Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “grid 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.

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

At least 361 records · Page 20

GPU Implementation of the OVERFLOW CFD Code

The high-performance computing (HPC) landscape is quickly changing to systems where most of the performance comes from specialized chips, specifically graphics processing units (GPUs). Such GPU systems are throughput machines, where efficient use of the GPU often requires code refactoring to expose a few orders of magnitude more fine grain parallelism than was previously used on the CPU. Recent modifications to OVERFLOW, an overset, structured grid, computational fluid dynamics flow solver, written in Fortran will be presented. These modifications include both code modernization efforts and algorithmic changes to enable OVERFLOW to efficiently utilize GPUs. Many of these algorithmic changes would likely also be applicable for other structured grid, stencil-based codes wanting to utilize GPUs. The capabilities that have been ported to run on the GPUs are presented, along with the performance gains of the GPU version relative the CPU version of OVERFLOW.

GPU Programming↗

GPU Implementation of the OVERFLOW CFD Code

The high-performance computing (HPC) landscape is quickly changing to systems where most of the performance comes from specialized chips, specifically graphics processing units (GPUs). Such GPU systems are throughput machines, where efficient use of the GPU often requires code refactoring to expose a few orders of magnitude more fine grain parallelism than was previously used on the CPU. Recent modifications to OVERFLOW, an overset, structured grid, computational fluid dynamics flow solver, written in Fortran will be presented. These modifications include both code modernization efforts and algorithmic changes to enable OVERFLOW to efficiently utilize GPUs. Many of these algorithmic changes would likely also be applicable for other structured grid, stencil-based codes wanting to utilize GPUs. The capabilities that have been ported to run on the GPUs are presented, along with the performance gains of the GPU version relative the CPU version of OVERFLOW.

GPU Programming↗

Two-dimensional CFD modeling of wave rotor flow dynamics

A two-dimensional Navier-Stokes solver developed for detailed study of wave rotor flow dynamics is described. The CFD model is helping characterize important loss mechanisms within the wave rotor. The wave rotor stationary ports and the moving rotor passages are resolved on multiple computational grid blocks. The finite-volume form of the thin-layer Navier-Stokes equations with laminar viscosity are integrated in time using a four-stage Runge-Kutta scheme. The Roe approximate Riemann solution scheme or the computationally less expensive Advection Upstream Splitting Method (AUSM) flux-splitting scheme are used to effect upwind-differencing of the inviscid flux terms, using cell interface primitive variables set by MUSCL-type interpolation. The diffusion terms are central-differenced. The solver is validated using a steady shock/laminar boundary layer interaction problem and an unsteady, inviscid wave rotor passage gradual opening problem. A model inlet port/passage charging problem is simulated and key features of the unsteady wave rotor flow field are identified. Lastly, the medium pressure inlet port and high pressure outlet port portion of the NASA Lewis Research Center experimental divider cycle is simulated and computed results are compared with experimental measurements. The model accurately predicts the wave timing within the rotor passage and the distribution of flow variables in the stationary inlet port region.

Welch, Gerard E.↗

Two-dimensional CFD modeling of wave rotor flow dynamics

A two-dimensional Navier-Stokes solver developed for detailed study of wave rotor flow dynamics is described. The CFD model is helping characterize important loss mechanisms within the wave rotor. The wave rotor stationary ports and the moving rotor passages are resolved on multiple computational grid blocks. The finite-volume form of the thin-layer Navier-Stokes equations with laminar viscosity are integrated in time using a four-stage Runge-Kutta scheme. Roe's approximate Riemann solution scheme or the computationally less expensive advection upstream splitting method (AUSM) flux-splitting scheme is used to effect upwind-differencing of the inviscid flux terms, using cell interface primitive variables set by MUSCL-type interpolation. The diffusion terms are central-differenced. The solver is validated using a steady shock/laminar boundary layer interaction problem and an unsteady, inviscid wave rotor passage gradual opening problem. A model inlet port/passage charging problem is simulated and key features of the unsteady wave rotor flow field are identified. Lastly, the medium pressure inlet port and high pressure outlet port portion of the NASA Lewis Research Center experimental divider cycle is simulated and computed results are compared with experimental measurements. The model accurately predicts the wave timing within the rotor passages and the distribution of flow variables in the stationary inlet port region.

