Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “gpu”

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 1,243 records · Page 69
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Accelerating the Inference of the Exa.TrkX Pipeline

Recently, graph neural networks (GNNs) have been successfully used for a variety of particle reconstruction problems in high energy physics, including particle tracking. The Exa.TrkX pipeline based on GNNs demonstrated promising performance in reconstructing particle tracks in dense environments. It includes five discrete steps: data encoding, graph building, edge filtering, GNN, and track labeling. All steps were written in Python and run on both GPUs and CPUs. In this work, we accelerate the Python implementation of the pipeline through customized and commercial GPU-enabled software libraries, and develop a C++ implementation for inferencing the pipeline. The implementation features an improved, CUDA-enabled fixed-radius nearest neighbor search for graph building and a weakly connected component graph algorithm for track labeling. GNNs and other trained deep learning models are converted to ONNX and inferenced via the ONNX Runtime C++ API. The complete C++ implementation of the pipeline allows integration with existing tracking software. We report the memory usage and average event latency tracking performance of our implementation applied to the TrackML benchmark dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Apparatus and method for providing workload distribution of threads among multiple compute units

In some examples, thermal aware optimization logic determines a characteristic (e.g., a workload or type) of a wavefront (e.g., multiple threads). For example, the characteristic indicates whether the wavefront is compute intensive, memory intensive, mixed, and/or another type of wavefront. The thermal aware optimization logic determines temperature information for one or more compute units (CUs) in one or more processing cores. The temperature information includes predictive thermal information indicating expected temperatures corresponding to the one or more CUs and historical thermal information indicating current or past thermal temperatures of at least a portion of a graphics processing unit (GPU). The logic selects the one or more compute units to process the plurality of threads based on the determined characteristic and the temperature information. The logic provides instructions to the selected subset of the plurality of CUs to execute the wavefront.

Rao, Karthik↗
DOE OSTI2022

DUNE Software and High Performance Computing

DUNE, like other HEP experiments, faces a challenge related to matching execution patterns of our production simulation and data processing software to the limitations imposed by modern high-performance computing facilities. In order to efficiently exploit these new architectures, particularly those with high CPU core counts and GPU accelerators, our existing software execution models require adaptation. In addition, the large size of individual units of raw data from the far detector modules pose an additional challenge somewhat unique to DUNE. Here we describe some of these problems and how we begin to solve them today with existing software frameworks and toolkits. We also describe ways we may leverage these existing software architectures to attack remaining problems going forward. This whitepaper is a contribution to the Computational Frontier of Snowmass21.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

COMPOFF: A Compiler Cost model using Machine Learning to predict the Cost of OpenMP Offloading

The HPC industry is inexorably moving towards an era of extremely heterogeneous architectures, with more devices configured on any given HPC platform and potentially more kinds of devices, some of them highly specialized. Writing a separate code suitable for each target system for a given HPC application is not practical. The better solution is to use directive-based parallel programming models such as OpenMP. OpenMP provides a number of options for offloading a piece of code to devices like GPUs. To select the best option from such options during compilation, most modern compilers use analytical models to estimate the cost of executing the original code and the different offloading code variants. Building such an analytical model for compilers is a difficult task that necessitates a lot of effort on the part of a compiler engineer. Recently, machine learning techniques have been successfully applied to build cost models for a variety of compiler optimization problems. In this paper, we present COMPOFF, a cost model which uses the multi-layer perceptrons to statically estimates the Cost of OpenMP OFFloading. We used six different transformations on a parallel code of Wilson Dslash Operator to support GPU offloading, and we predicted their cost of execution on different GPUs using COMPOFF during compile time. Our results show that this model can predict offloading costs with a root mean squared error in prediction of less than 0.5 seconds. Our preliminary findings indicate that this work will make it much easier and faster for scientists and compiler developers to port legacy HPC applications that use OpenMP to new heterogeneous computing environment.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Conversion of Resonance Parameters Between Wigner-Eisenbud R-matrix and Transition Matrix Pole Representation

