Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “accelerated 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 1,441 records · Page 80
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Massively-parallel Lagrangian particle code and applications

Massively-parallel, distributed-memory algorithms for the Lagrangian particle hydrodynamic method (Samulyak et al., 2018) have been developed, verified, and implemented. The key component of parallel algorithms is a particle management module that includes a parallel construction of octree databases, dynamic adaptation and refinement of octrees, and particle migration between parallel subdomains. The particle management module is based on the p4est (parallel forest of k-trees) library. The massively-parallel Lagrangian particle code has been applied to a variety of fundamental science and applied problems. A summary of Lagrangian particle code applications to the injection of impurities into thermonuclear fusion devices and to the simulation of supersonic hydrogen jets in support of laser-plasma wakefield acceleration research has also been presented.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Delivering real-time multi-modal materials analysis with enterprise beamlines

Contemporary advancements in low-cost automation and computation, reduced barrier to entry in developing artificial intelligence/machine learning (AI/ML), and increased ability to represent complex materials in digital form have led to a number of accelerated materials discovery platforms. However, many of these approaches operate with completely rigid vertical integration in an isolated feedback loop using limited modalities. In order to make a substantial impact on discovering new energy materials, AI-driven experiments must operate collaboratively with each other and researchers and over multiple measurement modalities. Herein, we describe the potential for an “internet of things” approach to self-driving enterprise beamlines that merges core information technologies, robotics, and multi-modal AI. The approach will enable full utility of light sources, collaborate effectively with other remote materials acceleration platforms, and help stride toward the world’s energy future.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Off-Equilibrium Reactivity of Boron-Enriched Metal Diboride Surfaces in Electroreduction Conditions

Boron-based materials, featuring B-dependent reactivity and diverse phases, are emerging as promising catalyst systems. However, the catalytic mechanism on many borides remains poorly understood due to complex surface reconstructions under reaction conditions. Here, we investigate the MoB 2 surface in conditions of hydrogen evolution reaction in acidic media, using grand canonical global optimization, grand canonical density functional theory, ab initio molecular dynamics, free energy surface sampling, and an analytical model for electrochemical barrier evaluation. We propose a boron-enrichment strategy to tune the surface reactivity of the hexagonal face of MoB 2 . We reveal the dynamic nature of the B-enriched surface under H coverage and kinetic trapping of the system in the metastable regime with an extensive examination of the deactivation pathways. The metastable center B site on B-enriched surfaces, featuring buckled-up configuration and a usual relaxation effect, is found to be highly active toward HER via the Volmer–Heyrovsky mechanism. In conclusion, this work demonstrates how off-equilibrium behaviors can arise from the interplay between adsorbate coverage and surface reconstruction on a seemingly simple surface, and we present a theoretical framework and computational workflows to address these behaviors, along with other realistic complexities, in kinetics simulations.

Adsorption↗
DOE OSTI2022

Throughput-Oriented and Accuracy-Aware DNN Training with BFloat16 on GPU

Deep Neural Networks (DNNs) have transformed the field of artificial intelligence and achieved extraordinary success in many areas. The training of DNNs is commonly compute and memory-intensive, which has resulted in several optimizations in the training phase. Among them, reduced precision is a typical and widely used technique to accelerate DNN training and reduce memory requirements. However, applying a widely adopted reduced precision format such as Float16 to all involved operations in DNN training is not optimal as the use of Float16 in some operations can hurt model accuracy. Meanwhile, additional optimizations including loss scaling and autocast techniques can mitigate the accuracy loss but lead to inherent overhead and inadequate use of reduced precision. In this work, we leverage another reduced precision format, BFloat16, and introduce a throughput-oriented and accuracy-aware approach to maximize the performance potential of DNN training. Since the high throughput provided by BFloat16 format is accompanied by low precision of the floating-point representation, this approach achieves high throughput by using BFloat16 on all DNN operations and avoids the accuracy loss through a customized accuracy-aware normalization. Results show that our approach outperforms the state-of-the-art mixed-precision training by 1.21x on an NVIDIA A100 GPU.