Welch, Gerard E.↗

Euler/Navier-Stokes flow computations on flexible configurations for stability analysis

Longitudinal dynamic stability derivatives required for design of aircraft are computed by using the state-of-the-art numerical methods for wing-body configurations. The flow is modeled using the Euler/Navier-Stokes equations with turbulence models and solved using an efficient finite-difference scheme suitable for patched structured grids. Computations are made at a flow regime that is beyond the limits of the current linear methods mostly used for computing stability derivatives. Flow conditions include shockwaves and viscous dominated vortical flows. Effect of Mach number and angle-of-attack on stability derivatives are demonstrated for a typical wing-body configuration. For the same configuration the effects of wing flexibility on the magnitude and phase angles of stability derivatives are also demonstrated.

Guruswamy, G.↗

Euler/Navier-Stokes Flow Computations on Flexible Configurations for Stability Analysis

Abstract Longitudinal dynamic stability derivatives required for design of aircraft are computed by using the state-of-the-art numerical methods for wing-body configurations. The flow is modeled using the Euler/Navier-Stokes equations with turbulence models and solved using an efficient finite-difference scheme suitable for patched structured grids. Computations are made at a flow regime that is beyond the limits of the current linear methods mostly used for computing stability derivatives. Flow conditions include shock-waves and viscous dominated vortical flows. Effect of Mach number and angle-of-attack on stability derivatives are demonstrated for a typical wing-body configuration. For the same configuration the effects of wing flexibility on the magnitude and phase angles of stability derivatives are also demonstrated.

Guruswamy, Guru P.↗

TranAir: Recent advances and applications

TranAir is a computer code which solves the full-potential equation for transonic flow about very general and complex configurations. Piecewise flat surface panels are used to describe the surface geometry. This paneled definition is then embedded in an unstructured cartesian flow field grid. Finite elements are used in the discretization of the flow field grid in a manner which is fully conservative and second-order accurate. Since geometries may be defined with relative ease, and since the user is not involved in the generation of the flow field grid, computational results may be generated rather quickly for a wide range of geometries. For transonic cases in the cruise angle-of-attack range, TranAir has generated results which are in generally good agreement with both Euler results and wind tunnel data. A typical transonic case runs in 1 to 2 CPU hours on a Cray X-MP. For subcritical cases, the code runs in 15 to 30 CPU minutes, even for geometries in which several thousand surface panels are used in the definition. This ability to rapidly and accurately provide both subsonic and transonic predictions about very complex aircraft configurations gives TranAir the potential of being a very powerful and widely used design tool.

Madson, Michael D.↗

Analysis of a Cylindrical Specimen Heated by an Impinging Hot Hydrogen Jet

A computational conjugate heat transfer methodology was developed, as a first step towards an efficient and accurate multiphysics, thermo-fluid computational methodology to predict environments for hypothetical solid-core, nuclear thermal engine thrust chamber and components. A solid conduction heat transfer procedure was implemented onto a pressure-based, multidimensional, finite-volume, turbulent, chemically reacting, thermally radiating, and unstructured grid computational fluid dynamics formulation. The conjugate heat transfer of a cylindrical material specimen heated by an impinging hot hydrogen jet inside an enclosed test fixture was simulated and analyzed. The solid conduction heat transfer procedure was anchored with a standard solid heat transfer code. Transient analyses were then performed with ,variable thermal conductivities representing three composites of a material utilized as flow element in a legacy engine test. It was found that material thermal conductivity strongly influences the transient heat conduction characteristics. In addition, it was observed that high thermal gradient occur inside the cylindrical specimen during an impulsive or a 10 s ramp start sequence, but not during steady-state operations.

