Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Programming model”

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 379 records · Page 21

Experiences with High-Level Programming Directives for Porting Applications to GPUs. In: Facing the Multicore--Challenge II, Lecture Notes in Computer Science.

HPC systems now exploit GPUs within their compute nodes to accelerate program performance. As a result, high-end application development has become extremely complex at the node level. In addition to restructuring the node code to exploit the cores and specialized devices, the programmer may need to choose a programming model such as OpenMP or CPU threads in conjunction with an accelerator programming model to share and manage the different node resources. This comes at a time when programmer productivity and the ability to produce portable code has been recognized as a major concern. In order to offset the high development cost of creating CUDA or OpenCL kernels, directives have been proposed for programming accelerator devices, but their implications are not well known. In this paper, we evaluate the state of the art accelerator directives to program several applications kernels, explore transformations to achieve good performance, and examine the expressivity and performance penalty of using high-level directives versus CUDA. We also compare our results to OpenMP implementations to understand the benefits of running the kernels in the accelerator versus CPU cores.

CUDA Implementation↗

Experiences with High-Level Programming Directives for Porting Applications to GPUs

HPC systems now exploit GPUs within their compute nodes to accelerate program performance. As a result, high-end application development has become extremely complex at the node level. In addition to restructuring the node code to exploit the cores and specialized devices, the programmer may need to choose a programming model such as OpenMP or CPU threads in conjunction with an accelerator programming model to share and manage the difference node resources. This comes at a time when programmer productivity and the ability to produce portable code has been recognized as a major concern. In order to offset the high development cost of creating CUDA or OpenCL kernels, directives have been proposed for programming accelerator devices, but their implications are not well known. In this paper, we evaluate the state of the art accelerator directives to program several applications kernels, explore transformations to achieve good performance, and examine the expressiveness and performance penalty of using high-level directives versus CUDA. We also compare our results to OpenMP implementations to understand the benefits of running the kernels in the accelerator versus CPU cores.

43 PARTICLE ACCELERATORS↗

Programs For Modeling Fault-Tolerant Computing Systems

Pade Approximation with Scaling, (PAWS) and Scaling Taylor Exponential Matrix (STEM) computer programs are software tools for design and validation. Provide flexible, user-friendly, language-based interface for input of Markov mathematical methods describing behaviors of fault-tolerant computer systems. Markov models include both recovery from faults via reconfiguration and behaviors of such systems when faults occur. PAWS and STEM produce exact solutions of probability of system failure and provide conservative estimate of number of significant digits in solution. Written in PASCAL and FORTRAN.

Butler, Ricky W.↗

ECP ST Project 2.3.1.06-STPM08-RAJA (Final Report)

Modern high-performance computing architectures are diverse, with hardware designs that feature multicore CPUs and CPUs plus accelerators, such as GPUs or FPGAs. Achieving good application performance often requires using a programming model and managing application data in ways that are best suited to a particular platform. For large codes that are used daily in production, and are under continual development, architecture-specific ports are untenable. Maintainability requires single-source code that is performance portable across a range of architectures and programming model back-ends. This report describes RAJA, Umpire, and CHAI, three software libraries that provide complementary capabilities to enable application portability for high performance computing (HPC) platforms. In particular, these libraries provide software abstractions that insulate application source code from hardware architecture and programming model-specific implementation details. These development of these libraries was motivated by the needs of multiphysics applications in the Weapons Simulation and Computing Program (WSC) at Lawrence Livermore National Laboratory (LLNL). Funding though the Exascale Computing Project (ECP) Software Technology (ST) project 2.3.1.06 RAJA has fostered outreach and collaboration with the ECP application and software technology development communities. In this report, we describe ECP adoption and integration of these tools to this point. The larger goal of the report is to describe to the ECP community what these projects offer, how they are used, and how to approach adoption and integration of them.

