SEARCH · Search NASA

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.

SourceResearch connectionFrom yearThrough year

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

At least 235 records · Page 13

All sources NASA NTRS DOE OSTI

DOE OSTI2019

Improving Ligand Geometry in Protein Data Bank Structures Computationally

Information about the three‐dimensional structures of complex biological molecules is an indispensable research tool for many fields of study, including biology, chemistry, pharmacology, and computer science. The Protein Data Bank (PDB) is an public digital archive providing access to structures of nucleic acids, proteins, and large macromolecular machines determined experimentally by X‐ray crystallography, nuclear magnetic resonance (NMR) spectroscopy, and 3‐dimensional electron microscopy (3DEM). PDB structures undergo validation for structural plausibility upon their deposition into the PDB using the program Mogul, which cross references each deposited structure against similar data in the Cambridge Structural Database (CSD). Ligands associated with PDB structures are a common source of structural inaccuracy. In this study, a programmatic pipeline was developed to determine if ligand geometric accuracy could be improved using known computational tools. Ligands with dubious geometry were identified through a Python mining code. A sample set of the identified structures was remodeled into minimum energy conformations using the molecular dynamics program AMBER and then fit to the original experimental density maps using the molecular modeling program Coot. The refined models were compared to the original models in the PDB as well as to similar structures in the CSD using the deposition statistical validation server. Preliminary results suggest that the pipeline effectively identifies and improves ligand structures that possess inaccurate geometry. This method can be used to evaluate and improve the accuracy of specific ligands in structures both archived and pending deposition. Support or Funding Information This work was supported by an NSF REU and the RCSB PDB [NSF (DBI‐1338415), NIH, and DOE.] This abstract is from the Experimental Biology 2019 Meeting. There is no full text article associated with this abstract published in The FASEB Journal .

Miller, Beck↗

DOE OSTI2020

Locality-Aware Scheduling for Scalable Heterogeneous Environments

Heterogeneous computing promise boost performance of scientific applications by allowing massively parallel execution of computational tasks. However, manually managing extremely heterogeneous, multi-device systems is complicated and may result in sub-optimal performance. Specifically, data management is an extremely challenging problem on multi-device systems. In this work, we introduce two locality-aware schedulers for the Minos Computing Library (MCL), an asynchronous, task-based programming model and runtime for extremely heterogeneous systems. The first scheduler implements a pure locality-aware algorithm to maximize data reuse, though it might incur in ”hot-spots” that limit system utilization. The second scheduler mitigates this drawback by dynamically targeting between locality-awareness and system utilization based on the current workload and available computing devices. Our results show that locality-awareness greatly benefit applications that exhibit data reuse, providing up to 6.9x and 7.9x over the original MCL scheduler and equivalent OpenCL implementations, respectively. Moreover, our schedulers introduce negligible overhead compared with the original MCL scheduler and achieve similar performance for applications that don’t benefit from data locality.

Architecture, co-design, Task-based programming mo↗

DOE OSTI2023

Pair distribution function analysis of discrete nanomaterials in PDFgui

Pair distribution functions (PDFs) are a leading tool for atomic structure analysis of nanomaterials. However, the most widely used programs for refining atomic structure against PDF data are based on extended crystallographic models, which cannot be applied to discrete, whole nanoparticles. Furthermore, this work describes a straightforward approach to simulate and refine atomistic models of discrete clusters and nanoparticles employing widely used PDF modelling programs such as PDFgui that utilize extended crystallographic models. In this approach, the whole particle to be modelled is contained within an expanded, and otherwise empty, unit cell that is sufficiently large to avoid correlations between atoms in neighbouring unit cells over the r range analyzed. The PDF of the particle is simulated as a composite using two conventional `phases': one that calculates the atom–atom correlations and one that approximates the local number density. This approach is first validated for large nanoparticles that are well modelled by a conventional shape factor model, and then applied to simulate the PDF of discrete particles and low-dimensional materials (graphene and MXene) and to model the experimental PDF data for single-layer FeS nanosheets. A comparison of this approach with the DiffPy-CMI program, which calculates the PDF of discrete species, shows that the composite modelling approach is equally or more accurate. Example input files for implementing this approach within PDFgui and TOPAS, and recommendations for selecting model parameters for reliable application of this refinement strategy, are provided.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Toward Automated Detection of Portability Bugs in Kokkos Parallel Programs

