SEARCH · Engineering Papers

Results for “computer architecture”

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 1,549 records · Page 86

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Characterizing the performance of node-aware strategies for irregular point-to-point communication on heterogeneous architectures

Supercomputer architectures are trending toward higher computational throughput due to the inclusion of heterogeneous compute nodes. These multi-GPU nodes increase on-node computational efficiency, while also increasing the amount of data to be communicated and the number of potential data flow paths. In this work, we characterize the performance of irregular point-to-point communication with MPI on heterogeneous compute environments through performance modeling, demonstrating the limitations of standard communication strategies for both device-aware and staging-through-host communication techniques. Presented models suggest staging communicated data through host processes then using node-aware communication strategies for high inter-node message counts. Notably, the models also predict that node-aware communication utilizing all available CPU cores to communicate inter-node data leads to the most performant strategy when communicating with a high number of nodes. Furthermore, model validation is provided via a case study of irregular point-to-point communication patterns in distributed sparse matrix–vector products. Importantly, we include a discussion on the implications model predictions have on communication strategy design for emerging supercomputer architectures.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2019

Data and Thread Placement in NUMA Architectures: A Statistical Learning Approach

Nowadays, NUMA architectures are common in compute-intensive systems. Achieving high performance for multi-threaded application requires both a careful placement of threads on computing units and a thorough allocation of data in memory. Finding such a placement is a hard problem to solve, because performance depends on complex interactions in several layers of the memory hierarchy. In this paper we propose a black-box approach to decide if an application execution time can be impacted by the placement of its threads and data, and in such a case, to choose the best placement strategy to adopt. We show that it is possible to reach near-optimal placement policy selection. Furthermore, solutions work across several recent processor architectures and decisions can be taken with a single run of low overhead profiling.

data↗

NASA NTRS1976

Fluid dynamics applications of the Illiac IV computer

The Illiac IV is a parallel-structure computer with computing power an order of magnitude greater than that of conventional computers. It can be used for experimental tasks in fluid dynamics which can be simulated more economically, for simulating flows that cannot be studied by experiment, and for combining computer and experimental simulations. The architecture of Illiac IV is described, and the use of its parallel operation is demonstrated on the example of its solution of the one-dimensional wave equation. For fluid dynamics problems, a special FORTRAN-like vector programming language was devised, called CFD language. Two applications are described in detail: (1) the determination of the flowfield around the space shuttle, and (2) the computation of transonic turbulent separated flow past a thick biconvex airfoil.

Maccormack, R. W.↗

NASA NTRSDate not supplied

Performance and Portability of a Linear Solver Across Emerging Architectures

A linear solver algorithm used by a large-scale unstructured-grid computational fluid dynamics application is examined for a broad range of familiar and emerging architectures. Efficient implementation of a linear solver is challenging on recent CPUs offering vector architectures. Vector loads and stores are essential to effectively utilize available memory bandwidth on CPUs, and maintaining performance across different CPUs can be difficult in the face of varying vector lengths offered by each. A similar challenge occurs on GPU architectures, where it is essential to have coalesced memory accesses to utilize memory bandwidth effectively. In this work, we demonstrate that restructuring a computation, and possibly data layout, with regard to architecture is essential to achieve optimal performance by establishing a performance benchmark for each target architecture in a low level language such as vector intrinsics or CUDA. In doing so, we demonstrate how a linear solver kernel can be mapped to Intel® Xeon™ and Xeon Phi™, Marvell® ThunderX2®, NEC® SX-Aurora™ TSUBASA Vector Engine, and NVIDIA® and AMD® GPUs. We further demonstrate that the required code restructuring can be achieved in higher level programming environments such as OpenACC, OCCA, and Intel® OneAPI™/SYCL, and that each generally results in optimal performance on the target architecture. Relative performance metrics for all implementations are shown, and subjective ratings for ease of implementation and optimization are suggested.