97 MATHEMATICS AND COMPUTING↗

Global Arrays Parallel Programming Toolkit

The two predominant classes of programming models for parallel computing are distributed memory and shared memory. Both shared memory and distributed memory models have advantages and shortcomings. Shared memory model is much easier to use but it ignores data locality/placement. Given the hierarchical nature of the memory subsystems in modern computers this characteristic can have a negative impact on performance and scalability. Careful code restructuring to increase data reuse and replacing fine grain load/stores with block access to shared data can address the problem and yield performance for shared memory that is competitive with message-passing. However, this performance comes at the cost of compromising the ease of use that the shared memory model advertises. Distributed memory models, such as message-passing or one-sided communication, offer performance and scalability but they are difficult to program. The Global Arrays toolkit attempts to offer the best features of both models. It implements a shared-memory programming model in which data locality is managed by the programmer. This management is achieved by calls to functions that transfer data between a global address space (a distributed array) and local storage. In this respect, the GA model has similarities to the distributed shared-memory models that provide an explicit acquire/release protocol. However, the GA model acknowledges that remote data is slower to access than local data and allows data locality to be specified by the programmer and hence managed. GA is related to the global address space languages such as UPC, Titanium, and, to a lesser extent, Co-Array Fortran. In addition, by providing a set of data-parallel operations, GA is also related to data-parallel languages such as HPF, ZPL, and Data Parallel C. However, the Global Array programming model is implemented as a library that works with most languages used for technical computing and does not rely on compiler technology for achieving parallel efficiency. It also supports a combination of task- and data-parallelism and is available as an extension of the message passing (MPI) model. The GA model exposes to the programmer the hierarchical memory of modern high-performance computer systems, and by recognizing the communication overhead for remote data transfer, it promotes data reuse and locality of reference. Virtually all the scalable architectures possess non-uniform memory access characteristics that reflect their multi-level memory hierarchies. These hierarchies typically comprise processor registers, multiple levels of cache, local memory, and remote memory. Over time, both the number of levels and the cost (in processor cycles) of accessing deeper levels has been increasing. It is important for any scalable programming model to address memory hierarchy since it is critical to the efficient execution of scalable applications.

ARMCI↗

FPChecker

CUDA is the programming model used to program NVIDIA GPUs, which are widely used in DOE supercomputers. FPChecker allows programmers to detect and fix hidden exceptions in the floating-point computations that CUDA executes. When a floating-point exception occurs (e.g., division by zero), GPUs cannot catch these errors. FPChecker intercepts each floating-point operations (addition, subtraction, multiplication and division) and reports to users where exceptions occur (file and line of code).

Laguna Peralta, Ignacio↗

Earth Source Heat: A Cascaded Systems Approach to DDU of Geothermal Energy on the Cornell Campus