Performance-portable programming frameworks provide abstractions for parallel execution to allow easily porting an application to multiple backend programming models, such as CUDA, HIP, and OpenMP. However, programs may still have portability bugs that manifest only on specific backends. Traditional testing is ineffective in discovering these bugs, as it would require concrete execution on all supported hardware configurations for a potentially infinite set of inputs. To mitigate this issue, we focused on a specific programming framework, Kokkos, and identified several categories of common portability bugs. We then developed Klokkos, a static analysis approach based on symbolic execution that can run on commodity hardware, before execution on supercomputers. As a proof-of-concept, we ran Klokkos on examples encoding the identified bugs. Our results show that Klokkos is effective, efficient, and precise: it detected all the considered bugs, quickly, and without any false positives. Although preliminary, our results motivate further research and development in this direction.

Kale, Vivek↗

DOE OSTI2018

Toward a MILP Modeling Framework for Distribution System Restoration

Large-scale blackouts and extreme weather events in recent decades raise the concern for improving the resilience of electric power infrastructures. Distribution service restoration (DSR), a fundamental application in outage management systems, allows restoration solutions for system operators when power outages happen. As distribution generators (DGs) and remotely controllable devices are increasingly installed in distribution systems, an advanced DSR framework is critical to perform optimally coordinated restoration that can achieve maximal restoration performance. This work introduces a DSR modeling framework, which can generate optimal switching sequences and estimated time of restoration in the presence of remotely controllable switches, manually operated switches, and dispatchable DGs. Two mathematical models, a variable time step model and a fixed time step model, are presented and compared. The proposed models are formulated as a mixed-integer linear programming model, and their effectiveness is evaluated via the IEEE 123 node test feeder.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2019

SST-GPU: An Execution -Driven CUDA Kernel Scheduler and Streaming-Multiprocessor Compute Model

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of massive amounts of data have created a space for massively parallel acceleration where the context for thousands of concurrent threads are resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. The design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. To address the need for a scalable, decentralized GPU model that can model large GPUs, chiplet-based GPUs and multi-node GPUs, this report details the first steps in integrating the open-source, execution driven GPGPU-Sim into the SST framework. The first stage of this project, creates two elements: a kernel scheduler SST element accepts work from SST CPU models and schedules it to an SM-collection element that performs cycle-by-cycle timing using SSTs Mem Hierarchy to model a flexible memory system.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Optimizing equity in energy policy interventions: A quantitative decision-support framework for energy justice

This paper presents a quantitative framework to support policy decision-making around equitable energy interventions. By combining sociodemographic and techno-economic models in the energy space, we propose a linear programming model to calculate the optimal portfolio of energy investments that explicitly minimizes the energy burden of a given population of energy insecure households. The model is formulated as a multi-objective optimization suitable to support the decisions on weatherization and deployment of distributed energy resources. We illustrate our methodology with a case study involving a population of 14,043 energy insecure households in Wayne County, Detroit, United States.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2018

Toward a Synthetic Model for Distribution System Restoration and Crew Dispatch

Distribution service restoration (DSR) is critical for improving the resilience and reliability of modern distribution systems by strategically and sequentially energizing the system components and customer loads. Restoring electricity service to affected customers also requires multiple crews with different skill sets to perform multiple tasks that are procedurally interdependent with safety guaranteed. However, in existing DSR practices, switch operations and crew dispatch are scheduled separately, and their interdependence is not fully considered. As advanced technologies are enabling remote communication, control, and dispatch, utilities now desire an integrated DSR framework to achieve seamless coordination among multiple DSR tasks such as switch operation, crew dispatch, and component repair. In this paper, we introduce a synthetic model that integrates the service restoration model and the crew dispatch model based on a universal routing model. The proposed model can provide the estimated time of restoration for each load, the switching sequence for safely operating remotely/manually operated switches, and dispatch solutions for crews with different skill sets. The proposed synthetic model is formulated as a mixed-integer linear programming model, and its effectiveness is evaluated via the IEEE 123 bus test feeder and several large-scale test feeders (EPRI Ckt5, Ckt7, Ckt24, and IEEE 8500 node test feeder.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2019

