Search NASA⌕ Search

SEARCH · Search NASA

Results for “data parallel algorithms”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Rapid simulation of X-ray scatter measurements for threat detection via GPU-based ray-tracing

Scatter-based X-ray imaging has increased in prominence in areas ranging from cancer diagnostics to threat detection in aviation security, due largely to the development of new algorithms and components over the last decade. However, system design and algorithm development are often hindered by an inability to generate a sucient amount of accurate data. To further the development of scatter-based systems, we created a rapid X-ray scatter simulation tool built with a GPU-centric, parallel ray-tracing framework (NVIDIA OptiX). This tool models a full range of X-ray imaging components and describes 3D objects formed with heterogeneous media using polygon meshes. The scatter simulation algorithm we used is similar to the previously-described hybrid approach; however, instead of employing Monte Carlo techniques, we developed a purely analytical algorithm to sample the distribution of single-scatter events throughout the region of interest. The contribution of scattered photons to the measured signal is then calculated using the first-Born approximation. Here, the accuracy of the implemented pipeline has been validated by comparing simulated against experimental data obtained with a laboratory X-ray scattering system and phantoms of varied materials. Using a single desktop computer with an NVIDIA GTX 770 GPU, we show that the scatter signal generated by an incident fan beam and recorded by a 125 125 element detector array can be simulated in on the order of a few to tens of minutes (depending on the object extent and complexity). As a point of comparison, simulations performed via CPU-based Monte Carlo tools, such as GEANT4 (i.e., the gold standard), can take up to tens of hours to achieve comparable results.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

cuTS: Scaling Subgraph Isomorphism on Distributed Multi-GPUSystems Using Trie Based Data Structure

Subgraph isomorphism is a pattern-matching algorithm widely used in many domains such as chem-informatics, bioinformatics, databases, and social network analysis. It is computationally expensive and is a proven NP-hard problem. The massive parallelism offered by the GPU hardware is well suited for solving the subgraph isomorphism. However, current GPU implementations are far from the achievable performance. Moreover, the enormous memory requirement of current approaches limits the problem size that can be handled. This work analyzes the fundamental challenges associated with processing the subgraph isomorphism on GPUs and develops an efficient GPU hardware-aware implementation. We also develop a new GPU-friendly trie-based data structure to drastically reduce the intermediate storage space requirement. Hence, our approach runs larger benchmarks than the competitors. We also develop the first distributed sub-graph isomorphism algorithm for GPUs. Our experimental evaluation section demonstrates the efficacy of our approach by comparing the execution time and number of cases that we can handle against the state-of-the-art GPU implementations.

Xiang, Lizhi↗
DOE OSTI2020

Reducing Communication in Graph Neural Network Training

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus higher communication costs compared to dense matrices, making GNNs harder to scale to high concurrencies than convolutional or fully-connected neural networks. Here, we introduce a family of parallel algorithms for training GNNs and show that they can asymptotically reduce communication compared to previous parallel GNN training methods. We implement these algorithms, which are based on 1D, 1. 5D, 2D, and 3D sparse-dense matrix multiplication, using torch.distributed on GPU-equipped clusters. Our algorithms optimize communication across the full GNN training pipeline. We train GNNs on over a hundred GPUs on multiple datasets, including a protein network with over a billion edges.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Dynamic Network Analysis of Nuclear Science Literature for Research Influence Assessment

Analyzing nuclear science literature via data-driven methods is a critical step for assessing research influence and technology advancements. Indicators of scholarly activities may be buried in large volumes of nuclear research publications and collaboration networks over time. Mining for relevant scholarly influence trends in large volumes of text can be computationally challenging; however, open-source information on research collaborations over time can offer opportunities to extract meaningful insights. While network centrality analysis of scholarly research provides topology-based insights, additional emphasis on dynamics associated with the diffusion of information through these networks is important. Here this paper represents a step in that direction through the development of a novel dynamic network analysis framework and computational engine to identify key entities and capabilities over time within global scholarly nuclear science collaboration networks. Network theoretic, stochastic simulation, and optimization methods are leveraged to address variability in scholarly interactions, influence propagation, and collaboration patterns via network connections. A topic-aware influence maximization algorithm is developed to address the goal of identifying key influential authors in diverse research topics over time. Efficient parallelized implementation of the algorithm is applied to reduce computational costs. A proof-of-concept case study using open-source Scopus data with 33,517 published nuclear research papers from 2000-2019 is presented and representative analytic insights are generated. Broad implications of these insights are discussed and future research directions are also identified.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2024

