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 55 records · Page 3

Critical Role of the Public Theory & Modeling Program for Commercial Fusion Energy

This white paper contributes input from the Executive Committee of the Theory Coordinating Committee to the 2024 FESAC Decadal Plan Subcommittee. It is argued that the public Theory and Modeling program plays a critical role in the pursuit of commercial fusion energy. A new mechanism for fostering engagement between the fusion industry and the public Theory and Modeling program could provide better alignment between the goals of the public program and the needs of private industry.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Center for Programming Models for Scalable Parallel Computing - Towards Enhancing OpenMP for Manycore and Heterogeneous Nodes (Final Report)

OpenMP was not well recognized at the beginning of the project, around year 2003, because of its limited use in DoE production applications and the inmature hardware support for an efficient implementation. Yet in the recent years, it has been graduately adopted both in HPC applications, mostly in the form of MPI+OpenMP hybrid code, and in mid-scale desktop applications for scientific and experimental studies. We have observed this trend and worked deligiently to improve our OpenMP compiler and runtimes, as well as to work with the OpenMP standard organization to make sure OpenMP are evolved in the direction close to DoE missions. In the Center for Programming Models for Scalable Parallel Computing project, the HPCTools team at the University of Houston (UH), directed by Dr. Barbara Chapman, has been working with project partners, external collaborators and hardware vendors to increase the scalability and applicability of OpenMP for multi-core (and future manycore) platforms and for distributed memory systems by exploring different programming models, language extensions, compiler optimizations, as well as runtime library support.

97 MATHEMATICS AND COMPUTING↗

Enhancing the MPI Programming Model for PetaScale Systems (Final Report)

This project performed research into enhancing the MPI programming model in two ways: developing improved algorithms and implementation strategies, tested and realized in the MPICH implementation, and exploring extensions to the MPI standard to better support PetaScale and ExaScale systems.

97 MATHEMATICS AND COMPUTING↗

Programming Models: Re-cap of June Meeting [Slides]

A programming model is a set of software technologies that support the expression of algorithms and provide applications with an abstract representation of the capabilities of the underlying hardware architecture. The primary goals are productivity, portability and performance.

97 MATHEMATICS AND COMPUTING↗

A Programming Model Performance Study Using the NAS Parallel Benchmarks

Harnessing the power of multicore platforms is challenging due to the additional levels of parallelism present. In this paper we use the NAS Parallel Benchmarks to study three programming models, MPI, OpenMP and PGAS to understand their performance and memory usage characteristics on current multicore architectures. To understand these characteristics we use the Integrated Performance Monitoring tool and other ways to measure communication versus computation time, as well as the fraction of the run time spent in OpenMP. The benchmarks are run on two different Cray XT5 systems and an Infiniband cluster. Our results show that in general the three programming models exhibit very similar performance characteristics. In a few cases, OpenMP is significantly faster because it explicitly avoids communication. For these particular cases, we were able to re-write the UPC versions and achieve equal performance to OpenMP. Using OpenMP was also the most advantageous in terms of memory usage. Also we compare performance differences between the two Cray systems, which have quad-core and hex-core processors. We show that at scale the performance is almost always slower on the hex-core system because of increased contention for network resources.

Shan, Hongzhang↗

Fault Tolerance for OpenSHMEM. In: PGAS '14 Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models. Article No. 23

On today's supercomputing systems, faults are becoming a norm rather than an exception. Given the complexity required for achieving expected scalability and performance on future systems, this situation is expected to become worse. The systems are expected to function in a nearly constant presence of faults. To be productive on these systems, programming models will require both hardware and software to be resilient to faults. With the growing importance of PGAS programming model and OpenSHMEM, as a part of HPC software stack, a lack of a fault tolerance model may become a liability for its users. Towards this end, in this paper, we discuss the viability of using checkpoint/restart as a fault-tolerance method for OpenSHMEM, propose a selective checkpoint/restart fault-tolerance model, and discuss challenges associated with implementing the proposed model.