Wang, Ten-See↗

Calculation of unsteady linearized Euler flows in cascades using harmonically deforming grids

A method for calculating unsteady, inviscid, compressible flows in cascades is presented. Using the linearized Euler technique, the flow is decomposed into a steady or mean flow plus a harmonically varying small disturbance flow. The equations that describe the small disturbance flow are linear variable coefficient equations, and are solved using a pseudo-time time marching Lax-Wendroff technique. Unlike previous linearized methods, however, the solution is computed on a harmonically deforming computational grid that conforms to the motion of the vibrating airfoils. The mean flow and perturbation flow solutions are defined in the deforming coordinate system rather than in a coordinate system fixed in space. Hence, no extrapolation terms are required to implement the upwash boundary conditions at the airfoil surfaces, significantly improving the accuracy of the method. For transonic flow calculations, unsteady shock motions are modelled using shock capturing. The unsteady loads due to the shock motion are then seen as pressure impulses. Representative computational results are presented for transonic channel flows and subsonic and transonic cascade flows.

Hall, Kenneth C.↗

Load Balancing Sequences of Unstructured Adaptive Grids

Mesh adaption is a powerful tool for efficient unstructured grid computations but causes load imbalance on multiprocessor systems. To address this problem, we have developed PLUM, an automatic portable framework for performing adaptive large-scale numerical computations in a message-passing environment. This paper makes several important additions to our previous work. First, a new remapping cost model is presented and empirically validated on an SP2. Next, our load balancing strategy is applied to sequences of dynamically adapted unstructured grids. Results indicate that our framework is effective on many processors for both steady and unsteady problems with several levels of adaption. Additionally, we demonstrate that a coarse starting mesh produces high quality load balancing, at a fraction of the cost required for a fine initial mesh. Finally, we show that the data remapping overhead can be significantly reduced by applying our heuristic processor reassignment algorithm.

Biswas, Rupak↗

Bypass flow computations on the LOFA transient in a VHTR

Bypass flow in the prismatic gas-cooled very high temperature reactor (VHTR) is not intentionally designed to occur, but is present in the gaps between graphite blocks. Previous studies of the bypass flow in the core indicated that the cooling provided by flow in the bypass gaps had a significant effect on temperature and flow distributions for normal operating conditions. However, the flow and heat transports in the core are changed significantly after a Loss of Flow Accident (LOFA). This study aims to study the effect and role of the bypass flow after a LOFA in terms of the temperature and flow distributions and for the heat transport out of the core by natural convection of the coolant for a 1/12 symmetric section of the active core which is composed of images and mirror images of two sub-region models. The two sub-region models, 9 x 1/12 and 15 x 1/12 symmetric sectors of the active core, are employed as the CFD flow models using computational grid systems of 70.2 million and 117 million nodes, respectively. It is concluded that the effect of bypass flow is significant for the initial conditions and the beginning of LOFA, but the bypass flow has little effect after a long period of time in the transient computation of natural circulation.

99 GENERAL AND MISCELLANEOUS↗

Integration Of PanDA Workload Management System With Supercomputers for ATLAS and Data Intensive Science

The Large Hadron Collider (LHC), operating at the international CERN Laboratory in Geneva, Switzerland, is leading Big Data driven scientific explorations. Experiments at the LHC explore the fundamental nature of matter and the basic forces that shape our universe, and were recently credited for the discovery of a Higgs boson. ATLAS, one of the largest collaborations ever assembled in the sciences, is at the forefront of research at the LHC. To address an unprecedented multi-petabyte data processing challenge, the ATLAS experiment is relying on a heterogeneous distributed computational infrastructure. The ATLAS experiment uses PanDA (Production and Data Analysis) Workload Management System for managing the workflow for all data processing on over 150 data centers. Through PanDA, ATLAS physicists see a single computing facility that enables rapid scientific breakthroughs for the experiment, even though the data centers are physically scattered all over the world. While PanDA currently uses more than 250,000 cores with a peak performance of 0.3 petaFLOPS, LHC data taking runs require more resources than Grid computing can possibly provide. To alleviate these challenges, LHC experiments are engaged in an ambitious program to expand the current computing model to include additional resources such as the opportunistic use of supercomputers. We will describe a project aimed at integration of PanDA WMS with supercomputers in United States, Europe and Russia (in particular with Titan supercomputer at Oak Ridge Leadership Computing Facility (OLCF), MIRA supercomputer at Argonne Leadership Computing Facilities (ALCF), Supercomputer at the National Research Center Kurchatov Institute , IT4 in Ostrava and others). Current approach utilizes modified PanDA pilot framework for job submission to the supercomputers batch queues and local data management, with light-weight MPI wrappers to run single threaded workloads in parallel on LCFs multi-core worker nodes. This implementation was tested with a variety of Monte-Carlo workloads on several supercomputing platforms for ALICE and ATLAS experiments and it is in full production for the ATLAS experiment since September 2015. We will present our current accomplishments with running PanDA WMS at supercomputers and demonstrate our ability to use PanDA as a portal independent of the computing facilities infrastructure for High Energy and Nuclear Physics as well as other data-intensive science applications, such as bioinformatics and astro-particle physics.