A network approach for multiscale catchment classification using traits

Abstract. The classification of river catchments into groups with similar biophysical characteristics is useful to understand and predict their hydrological behavior. The increasing availability of remote sensing and other large-scale geospatial datasets has enabled the use of advanced data-driven approaches to classify catchments using traits such as topography, geology, climate, land cover, land use, and human influence. Unsupervised clustering algorithms based on the Euclidean distance are commonly used for trait-based classification but are not suitable for highly dimensional data. In this study we present a new network-based method for multi-scale catchment classification, which can be applied to large datasets and used to determine the traits associated with different catchment groups. In this framework, two networks are analyzed in parallel: the first being where the nodes are traits and the second being where the nodes are catchments. In both cases, edges represent pairwise similarity, and a network cluster detection algorithm is used for the classification. The trait network is used to investigate redundancy in the trait data and to condense this information into a small number of interpretable categories. The catchments network is used to classify the catchments into clusters and to identify representative catchments for the different groups using the degree centrality metric. We apply this method to classify 9067 river catchments across the contiguous United States at both regional and continental scales using 274 non-categorical traits. At the continental scale, we identify 25 interpretable trait categories and 34 catchment clusters of sizes greater than 50. We find that catchments with similar trait categories are typically located in the same region, with different spatial patterns emerging among clusters dominated by natural and anthropogenic traits. We also find that the catchment clusters exhibit distinct hydrological behavior based on an analysis of streamflow indices. This network approach provides several advantages over traditional means of classification, including better separation of clusters, the use of alternate similarity metrics that are more suitable for highly dimensional data, and reducing redundancy in the trait information. The paired catchment–trait networks enable analysis of hydrological behavior using the dominant trait categories for each catchment cluster. The approach can be used at multiple spatial scales since the network topologies adjust automatically to reflect the trait patterns at the scale of investigation. Finally, the representative catchments identified as hub nodes in the network can be used to guide transferable observational and modeling strategies. The method is broadly applicable beyond hydrology for classification of other complex systems that utilize different types of trait datasets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Distributed non-negative matrix factorization with determination of the number of latent features

The holistic analysis and understanding of the latent (that is, not directly observable) variables and patterns buried in large datasets is crucial for data-driven science, decision making and emergency response. Such exploratory analyses require devising unsupervised learning methods for data mining and extraction of the latent features, and non-negative matrix factorization (NMF) is one of the prominent such methods. NMF is based on compute-intense non-convex constrained minimization, which, for large datasets requires fast and distributed algorithms. However, current parallel implementations of NMF fail to estimate the number of latent features. In practice, identifying these features is both difficult and significant for pattern recognition and latent feature analysis, especially for large dense matrices. Here, we introduce a distributed NMF algorithm coupled with distributed custom clustering followed by a stability analysis on dense data, which we call DnMFk, to determine the number of latent variables. The results on synthetic data and the classical Swimmer data set demonstrate the accuracy of model determination while scaling nearly linearly across multiple processors for large data. Further, we employ DnMFk to determine the number of hidden features from a terabyte matrix.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Development of Steady-State and Dynamic Mass and Energy Constrained Neural Networks for Distributed Chemical Systems Using Noisy Transient Data

The paper presents the development of algorithms for mass and energy constrained neural network models that can exactly conserve the overall mass and energy of distributed chemical process systems, even though the noisy transient data used for optimal model training violate the same. In contrast to approximately satisfying mass and energy balance constraints of a system by soft penalization of objective function, algorithms have been developed for solving equality-constrained nonlinear optimization problems, thus providing the guarantee of exactly satisfying the system mass and energy conservation laws. For developing dynamic mass-energy constrained network models for distributed systems, hybrid series and parallel dynamic-static neural networks have been leveraged. The developed algorithms for solving both the training and forward problems are validated using both steady-state and dynamic data in the presence of various noise characteristics. The developed data-driven algorithms are flexible to exactly satisfy mass and energy balance constraints for dynamic chemical processes if the system holdup information is available. The proposed network structures and algorithms are applied to the development of data-driven lumped and distributed models of an adiabatic superheater/reheater system, a nonisothermal continuous stirred tank reactor, as well as an electrically heated plug-flow reactor system where one form of energy gets transformed to another. It has been observed that the mass-energy constrained neural networks yield a root mean squared error of <1% with respect to the system truth for the case studies evaluated in this work.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Shot-noise-induced lower temperature limit of the nonneutral plasma parallel temperature diagnostic

