Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “heterogeneous 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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
DOE OSTI2012

Dual compile strategy for parallel heterogeneous execution

The purpose of the Dual Compile Strategy is to increase our trust in the Compute Engine during its execution of instructions. This is accomplished by introducing a heterogeneous Monitor Engine that checks the execution of the Compute Engine. This leads to the production of a second and custom set of instructions designed for monitoring the execution of the Compute Engine at runtime. This use of multiple engines differs from redundancy in that one engine is working on the application while the other engine is monitoring and checking in parallel instead of both applications (and engines) performing the same work at the same time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

Integrating Asynchronous Task Parallelism with OpenSHMEM, In: OpenSHMEM 2016: OpenSHMEM and Related Technologies. Enhancing OpenSHMEM for Hybrid Environments

Partitioned Global Address Space (PGAS) programming models combine shared and distributed memory features, and provide a foundation for high-productivity parallel programming using lightweight one-sided communications. The OpenSHMEM programming interface has recently begun gaining popularity as a lightweight library-based approach for developing PGAS applications, in part through its use of a symmetric heap to realize more efficient implementations of global pointers than in other PGAS systems. However, current approaches to hybrid inter-node and intra-node parallel programming in OpenSHMEM rely on the use of multithreaded programming models (e.g., pthreads, OpenMP) that harness intra-node parallelism but are opaque to the OpenSHMEM runtime. This OpenSHMEM+X approach can encounter performance challenges such as bottlenecks on shared resources, long pause times due to load imbalances, and poor data locality. Furthermore, OpenSHMEM+X requires the expertise of hero-level programmers, compared to the use of just OpenSHMEM. All of these are hard challenges to mitigate with incremental changes. This situation will worsen as computing nodes increase their use of accelerators and heterogeneous memories.

Computer Science↗
DOE OSTI2014

A Nth-order linear algorithm for extracting diffuse correlation spectroscopy blood flow indices in heterogeneous tissues

Conventional semi-infinite analytical solutions of correlation diffusion equation may lead to errors when calculating blood flow index (BFI) from diffuse correlation spectroscopy (DCS) measurements in tissues with irregular geometries. Very recently, we created an algorithm integrating a Nth-order linear model of autocorrelation function with the Monte Carlo simulation of photon migrations in homogenous tissues with arbitrary geometries for extraction of BFI (i.e., αD{sub B}). The purpose of this study is to extend the capability of the Nth-order linear algorithm for extracting BFI in heterogeneous tissues with arbitrary geometries. The previous linear algorithm was modified to extract BFIs in different types of tissues simultaneously through utilizing DCS data at multiple source-detector separations. We compared the proposed linear algorithm with the semi-infinite homogenous solution in a computer model of adult head with heterogeneous tissue layers of scalp, skull, cerebrospinal fluid, and brain. To test the capability of the linear algorithm for extracting relative changes of cerebral blood flow (rCBF) in deep brain, we assigned ten levels of αD{sub B} in the brain layer with a step decrement of 10% while maintaining αD{sub B} values constant in other layers. Simulation results demonstrate the accuracy (errors < 3%) of high-order (N ≥ 5) linear algorithm in extracting BFIs in different tissue layers and rCBF in deep brain. By contrast, the semi-infinite homogenous solution resulted in substantial errors in rCBF (34.5% ≤ errors ≤ 60.2%) and BFIs in different layers. The Nth-order linear model simplifies data analysis, thus allowing for online data processing and displaying. Future study will test this linear algorithm in heterogeneous tissues with different levels of blood flow variations and noises.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2022

pnnl/mcl-runtime

The Minos Computing Library (MCL) is a task-based programming language and runtime for extremely heterogeneous systems. MCL facilitates writing program for heterogeneous devices and porting applications across different systems and devices. MCL supports asynchronous execution of computing tasks on all available heterogeneous devices, including GPUs, FGPAs, fixed-point accelerators, and AI accelerators. MCL provides a high-level programming interface and automatically and autonomously performs resource management, load balancing, and locality-aware scheduling.