The goal of this research is to develop a numerical code for translation between the current standard, Wigner-Eisenbud R-matrix parameters and a novel pole-representation of cross sections. The method follows Ducru et al. and constructs the conversion between these parametric representations of the scattering and reaction data. This pole representation, which expresses cross sections as a sum of simple poles (and their attendant residues), is examined in the context of the advantages provided by this compact, computationally efficient representation. These advantages include the ability to doppler broaden cross sections on-the-fly as well as a lower memory footprint when generating cross sections, an attractive feature to those interested in parallel GPU based Monte Carlo. Some conversion methods between R-matrix parameters and S-matrix poles have relied on curve fitting techniques. It is unknown weather these numerical methods necessarily preserve certain underlying physics properties of the standard R-matrix cross section model (such as unitarity). The direct conversion studied here aim to preserve such properties. This knowledge is of interest for future work into the generation of resonance parameter sensitivities.

CLUTCH↗
DOE OSTI2022

Methods for the separation of CO2 from a gas stream

Disclosed herein are 2-stage membrane separation methods for capturing CO2 from a feed gas. The methods can employ two selectively permeable membranes, which may be the same or different. The selectively permeable membrane can have a carbon dioxide permeance of from 500 to 3000 GPU at 57° C. and 1 atm feed pressure and a carbon dioxide:nitrogen selectivity of from 10 to 1000 at 57° C. and 1 atm feed pressure. High pressure ratios across the membranes can be achieved by compressing the feed gas to a high pressure, by using vacuum pumps to create a lowered pressure on the permeate side of the membrane, by using a sweep stream, or a combination thereof. When a sweep stream is used, the sweep stream may include a portion of the retentate gas stream obtained from the retentate side of one or more of the membranes used.

Ho, W. S. Winston↗
DOE OSTI2022

Transforming Energy Through Computational Excellence: Bringing Low Mach Number Reactive Flow Simulations at the Exascale

PeleLMeX's unique capabilities are allowing for reactive flow modeling at unprecedented scales and a reasonable time and cost. The code is currently being extended to tackle more practical, design-oriented simulations by implementing Large Eddy Simulation and data-driven chemical models, providing a fast but accurate tool for engineers considering the emergence of GPU-accelerated platforms. These extensions are critical for enabling the physical insight required to design the next generation of combustion devices as a key component of a renewable energy future.

MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Porting numerical integration codes from CUDA to oneAPI: a case study

We present our experience in porting optimized CUDA implementations to oneAPI. We focus on the use case of numerical integration, particularly the CUDA implementations of PAGANI and $m$-Cubes. We faced several challenges that caused performance degradation in the oneAPI ports. These include differences in utilized registers per thread, compiler optimizations, and mappings of CUDA library calls to oneAPI equivalents. After addressing those challenges, we tested both the PAGANI and m-Cubes integrators on numerous integrands of various characteristics. To evaluate the quality of the ports, we collected performance metrics of the CUDA and oneAPI implementations on the Nvidia V100 GPU. We found that the oneAPI ports often achieve comparable performance to the CUDA versions, and that they are at most 10% slower.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Machine Learning 5G Attack Detection in Programmable Logic

Machine learning-assisted network security may significantly contribute to securing 5G components. However, machine learning network security inference speeds generally require tens to hundreds of milliseconds thereby introducing significant latency in 5G operations. The inference latency can be reduced by deploying the machine learning model to programmable logic in a field programmable gate array (FPGA) at the cost of a small loss in accuracy. In order to quantify this loss, as well as to establish baseline performance inference speeds for programmable logic implementations, this work explores an autoencoder and a ß-variational autoencoder deployed on two different FPGA evaluation boards and compares accuracy and performance against an NVIDIA A100 GPU implementation. A publicly available 5G dataset containing 10 types of attacks along with normal traffic is introduced as part of the evaluation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

High speed two-dimensional event detection and imaging using an analog interface and a massively parallel processor

A quantitative pulse count (event detection) algorithm with linearity to high count rates is accomplished by combining a high-speed, high frame rate camera with simple logic code run on a massively parallel processor such as a GPU or a FPGA. The parallel processor elements examine frames from the camera pixel by pixel to find and tag events or count pulses. The tagged events are combined to form a combined quantitative event image.