Abstract We develop a new algorithm to estimate the temperature of a nonneutral plasma in a Penning-Malmberg trap. The algorithm analyzes data obtained by slowly lowering a voltage that confines one end of the plasma and collecting escaping charges, and is a maximum likelihood estimator based on a physically-motivated model of the escape protocol presented in (Beck in Measurement of the magnetic and temperature dependence of the electron-electron anisotropic temperature relaxation rate. PhD thesis, 1990). Significantly, our algorithm may be used on single-count data, allowing for improved fits with low numbers of escaping electrons. This is important for low-temperature plasmas such as those used in antihydrogen trapping. We perform a Monte Carlo simulation of our algorithm, and assess its robustness to intrinsic shot noise and external noise. The assumptions in this paper allow for a lower bound for measurable plasma temperatures of approximately $3\,\mathrm{K}$ 3 K for plasmas of length $1\,\mathrm{cm}$ 1 cm , with approximately 100 particle counts needed for an accuracy of $\pm 10 \%$ ± 10 % .

Zhong, Adrianne (ORCID:0000000162618736)↗
DOE OSTI2024

HydraGNN_Predictive_GFM_2024 - Ensemble of predictive graph foundation models for ground state atomistic materials modeling

We provide the ensemble of fifteen pre-trained graph foundation models (GFMs) for atomistic materials modeling applications. Each one of the fifteen GFMs has been trained on five open-source datasets that (once aggregated) amount to over 154 million atomistic structures, which cover over two-thirds of the natural elements of the periodic table and that comprises a broad set of organic and inorganic compounds. This vast set of atomistic structures comprises ground state configurations that are dynamically stable (i.e., equilibrated structures with atomic forces approximately close to zero values) as well as dynamically unstable structures (i.e., non-equilibrium structures with non-negligible non-zero values of atomic forces). The ensemble of datasets aggregated does NOT include excited states. The datasets have been curated to remove atomistic structures with spectral norm of the force tensor above 100 eV/angstrom. Moreover, a linear term of the energy was computed for each dataset using a linear regression model that uses the chemical concentration of each natural element as regressor. The linear term predicted by the linear regression model has been subtracted from each original energy value to perform a re-alignment of the energy values across different electronic structures approximation theories performed to generate the diverse multi-source, multi-fidelity datasets. The folder "ADIOS_files" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "ADIOS_files" directory contains 6 sub-directories named as follows: - ANI1x-v3.bp - MPTrj-v3.bp - OC2020-20M-v3.bp - OC2020-v3.bp - OC2022-v3.bp - qm7x-v3.bp Each sub-directory contains the pre-processed datasets converted in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used to the development, training, and performance testing of the ensemble go predictive graph foundation models. Each GFM was developed using HydraGNN (https://github.com/ORNL/HydraGNN) as underlying graph neural network (GNN) architecture. The multi-task learning (MTL) capability of HydraGNN was used to simultaneously train the GFMs on labeled values for direct predictions of energy (a total system property of an atomistic structure that measures the chemical stability) and atomic forces (an atomic level property of an atomistic structure that measures the dynamical stability). The hyper parameters of the GFM have been tuned using scalable hyperparameter optimization (HPO) algorithms implemented in the software DeepHyper (https://github.com/deephyper/deephyper). The pre-training of each HPO trial was performed using distributed data parallelism (DDP) to scale the training across 128 compute nodes of the exascale OLCF supercomputer Frontier. Each HPO trial was trained only for 10 epochs and an early stopping was performed to avoid wasting significant computational resources on GNN architectures that were clearly underperforming. For each HPO trial, the 'omnistat' tool developed by (AMD Research - Advanced Micro Device) was used to measure the total energy consumption in kWh. The ensemble of GFMs was obtained by selecting the fifteen best performing HPO trials. Four models have been selected for their clear advantage in accuracy, and these are the GFMs with IDs 229, 156, 147, 260. Additional eleven models have been selected based on judicious balance between accuracy and energy consumption needed for training, and these are the GFMs with IDs 165, 78, 137, 1, 175, 171, 181, 67, 179, 167, 351. Each selected GFM of the ensemble was continued to cumulate a total of at most 30 epochs. In some cases, the total number of epochs actually performed was les than 30 due to two combined factors: (1) the size of the GFM (i.e., the number of model parameters to train) and (2) the total wall-clock time for which the computational resources could be allocated on OLCF-Frontier. The "Ensemble_of_models" directory contains 15 sub-directories named as follows: - gfm_0.229 - gfm_0.156 - gfm_0.147 - gfm_0.260 - gfm_0.165 - gfm_0.78 - gfm_0.137 - gfm_0.1 - gfm_0.175 - gfm_0.171 - gfm_0.181 - gfm_0.67 - gfm_0.179 - gfm_0.167 - gfm_0.351 Each one of these sub-directories refers to one of the fifteen HPO trials that have been selected to continue the pre-training with at most 30 epochs. With each sub-directory associated with a specific HPO trial, the following files can be found: - config.json: file for argument parsing to develop and train an HydraGNN architecture - gfm_0.ID_epoch_N.pk: file with model parameters for HPO ID trial after N epochs of training The ensemble of fifteen GFM architectures was used for (1) ensemble averaging to stabilize the predictions of energy and atomic forces after pre-training for post-processing analysis and (2) ensemble uncertainty quantification (UQ). The code used to develop, pre-train, and load the pre-trained models for post-processing analysis is available on the ORNL-GitHub at the following link: https://github.com/ORNL/HydraGNN/tree/Predictive_GFM_2024

