problems on hybrid CPU-GPU systems

Aiming to fully exploit the computing power of all CPUs and all graphics processing units (GPUs) on hybrid CPU-GPU systems to solve dense linear algebra problems, in this paper we design a class of heterogeneous tile algorithms to maximize the degree of parallelism, to minimize the communication volume, and to accommodate the heterogeneity between CPUs and GPUs. The new heterogeneous tile algorithms are executed upon our decentralized dynamic scheduling runtime system, which schedules a task graph dynamically and transfers data between compute nodes automatically. The runtime system uses a new distributed task assignment protocol to solve data dependencies between tasks without any coordination between processing units. By overlapping computation and communication through dynamic scheduling, we are able to attain scalable performance for the double-precision Cholesky factorization and QR factorization. Finally, our approach demonstrates a performance comparable to Intel MKL on shared-memory multicore systems and better performance than both vendor (e.g., Intel MKL) and open source libraries (e.g., StarPU) in the following three environments: heterogeneous clusters with GPUs, conventional clusters without GPUs, and shared-memory systems with multiple GPUs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

Experiences in autotuning matrix multiplication for energy minimization on GPUs

In this study, we report extensive results and analysis of autotuning the computationally intensive graphics processing units kernel for dense matrix–matrix multiplication in double precision. In contrast to traditional autotuning and/or optimization for runtime performance only, we also take the energy efficiency into account. For kernels achieving equal performance, we show significant differences in their energy balance. We also identify the memory throughput as the most influential metric that trades off performance and energy efficiency. Finally, as a result, the performance optimal case ends up not being the most efficient kernel in overall resource use.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Methods for multitasking among real-time embedded compute tasks running on the GPU: Methods for Multitasking Real-time Embedded GPU Computing Tasks

Here, we provide an extensive survey on wide spectrum of scheduling methods for multitasking among graphics processing unit (GPU) computing tasks. We then design several schedulers and explain in detail the selected methods we have developed to implement our scheduling strategies. Next, we compare the performance of schedulers on various workloads running on Fermi and Kepler architectures and arrive at the following major conclusions: (1) Small kernels benefit from running kernels concurrently. (2) The combination of small kernels, high-priority kernels with longer runtimes, and lower-priority kernels with shorter runtimes benefits from a CPU scheduler that dynamically changes kernel order on the Fermi architecture. (3) Because of limitations of existing GPU architectures, currently CPU schedulers outperform their GPU counterparts. We also provide results and observations obtained from implementing and evaluating our schedulers on the NVIDIA Jetson TX1 system-on-chip architecture. We observe that although TX1 has the newer Maxwell architecture, the mechanism used for scheduler timings behaves differently on TX1 compared to Kepler leading to incorrect timings. In this paper, we describe our methods that allow us to report correct timings for CPU schedulers running on TX1. Lastly, we propose new research directions involving the investigation of additional scheduling strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

OpenABLext: An automatic code generation framework for agent-based simulations on CPU-GPU-FPGA heterogeneous platforms

The execution of agent-based simulations (ABSs) on hardware accelerator devices such as graphics processing units (GPUs) has been shown to offer great performance potentials. However, in heterogeneous hardware environments, it can become increasingly difficult to find viable partitions of the simulation and provide implementations for different hardware devices. To automate this process, we present OpenABLext, an extension to OpenABL, a model specification language for ABSs. By providing a device-aware OpenCL backend, OpenABLext enables the co-execution of ABS on heterogeneous hardware platforms consisting of central processing units, GPUs, and field programmable gate arrays (FPGAs).We present a novel online dispatching method that efficiently profiles partitions of the simulation during run-time to optimize the hardware assignment while using the profiling results to advance the simulation itself. In addition, OpenABLext features automated conflict resolution based on user-specified rules, supports graph-based simulation spaces, and utilizes an efficient neighbor search algorithm. We show the improved performance of OpenABLext and demonstrate the potential of FPGAs in the context of ABS. We illustrate how co-execution can be used to further lower execution times. OpenABLext can be seen as an enabler to tap the computing power of heterogeneous hardware platforms for ABS.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Assessing data change in scientific datasets