Central, PNNL Developer↗
NASA NTRS2002

Graph Partitioning for Parallel Applications in Heterogeneous Grid Environments

The problem of partitioning irregular graphs and meshes for parallel computations on homogeneous systems has been extensively studied. However, these partitioning schemes fail when the target system architecture exhibits heterogeneity in resource characteristics. With the emergence of technologies such as the Grid, it is imperative to study the partitioning problem taking into consideration the differing capabilities of such distributed heterogeneous systems. In our model, the heterogeneous system consists of processors with varying processing power and an underlying non-uniform communication network. We present in this paper a novel multilevel partitioning scheme for irregular graphs and meshes, that takes into account issues pertinent to Grid computing environments. Our partitioning algorithm, called MiniMax, generates and maps partitions onto a heterogeneous system with the objective of minimizing the maximum execution time of the parallel distributed application. For experimental performance study, we have considered both a realistic mesh problem from NASA as well as synthetic workloads. Simulation results demonstrate that MiniMax generates high quality partitions for various classes of applications targeted for parallel execution in a distributed heterogeneous environment.

Bisws, Rupak↗
DOE OSTI2025

Micrometer: Micromechanics transformer for predicting full field mechanical responses of heterogeneous materials

Predicting mechanical responses of heterogeneous materials across scales remains a significant challenge. Traditional computational methods often struggle with complex and multiscale nature of these materials, limiting their effectiveness in real-world applications. Here, in this paper, we introduce Micrometer, a vision transformer based deep learning model designed to predict full field mechanical responses of heterogeneous materials, bridging the gap between computer vision and solid mechanics problems. We show that Micrometer, trained on a large-scale high-resolution dataset of 2D fiber-reinforced composites, can achieve state-of-the-art performance in predicting microscale strain fields across a wide range of material properties and loading conditions. Our model demonstrates accuracy and computational efficiency in applications such as computational homogenization and multiscale modeling, reducing computational time by up to two orders of magnitude compared to conventional numerical solvers while maintaining less than 1 % errors in predicting macroscale stress fields. Furthermore, we showcase Micrometer’s adaptability through transfer learning experiments on new materials with limited data, highlighting its potential to tackle diverse scenarios in computational solid mechanics. These results represent a significant step towards AI-driven innovation in materials science, addressing the limitations of traditional numerical methods and paving the way for more efficient simulations of heterogeneous materials across various industrial applications.

Composite materials↗
DOE OSTI2017

Modeling and Simulation of High Dimensional Stochastic Multiscale PDE Systems at the Exascale

The thrust of the proposal was to exploit modern data-mining tools in a way that will create a systematic, computer-assisted approach to the representation of random media -- and also to the representation of the solutions of an array of important physicochemical processes that take place in/on such media. A parsimonious representation/parametrization of the random media links directly (via uncertainty quantification tools) to good sampling of the distribution of random media realizations. It also links directly to modern multiscale computational algorithms (like the equation-free approach that has been developed in our group) and plays a crucial role in accelerating the scientific computation of solutions of nonlinear PDE models (deterministic or stochastic) in such media – both solutions in particular realizations of the random media, and estimation of the statistics of the solutions over multiple realizations (e.g. expectations).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

A-SST Initial Specification

The U.S. Army Research Office (ARO), in partnership with IARPA, are investigating innovative, efficient, and scalable computer architectures that are capable of executing next-generation large scale data-analytic applications. These applications are increasingly sparse, unstructured, non-local, and heterogeneous. Under the Advanced Graphic Intelligence Logical computing Environment (AGILE) program, Performer teams will be asked to design computer architectures to meet the future needs of the DoD and the Intelligence Community (IC). This design effort will require flexible, scalable, and detailed simulation to assess the performance, efficiency, and validity of their designs. To support AGILE, Sandia National Labs will be providing the AGILE-enhanced Structural Simulation Toolkit (A-SST). This toolkit is a computer architecture simulation framework designed to support fast, parallel, and multi-scale simulation of novel architectures. This document describes the A-SST framework, some of its library of simulation models, and how it may be used by AGILE Performers.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