Data-intensive science↗

Local time stepping for the shallow water equations in MPAS

In this work we assess the performance of a set of local time-stepping (LTS) schemes for the shallow water equations implemented in the Model for Prediction Across Scales (MPAS). The goal of LTS is to speed up the simulation by allowing different time-steps on different regions of the computational grid. The LTS schemes considered here were originally introduced by Hoang et al. (2019) [26], who laid out the mathematical foundation of the methods. Here, the authors take on the task of presenting a fast, efficient and scalable parallel implementation of these LTS methods on high performance computing machines, with the aim to provide a recipe for other climate modeling groups that may be interested in employing LTS algorithms in their codes. As a matter of fact, even if MPAS is our framework of choice, our approach is general enough and could be of interest to other groups beyond the MPAS community. Due to their nature, LTS methods possess an inherent load imbalance that needs to be carefully addressed in order to obtain efficient scalability. Even more important is the far from trivial task of computing the right-hand side terms only on specific LTS regions during the time-stepping procedure. An inefficient handling of this task causes a drastic decay of the CPU time performance, making the LTS algorithms practically of no use. The emphasis of the present work is therefore on the computational and parallel aspects of the LTS methods, whose proper treatment is crucial to make the methods run faster against existing strategies, such as for instance high-order explicit global time-stepping schemes. This is in fact the ultimate goal of using an LTS procedure and it is the one to which we direct all our optimization efforts.

97 MATHEMATICS AND COMPUTING↗

PLUM: Parallel Load Balancing for Adaptive Unstructured Meshes

Mesh adaption is a powerful tool for efficient unstructured-grid computations but causes load imbalance among processors on a parallel machine. We present a novel method called PLUM to dynamically balance the processor workloads with a global view. This paper presents the implementation and integration of all major components within our dynamic load balancing strategy for adaptive grid calculations. Mesh adaption, repartitioning, processor assignment, and remapping are critical components of the framework that must be accomplished rapidly and efficiently so as not to cause a significant overhead to the numerical simulation. A data redistribution model is also presented that predicts the remapping cost on the SP2. This model is required to determine whether the gain from a balanced workload distribution offsets the cost of data movement. Results presented in this paper demonstrate that PLUM is an effective dynamic load balancing strategy which remains viable on a large number of processors.

Oliker, Leonid↗

Strategies for the GPU Implementation of the OVERFLOW CFD Code

Wondering how to port a large, computational fluid dynamics (CFD) solver, written in Fortran, to run effectively on GPUs? Join this talk to learn about the strategies NASA’s OVERFLOW CFD code has used to effectively utilize GPUs to greatly improve the time to solution compared to CPUs. OVERFLOW is an overset, structured grid, computational fluid dynamics (CFD) flow solver developed by NASA and widely used by government, US industry, and academia. It is known for its effective use of CPU hardware, but this talk will discuss recent efforts to modify the code to run efficiently on GPUs. We will describe our use of OpenACC, CUDA Fortran, and CUDA C++, discussing why and how we use each to map our problem onto NVIDIA GPUs. We will also describe structural changes we made in the code to expose enough parallelism to effectively use the GPU hardware. Finally, we will present the performance benefits from running OVERFLOW on GPUs compared to the well optimized CPU version of the code.