This report documents the completion of the DOE study DE-EE0008103: Earth Source Heat: A Cascaded Systems Approach to DDU of Geothermal Energy on the Cornell Campus. This study involved a comprehensive evaluation of the potential for Earth Source Heat (ESH), Cornell’s specific application of Deep Direct Use (DDU) geothermal energy, to create a viable renewable source of thermal energy for its Ithaca, NY campus district heating system. The study included stochastic modeling that married each of two potential subsurface resources (two specific geological reservoirs) to documented campus heating operations based on hourly campus heating profiles and proposed integrated equipment controls (variable speed pumps and heat pumps). The outputs of the subsurface modeling were used as inputs for a Cornell-developed surface heat use Excel-based modeling program (the program was named “Modeled ENergy Use”, or “MEnU”). This allowed Cornell to compute realistic annual totals of extractable and useable heat for the campus, including details like heat losses, minimum summer demand, and controllable building temperature settings. The Cornell team then evaluated the costs and benefits of each modeled scenario. The primary evaluation was a standard “single bottom line” economic calculation for the Levelized Cost of Heat (LCOH). This represents the annualized cost (per unit heat) for Cornell. Additional valuations were also computed based on the benefit to the environment and to the regional economy (i.e., economic benefits external to campus). The results of this study demonstrate that if suitable reservoir flow can be attained, Earth Source Heat would be a viable technology to supply Cornell’s district heating system. This viability is based on the following criteria: (1) The modeled system produced a total useable heat output that exceeded the minimum annual campus heat load determined at the onset of the project (i.e., offsetting at least 20% of the annual campus thermal load). The output range is substantial depending on both the subsurface resource and the surface applications; at the high end, our modeled solutions produced up to ~70% of existing campus heat load with a single well pair producing 70 kg/s with integrated high-temperature heat pumps, and (2) Modeling demonstrated that multiple geothermal reservoirs could provide economically viable results when heat pumps were strategically integrated, a design that has been proven in at least one European installation already. In this context, “economically viable” means that the LCOH for the project is less than the regional commercial price of heat that would be generated using natural gas (the most common and cheapest fossil alternative in our area). Based on a single-bottom-line (LCOH) valuation, our results show that economic success is likely for any reservoir deeper than about 2.25 km where a sufficient permeability exists (or can be created with stimulation or similar engineering enhancement) and reasonable production temperatures sustained over time. The LCOH values of $\$ 4.77$ to $\$ 6.46$ per MMBtu are all lower than the comparable cost of providing heat energy with a natural gas boiler for a facility in the Northeast U.S. that obtains natural gas at commercial rates (Commercial heat costs would include at least $\$ 9.41$ in fuel costs, representing total boiler/transfer efficiency of 85% using gas at $\$ 8.00$ per MMBtu; LCOH would be higher if capital equipment and other operating costs were included). In addition to LCOH, Cornell’s scope also included evaluation of the Environmental value and Regional Economic value of each scenario. When considering the environmental and regional economic value of such a project, the overall “triple bottom line” cost (i.e., the LCOH less the LCOH ENV and LCOH REG values) is even lower and in some cases negative; i.e., in some cases a project achieving the listed performance would have higher value to the environment and to the regional economy than the total project costs over the 30-year project timeframe.

15 GEOTHERMAL ENERGY↗

Airborne antenna pattern calculations

Use of calculation program START and modeling program P 3D to produce radiation patterns of antennas mounted on a space station is discussed. Basic components of two space stations in the early design stage are simulated and radiation patterns for antennas mounted on the modules are presented.

Bagherian, A. B.↗

Development of a Phasor Diagram Creator to Visualize the Piston and Displacer Forces in an Advanced Stirling Convertor

The steady state, nearly sinusoidal behavior of the components in a Free Piston Stirling Engine allows for visualization of the forces in the system using phasor diagrams. Based on Newton's second law, F=ma, any phasor diagrams modeling a given component in a system should close if all of the acting forces have been considered. Since the Advanced Stirling Radioisotope Generator (ASRG), currently being developed for future NASA deep space missions, is made up of such nearly sinusoidally oscillating components, its phasor diagrams would also be expected to close. A graphical user interface (GUI) has been written in MATLAB by taking user input data, passing it to Sage, a 1-D thermodynamic modeling program used to model the Stirling convertor, running Sage and then automatically plotting the phasor diagrams. Using this software tool, the effect of varying different Sage inputs on the phasor diagrams was determined. The parameters varied were piston amplitude, hot end temperature, cold end temperature, operating frequency, and displacer spring constant. By using these phasor diagrams, better insight can be gained as to why the convertor operates the way that it does.

