SEARCH · Search NASA

Results for “data parallel”

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 1,333 records · Page 74

All sources NASA NTRS DOE OSTI

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 OSTI2020

Summer Proceedings 2019

The Computer Science Research Institute (CSRI) brings university faculty and students to Sandia for focused collaborative research on Department of Energy (DOE) computer and computational science problems. The institute provides an opportunity for university researchers to learn about problems in computer and computational science at DOE laboratories. Participants conduct leading-edge research, interact with scientists and engineers at the laboratories, and help transfer results of their research to programs at the labs. Some specific CSRI research interest areas are: scalable solvers, optimization, adaptivity and mesh refinement, graph-based, discrete, and combinatorial algorithms, uncertainty estimation, mesh generation, dynamic load-balancing, virus and other malicious-code defense, visualization, scalable cluster computers and heterogeneous computers, data-intensive computing, environments for scalable computing, parallel input/output, advanced architectures, and theoretical computer science. The CSRI Summer Program includes the organization of a weekly seminar series and the publication of this summer proceedings.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

CSRI Summer Proceedings 2020

The Computer Science Research Institute (CSRI) brings university faculty and students to Sandia for focused collaborative research on Department of Energy (DOE) computer and computational science problems. The institute provides an opportunity for university researchers to learn about problems in computer and computational science at DOE laboratories. Participants conduct leading-edge research, interact with scientists and engineers at the laboratories, and help transfer results of their research to programs at the labs. Some specific CSRI research interest areas are: scalable solvers, optimization, adaptivity and mesh refinement, graph-based, discrete, and combinatorial algorithms, uncertainty estimation, mesh generation, dynamic load-balancing, virus and other malicious-code defense, visualization, scalable cluster computers, data-intensive computing, environments for scalable computing, parallel input/output, advanced architectures, and theoretical computer science. The CSRI Summer Program is organized by CSRI and typically includes the organization of a weekly seminar series and the publication of a summer proceedings. In 2020, the CSRI summer program was executed completely virtually; all student interns worked from home, due to the COVID-19 pandemic.

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 OSTI2021

Integrating PGAS and MPI-based Graph Analysis

This project demonstrates that Chapel programs can interface with MPI-based libraries written in C++ without storing multiple copies of shared data. Chapel is a language for productive parallel computing using global address spaces (PGAS). We identified two approaches to interface Chapel code with the MPI-based Grafiki and Trilinos libraries. The first uses a single Chapel executable to call a C function that interacts with the C++ libraries. The second uses the mmap function to allow separate executables to read and write to the same block of memory on a node. We also encapsulated the second approach in Docker/Singularity containers to maximize ease of use. Comparisons of the two approaches using shared and distributed memory installations of Chapel show that both approaches provide similar scalability and performance.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

DGaaS: GPU as a Service on Distributed Computing System

In the rapidly evolving landscape of scientific computing, Graphics Processing Units (GPUs) have become indispensable for their unparalleled ability to handle parallel tasks in complex calculations, simulations, and data analysis. Their utility is further magnified in machine learning and AI applications, where they significantly accelerate model training and predictive analytics. Within this context, the Triton Inference Server emerges as a pivotal open-source tool, specializing in AI inferencing and optimizing GPU utilization across various platforms and frameworks. This paper presents an in-depth study on distributed High Throughput Computing (HTC), specifically focusing on the HTCondor framework and its resource provisioning tools, GlideinWMS and HEPCloud. These systems enable large-scale scientific experiments like CMS and DUNE to efficiently access and utilize vast computational resources. The paper explores the core architectural components of GlideinWMS, including jobs, user pools, and worker nodes, and discusses their integration with GPUs and the Triton server. The primary aim of this research is to develop a solution that optimizes GPU utilization by leveraging Glideins and containers. This approach allows computational jobs, particularly those involving AI models, to use GPUs only when essential, thereby facilitating efficient sharing of limited GPU resources. To validate this architecture, the study conducted three key tests involving custom scripts, container-based servers, and Triton server deployments. However, the study faces challenges, notably in locating the Triton server and ensuring secure remote access. To address these issues, future work will focus on developing a proxy mechanism and enhancing security protocols. In conclusion, this study offers a comprehensive roadmap for effective and efficient GPU utilization in distributed High Throughput Computing. It aims to contribute significantly to the scientific community by solving pressing problems and implementing robust solutions in collaboration with the GlideinWMS and HEPCloud teams. The research sets the stage for a more efficient, scalable, and cost-effective paradigm in scientific computing.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Machine Learning-Driven Conservative-to-Primitive Conversion in Hybrid Piecewise Polytropic and Tabulated Equations of State