GPU Programming↗

Web Proxy Auto Discovery for the WLCG

All four of the LHC experiments depend on web proxies (that is, squids) at each grid site to support software distribution by the CernVM FileSystem (CVMFS). CMS and ATLAS also use web proxies for conditions data distributed through the Frontier Distributed Database caching system. ATLAS & CMS each have their own methods for their grid jobs to find out which web proxies to use for Frontier at each site, and CVMFS has a third method. Those diverse methods limit usability and flexibility, particularly for opportunistic use cases, where an experiment’s jobs are run at sites that do not primarily support that experiment. This paper describes a new Worldwide LHC Computing Grid (WLCG) system for discovering the addresses of web proxies. The system is based on an internet standard called Web Proxy Auto Discovery (WPAD). WPAD is in turn based on another standard called Proxy Auto Configuration (PAC). Both the Frontier and CVMFS clients support this standard. The input into the WLCG system comes from squids registered in the ATLAS Grid Information System (AGIS) and CMS SITECONF files, cross-checked with squids registered by sites in the Grid Configuration Database (GOCDB) and the OSG Information Management (OIM) system, and combined with some exceptions manually configured by people from ATLAS and CMS who operate WLCG Squid monitoring. WPAD servers at CERN respond to http requests from grid nodes all over the world with a PAC file that lists available web proxies, based on IP addresses matched from a database that contains the IP address ranges registered to organizations. Large grid sites are encouraged to supply their own WPAD web servers for more flexibility, to avoid being affected by short term long distance network outages, and to offload the WLCG WPAD servers at CERN. The CERN WPAD servers additionally support requests from jobs running at non-grid sites (particularly for LHC@Home) which it directs to the nearest publicly accessible web proxy servers. Furthermore, the responses to those requests are geographically ordered based on a separate database that maps IP addresses to longitude and latitude.

97 MATHEMATICS AND COMPUTING↗

The Random Ray Method for neutral particle transport

A new approach to solving partial differential equations (PDEs) based on the method of characteristics (MOC) is presented. The Random Ray Method (TRRM) uses a stochastic rather than deterministic discretization of characteristic tracks to integrate the phase space of a problem. TRRM is potentially applicable in a number of transport simulation fields where long characteristic methods are used, such as neutron transport and gamma ray transport in reactor physics as well as radiative transfer in astrophysics. In this study, TRRM is developed and then tested on a series of exemplar reactor physics benchmark problems. The results show extreme improvements in memory efficiency compared to deterministic MOC methods, while also reducing algorithmic complexity, allowing for a sparser computational grid to be used while maintaining accuracy.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

INTEGRATION OF PANDA WORKLOAD MANAGEMENT SYSTEM WITH SUPERCOMPUTERS

Abstract The Large Hadron Collider (LHC), operating at the international CERN Laboratory in Geneva, Switzerland, is leading Big Data driven scientific explorations. Experiments at the LHC explore the funda- mental nature of matter and the basic forces that shape our universe, and were recently credited for the dis- covery of a Higgs boson. ATLAS, one of the largest collaborations ever assembled in the sciences, is at the forefront of research at the LHC. To address an unprecedented multi-petabyte data processing challenge, the ATLAS experiment is relying on a heterogeneous distributed computational infrastructure. The ATLAS experiment uses PanDA (Production and Data Analysis) Workload Management System for managing the workflow for all data processing on over 140 data centers. Through PanDA, ATLAS physicists see a single computing facility that enables rapid scientific breakthroughs for the experiment, even though the data cen- ters are physically scattered all over the world. While PanDA currently uses more than 250000 cores with a peak performance of 0.3+ petaFLOPS, next LHC data taking runs will require more resources than Grid computing can possibly provide. To alleviate these challenges, LHC experiments are engaged in an ambitious program to expand the current computing model to include additional resources such as the opportunistic use of supercomputers. We will describe a project aimed at integration of PanDA WMS with supercomputers in United States, Europe and Russia (in particular with Titan supercomputer at Oak Ridge Leadership Com- puting Facility (OLCF), Supercomputer at the National Research Center Kurchatov Institute , IT4 in Ostrava, and others). The current approach utilizes a modified PanDA pilot framework for job submission to the supercomputers batch queues and local data management, with light-weight MPI wrappers to run single- threaded workloads in parallel on Titan s multi-core worker nodes. This implementation was tested with a variety of Monte-Carlo workloads on several supercomputing platforms. We will present our current accom- plishments in running PanDA WMS at supercomputers and demonstrate our ability to use PanDA as a portal independent of the computing facility s infrastructure for High Energy and Nuclear Physics, as well as other data-intensive science applications, such as bioinformatics and astro-particle physics.

De, K↗