Balar: A SST GPU Component for Performance Modeling and Profiling

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of massive amounts of data have created a space for massively parallel accelerators capable of maintaining context for thousands of concurrent threads resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. One path for the design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. The SST framework has been proven to scale up to run simulations containing tens of thousands of nodes. A previous report described the initial integration of the open-source, execution-driven GPU simulator, GPGPU-Sim, into the SST framework. This report discusses the results of the integration and how to use the new GPU component in SST. It also provides examples of what it can be used to analyze and a correlation study showing how closely the execution matches that of a Nvidia V100 GPU when running kernels and mini-apps.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

SST-GPU: A Scalable SST GPU Component for Performance Modeling and Profiling

Programmable accelerators have become commonplace in modern computing systems. Advances in programming models and the availability of unprecedented amounts of data have created a space for massively parallel accelerators capable of maintaining context for thousands of concurrent threads resident on-chip. These threads are grouped and interleaved on a cycle-by-cycle basis among several massively parallel computing cores. One path for the design of future supercomputers relies on an ability to model the performance of these massively parallel cores at scale. The SST framework has been proven to scale up to run simulations containing tens of thousands of nodes. A previous report described the initial integration of the open-source, execution-driven GPU simulator, GPGPU-Sim, into the SST framework. This report discusses the results of the integration and how to use the new GPU component in SST. It also provides examples of what it can be used to analyze and a correlation study showing how closely the execution matches that of a Nvidia V100 GPU when running kernels and mini-apps.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

Porting Adaptive Ensemble Molecular Dynamics Workflows to the Summit Supercomputer

Molecular dynamics (MD) simulations must take very small (femtosecond) integration steps in simulation-time to avoid numerical errors. Efficient use of parallel programming models and accelerators in state-of-the art MD programs now is pushing Moore’s limit for time-per-MD step. As a result, directly simulating timescales beyond milliseconds will not be attainable directly, even at exascale. However, concepts from statistical physics can be used to combine many parallel simulations to provide information about longer timescales and to adequately sample the simulation space, while preserving details about the dynamics of the system. Implementing such an approach requires a workflow program that allows adaptable steering of task assignments based on extensive statistical analysis of intermediate results. Here we report the implementation of such an adaptable workflow program to drive simulations on the Summit IBM Power System AC922, a pre-exascale supercomputer at the Oak Ridge Leadership Computing Facility (OLCF). We compare to experiences on Titan, Summit’s predecessor, report the performance of the workflow and its components, and describe the porting process. We find that using a workflow program managed by a Mongo database can provide the fault tolerance, scalable performance, task dispatch rate, and reconfigurability required for robust and portable implementation of ensemble simulations such as are used in enhanced-sampling molecular dynamics. This type of workflow generator can also be used to provide adaptive steering of ensemble simulations for other applications in addition to MD.

Ossyra, John R.↗

DOE OSTI2023

Enabling Fortran Standard Parallelism in GAMESS for Accelerated Quantum Chemistry Calculations

The performance of Fortran 2008 DO CONCURRENT (DC) relative to OpenACC and OpenMP target offloading (OTO) with different compilers is studied for the GAMESS quantum chemistry application. Specifically, DC and OTO are used to offload the Fock build, which is a computational bottleneck in most quantum chemistry codes, to GPUs. The DC Fock build performance is studied on NVIDIA A100 and V100 accelerators and compared with the OTO versions compiled by the NVIDIA HPC, IBM XL, and Cray Fortran compilers. The results show that DC can speed up the Fock build by 3.0× compared with that of the OTO model. Finally, with similar offloading efforts, DC is a compelling programming model for offloading Fortran applications to GPUs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Application of performance portability solutions for GPUs and many-core CPUs to track reconstruction kernels