Xie, Zhen↗
DOE OSTI2021

Spot Size Optimization of the Scorpius Accelerator

The Scorpius Linear Induction Accelerator (LIA) is being developed by the Advanced Sources and Diagnostics (ASD) Project and will complement other U1a capabilities by providing a multi-pulse, DARHT-class, flash-radiography capability. Commissioning activities are expected to end in Spring of 2026. All of the diagnostics discussed in this chapter are relevant to LIAs that generate high-current relativistic electron beams, and some diagnostics will also be relevant to other accelerators. The Scorpius Accelerator will be the world’s most advance LIA. Although significant technological advancements have been incorporated throughout the machine, many performance aspects of Scorpius will be similar to those of FXR and DARHT Axis-I and -II. These LIAs offer the same challenges, whether it is suppressing beam instabilities, improving diagnostic accuracy, validating computer simulations and beam tunes, or reducing beam-target interaction effects. However, the ultimate figure of merit is consistent between these LIAs, which is spot size and dose.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

Foundational Science to Accelerate Nuclear Energy Innovation [Brochure]

The foundational science gaps inhibiting the advancement of nuclear energy technologies are identified and tackled in five priority research opportunities. These opportunities pave the way to accelerate the development and ultimately the adoption of new nuclear energy systems. They include the fundamental aspects of ion-electron interactions; novel properties of next-generation coolants and solvents; interfacial dynamics, not only in solids, but in other aspects of nuclear reactors; novel operando and in-situ monitoring and sensing; and artificial intelligence to accelerate condensed phases discovery. Building on the foundation established by previous BES workshops, these opportunities encompass recent advances in fundamental knowledge and focus on the experimental and computational methods needed to resolve major technical challenges for nuclear energy technologies. Through developing fundamental scientific insight as well as pushing the frontiers of modeling complex systems and probing the operation of materials and chemical systems in extreme environments, research motivated by the priorities identified here will further develop the promise, potential, and utilization of nuclear energy for a clean energy future. The PROs are as follows: (1) Master complex electronic structures to tailor thermochemical reactivity, transport, and microstructural evolution; (2) Interrogate and direct the physics and chemistry underpinning next-generation coolants and solvents; (3) Elucidate and control the underlying physics and chemistry of interfaces in complex nuclear environments; (4) Bridge multi-fidelity multi-resolution experiments, computational modeling, and data science to control dynamic behavior; and (5) Harness artificial intelligence to design inherently resilient condensed phases.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Abstract for CRADA between National Energy Technology Laboratory and Mattiq, Inc.

To decarbonize the chemicals and fuels industry, we require new and innovative technologies that can leverage renewable feedstocks including renewable electricity and renewable carbon sources, such as CO 2 . State-of-the-art (SOTA) CO 2 utilization technologies that can produce renewable chemicals and fuels, such as the electrochemical reduction of CO 2 , are still significantly lacking in efficiency, and are therefore not cost-competitive with existing infrastructure. The key bottleneck to cost-competitive chemicals and fuels sourced from CO 2 and renewable electricity is the lack of any efficient catalyst material. The National Energy Technology Laboratory (NETL) and Mattiq will collaborate in the development of an efficient catalyst material that can effectively convert CO 2 into products of interest. Specifically, NETL will utilize high-performance computing to greatly reduce the number of potential materials to be investigated by Mattiq ultrahigh-throughput experimental catalyst discovery framework. This work is poised to rapidly accelerate the development of novel and efficient CO 2 reduction electrocatalysts that can bring CO 2 utilization closer to commercial viability.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

$\mathrm{SageNet}$: Fast Neural Network Emulation of the Stiff-amplified Gravitational Waves from Inflation