Implications of Grain-Scale Mineralogical Heterogeneity for Radionuclide Transport in Fractured Media

The geological disposal of nuclear waste is based on the multi-barrier concept, comprising various engineered and natural barriers, to confine the radioactive waste and isolate it from the biosphere. Some of the planned repositories for high-level nuclear waste will be hosted in fractured crystalline rock formations. The potential of these formations to act as natural transport barriers is related to two coupled processes: diffusion into the rock matrix and sorption onto the mineral surfaces available in the rock matrix. Different in situ and laboratory experiments have pointed out the ubiquitous heterogeneous nature of the rock matrix: mineral surfaces and pore space are distributed in complex microstructures and their distribution is far from being homogeneous (as typically assumed by Darcy-scale coarse reactive transport models). We use a synthetically generated fracture–matrix system to assess the implications of grain-scale physical and mineralogical heterogeneity on cesium transport and retention. The resulting grain-scale reactive transport model is solved using high-performance computing technologies, and the results are compared with those derived from two alternative models, denoted as upscaled models, where mineral abundance is averaged over the matrix volume. In the grain-scale model, the penetration of cesium into the matrix is faster and the penetration front is uneven and finger-shaped. The analysis of the cesium breakthrough curves computed at two different points in the fracture shows that the upscaled models provide later first-arrival time estimates compared to the grain-scale model. The breakthrough curves computed with the three models converge at late times. These results suggest that spatially averaged upscaled parameters of sorption site distribution can be used to predict the late-time behavior of breakthrough curves but could be inadequate to simulate the early behavior.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
NASA NTRS1994

Stratospheric aerosol acidity, density, and refractive index deduced from SAGE 2 and NMC temperature data

Water vapor concentrations obtained by the Stratospheric Aerosol and Gas Experiment 2 (SAGE 2) and collocated temperatures provided by the National Meteorological Center (NMC) from 1986 to 1990 are used to deduce seasonally and zonally averaged acidity, density, and refractive index of stratospheric aerosols. It is found that the weight percentage of sulfuric acid in the aerosols increases from about 60 just above the tropopause to about 86 at 35 km. The density increases from about 1.55 to 1.85 g/cu cm between the same altitude limits. Some seasonal variations of composition and density are evident at high latitudes. The refractive indices at 1.02, 0.694, and 0.532 micrometers increase, respectively, from about 1.425, 1.430, and 1.435 just above the tropopause to about 1.445, 1.455, and 1.458 at altitudes above 27 km, depending on the season and latitude. The aerosol properties presented can be used in models to study the effectiveness of heterogeneous chemistry, the mass loading of stratospheric aerosols, and the extinction and backscatter of aerosols at different wavelengths. Computed aerosol surface areas, rate coefficients for the heterogeneous reaction ClONO2 + H2O yields HOCl + HNO3 and aerosol mass concentrations before and after the Pinatubo eruption in June 1991 are shown as sample applications.

Yue, G. K.↗
DOE OSTI2022

Development and performance of a HemeLB GPU code for human-scale blood flow simulation

In recent years, it has become increasingly common for high performance computers (HPC) to possess some level of heterogeneous architecture - typically in the form of GPU accelerators. In some machines these are isolated within a dedicated partition, whilst in others they are integral to all compute nodes - often with multiple GPUs per node - and provide the majority of a machine's compute performance. In light of this trend, it is becoming essential that codes deployed on HPC are updated to execute on accelerator hardware. Here, in this paper, we introduce a GPU implementation of the 3D blood flow simulation code HemeLB that has been developed using CUDA C++. We demonstrate how taking advantage of NVIDIA GPU hardware can achieve significant performance improvements compared to the equivalent CPU only code on which it has been built whilst retaining the excellent strong scaling characteristics that have been repeatedly demonstrated by the CPU version. With HPC positioned on the brink of the exascale era, we use HemeLB as a motivation to provide a discussion on some of the challenges that many users will face when deploying their own applications on upcoming exascale machines.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Integrated Experimental and Computational K-Edge X-ray Absorption Near-Edge Structure Analysis of Vanadium Catalysts