Next generation High-Energy Physics (HEP) experiments are presented with significant computational challenges, both in terms of data volume and processing power. Using compute accelerators, such as GPUs, is one of the promising ways to provide the necessary computational power to meet the challenge. The current programming models for compute accelerators often involve using architecture-specific programming languages promoted by the hardware vendors and hence limit the set of platforms that the code can run on. Developing software with platform restrictions is especially unfeasible for HEP communities as it takes significant effort to convert typical HEP algorithms into ones that are efficient for compute accelerators. Multiple performance portability solutions have recently emerged and provide an alternative path for using compute accelerators, which allow the code to be executed on hardware from different vendors. We apply several portability solutions, such as Kokkos, SYCL, C++17 std::execution::par, Alpaka, and OpenMP/OpenACC, on two mini-apps extracted from the mkFit project: p2z and p2r. These apps include basic kernels for a Kalman filter track fit, such as propagation and update of track parameters, for detectors at a fixed z or fixed r position, respectively. The two mini-apps explore different memory layout formats. We report on the development experience with different portability solutions, as well as their performance on GPUs and many-core CPUs, measured as the throughput of the kernels from different GPU and CPU vendors such as NVIDIA, AMD and Intel.

Kwok, Ka Hei Martin↗

DOE OSTI2020

Modeling thin layers of analytes on substrates for spectral analysis: use of solid/liquid n and k values to model reflectance spectra

Since solids are only sometimes seen en masse in a pure bulk form, and for liquids other than water almost never, a capability to model reflectance spectra from analytes deposited on various substrates would be highly advantageous. If available, the real, n ( ν ) , and imaginary, k ( ν ) , components of the complex refractive index, n n + i k , can be used to simulate infrared spectra, accounting for reflection, refraction, and absorption phenomena as a function of wavelength. We focus on using the Pacific Northwest National Laboratory (PNNL) derived n / k vectors for solid and liquid analytes deposited as thin layers on different types of substrates including conductors, such as aluminum, and inorganic dielectrics, such as glass. The model is an adaptation of the Monte Carlo ray trace modeling program, TracePro, extended through the use of its macrolanguage. The model is tested using thin films of organic liquids including silicone oil and no. 2 diesel fuel, as well as organic solids such as caffeine and acetaminophen on aluminum and glass. The predicted spectra for the solid films were compared to experimental hemispherical reflectance data measured using a Fourier transform spectrometer with an integrating sphere. The thickness of the calculated layer is a parameter for predicting the (transflectance) spectra and is obtained using the areal density measured from gravimetric methods to generate the thin-layer samples. Comparison of the calculated spectra with experimental hemispherical reflectance data shows excellent agreement, indicating promise for the use of measured n / k data to synthesize reference spectral data. In particular, accounting for the inhomogeneity of the deposits greatly improved the match with experimental data. Finally, the theoretical modeling shows that for thicker layers (ca. 20 to 100 μm) of typical organics possessing moderately strong k values, the longwave infrared features are often saturated and better spectral contrast is obtained from the overtone/combination bands in the shortwave infrared.

42 ENGINEERING↗

DOE OSTI2024

Application of performance portability solutions for GPUs and many-core CPUs to track reconstruction kernels

Next generation High-Energy Physics (HEP) experiments are presented with significant computational challenges, both in terms of data volume and processing power. Using compute accelerators, such as GPUs, is one of the promising ways to provide the necessary computational power to meet the challenge. The current programming models for compute accelerators often involve using architecture-specific programming languages promoted by the hardware vendors and hence limit the set of platforms that the code can run on. Developing software with platform restrictions is especially unfeasible for HEP communities as it takes significant effort to convert typical HEP algorithms into ones that are efficient for compute accelerators. Multiple performance portability solutions have recently emerged and provide an alternative path for using compute accelerators, which allow the code to be executed on hardware from different vendors. We apply several portability solutions, such as Kokkos, SYCL, C++17 std::execution::par and Alpaka, on two mini-apps extracted from the mkFit project: p2z and p2r. These apps include basic kernels for a Kalman filter track fit, such as propagation and update of track parameters, for detectors at a fixed z or fixed r position, respectively. The two mini-apps explore different memory layout formats. We report on the development experience with different portability solutions, as well as their performance on GPUs and many-core CPUs, measured as the throughput of the kernels from different GPU and CPU vendors such as NVIDIA, AMD and Intel.