Programming models↗

NASA NTRS1997

Parallel Proximity Detection for Computer Simulation

The present invention discloses a system for performing proximity detection in computer simulations on parallel processing architectures utilizing a distribution list which includes movers and sensor coverages which check in and out of grids. Each mover maintains a list of sensors that detect the mover's motion as the mover and sensor coverages check in and out of the grids. Fuzzy grids are includes by fuzzy resolution parameters to allow movers and sensor coverages to check in and out of grids without computing exact grid crossings. The movers check in and out of grids while moving sensors periodically inform the grids of their coverage. In addition, a lookahead function is also included for providing a generalized capability without making any limiting assumptions about the particular application to which it is applied. The lookahead function is initiated so that risk-free synchronization strategies never roll back grid events. The lookahead function adds fixed delays as events are scheduled for objects on other nodes.

Steinman, Jeffrey S.↗

NASA NTRS1998

Parallel Proximity Detection for Computer Simulations

The present invention discloses a system for performing proximity detection in computer simulations on parallel processing architectures utilizing a distribution list which includes movers and sensor coverages which check in and out of grids. Each mover maintains a list of sensors that detect the mover's motion as the mover and sensor coverages check in and out of the grids. Fuzzy grids are included by fuzzy resolution parameters to allow movers and sensor coverages to check in and out of grids without computing exact grid crossings. The movers check in and out of grids while moving sensors periodically inform the grids of their coverage. In addition, a lookahead function is also included for providing a generalized capability without making any limiting assumptions about the particular application to which it is applied. The lookahead function is initiated so that risk-free synchronization strategies never roll back grid events. The lookahead function adds fixed delays as events are scheduled for objects on other nodes.

Steinman, Jeffrey S.↗

DOE OSTI2022

Development of a Cloud-based Application to Enable a Scalable Risk-informed Predictive Maintenance Strategy at Nuclear Power Plants

Light-water reactor operations and maintenance (O&M) costs are prohibitively high, thus contributing to the premature decommissioning of nuclear power plants (NPPs). This is partly due to how the equipment is monitored. In recent years, cloud computing has emerged as a dominant technology by virtue of its low costs, computing and storage adaptability, and ability to host applications over numerous types of virtual infrastructures. Cloud computing can be a cost-effective alternative to onsite storage and diagnostics. This paper conducts a techno-economic assessment of a provisional cloud deployment architecture for a NPP predictive monitoring (PdM) system. The cloud-based monitoring system would enable maintenance and diagnostics (M&D) analysts and other authorized plant users to remotely monitor equipment functionality so as to enable PdM practices and early detection of faults. The Microsoft Azure cloud platform is included in the proposed cloud architecture to provide data processing and storage, sensor device networking, and database management; however, this analysis could be extended to other cloud computing service providers as well. For the techno-economic assessment, technical feasibility is measured in terms of network performance metrics such as response time, latency, and throughput, whereas economic feasibility is measured in terms of operational costs and capital expenditures. Finally, this report covers certain regulatory and security aspects that may concern licensees looking to implement cloud computing. The report focuses on the integration of sensor database storage, the application of cloud resources to PdM, and the identification of technological and economic hurdles associated with moving to a cloud-computing-based architecture.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2015

Electronic structure and photovoltaic application of BiI{sub 3}

Rapid recent improvement in photovoltaic efficiency in hybrid lead halide perovskite materials has provided the impetus for understanding other, related main-group halide systems. Here, we show that the closely related but less toxic bismuth iodide BiI{sub 3} can show promising optoelectronic properties. Layered binary BiI{sub 3} is used here as the active layer in planar solar cell architectures (efficiency approximately 0.3%). Experimental and computational studies of absolute band positions of BiI{sub 3} are also presented, to help in the rational design of device architectures that would allow efficient charge transfer at the interfaces.