Accurate modeling of the inflationary gravitational waves (GWs) requires time-consuming, iterative numerical integrations of differential equations to take into account their backreaction on the expansion history. To improve computational efficiency while preserving accuracy, we present the Stiff-amplified Gravitational-wave Emulator Network (SageNet), a deep learning framework designed to replace conventional numerical solvers (code available at https://github.com/YifangLuo/SageNet). SageNet employs a long short-term memory architecture to emulate the present-day energy density spectrum of the inflationary GWs with possible stiff amplification, Ω GW (f). Trained on a data set of 25,689 numerically generated solutions, SageNet allows accurate reconstructions of Ω GW (f) and generalizes well to a wide range of cosmological parameters; 90.9% of the test emulations with randomly distributed parameters exhibit errors of under 4%. In addition, SageNet demonstrates its ability to learn and reproduce the artificial, adaptive sampling patterns in numerical calculations, which implement denser sampling of frequencies around changes in spectral indices in Ω GW (f). The dual capability of learning both physical and artificial features of the numerical GW spectra establishes SageNet as a robust alternative to exact numerical methods. Finally, our benchmark tests show that SageNet reduces the computation time from tens of seconds to milliseconds, achieving a speedup of ∼10 4 times over standard CPU-based numerical solvers with the potential for further acceleration on GPU hardware. These capabilities make SageNet a powerful tool for accelerating Bayesian inference procedures for extended cosmological models. In a broad sense, the SageNet framework offers a fast, accurate, and generalizable solution to modeling cosmological observables whose theoretical predictions demand costly differential equation solvers.

Astronomy data modeling↗
DOE OSTI2020

Monitor support on accelerated processing device

A technique for implementing synchronization monitors on an accelerated processing device (“APD”) is provided. Work on an APD includes workgroups that include one or more wavefronts. All wavefronts of a workgroup execute on a single compute unit. A monitor is a synchronization construct that allows workgroups to stall until a particular condition is met. Responsive to all wavefronts of a workgroup executing a wait instruction, the monitor coordinator records the workgroup in an “entry queue.” The workgroup begins saving its state to a general APD memory and, when such saving is complete, the monitor coordinator moves the workgroup to a “condition queue.” When the condition specified by the wait instruction is met, the monitor coordinator moves the workgroup to a “ready queue,” and, when sufficient resources are available on a compute unit, the APD schedules the ready workgroup for execution on a compute unit.

42 ENGINEERING↗
DOE OSTI2020

OpenCGRA: An Open-Source Unified Framework for Modeling,Testing, and Evaluating CGRAs

Coarse-grained reconfigurable arrays (CGRAs),loosely defined as arrays of functional units (e.g, adder, sub-tractor, multiplier, divider, or larger multi-operation units, butsmaller than a general-purpose core) interconnected through aNetwork-on-Chip, provide higher flexibility than domain-specificASIC accelerators while offering increased hardware efficiencywith respect to fine-grained reconfigurable devices, such as FieldProgrammable Gate Arrays (FPGAs). The fast evolving fieldsof machine learning and edge computing, which are seeing acontinuous flow of novel algorithms and larger models, makeCGRAs ideal target architectures to allow domain specializationwithout loosing too much generality. They also generally offerquicker and more effective reconfigurability than FPGAs, po-tentially allowing adaptation during actual algorithm execution,and implement a dataflow programming paradigm that adaptswell to these emerging workloads. Designing and generating aCGRA, however, still requires to define the type and number ofthe specific functional units, implement their interconnect andthe network topology, and perform its simulation and validation,given a variety of workloads of interest.In this paper, we propose OpenCGRA, a Python-based unifiedframework that integrates generation, modeling, testing and eval-uation for CGRAs. OpenCGRA is the first open-source integratedframework able to support the full top-to-bottom design flow forspecializing and implementing CGRAs: modeling at different ab-straction levels (functional level, cycle level, register-transfer level),generation, simulation, testing at different granularities (unit test-ing, integration testing, property-based testing), and characteriza-tion (area, power, and timing). OpenCGRAs will be made availableon GitHub.