Saha, Dipanjan↗

Development of a Phasor Diagram Creator to Visualize the Piston and Displacer Forces in an Advanced Stirling Convertor

The steady-state, nearly sinusoidal behavior of the components in a free-piston Stirling engine allows for visualization of the forces in the system using phasor diagrams. Based on Newton's second law, F = ma, any phasor diagrams modeling a given component in a system should close if all of the acting forces have been considered. Since the Advanced Stirling Radioisotope Generator (ASRG), currently being developed for future NASA deep space missions, is made up of such nearly sinusoidally oscillating components, its phasor diagrams would also be expected to close. A graphical user interface (GUI) has been written in MATLAB (MathWorks), which takes user input data, passes it to Sage (Gedeon Associates), a one-dimensional thermodynamic modeling program used to model the Stirling convertor, runs Sage, and then automatically plots the phasor diagrams. Using this software tool, the effect of varying different Sage inputs on the phasor diagrams was determined. The parameters varied were piston amplitude, hot-end temperature, cold-end temperature, operating frequency, and displacer spring constant. These phasor diagrams offer useful insight into convertor operation and performance.

Saha, Dipanjan↗

An Evaluation of One-Sided and Two-Sided Communication Paradigms on Relaxed-Ordering Interconnect

The Cray Gemini interconnect hardware provides multiple transfer mechanisms and out-of-order message delivery to improve communication throughput. In this paper we quantify the performance of one-sided and two-sided communication paradigms with respect to: 1) the optimal available hardware transfer mechanism, 2) message ordering constraints, 3) per node and per core message concurrency. In addition to using Cray native communication APIs, we use UPC and MPI micro-benchmarks to capture one- and two-sided semantics respectively. Our results indicate that relaxing the message delivery order can improve performance up to 4.6x when compared with strict ordering. When hardware allows it, high-level one-sided programming models can already take advantage of message reordering. Enforcing the ordering semantics of two-sided communication comes with a performance penalty. Furthermore, we argue that exposing out-of-order delivery at the application level is required for the next-generation programming models. Any ordering constraints in the language specifications reduce communication performance for small messages and increase the number of active cores required for peak throughput.

97 MATHEMATICS AND COMPUTING↗

A Framework for the Analysis of Compiler Optimizations

Compilers transform program source code to machine executable code. During this transformation, they perform a number of compiler optimizations to improve the performance of the generated executable code. Importantly, applying those optimizations depends on the source code structure, such as the parallel programming model used to parallelize an algorithm. Often, implementations of the same algorithm with different programming models have vastly different performance because the compiler optimized them differently. We create FAROS, a framework to structure and automate the analysis of compiler optimizations on programs. FAROS automates the building process, execution profiling, and analysis of compiler optimization of programs, through a configuration interface. It outputs compiler optimization reports to show which optimizations applied to which line of source code, leveraging compilation remarks output by the compiler. Also, FAROS supports benchmarking performance of different program versions by collecting execution time results. In this first release of FAROS, we provide a configuration file to analyze compiler optimization differences for sequential vs OpenMP compilation, including 38 programs consisting of HPC proxy/mini/large applications, and NAS and Rodina kernels for analysis.

Georgakoudis, Giorgis↗

A computer program for modeling non-spherical eclipsing binary star systems

The accurate analysis of eclipsing binary light curves is fundamental to obtaining information on the physical properties of stars. The model described accounts for the important geometric and photometric distortions such as rotational and tidal distortion, gravity brightening, and reflection effect. This permits a more accurate analysis of interacting eclipsing star systems. The model is designed to be useful to anyone with moderate computing resources. The programs, written in FORTRAN 4 for the IBM 360, consume about 80k bytes of core. The FORTRAN program listings are provided, and the computational aspects are described in some detail.

Wood, D. B.↗

Mathematical programming formulations for satellite synthesis

The problem of satellite synthesis can be described as optimally allotting locations and sometimes frequencies and polarizations, to communication satellites so that interference from unwanted satellite signals does not exceed a specified threshold. In this report, mathematical programming models and optimization methods are used to solve satellite synthesis problems. A nonlinear programming formulation which is solved using Zoutendijk's method and a gradient search method is described. Nine mixed integer programming models are considered. Results of computer runs with these nine models and five geographically compatible scenarios are presented and evaluated. A heuristic solution procedure is also used to solve two of the models studied. Heuristic solutions to three large synthesis problems are presented. The results of our analysis show that the heuristic performs very well, both in terms of solution quality and solution time, on the two models to which it was applied. It is concluded that the heuristic procedure is the best of the methods considered for solving satellite synthesis problems.