14 SOLAR ENERGY↗

DOE OSTI2018

Accelerated Architectures Create Programming Opportunities

In the early 2000s, industry switched to multicore microprocessors to address semiconductors' speed and power limits. However, the change was unsuccessful, leading to dire claims that “Moore's law is ending.” In conclusion, this column suggests that while the approach was sound, it needed a deeper architectural transformation. Industry has since discovered a suitable architecture, but work remains on software to support it.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS2017

Archive Management of NASA Earth Observation Data to Support Cloud Analysis

NASA collects, processes and distributes petabytes of Earth Observation (EO) data from satellites, aircraft, in situ instruments and model output, with an order of magnitude increase expected by 2024. Cloud-based web object storage (WOS) of these data can simplify the execution of such an increase. More importantly, it can also facilitate user analysis of those volumes by making the data available to the massively parallel computing power in the cloud. However, storing EO data in cloud WOS has a ripple effect throughout the NASA archive system with unexpected challenges and opportunities. One challenge is modifying data servicing software (such as Web Coverage Service servers) to access and subset data that are no longer on a directly accessible file system, but rather in cloud WOS. Opportunities include refactoring of the archive software to a cloud-native architecture; virtualizing data products by computing on demand; and reorganizing data to be more analysis-friendly.

Lynnes, Christopher↗

NASA NTRS2017

Archive Management of NASA Earth Observation Data to Support Cloud Analysis

Lynnes, Christopher↗

DOE OSTI2025

Distributed Cross-Channel Hierarchical Aggregation for Foundation Models

Vision-based scientific foundation models hold significant promise for advancing scientific discovery and innovation. This potential stems from their ability to aggregate images from diverse sources—such as varying physical groundings or data acquisition systems—and to learn spatio-temporal correlations using transformer architectures. However, tokenizing and aggregating images can be compute-intensive, a challenge not fully addressed by current distributed methods. In this work, we introduce the Distributed Cross-Channel Hierarchical Aggregation (D-CHAG) approach designed for datasets with a large number of channels across image modalities. Our method is compatible with any model-parallel strategy and any type of vision transformer architecture, significantly improving computational efficiency. We evaluated D-CHAG on hyperspectral imaging and weather forecasting tasks. When integrated with tensor parallelism and model sharding, our approach achieved up to a 75% reduction in memory usage and more than doubled sustained throughput on up to 1,024 AMD GPUs on the Frontier Supercomputer.

Tsaris, Aristeidis (aris) [ORNL] (ORCID:0000000277↗

DOE OSTI2025

Harnessing ferro-valleytricity in pentalayer rhombohedral graphene for memory and compute

Two-dimensional materials with multiple degrees of freedom, including spin, valleys, and orbitals, open up an exciting avenue for engineering multifunctional devices. Beyond spintronics, these degrees of freedom can lead to novel quantum effects such as valley-dependent Hall effects and orbital magnetism, which could revolutionize next-generation electronics. However, achieving independent control over valley polarization and orbital magnetism has been a challenge due to the need for large electric fields. A recent breakthrough involving pentalayer rhombohedral graphene has demonstrated the ability to individually manipulate anomalous Hall signals and orbital magnetic hysteresis, forming what is known as a valley-magnetic quartet. Here, we leverage the electrically tunable ferro-valleytricity of pentalayer rhombohedral graphene to develop nonvolatile memory and in-memory computation applications. We propose an architecture for a dense, scalable, and selector-less nonvolatile memory array that harnesses the electrically tunable ferro-valleytricity. In our designed array architecture, nondestructive read and write operations are conducted by sensing the valley state through two different pairs of terminals, allowing for independent optimization of read/write peripheral circuits. The power consumption of our PRG-based array is remarkably low, with only ∼6 nW required per write operation and ∼2.3 nW per read operation per cell. This consumption is orders of magnitude lower than that of the majority of state-of-the-art cryogenic memories. Additionally, we engineer in-memory computation by implementing majority logic operations within our proposed nonvolatile memory array without modifying the peripheral circuitry. In conclusion, our framework presents a promising pathway toward achieving ultra-dense cryogenic memory and in-memory computation capabilities.