Summary Scientific datasets are growing rapidly and becoming critical to next‐generation scientific discoveries. The validity of scientific results relies on the quality of data used and data are often subject to change, for example, due to observation additions, quality assessments, or processing software updates. The effects of data change are not well understood and difficult to predict. Datasets are often repeatedly updated and recomputing derived data products quickly becomes time consuming and resource intensive and may in some cases not even be necessary, thus delaying scientific advance. Despite its importance, there is a lack of systematic approaches for best comparing data versions to quantify the changes, and ad‐hoc or manual processes are commonly used. In this article, we propose a novel hierarchical approach for analyzing data changes, including real‐time (online) and offline analyses. We employ a variety of fast‐to‐compute numerical analyses, graphical data change representations, and more resource‐intensive recomputations of a subset of the data product. We illustrate the application of our approach using three scientific diverse use cases, namely, satellite, cosmological, and x‐ray data. The results show that a variety of data change metrics should be employed to enable a comprehensive representation and qualitative evaluation of data changes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

HIPLZ: Enabling performance portability for exascale systems

While heterogeneous computing has emerged as a dominant trend in current and future High-Performance Computing (HPC) systems, it is also widely recognized that this shift has led to increased software complexity due to a proliferation of programming systems for different heterogeneous processors. One such example is the Heterogeneous-Compute Interface for Portability from AMD (HIP ), which is composed of a C Runtime API and C++ Kernel Language. Many HPC applications will likely use HIP on future exascale systems (e.g., Frontier and El Capitan), but HIP currently only targets AMD and NVIDIA processors. This limitation creates challenges for users who would also like to run their applications on exascale systems based on other architectures (e.g., Aurora, which is based on Intel hardware) that are currently not targeted by HIP . In this paper, we introduce the design and implementation of HIPLZ , a compiler and runtime system that uses the Intel Level Zero API to support HIP on Intel GPU architectures. We discuss the design of HIPLZ , derived from HIPCL (an implementation of HIP on top of OpenCL ), and portability issues that occur from using the Level Zero runtime as a backend. We evaluate our implementation by running several performance benchmarks and mini-apps written in HIP on Intel architectures using HIPLZ . Our results show that this approach provides competitive performance relative to Intel's OpenCL implementations on Intel Gen9 and UHD Graphics 770 GPUs, while providing good coverage of features needed by HPC applications. Overall, this approach is a promising demonstration of enabling performance portability for exascale systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

OpenACC acceleration of an unstructured CFD solver based on a reconstructed discontinuous Galerkin method for compressible flows

Here, an OpenACC directive-based graphics processing unit (GPU) parallel scheme is presented for solving the compressible Navier–Stokes equations on 3D hybrid unstructured grids with a third-order reconstructed discontinuous Galerkin method. The developed scheme requires the minimum code intrusion and algorithm alteration for upgrading a legacy solver with the GPU computing capability at very little extra effort in programming, which leads to a unified and portable code development strategy. A face coloring algorithm is adopted to eliminate the memory contention because of the threading of internal and boundary face integrals. A number of flow problems are presented to verify the implementation of the developed scheme. Timing measurements were obtained by running the resulting GPU code on one Nvidia Tesla K20c GPU card (Nvidia Corporation, Santa Clara, CA, USA) and compared with those obtained by running the equivalent Message Passing Interface (MPI) parallel CPU code on a compute node (consisting of two AMD Opteron 6128 eight-core CPUs (Advanced Micro Devices, Inc., Sunnyvale, CA, USA)). Speedup factors of up to 24× and 1.6× for the GPU code were achieved with respect to one and 16 CPU cores, respectively. The numerical results indicate that this OpenACC-based parallel scheme is an effective and extensible approach to port unstructured high-order CFD solvers to GPU computing.

97 MATHEMATICS AND COMPUTING↗