We present a novel machine learning (ML)-based method to accelerate conservative-to-primitive inversion, focusing on hybrid piecewise polytropic and tabulated equations of state. Traditional root-finding techniques are computationally expensive, particularly for large-scale relativistic hydrodynamics simulations. To address this, we employ feedforward neural networks (NNC2PS and NNC2PL), trained in PyTorch (2.0+) and optimized for GPU inference using NVIDIA TensorRT (8.4.1), achieving significant speedups with minimal accuracy loss. The NNC2PS model achieves 𝐿 1 and 𝐿 ∞ errors of 4.54 × 10 −7 and 3.44 × 10−6, respectively, while the NNC2PL model exhibits even lower error values. TensorRT optimization with mixed-precision deployment substantially accelerates performance compared to traditional root-finding methods. Specifically, the mixed-precision TensorRT engine for NNC2PS achieves inference speeds approximately 400 times faster than a traditional single-threaded CPU implementation for a dataset size of 1,000,000 points. Ideal parallelization across an entire compute node in the Delta supercomputer (dual AMD 64-core 2.45 GHz Milan processors and 8 NVIDIA A100 GPUs with 40 GB HBM2 RAM and NVLink) predicts a 25-fold speedup for TensorRT over an optimally parallelized numerical method when processing 8 million data points. Moreover, the ML method exhibits sub-linear scaling with increasing dataset sizes. We release the scientific software developed, enabling further validation and extension of our findings. By exploiting the underlying symmetries within the equation of state, these findings highlight the potential of ML, combined with GPU optimization and model quantization, to accelerate conservative-to-primitive inversion in relativistic hydrodynamics simulations.

conservative-to-primitive conversion↗

NASA NTRS1976

TSE computers - A means for massively parallel computations

A description is presented of hardware concepts for building a massively parallel processing system for two-dimensional data. The processing system is to use logic arrays of 128 x 128 elements which perform over 16 thousand operations simultaneously. Attention is given to image data, logic arrays, basic image logic functions, a prototype negator, an interleaver device, image logic circuits, and an image memory circuit.

Strong, J. P., III↗

NASA NTRS1977

Application of an ultrasonic phase insensitive receiver to material measurements

The theory of a phase insensitive receiver based on acousto-electric effect is presented along with experimental characteristics of a CdS acousto-electric converter (AEC). Since the AEC is nearly phase insensitive, it is ideal for measurements in inhomogeneous materials and/or materials with irregular flatness and parallelism. Through transmission ultrasonic C-scan data of phantom flaws demonstrates a significant improvement in flaw characterization with an AEC over that of a conventional transducer. In addition, measurements with conventional transducers in anisotropically stressed metal samples are shown to lead to grossly inaccurate results due to phase sensitivity. Various other measurements are presented with data contrasting conventional transducers with an AEC in specific NDE applications.

Heyman, J. S.↗

NASA NTRS1977

Application of an ultrasonic phase insensitive receiver to material measurements

Heyman, J. S.↗

NASA NTRS1977

High-speed computerized tomography

The development of a high-speed reconstruction processor and a channelized architecture to use with a high-resolution tomographic unit is discussed with attention to the convolution reconstruction algorithm. By means of this algorithm, input data and intermediate result precision required throughout the algorithm execution have been studied with computer simulation using profile data derived from mathematically simulated test objects and experimental animal data. A prototype section for a highly parallel all-digital system executes 60 million arithmetic operations per second, and the full-scale version is expected to reconstruct 500 to 1000 cross sections per second.

Swartzlander, E. E., Jr.↗

NASA NTRS1977

50 Mbps hardware development for Shuttle Ku-band communications

The performance of a 5-Mbps coded system developed for Shuttle Ku-band communications is described. The system consists of a rate 1/2, constraint length 7 convolutional encoder-decoder and soft decision symbol synchronizer; the system has been band-limited at the transmitted symbol rate. Five convolutional decoders are operated in parallel to permit operation at the required data rate. It is found that the multiplexed encoder-decoder system does not exhibit any observable coding gain degradation when the channel is limited to the symbol rate at baseband.