Kwok, Ka Martin↗

DOE OSTI2025

ChatHPC: Building the Foundations for a Productive and Trustworthy AI-Assisted HPC Ecosystem

ChatHPC democratizes large language models for the high-performance computing (HPC) community by providing the infrastructure, ecosystem, and knowledge needed to apply modern generative AI technologies to rapidly create specific capabilities for critical HPC components while using relatively modest computational resources. Our divide-and-conquer approach focuses on creating a collection of reliable, highly specialized, and optimized AI assistants for HPC based on the cost-effective and fast Code Llama fine-tuning processes and expert supervision. We target major components of the HPC software stack, including programming models, runtimes, I/O, tooling, and math libraries. Thanks to AI, ChatHPC provides a more productive HPC ecosystem by boosting important tasks related to portability, parallelization, optimization, scalability, and instrumentation, among others. With relatively small datasets (on the order of KB), the AI assistants, which are created in a few minutes by using one node with two NVIDIA H100 GPUs and the ChatHPC library, can create new capabilities with Meta’s 7-billion parameter Code Llama base model to produce high-quality software with a level of trustworthiness of up to 90% higher than the 1.8-trillion parameter OpenAI ChatGPT-4o model for critical programming tasks in the HPC software stack.

Young, Aaron [ORNL] (ORCID:0000000254484667)↗

DOE OSTI2017

Scalable Failure Masking for Stencil Computations using Ghost Region Expansion and Cell to Rank Remapping

In order to achieve exascale systems, application resilience needs to be addressed. Some programming models, such as task-DAG (directed acyclic graphs) architectures, currently embed resilience features whereas traditional SPMD (single program, multiple data) and message-passing models do not. Since a large part of the community's code base follows the latter models, it is still required to take advantage of application characteristics to minimize the overheads of fault tolerance. To that end, this paper explores how recovering from hard process/node failures in a local manner is a natural approach for certain applications to obtain resilience at lower costs in faulty environments. In particular, this paper targets enabling online, semitransparent local recovery for stencil computations on current leadership-class systems as well as presents programming support and scalable runtime mechanisms. Also described and demonstrated in this paper is the effect of failure masking, which allows the effective reduction of impact on total time to solution due to multiple failures. Furthermore, we discuss, implement, and evaluate ghost region expansion and cell-to-rank remapping to increase the probability of failure masking. To conclude, this paper shows the integration of all aforementioned mechanisms with the S3D combustion simulation through an experimental demonstration (using the Titan system) of the ability to tolerate high failure rates (i.e., node failures every five seconds) with low overhead while sustaining performance at large scales. In addition, this demonstration also displays the failure masking probability increase resulting from the combination of both ghost region expansion and cell-to-rank remapping.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2018

Performing fully parallel constraint logic programming on a quantum annealer

A quantum annealer exploits quantum effects to solve a particular type of optimization problem. The advantage of this specialized hardware is that it effectively considers all possible solutions in parallel, thereby potentially outperforming classical computing systems. However, despite quantum annealers having recently become commercially available, there are relatively few high-level programming models that target these devices. In this article, we show how to compile a subset of Prolog enhanced with support for constraint logic programming into a two-local Ising-model Hamiltonian suitable for execution on a quantum annealer. In particular, we describe the series of transformations one can apply to convert constraint logic programs expressed in Prolog into an executable form that bears virtually no resemblance to a classical machine model yet that evaluates the specified constraints in a fully parallel manner. We evaluate our efforts on a 1,095-qubit D-Wave 2X quantum annealer and describe the approach's associated capabilities and shortcomings.

97 MATHEMATICS AND COMPUTING↗