Waugh, Justin↗
DOE OSTI2023

FunMC^2: A Filter for Uncertainty Visualization of Marching Cubes on Multi-Core Devices

Visualization is an important tool for scientists to extract understanding from complex scientific data. Scientists need to understand the uncertainty inherent in all scientific data in order to interpret the data correctly. Uncertainty visualization has been an active and growing area of research to address this challenge. Algorithms for uncertainty visualization can be expensive, and research efforts have been focused mainly on structured grid types. Further, support for uncertainty visualization in production tools is limited. In this paper, we adapt an algorithm for computing key metrics for visualizing uncertainty in Marching Cubes (MC) to multi-core devices and present the design, implementation, and evaluation for a Filter for uncertainty visualization of Marching Cubes on Multi-Core devices (FunMC2). FunMC2 accelerates the uncertainty visualization of MC significantly, and it is portable across multi-core CPUs and GPUs. Evaluation results show that FunMC2 based on OpenMP runs around 11× to 41× faster on multi-core CPUs than the corresponding serial version using one CPU core. FunMC2 based on a single GPU is around 5× to 9× faster than FunMC2 running by OpenMP. Moreover, FunMC2 is flexible enough to process ensemble data with both structured and unstructured mesh types. Furthermore, we demonstrate that FunMC2 can be seamlessly integrated as a plugin into ParaView, a production visualization tool for post-processing.

Wang, Jay↗
DOE OSTI2023

Exploring for Superhot Geothermal Targets in Magmatic Settings: 2022 Field Campaign at Newberry Volcano

This paper presents preliminary results from a subset of work carried out as part of a multinational research project entitled DErisking Exploration for multiple geothermal Plays in magmatic ENvironments (DEEPEN), supported by the U.S. Department of Energy (DOE) and Geothermica, a joint effort by EU member states and associated countries. The DEEPEN project will develop a customized approach to exploration for supercritical and superhot geothermal plays in magmatic systems, which will be applied to two demonstration sites. This paper summarizes field activities carried out at the U.S. demonstration site, Newberry Volcano in central Oregon. The objective of this work effort is to refine the subsurface model of Newberry Volcano, with special focus on deeper zones including the magmatic plumbing system and other key geologic elements. New data collection included gravity and wideband magnetotelluric (MT) surveys, as well as reinstallation of a seismic network. The National Renewable Energy Laboratory (NREL) and Enthalpion Energy LLC (Enthalpion) worked with the Deschutes National Forest Fort Rock District to use a low ground disturbance method of MT deployment to collect MT data inside the caldera and other restricted areas inside the National Volcanic Monument. This opened these areas to geophysical exploration for the first time in decades. Sites along and adjacent to the south rim of the volcano constituted the primary survey objectives. A team from Lawrence Berkeley National Laboratory (LBNL), the U.S. Geological Survey (USGS), and AltaRock also began the process of reinstalling the seismic network from the AltaRock enhanced geothermal system (EGS) demonstration in anticipation of further development activities at the site. The data ingestion, reduction, and analysis phase of the project is ongoing. We are currently processing the MT and gravity data and are developing a new, highly GPU-accelerated, 3D joint MT and gravity inversion to better localize the south rim/south flank conductive target and better understand its relationship to deep heat, fluid sources, and surface extrusive features. Joint inversions, which have not yet been undertaken at Newberry, will allow us to obtain constraints on the geologic model that cannot be determined from each method in isolation, improving our ability to image key geologic features at depth.

geophysics↗
DOE OSTI2023

Virtual Infrastructure Twins: Software Testing Platforms for Computing-Instrument Ecosystems

Science ecosystems are being built by federating computing systems and instruments located at geographically distributed sites over wide-area networks. These computing-instrument ecosystems are expected to support complex workflows that incorporate remote, automated AI-driven science experiments. Their realization, however, requires various designs to be explored and software components to be developed, in order to support the orchestration of distributed computations and experiments. It is often too expensive, infeasible, or disruptive for the entire ecosystem to be available during the typically long software development and testing periods. We propose a Virtual Infrastructure Twin (VIT) of the ecosystem that emulates its network and computing components, and incorporates its instrument software simulators. It provides a software environment nearly identical to the ecosystem to support early development and testing, and design space exploration. We present a brief overview of previous digital infrastructure twins that culminated in the VIT concept, including (i) the virtual science network environment for developing software-defined networking solutions, and (ii) the virtual federated science instrument environment for testing the federation software stack and remote instrument control software. We briefly describe VITs for Nion microscope steering and access to GPU systems.