2D materials↗

DOE OSTI2021

Benchmarking the Performance of Neuromorphic and Spiking Neural Network Simulators

Software simulators play a critical role in the development of new algorithms and system architectures in any field of engineering. Neuromorphic computing, which has shown potential in building brain-inspired energy-efficient hardware, suffers a slow-down in the development cycle due to a lack of flexible and easy-to-use simulators of either neuromorphic hardware itself or of spiking neural networks (SNNs), the type of neural network computation executed on most neuromorphic systems. While there are several openly available neuromorphic or SNN simulation packages developed by a variety of research groups, they have mostly targeted computational neuroscience simulations, and only a few have targeted small-scale machine learning tasks with SNNs. Evaluations or comparisons of these simulators have often targeted computational neuroscience-style workloads. In this work, we seek to evaluate the performance of several publicly available SNN simulators with respect to non-computational neuroscience workloads, in terms of speed, flexibility, and scalability. We evaluate the performance of the NEST, Brian2, Brian2GeNN, BindsNET and Nengo packages under a common front-end neuromorphic framework. Our evaluation tasks include a variety of different network architectures and workload types to mimic the computation common in different algorithms, including feed-forward network inference, genetic algorithms, and reservoir computing. We also study the scalability of each of these simulators when running on different computing hardware, from single core CPU workstations to multi-node supercomputers. Our results show that the BindsNET simulator has the best speed and scalability for most of the SNN workloads (sparse, dense, and layered SNN architectures) on a single core CPU. However, when comparing the simulators leveraging the GPU capabilities, Brian2GeNN outperforms the others for these workloads in terms of scalability. NEST performs the best for small sparse networks and is also the most flexible simulator in terms of reconfiguration capability NEST shows a speedup of at least 2x compared to the other packages when running evolutionary algorithms for SNNs. The multi-node and multi-thread capabilities of NEST show at least 2x speedup compared to the rest of the simulators (single core CPU or GPU based simulators) for large and sparse networks. We conclude our work by providing a set of recommendations on the suitability of employing these simulators for different tasks and scales of operations. We also present the characteristics for a future generic ideal SNN simulator for different neuromorphic computing workloads.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Reference Architecture Discussion [Slides]

NREL is developing reference architectures - industry-validated and verified models - to provide a common operational view and emulation environment for analyzing risk to the energy sector. In this presentation, we overview our work in developing these architectures.

97 MATHEMATICS AND COMPUTING↗

NASA NTRS1992

A new explicit variable time-integration self-starting methodology for computational structural dynamics

A new explicit variable time-integration methodology and architecture which possesses self-starting attributes, eliminates the need to involve acceleration computations, and which has improved accuracy characteristics in comparison to the traditional central-difference-type formulations customarily advocated is described for applicability to computational structural dynamics. To sharpen the focus of the present study, an explicit variable time-integration architecture which is relatively simple, yet effective, is described. Unlike variable explicit time-integration formulations adopted in the past, the present self-starting variable time-integration architecture and implementation aspects facilitate a simplified representation and a straightforward and effective approach for combining finite element meshes requiring different time steps in a single analysis. Numerical test cases are provided which demonstrate the applicability of the proposed formulations.

Tamma, Kumar K.↗

DOE OSTI2017

Scaling deep learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors --- including NVIDIA, Intel, AMD, and IBM --- have architectural road-maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. This paper provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consists of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling --- sometimes encouraged by restricted GPU memory --- NVLink is less important.

Gawande, Nitin A.↗

NASA NTRS2018

High-Performance Spaceflight Computing (HPSC) Program Overview

The High Performance Spaceflight Computing (HPSC) project is dramatically advancing the state of the art for spaceflight computing, providing both increased performance and greater operational flexibility. Initial studies derived an reference architecture for the HPSC Chiplet, and this has evolved as development has progress. NASA and JPL are jointly developing HPSC Middleware to ease the development of future applications for the Chiplet. Several NASA use cases are identified for HPSC, ranging from smallsats to crewed missions.

avionics↗