Vang, H. A.↗

NASA NTRS1980

Application of a microprocessor to a spacecraft attitude control

The attitude control system (ACS) microprocessor development work spanned three main design areas: hardware and instruction set, ACS firmware, and hardware firmware verification testing. The processor hardware utilizes two parallel 4 bit microprocessors. The firmware includes data processing for five sensors, four attitude control laws, and telemetry and commands.

Brady, D. H.↗

NASA NTRS1981

LANDSAT Range Resource Information System

A series of test products were developed from LANDSAT data sets for North Central Texas that paralleled the needs of ranchers, technical personnel, and the media. The products and evaluation questionnaires were mailed to approximately 150 ranchers who had reported an interest in evaluating the information systems. In addition to the rancher group, fourteen media people and a thirty-three member group in the agri business/technical community was also chosen to receive test products. The group responses are analyzed. Examples of the test products and associated questionnaires are included.

Boyd, W. E.↗

NASA NTRS1982

On the geodetic applications of simultaneous range-differencing to LAGEOS

The possibility of improving the accuracy of geodetic results by use of simultaneously observed ranges to Lageos, in a differencing mode, from pairs of stations was studied. Simulation tests show that model errors can be effectively minimized by simultaneous range differencing (SRD) for a rather broad class of network satellite pass configurations. The methods of least squares approximation are compared with monomials and Chebyshev polynomials and the cubic spline interpolation. Analysis of three types of orbital biases (radial, along- and across track) shows that radial biases are the ones most efficiently minimized in the SRC mode. The degree to which the other two can be minimized depends on the type of parameters under estimation and the geometry of the problem. Sensitivity analyses of the SRD observation show that for baseline length estimations the most useful data are those collected in a direction parallel to the baseline and at a low elevation. Estimating individual baseline lengths with respect to an assumed but fixed orbit not only decreases the cost, but it further reduces the effects of model biases on the results as opposed to a network solution. Analogous results and conclusions are obtained for the estimates of the coordinates of the pole.

Pablis, E. C.↗

NASA NTRS1987

Optimization of V-groove radiator configuration

In the design of spacecraft radiators intended to provide cryogenic cooling, it is important to minimize the space occupied by radiator shielding while satisfying the performance requirements. This study develops and tests the first step toward optimizing radiator shield configurations and examines the design of the highly effective V-groove radiator concept. This investigation, which makes use of a special purpose Monte Carlo/ray tracing computer program, directly identifies the two shield configuration which minimizes radiator footprint for a given temperature drop. Furthermore, multiple shield configurations may be analyzed through a combination of analysis and program statistics. The results presented demonstrate the sensitivity of intershield temperature drop to shield angle and/or offset and provide a comparison of angled and parallel shield configurations. Good agreement with experimental data is shown for a multiple shield configuration.

Schember, Helene R.↗

NASA NTRS1987

Degree of cure and viscosity of Hercules HBRF-55 resin

The rate of cure and viscosity were measured for Hercules HBRF-55 resin. The rate of cure was measured by differential scanning calorimetry, while the viscosity was measured by a parallel disk and plate type apparatus. The data were fitted to analytic expressions to make them suitable for use in numerical calculations.

Bhi, S. T.↗

NASA NTRS1989

Rarefied gas flow through two-dimensional nozzles

A kinetic theory analysis is made of the flow of a rarefied gas from one reservoir to another through two-dimensional nozzles with arbitrary curvature. The Boltzmann equation simplified by a model collision integral is solved by means of finite-difference approximations with the discrete ordinate method. The physical space is transformed by a general grid generation technique and the velocity space is transformed to a polar coordinate system. A numerical code is developed which can be applied to any two-dimensional passage of complicated geometry for the flow regimes from free-molecular to slip. Numerical values of flow quantities can be calculated for the entire physical space including both inside the nozzle and in the outside plume. Predictions are made for the case of parallel slots and compared with existing literature data. Also, results for the cases of convergent or divergent slots and two-dimensional nozzles with arbitrary curvature at arbitrary knudsen number are presented.

De Witt, Kenneth J.↗