Hao, Pengfei↗

A multi-objective programming model for assessment the GHG emissions in MSW management

Highlights: • The multi-objective multi-period optimization model. • The solution approach for the generation of the Pareto front with mathematical programming. • The very detailed description of the model (decision variables, parameters, equations). • The use of IPCC 2006 guidelines for landfill emissions (first order decay model) in the mathematical programming formulation. - Abstract: In this study a multi-objective mathematical programming model is developed for taking into account GHG emissions for Municipal Solid Waste (MSW) management. Mathematical programming models are often used for structure, design and operational optimization of various systems (energy, supply chain, processes, etc.). The last twenty years they are used all the more often in Municipal Solid Waste (MSW) management in order to provide optimal solutions with the cost objective being the usual driver of the optimization. In our work we consider the GHG emissions as an additional criterion, aiming at a multi-objective approach. The Pareto front (Cost vs. GHG emissions) of the system is generated using an appropriate multi-objective method. This information is essential to the decision maker because he can explore the trade-offs in the Pareto curve and select his most preferred among the Pareto optimal solutions. In the present work a detailed multi-objective, multi-period mathematical programming model is developed in order to describe the waste management problem. Apart from the bi-objective approach, the major innovations of the model are (1) the detailed modeling considering 34 materials and 42 technologies, (2) the detailed calculation of the energy content of the various streams based on the detailed material balances, and (3) the incorporation of the IPCC guidelines for the CH{sub 4} generated in the landfills (first order decay model). The equations of the model are described in full detail. Finally, the whole approach is illustrated with a case study referring to the application of the model in a Greek region.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Sparse Deep Neural Network Inference using different Programming Models

Sparse deep neural networks have gained increasing attention recently in achieving speedups on inference with reduced memory footprints. However, the real-world applications are little shown with specialized optimizations, yet a wide variety of DNN tasks remain dense without exploiting the advantages of sparsity in networks. Recent work presented by MIT/IEEE/Amazon GraphChallenge has demonstrated significant speedups and various techniques. Still, we find that there is limited investigation of the impact of various Python and C\slash C++ based programming models to explore new opportunities in general cases. In this work, we provide performance evaluation through different programming models using CuPy, cuSPARSE, and OpenMP to discuss the advantages and disadvantages of our sparse implementations on single-GPU and multiple GPUs of NVIDIA DGX-A100 40GB/80GB platforms.

machine learning, HPC↗

Keys to the House: Unlocking Residential Savings With Program Models for Home Energy Upgrades

After more than 40 years of effort, energy efficiency program administrators and associated contractors still find it challenging to penetrate the home retrofit market, especially at levels commensurate with state and federal goals for energy savings and emissions reductions. Residential retrofit programs further have not coalesced around a reliably successful model. They still vary in design, implementation and performance, and they remain among the more difficult and costly options for acquiring savings in the residential sector. If programs are to contribute fully to meeting resource and policy objectives, administrators need to understand what program elements are key to acquiring residential savings as cost effectively as possible. To that end, the U.S. Department of Energy (DOE) sponsored a comprehensive review and analysis of home energy upgrade programs with proven track records, focusing on those with robustly verified savings and constituting good examples for replication. The study team reviewed evaluations for the period 2010 to 2014 for 134 programs that are funded by customers of investor-owned utilities. All are programs that promote multi-measure retrofits or major system upgrades. We paid particular attention to useful design and implementation features, costs, and savings for nearly 30 programs with rigorous evaluations of performance. This meta-analysis describes program models and implementation strategies for (1) direct install retrofits; (2) heating, ventilating and air-conditioning (HVAC) replacement and early retirement; and (3) comprehensive, whole-home retrofits. We analyze costs and impacts of these program models, in terms of both energy savings and emissions avoided. These program models can be useful guides as states consider expanding their strategies for acquiring energy savings as a resource and for emissions reductions. We also discuss the challenges of using evaluations to create program models that can be confidently applied in multiple jurisdictions.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Designing a unified programming model for heterogeneous machines