X-ray Absorption Near-Edge Structure (XANES) spectroscopy is a powerful tool to reveal key structural and electronic features of isolated catalytic sites, yet insights into molecular structure and more detailed orbital analysis through a combination of experimental and computed XANES analysis are necessary for accurate interpretation of the spectra, especially when significant heterogeneity exits among the catalytic sites. Herein, we present an integrated computational and experimental strategy to determine both primary and secondary bonding interactions within the XANES pre-edge region for organovanadium complexes, which was developed using a series of well-defined molecular vanadium complexes and then applied to the characterization of a supported organovanadium olefin hydrogenation catalyst. Time-dependent density functional theory is used to predict the energy of pre-edge XANES features for a series of vanadium complexes with a variety of oxidation states and local coordination environments. Further, a calibration scheme incorporating different density functionals and basis sets is established, resulting in an optimized scheme that accurately predicts pre-edge energies with a mean absolute error of 0.40 eV. Second-shell coordination (e.g., V---V) effects within XANES are identified through the analysis of the computed dominant orbital contributions for multi-vanadium complexes. Orbital analysis also provided confirmation that the vanadium-hydride formation combined with the heterogeneity of the catalytic active species in ole-fin hydrogenation caused the energy shift and broadening of the pre-edge peak after hydrogen treatment of the silica-supported organovanadium pre-catalyst. This work further elucidates computational XANES simulations and techniques potentially guiding characterization in surface organometallic chemistry.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Effect of Collective Dynamics and Anharmonicity on Entropy in Heterogenous Catalysis: Building the Case for Advanced Molecular Simulations

In this paper, we present a perspective on the computational determination of entropy and its effects and consequences on heterogeneous catalysis. Special attention is paid to the role of anharmonicity and the deviations from the standard harmonic oscillator approximations which can fail to provide a reliable assessment of entropy. To address these challenges, advanced methodologies are needed that can explicitly account for these thermodynamic drivers through the appropriate statistical sampling of reactive free energy surfaces. We discuss where anharmonicity should be expected, where it has been observed from a theoretical perspective, and the methods currently employed to address it. We concentrate on three types of systems where we have observed major, nonnegligible anharmonic effects: (1) supported nanoparticles, where the migration of metal atoms, complexes, and entire clusters exhibit anharmonic behavior in their dynamic motion; (2) porous solids where confinement effects distort potential energy surfaces and hinder molecular motions resulting in large entropic terms; and (3) solid/liquid interfaces, where interactions between solvent molecules and adsorbed species can result in large solvent organization free energy and unique reactivity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Performance Potential of Mixed Data Management Modes for Heterogeneous Memory Systems

Many high-performance systems now include different types of memory devices within the same compute platform to meet strict performance and cost constraints. Such heterogeneous memory systems often include an upper-level tier with better performance, but limited capacity, and lower-level tiers with higher capacity, but less bandwidth and longer latencies for reads and writes. To utilize the different memory layers efficiently, current systems rely on hardware-directed, memory -side caching or they provide facilities in the operating system (OS) that allow applications to make their own data-tier assignments. Since these data management options each come with their own set of trade-offs, many systems also include mixed data management configurations that allow applications to employ hardware- and software-directed management simultaneously, but for different portions of their address space. Despite the opportunity to address limitations of stand-alone data management options, such mixed management modes are under-utilized in practice, and have not been evaluated in prior studies of complex memory hardware. In this work, we develop custom program profiling, configurations, and policies to study the potential of mixed data management modes to outperform hardware- or software-based management schemes alone. Our experiments, conducted on an Intel ® Knights Landing platform with high-bandwidth memory, demonstrate that the mixed data management mode achieves the same or better performance than the best stand-alone option for five memory intensive benchmark applications (run separately and in isolation), resulting in an average speedup compared to the best stand-alone policy of over 10 %, on average.