CGRA, synthesis↗
DOE OSTI2020

Modular autopilot design and development featuring bayesian non-parametric adaptive control

According to an embodiment, there is provided an onboard integrated computational system for an unmanned aircraft system (“Stabilis” autopilot). This is an integrated suite of hardware, software, and data-to-decisions services that are designed to meet the needs of business and research developers of UAS. Stabilis is designed to accelerate the development of any UAS platform and avionics system; it does so with hardware modularity and software adaptation. The Stabilis offers multiple technological advantages technological advantages including: Plug-and-adapt functionality; Data-to-decisions capability; and, On board parallelization capability.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Data Cards for Standardized Metadata Across DOE-Aligned Data Initiatives: Toward Transparent, Interoperable, and Governed Dataset Documentation

As data-intensive research, advanced computing, and artificial intelligence become increasingly central to scientific and operational workflows, the need for consistent, transparent, and machine-actionable documentation has grown correspondingly. Multiple DOE-aligned communities—including Office of Science, Genesis Mission, American Science Cloud (AmSC), National Nuclear Security Administration (NNSA) stewardship and governance, and related cross-laboratory collaborations—have independently developed metadata practices to support discovery, access, reuse, repository deposit, and compliance.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2021

Heating and acceleration of ions with Kappa distribution functions by low‐frequency Alfvén wave

Abstract Heating and acceleration of ions with Kappa distribution functions (with parameter ) in low‐beta plasmas, by a low‐frequency Alfvén wave, is investigated using test‐particle simulations, yielding interesting new results. As long as the Alfvén wave amplitude is sufficiently large, the computed net heating energy of ions becomes independent of the wave frequency and amplitude, always approaching the same value of . The eventual energy of ions is dictated only by the initial ion energy and the ratio of the magnetic field energy density to the plasma density. The heating effect of the Kappa ions increases with . During the heating process, the ions are picked up by the Alfvén wave and pitch angle scattered, forming a quasi‐isotropic spherical shell velocity distribution. The Kappa ions are accelerated in the parallel direction, reaching a bulk flow speed roughly equal to the local Alfvén speed. Higher ‐value in the initial Kappa distribution leads to faster saturation. The above results may explain certain features of the ion heating and acceleration in the solar wind and corona.

Li, Kehua↗
DOE OSTI2022

NekRS, a GPU-accelerated spectral element Navier–Stokes solver

The development of NekRS, a GPU-oriented thermal-fluids simulation code based on the spectral element method (SEM) is described. For performance portability, the code is based on the open concurrent compute abstraction and leverages scalable developments in the SEM code Nek5000 and in libParanumal, which is a library of high-performance kernels for high-order discretizations and PDE-based miniapps. Critical performance sections of the Navier–Stokes time advancement are addressed. Performance results on several platforms are presented here, including scaling to 27,648 V100s on OLCF Summit, for calculations of up to 60B gridpoints.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Accelerating Binarized Neural Networks via Bit-Tensor-Cores in Turing GPUs

Despite foreseeing tremendous speedups over conventional deep neural networks, the performance advantage of binarized neural networks (BNNs) has merely been showcased on general-purpose processors such as CPUs and GPUs. In fact, due to being unable to leverage bit-level-parallelism with a word-based architecture, GPUs have been criticized for extremely low utilization (1%) when executing BNNs. Consequently, the latest tensorcores in NVIDIA Turing GPUs start to experimentally support bit computation. In this work, we look into this brand new bit computation capability and characterize its unique features. We show that the stride of memory access can significantly affect performance delivery and a data-format co-design is highly desired to support the tensorcores for achieving superior performance than existing software solutions without tensorcores. We realize the tensorcore-accelerated BNN design, particularly the major functions for fully-connect and convolution layers — bit matrix multiplication and bit convolution. Evaluations on two NVIDIA Turing GPUs show that, with ResNet-18, our BTC-BNN design can process ImageNet at a rate of 5.6K images per second, 77% faster than state-of-the-art. Our BNN approach is released on https://github.com/pnnl/TCBNN.