While high-efficiency machines are increasingly embracing heterogeneous architectures and massive multithreading, contemporary mainstream programming languages reflect a mental model in which processing elements are homogeneous, concurrency is limited, and memory is a flat undifferentiated pool of storage. Moreover, the current state of the art in programming heterogeneous machines tends towards using separate programming models, such as OpenMP and CUDA, for different portions of the machine. Both of these factors make programming emerging heterogeneous machines unnecessarily difficult. We describe the design of the Phalanx programming model, which seeks to provide a unified programming model for heterogeneous machines. It provides constructs for bulk parallelism, synchronization, and data placement which operate across the entire machine. Our prototype implementation is able to launch and coordinate work on both CPU and GPU processors within a single node, and by leveraging the GASNet runtime, is able to run across all the nodes of a distributed-memory machine.

Garland, Michael↗

Comparison of Building Energy Modeling Programs: Building Loads

This technical report presented the methodologies, processes, and results of comparing three Building Energy Modeling Programs (BEMPs) for load calculations: EnergyPlus, DeST and DOE-2.1E. This joint effort, between Lawrence Berkeley National Laboratory, USA and Tsinghua University, China, was part of research projects under the US-China Clean Energy Research Center on Building Energy Efficiency (CERC-BEE). Energy Foundation, an industrial partner of CERC-BEE, was the co-sponsor of this study work. It is widely known that large discrepancies in simulation results can exist between different BEMPs. The result is a lack of confidence in building simulation amongst many users and stakeholders. In the fields of building energy code development and energy labeling programs where building simulation plays a key role, there are also confusing and misleading claims that some BEMPs are better than others. In order to address these problems, it is essential to identify and understand differences between widely-used BEMPs, and the impact of these differences on load simulation results, by detailed comparisons of these BEMPs from source code to results. The primary goal of this work was to research methods and processes that would allow a thorough scientific comparison of the BEMPs. The secondary goal was to provide a list of strengths and weaknesses for each BEMP, based on in-depth understandings of their modeling capabilities, mathematical algorithms, advantages and limitations. This is to guide the use of BEMPs in the design and retrofit of buildings, especially to support China’s building energy standard development and energy labeling program. The research findings could also serve as a good reference to improve the modeling capabilities and applications of the three BEMPs. The methodologies, processes, and analyses employed in the comparison work could also be used to compare other programs. The load calculation method of each program was analyzed and compared to identify the differences in solution algorithms, modeling assumptions and simplifications. Identifying inputs of each program and their default values or algorithms for load simulation was a critical step. These tend to be overlooked by users, but can lead to large discrepancies in simulation results. As weather data was an important input, weather file formats and weather variables used by each program were summarized. Some common mistakes in the weather data conversion process were discussed. ASHRAE Standard 140-2007 tests were carried out to test the fundamental modeling capabilities of the load calculations of the three BEMPs, where inputs for each test case were strictly defined and specified. The tests indicated that the cooling and heating load results of the three BEMPs fell mostly within the range of spread of results from other programs. Based on ASHRAE 140-2007 test results, the finer differences between DeST and EnergyPlus were further analyzed by designing and conducting additional tests. Potential key influencing factors (such as internal gains, air infiltration, convection coefficients of windows and opaque surfaces) were added one at a time to a simple base case with an analytical solution, to compare their relative impacts on load calculation results. Finally, special tests were designed and conducted aiming to ascertain the potential limitations of each program to perform accurate load calculations. The heat balance module was tested for both single and double zone cases. Furthermore, cooling and heating load calculations were compared between the three programs by varying the heat transfer between adjacent zones, the occupancy of the building, and the air-conditioning schedule.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE/UCAR Cooperative Agreement for the Regional and Global Climate Modeling Program