Effler, Chad↗
DOE OSTI2019

Big data analytics in smart grids: state-of-the-art, challenges, opportunities, and future directions

Big data has a potential to unlock novel groundbreaking opportunities in the power grid sector that enhances a multitude of technical, social, and economic gains. The currently untapped potential of applying the science of big data for better planning and operation of the power grid is a very challenging task and needs significant efforts all-around. As power grid technologies evolve in conjunction with measurement and communication technologies, this results in unprecedented amount of heterogeneous big data sets from diverse sources. In particular, computational complexity, data security, and operational integration of big data into utility decision frameworks are the key challenges to transform the heterogeneous large dataset into actionable outcomes. Moreover, due to the complex nature of power grids along with the need to balance power in real time, seamless integration of big data into utility operations is very critical. In this context, big data analytics combined with grid visualization can lead to better situational awareness and predictive decisions. This paper presents a comprehensive state-of-the-art review of big data analytics and its applications in power grids, and also identifies challenges and opportunities from utility, industry, and research perspectives. The paper analyzes research gaps and presents insights on future research directions to integrate big data analytics into electric utility decision framework. Detailed information for utilities looking to apply big data analytics and details insights on how utilities can enhance revenue streams and bring disruptive innovation in the industry are discussed. More importantly, general guidelines for utilities to make the right investment in the adoption of big data analytics by unveiling interdependencies among critical infrastructures and operations are also provided.

13 HYDRO ENERGY↗
DOE OSTI2024

IRIS-GNN: Leveraging Graph Neural Networks for Scheduling on Truly Heterogeneous Runtime Systems

The diversity of accelerators in computer systems poses significant challenges for software developers, such as managing vendor-specific compiler toolchains, code fragmentation requiring different kernel implementations, and performance portability issues. To address these, the Intelligent Runtime System (IRIS) was developed. IRIS works across various systems, from smartphones to supercomputers, enabling automatic performance scaling based on available accelerators. It introduces abstract tasks for seamless execution transitions between accelerators while ensuring memory consistency and task dependencies. Although IRIS simplifies system details, optimal dynamic scheduling still requires user input to understand workload structures. To address this, we introduce a new scheduling policy for IRIS, termed IRIS-GNN, which is the first IRIS hybrid policy that operates in conjunction with the dynamic policies. This policy employs a Graph-Neural Network (GNN) to conduct Graph Classification of any task graphs submitted to IRIS. This GNN analyzes the structure and attributes of the task graph, categorizing it as either locality, concurrency, or mixed. This classification subsequently guides the selection of the dynamic policy used by IRIS. We provide a comparison of the performance of IRIS-GNN against the complete spectrum of IRIS’s dynamic policies, assess the overhead introduced by the GNN within this scheduling framework, and ultimately explore its practical application in real-world scenarios.

Johnston, Beau↗
NASA NTRSDate not supplied

A Partitioned -Task Parallel Implementation of the NASA Multiscale Analysis Tool for High Performance Computing

The NASA Multiscale Analysis Tool (NASMAT) is a “plug and play” software package that allows users to conduct massively multiscale modeling of hierarchical and nonlinear materials. This work extends the scalability and improves the High Performance Computing friendliness of NASMAT by adopting a Partitioned Task-Parallel approach. Interoperability of NASMAT with external software is enhanced through preCICE, a open source library for multiphysics coupling in a partitioned manner. Enhancement through preCICE allows for easy integration of NASMAT to other macro solvers and dissociates the parallelization strategy adopted within NASMAT from the macro solver. The task-parallel framework based on Master-Worker approach is implemented as the parallelization scheme. The scheme accounts for hierarchy of multiple scales (task-dependence) and heterogeneous nature (dynamic load balancing) of computations. The applicability and scalability of the framework will be evaluated by analyzing large scale engineering problems through massively multiscale methods.

NASMAT↗