36 MATERIALS SCIENCE↗
DOE OSTI2020

Fast shared-memory streaming multilevel graph partitioning

In this report we show that a fast parallel graph partitioner can benefit many applications by reducing data transfers. The online methods for partitioning graphs have to be fast and they often rely on simple one-pass streaming algorithms, while the offline methods for partitioning graphs contain more involved algorithms and the most successful methods in this category belong to the multilevel approaches. In this work, we assess the feasibility of using streaming graph partitioning algorithms within the multilevel framework. Our end goal is to come up with a fast parallel offline multilevel partitioner that can produce competitive cutsize quality. We rely on a simple but fast and flexible streaming algorithm throughout the entire multilevel framework. This streaming algorithm serves multiple purposes in the partitioning process: a clustering algorithm in the coarsening, an effective algorithm for the initial partitioning, and a fast refinement algorithm in the uncoarsening. Its simple nature also lends itself easily for parallelization. The experiments on various graphs show that our approach is on the average up to 5.1x faster than the multi-threaded MeTiS, which comes at the expense of only 2x worse cutsize.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

FTK: A Simplicial Spacetime Meshing Framework for Robust and Scalable Feature Tracking

In this work, we present the Feature Tracking Kit (FTK), a framework that simplifies, scales, and delivers various feature-tracking algorithms for scientific data. The key of FTK is our simplicial spacetime meshing scheme that generalizes both regular and unstructured spatial meshes to spacetime while tessellating spacetime mesh elements into simplices. The benefits of using simplicial spacetime meshes include (1) reducing ambiguity cases for feature extraction and tracking, (2) simplifying the handling of degeneracies using symbolic perturbations, and (3) enabling scalable and parallel processing. The use of simplicial spacetime meshing simplifies and improves the implementation of several feature-tracking algorithms for critical points, quantum vortices, and isosurfaces. As a software framework, FTK provides end users with VTK/ParaView filters, Python bindings, a command line interface, and programming interfaces for feature-tracking applications. We demonstrate use cases as well as scalability studies through both synthetic data and scientific applications including tokamak, fluid dynamics, and superconductivity simulations. We also conduct end-to-end performance studies on the Summit supercomputer. FTK is open sourced under the MIT license: https://github.com/hguo/ftk.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