Rao, Nageswara↗
DOE OSTI2023

Apparatus and method for providing workload distribution of threads among multiple compute units

In some examples, thermal aware optimization logic determines a characteristic (e.g., a workload or type) of a wavefront (e.g., multiple threads). For example, the characteristic indicates whether the wavefront is compute intensive, memory intensive, mixed, and/or another type of wavefront. The thermal aware optimization logic determines temperature information for one or more compute units (CUs) in one or more processing cores. The temperature information includes predictive thermal information indicating expected temperatures corresponding to the one or more CUs and historical thermal information indicating current or past thermal temperatures of at least a portion of a graphics processing unit (GPU). The logic selects the one or more compute units to process the plurality of threads based on the determined characteristic and the temperature information. The logic provides instructions to the selected subset of the plurality of CUs to execute the wavefront.

Rao, Karthik↗
DOE OSTI2023

Non-Orthogonal Configuration Interaction for Fragments

An overview is given of the non-orthogonal configuration interaction (NOCI) implementation in the open-source program GronOR. After pointing out the specifics of NOCI and its extension to ensembles of molecules NOCI-Fragments (NOCI-F), the theoretical foundations of the approaches are described. The introduction of a common molecular orbital basis, the selection of the most contributing determinants pairs, and a massively parallel and GPU-accelerated implementation have made possible the application of NOCI to medium-sized systems as illustrated in a short overview of some of the recent applications.

de Graaf, C.↗
DOE OSTI2022

Matrix Multiply Performance of GPUs on Exascale-class HPE/Cray Systems

The computation of dense matrix-matrix products (GEMMs) is central to many modeling and simulation workloads as well as AI/ML deep learning campaigns. In fact, millions of dollars are spent annually on computing GEMMs, and large model training demands are increasing exponentially. Specialized processors such as GPUs are designed to perform well for these operations. However, the performance of GEMMs on GPUs can exhibit complex behaviors depending on many factors, making it challenging to optimize the performance of GEMMs on these processors. In this study we undertake an examination of GEMM performance on several leading GPU models taken from product lines of GPUs to be deployed in forthcoming exascale computing systems. We show results to illustrate the many factors that can affect performance of GEMMs on GPUs. We then present data collected from a large number of test runs for an example GEMM operation to show the dependence behaviors of GEMM rate on matrix dimensions. Finally, we show results from machine learning-based performance models using novel feature engineering methods to fit the measured performance, providing a potential basis for GEMM performance tuning and autotuning methods for GPUs. Recommendations are also given for how to achieve high GEMM performance on modern GPUs.

Melesse Vergara, Veronica↗
DOE OSTI2024

Object Detection and Recognition with PointPillars in LiDAR Point Clouds – Comparisions

In the field of autonomous systems, neural networks have been leveraged for object detection and recognition in 2-dimensional images captured by cameras. Other types of sensors are available for sensing surroundings, including LiDAR sensors, and corresponding networks have been developed to perform detection and recognition in the point clouds generated by these sensors. The approaches are similar, both perform convolutions, but have distinct characteristics and challenges. In designing and configuring autonomous systems, a variety of LiDAR sensors are available, along with configurable deep neural networks to leverage their data. This work presents a review of the PointPillars network, an evolution of the seminal PointNet, comparing accuracy and training time relative to different LiDAR sensors, network and training parameters, CPU and GPU hardware, and the criticality of the use of reflective intensity as a feature. The value of using reflectivity as a predictive feature is explored and quantified to determine if it makes a significant difference in accuracy of the PointPillars network. Two separate LiDAR sensors are utilized, a 16-plane and a 32-plane, and corresponding accuracies and training times with the PointPillars network are evaluated.

LiDAR, machine learning, neural network, object re↗