This progress report describes research supported by Cooperative Agreement between the University Corporation for Atmospheric Research (UCAR) and the U.S. Department of Energy (DOE) Biological and Environmental Research (BER). The purpose of the Cooperative Agreement is to provide support for an integrated research program to address key science questions relevant to the DOE Regional and Global Climate Modeling Program as part of the U.S. Global Change Research Program (USGCRP). The Cooperative Agreement funds four tasks that address key aspects of climate science, and this report provides a summary of activities for each task during the past year. As part of the Cooperative Agreement supported science, the Climate Change Prediction (CCP) group at the National Center for Atmospheric Research (NCAR), provides leadership to the Community Earth System Model (CESM) Climate Variability and Change Working Group (CVCWG) through co-chairs Gerald Meehl and Susan Bates (with DOE-funded co-chair Peter Gleckler, along with Clara Deser and Shang-Ping Xie). Over the past year CCP has played a leadership role in performing climate change simulations and analyses with the Community Climate System Model version 4 (CCSM4) and CESM version 1. These simulations and analyses made strong contributions to the federal USGCRP in several high priority areas. We have also been involved in planning for the sixth phase of the Coupled Model Intercomparison Project (CMIP6) which started in 2015. Simulations from CMIP6 will form the basis for ongoing U.S. National Assessment activities, and the IPCC AR6.

54 ENVIRONMENTAL SCIENCES↗

Early Evaluation of Directive-Based GPU Programming Models for Productive Exascale Computing

Graphics Processing Unit (GPU)-based parallel computer architectures have shown increased popularity as a building block for high performance computing, and possibly for future Exascale computing. However, their programming complexity remains as a major hurdle for their widespread adoption. To provide better abstractions for programming GPU architectures, researchers and vendors have proposed several directive-based GPU programming models. These directive-based models provide different levels of abstraction, and required different levels of programming effort to port and optimize applications. Understanding these differences among these new models provides valuable insights on their applicability and performance potential. In this paper, we evaluate existing directive-based models by porting thirteen application kernels from various scientific domains to use CUDA GPUs, which, in turn, allows us to identify important issues in the functionality, scalability, tunability, and debuggability of the existing models. Our evaluation shows that directive-based models can achieve reasonable performance, compared to hand-written GPU codes.

Lee, Seyong↗

Getting To Exascale: Applying Novel Parallel Programming Models To Lab Applications For The Next Generation Of Supercomputers

As supercomputing moves toward exascale, node architectures will change significantly. CPU core counts on nodes will increase by an order of magnitude or more. Heterogeneous architectures will become more commonplace, with GPUs or FPGAs providing additional computational power. Novel programming models may make better use of on-node parallelism in these new architectures than do current models. In this paper we examine several of these novel models – UPC, CUDA, and OpenCL –to determine their suitability to LLNL scientific application codes. Our study consisted of several phases: We conducted interviews with code teams and selected two codes to port; We learned how to program in the new models and ported the codes; We debugged and tuned the ported applications; We measured results, and documented our findings. We conclude that UPC is a challenge for porting code, Berkeley UPC is not very robust, and UPC is not suitable as a general alternative to OpenMP for a number of reasons. CUDA is well supported and robust but is a proprietary NVIDIA standard, while OpenCL is an open standard. Both are well suited to a specific set of application problems that can be run on GPUs, but some problems are not suited to GPUs. Further study of the landscape of novel models is recommended.

97 MATHEMATICS AND COMPUTING↗

Hierarchical computation in the SPMD programming model

Large-scale parallel machines are programmed mainly with the single program, multiple data (SPMD) model of parallelism. While this model has advantages of scalability and simplicity, it does not fit well with divide-and-conquer parallelism or hierarchical machines that mix shared and distributed memory. In this paper, we define the recursive single program, multiple data model (RSPMD) that extends SPMD with a hierarchical team mechanism to support hierarchical algorithms and machines. We implement this model in the Titanium language and describe how to eliminate a class of deadlocks by ensuring alignment of collective operations. We present application case studies evaluating the RSPMD model, showing that it enables divide-and-conquer algorithms such as sorting to be elegantly expressed and that team collective operations increase performance of conjugate gradient by up to a factor of two. The model also facilitates optimizations for hierarchical machines, improving scalability of particle in cell by 8x and performance of sorting and a stencil code by up to 40% and 14%, respectively.