Today's high-performance computing (HPC) applications are producing vast volumes of data, which are challenging to store and transfer efficiently during the execution, such that data compression is becoming a critical technique to mitigate the storage burden and data movement cost. Huffman coding is arguably the most efficient Entropy coding algorithm in information theory, such that it could be found as a fundamental step in many modern compression algorithms such as DEFLATE. On the other hand, today's HPC applications are more and more relying on the accelerators such as GPU on supercomputers, while Huffman encoding suffers from low throughput on GPUs, resulting in a significant bottleneck in the entire data processing. In this paper, we propose and implement an efficient Huffman encoding approach based on modern GPU architectures, which addresses two key challenges: (1) how to parallelize the entire Huffman encoding algorithm, including codebook construction, and (2) how to fully utilize the high memory-bandwidth feature of modern GPU architectures. The detailed contribution is fourfold. (1) We develop an efficient parallel codebook construction on GPUs that scales effectively with the number of input symbols. (2) We propose a novel reduction based encoding scheme that can efficiently merge the codewords on GPUs. (3) We optimize the overall GPU performance by leveraging the state-of-the-art CUDA APIs such as Cooperative Groups. (4) We evaluate our Huffman encoder thoroughly using six real-world application datasets on two advanced GPUs and compare with our implemented multi-threaded Huffman encoder. Experiments show that our solution can improve the encoding throughput by up to 5.0x and 6.8x on NVIDIA RTX 5000 and V100, respectively, over the state-of-the-art GPU Huffman encoder, and by up to 3.3x over the multi-thread encoder on two 28-core Xeon Platinum 8280 CPUs.

Tian, Jiannan↗
DOE OSTI2021

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

Today's high-performance computing (HPC) applications are producing vast volumes of data, which are challenging to store and transfer efficiently during the execution, such that data compression is becoming a critical technique to mitigate the storage burden and data movement cost. Huffman coding is arguably the most efficient Entropy coding algorithm in information theory, such that it could be found as a fundamental step in many modern compression algorithms such as DEFLATE. On the other hand, today's HPC applications are more and more relying on the accelerators such as GPU on supercomputers, while Huffman encoding suffers from low throughput on GPUs, resulting in a significant bottleneck in the entire data processing. In this paper, we propose and implement an efficient Huffman encoding approach based on modern GPU architectures, which addresses two key challenges: (1) how to parallelize the entire Huffman encoding algorithm, including codebook construction, and (2) how to fully utilize the high memory-bandwidth feature of modern GPU architectures. The detailed contribution is fourfold. (1) We develop an efficient parallel codebook construction on GPUs that scales effectively with the number of input symbols. (2) We propose a novel reduction based encoding scheme that can efficiently merge the codewords on GPUs. (3) We optimize the overall GPU performance by leveraging the state-of-the-art CUDA APIs such as Cooperative Groups. (4) We evaluate our Huffman encoder thoroughly using six real-world application datasets on two advanced GPUs and compare with our implemented multithreaded Huffman encoder. Experiments show that our solution can improve the encoding throughput by up to 5.0× and 6.8× on NVIDIA RTX 5000 and V100, respectively, over the state-of-the-art GPU Huffman encoder, and by up to 3.3× over the multithread encoder on two 28-core Xeon Platinum 8280 CPUs.

Tian, Jiannan↗
DOE OSTI2022

A lightweight, user-configurable detector ASIC digital architecture with on-chip data compression for MHz X-ray coherent diffraction imaging

Today, most X-ray pixel detectors used at light sources transmit raw pixel data off the detector ASIC. With the availability of more advanced ASIC technology nodes for scientific application, more digital functionalities from the computing domains (e.g., compression) can be integrated directly into a detector ASIC to increase data velocity. In this paper, we describe a lightweight, user-configurable detector ASIC digital architecture with on-chip compression which can be implemented in 130 nm technologies in a reasonable area on the ASIC periphery. In addition, we present a design to efficiently handle the variable data from the stream of parallel compressors. The architecture includes user-selectable lossy and lossless compression blocks. The impact of lossy compression algorithms is evaluated on simulated and experimental X-ray ptychography datasets. This architecture is a practical approach to increase pixel detector frame rates towards the continuous 1 MHz regime for not only coherent imaging techniques such as ptychography, but also for other diffraction techniques at X-ray light sources.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Demonstrating Cross-Facility Data Processing at Scale with Laue Microdiffraction

In February and April 2023 live, at-scale data processing demonstrations were conducted between the Advanced Photon Source (APS), a synchrotron light source, and the Argonne Leadership Computing Facility (ALCF). These tests were run as part of a novel beamline technique: coded aperture laue micro-diffraction. This technique requires a significant amount of compute to decode appeture patterns embedded in the detector stream. An autonomous system was able to send data to ALCF during an experiment, utilize 50 nodes of the Polaris supercomputer to process 6-12 hour scans, and return the data back to the APS within 12-15 minutes behind the detector. With scan points arriving every 72 seconds, the system kept up with the beamline, potentially enabling in-experiment analysis. The data processing system utilizes Globus infrastructure and an on-demand queue to dynamically acquire nodes on Polaris. The underlying reconstruction algorithms were parallelized via MPI and accelerated with custom CUDA kernels.