Li, Ang↗
DOE OSTI2022

Algorithm 1028: VTMOP: Solver for Blackbox Multiobjective Optimization Problems

VTMOP is a Fortran 2008 software package containing two Fortran modules for solving computationally expensive bound-constrained blackbox multiobjective optimization problems. VTMOP implements the algorithm of [32], which handles two or more objectives, does not require any derivatives, and produces well-distributed points over the Pareto front. The first module contains a general framework for solving multiobjective optimization problems by combining response surface methodology, trust region methodology, and an adaptive weighting scheme. The second module features a driver subroutine that implements this framework when the objective functions can be wrapped as a Fortran subroutine. Lastly, support is provided for both serial and parallel execution paradigms, and VTMOP is demonstrated on several test problems as well as one real-world problem in the area of particle accelerator optimization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Developing Multi-Gene CRISPRa/I Programs to Accelerate DBTL Cycles in ABF Hosts Engineered for Chemical Production (CRADA 468)

Bacterial metabolism is comprised of large and complex gene networks that can produce valuable chemical products. Sophisticated organism engineering efforts are required to optimize production of high-value compounds from these networks. In principle, synthetic multi-gene transcriptional programs could be constructed to reengineer these networks for efficient industrial chemical production. In practice, however, our incomplete ability to understand and model the underlying networks, combined with our limited ability to predictably control the expression of multiple genes makes achieving this goal difficult. To overcome these challenges, we will combine new CRISPR-Cas multi-gene expression programs with computational modeling, machine learning, and multi-omics data to enhance the efficacy of design-build-test-learn (DBTL) cycles. For industrially promising microorganisms in early stages of development, creating technologies for rapidly engineering complex multi-gene programs could be transformative for accelerating data- and model-driven strain design. New CRISPR-Cas tools allow programmable gene activation (CRISPRa) or repression (CRISPRi) at multiple genes simultaneously, using the catalytically inactive Cas9 protein (dCas9) with guide RNAs that recognize DNA targets through predictable Watson-Crick base pairing. To enable accelerated DBTL cycles, we will combine these technologies with advanced Agile BioFoundry (ABF) capabilities for multi-omics data collection and machine learning. We will demonstrate the immediate applicability of these tools by rapidly improving the production of an industrial aromatic in multiple ABF organisms. We recently identified and optimized new transcriptional activators that can be linked to programmable CRISPR-Cas DNA binding domains to activate gene expression in E. coli. We can now use these CRISPRa tools as generalizable trans-acting regulators for combinatorial multi-gene expression tuning that can be easily transferred to new pathways and networks without additional genome engineering. We anticipate these tools will also transfer to new hosts. We have recently found that CRISPRa systems developed in E. coli can be readily ported to Pseudomonas putida, suggesting that multi-gene CRISPRa/i programs for diverse ABF organisms may be within reach.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

LigninGraphs: lignin structure determination with multiscale graph modeling

Lignin is an aromatic biopolymer found in ubiquitous sources of woody biomass. Designing and optimizing lignin valorization processes requires a fundamental understanding of lignin structures. Experimental characterization techniques, such as 2D-heteronuclear single quantum coherence (HSQC) nuclear magnetic resonance (NMR) spectra, could elucidate the global properties of the polymer molecules. Computer models could extend the resolution of experiments by representing structures at the molecular and atomistic scales. We introduce a graph-based multiscale modeling framework for lignin structure generation and visualization. The framework employs accelerated rejection-free polymerization and hierarchical Metropolis Monte Carlo optimization algorithms. We obtain structure libraries for various lignin feedstocks based on literature and new experimental NMR data for poplar wood, pinewood, and herbaceous lignin. The framework could guide researchers towards feasible lignin structures, efficient space exploration, and future kinetics modeling. Its software implementation in Python, LigninGraphs, is open-source and available on GitHub.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