Kamil, A↗

U.S. Department of Energy Reference Model Program RM1: Experimental Results.

The Reference Model Project (RMP), sponsored by the U.S. Department of Energy’s (DOE) Wind and Water Power Technologies Program within the Office of Energy Efficiency & Renewable Energy (EERE), aims at expediting industry growth and efficiency by providing nonproprietary Reference Models (RM) of MHK technology designs as study objects for opensource research and development (Neary et al. 2014a,b). As part of this program, MHK turbine models were tested in a large open channel facility at the University of Minnesota’s St. Anthony Falls Laboratory (UMN-SAFL). Reference Model 1 (RM1) is a 1:40 geometric scale dual-rotor axial flow horizontal axis device with counter-rotating rotors, each with a rotor diameter dT = 0.5m. Precise blade angular position and torque measurements were synchronized with three acoustic Doppler velocimeters (ADVs) aligned with each rotor and the midpoint for RM1. Flow conditions for each case were controlled such that depth, h = 1m, and volumetric flow rate, Qw = 2.425m3s-1, resulting in a hub height velocity of approximately Uhub = 1.05ms-1 and blade chord length Reynolds numbers of Rec ≈ 3.0x105. Vertical velocity profiles collected in the wake of each device from 1 to 10 rotor diameters are used to estimate the velocity recovery and turbulent characteristics in the wake, as well as the interaction of the counter-rotating rotor wakes. The development of this high resolution laboratory investigation provides a robust dataset that enables assessing turbulence performance models and their ability to accurately predict device performance metrics, including computational fluid dynamics (CFD) models that can be used to predict turbulent inflow environments, reproduce wake velocity deficit, recovery and higher order turbulent statistics, as well as device performance metrics.

17 WIND ENERGY↗

U.S. Department of Energy Reference Model Program RM2: Experimental Results

The Reference Model Project (RMP), sponsored by the U.S. Department of Energy’s (DOE) Wind and Water Power Technologies Program within the Office of Energy Efficiency & Renewable Energy (EERE), aims at expediting industry growth and efficiency by providing non-proprietary Reference Models (RM) of MHK technology designs as study objects for open-source research and development (Neary et al. 2014a,b). As part of this program, MHK turbine models were tested in a large open channel facility at the University of Minnesota’s St. Anthony Falls Laboratory (UMN - SAFL) . Reference Model 2 (RM2) is a 1:15 geometric scale dual - rotor cross flow vertical axis device with counter - rotating rotors, each with a rotor diameter d T = 0.43m and rotor height, h T = 0.323 m. RM2 is a river turbine designed for a site modeled after a reach in the lower Mississippi River near Baton Rouge, Louisiana (Barone et al. 2014) . Precise blade angular position and torque measurements were synchronized with three acoustic Doppler velocimeters (ADV) aligned with each rotor and the midpoint for RM2 . Flow conditions for each case were controlled such that depth, h = 1m, and volumetric flow rate, Q w = 2. 35m 3 s -1 , resulting in a hub height velocity of approximately U hub = 1. 2 ms -1 and blade chord length Reynolds numbers of Re c = 6 .1x10 4 . Vertical velocity profiles collected in the wake of each device from 1 to 10 rotor diameters are used to estimate the velocity recovery and turbulent characteristics in the wake, as well as the interaction of the counter-rotating rotor wakes. The development of this high resolution laboratory investigation provides a robust dataset that enables assessing computational fluid dynamics (CFD) models and their ability to accurately simulate turbulent inflow environments, device performance metrics, and to reproduce wake velocity deficit, recovery and higher order turbulent statistics.

13 HYDRO ENERGY↗