Prince, Michael↗
DOE OSTI2023

Exploring temporal community evolution: algorithmic approaches and parallel optimization for dynamic community detection

Abstract Dynamic (temporal) graphs are a convenient mathematical abstraction for many practical complex systems including social contacts, business transactions, and computer communications. Community discovery is an extensively used graph analysis kernel with rich literature for static graphs. However, community discovery in a dynamic setting is challenging for two specific reasons. Firstly, the notion of temporal community lacks a widely accepted formalization, and only limited work exists on understanding how communities emerge over time. Secondly, the added temporal dimension along with the sheer size of modern graph data necessitates new scalable algorithms. In this paper, we investigate how communities evolve over time based on several graph metrics under a temporal formalization. We compare six different algorithmic approaches for dynamic community detection for their quality and runtime. We identify that a vertex-centric (local) optimization method works as efficiently as the classical modularity-based methods. To its advantage, such local computation allows for the efficient design of parallel algorithms without incurring a significant parallel overhead. Based on this insight, we design a shared-memory parallel algorithm DyComPar , which demonstrates between 4 and 18 fold speed-up on a multi-core machine with 20 threads, for several real-world and synthetic graphs from different domains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Multichannel Analysis of Surface Waves Accelerated (MASWAccelerated): Software for efficient surface wave inversion using MPI and GPUs

Multichannel Analysis of Surface Waves (MASW) is a technique frequently used in geotechnical engineering and engineering geophysics to infer 1D layered models of seismic shear wave velocities in the top tens to hundreds of meters of the subsurface. We aim to accelerate MASW calculations by capitalizing on modern computer hardware available in the workstations of most engineers: multiple cores and graphics processing units (GPUs). We propose new parallel and GPU accelerated algorithms for computing 1D MASW inversion, and provide software implementations in C using Message Passing Interface (MPI) and CUDA. These algorithms take advantage of sparsity that arises in the problem, and the work balance between processes considers typical data trends. We compare our methods to an existing open source Matlab MASW tool. Our serial C implementation achieves a 2x speedup over the Matlab software, and we continue to see improvements by parallelizing the problem with MPI. Here we see nearly perfect strong and weak scaling for uniform data, and improve strong scaling for realistic data by repartitioning the problem to process mapping. By utilizing GPUs available on most modern workstations, we observe an additional 1.3x speedup over the serial C implementation on the first use of the method. We typically repeatedly evaluate theoretical dispersion curves as part of an optimization procedure, and on the GPU the kernel can be cached for faster reuse on later runs. We observe a 3.2x speedup on the cached GPU runs compared to the serial C runs. This work is the first open-source parallel or GPU-accelerated software tool for MASW imaging, and should enable geotechnical engineers to fully utilize all computer hardware at their disposal.

58 GEOSCIENCES↗
DOE OSTI2020

GPU-Based Static Data-Flow Analysis for Fast and Scalable Android App Vetting

Many popular vetting tools for Android applications use static code analysis techniques. In particular, Interprocedural Data-Flow Graph (IDFG) construction is the computation at the core of Android static data-flow analysis and consumes most of the analysis time. Many analysis tools use a worklist algorithm, an iterative fixed-point approach, to construct the IDFG. In this paper, we observe that a straightforward GPU parallelization of the worklist algorithm leads to significant underutilization of the GPU resources. We identify four performance bottlenecks, namely, frequent dynamic memory allocations, high branch divergence, workload imbalance, and irregular memory access patterns. Accordingly, we propose GDroid, a GPU-based worklist algorithm implementation with multiple fine-grained optimizations tailored to common characteristics of Android applications. The optimizations considered are: matrix-based data structure, memory access-based node grouping, and worklist merging. Our experimental evaluation, performed on 1000 Android applications, shows that the proposed optimizations are beneficial to performance, and GDroid can achieve up to 128X speedups against a plain GPU implementation.

Android security↗