Bhasin, Puneet↗

Burner liner thermal/structural load modeling: TRANCITS program user's manual

Transfer Analysis Code to Interface Thermal/Structural Problems (TRANCITS) is discussed. The TRANCITS code satisfies all the objectives for transferring thermal data between heat transfer and structural models of combustor liners and it can be used as a generic thermal translator between heat transfer and stress models of any component, regardless of the geometry. The TRANCITS can accurately and efficiently convert the temperature distributions predicted by the heat transfer programs to those required by the stress codes. It can be used for both linear and nonlinear structural codes and can produce nodal temperatures, elemental centroid temperatures, or elemental Gauss point temperatures. The thermal output of both the MARC and SINDA heat transfer codes can be interfaced directly with TRANCITS, and it will automatically produce stress model codes formatted for NASTRAN and MARC. Any thermal program and structural program can be interfaced by using the neutral input and output forms supported by TRANCITS.

Maffeo, R.↗

The addition of algebraic turbulence modeling to program LAURA

The Langley Aerothermodynamic Upwind Relaxation Algorithm (LAURA) is modified to allow the calculation of turbulent flows. This is accomplished using the Cebeci-Smith and Baldwin-Lomax eddy-viscosity models in conjunction with the thin-layer Navier-Stokes options of the program. Turbulent calculations can be performed for both perfect-gas and equilibrium flows. However, a requirement of the models is that the flow be attached. It is seen that for slender bodies, adequate resolution of the boundary-layer gradients may require more cells in the normal direction than a laminar solution, even when grid stretching is employed. Results for axisymmetric and three-dimensional flows are presented. Comparison with experimental data and other numerical results reveal generally good agreement, except in the regions of detached flow.

Cheatwood, F. Mcneil↗

Exascale Programming Approaches for Accelerated Climate Modeling for Energy

The Accelerated Climate Modeling for Energy (ACME) program is a leading-edge climate and Earth system model designed to address the U.S. Department of Energy (DOE) mission needs. The ACME project involves collaboration between seven National Laboratories, the National Center for Atmospheric Research, four academic institutions, and one private-sector company. The ACME project funds ongoing efforts to ensure the model continues to make efficient use of DOE Leadership Computing Facilities (LCFs) in order to best address the three driving grand challenge science questions:Water cycle: How will more realistic portrayals of features important to the water cycle (resolution, clouds, aerosols, snowpack, river routing, land use) affect river flow and associated freshwater supplies at the watershed scale?Cryosphere systems: Could a dynamical instability in the Antarctic ice sheet be triggered within the next 40 years?Biogeochemistry: What are the contributions and feedbacks from natural and managed systems to current greenhouse gas fluxes, and how will those factors and associated fluxes evolve in the future?

Norman, Matthew↗

Experimental apparatus and methodology to test and quantify thermal performance of micro and macro-encapsulated phase change materials in building envelope applications

Thermal energy storage (TES) is used as a viable technology to shift peak electricity demand caused by the space cooling requirements in buildings. Passive TES is implemented in building envelope via micro and macroencapsulation methods. This study describes the use of a state-of-the-art laboratory to test different PCM inclusions in simplified building walls. A microencapsulated PCM and two macroencapsulated PCMs are tested in a controlled environment to gather data for validation purposes of PCM modelling algorithms in building energy modelling programs. Data indicates that the chamber environment and the heating and cooling system can conduct full-cycle tests of wall panels with PCM inclusions. This study also generates data from parallel tests on 4 wall panels which can be used in building energy modelling programs to validate the PCM modelling algorithms. The cyclic tests also capture the thermal effects of PCMs and complex PCM behaviors like sub-cooling in PCM hydrate-salts.

25 ENERGY STORAGE↗