GPU-based Parallel Research Articles

Multithreaded and GPU-Based Implementations of a Modified Particle Swarm Optimization Algorithm with Application to Solving Large-Scale Systems of Nonlinear Equations

This paper presents a novel Graphics Processing Unit (GPU) accelerated implementation of a modified Particle Swarm Optimization (PSO) algorithm specifically designed to solve large-scale Systems of Nonlinear Equations (SNEs). The proposed GPU-based parallel version of the PSO algorithm uses the inherent parallelism of modern hardware architectures. Its performance is compared against both sequential and multithreaded Central Processing Unit (CPU) implementations. The primary objective is to evaluate the efficiency and scalability of PSO across different hardware platforms with a focus on solving large-scale SNEs involving thousands of equations and variables. The GPU-parallelized and multithreaded versions of the algorithm were implemented in the Julia programming language. Performance analyses were conducted on an NVIDIA A100 GPU and an AMD EPYC 7643 CPU. The tests utilized a set of challenging, scalable SNEs with dimensions ranging from 1000 to 5000. Results demonstrate that the GPU accelerated modified PSO substantially outperforms its CPU counterparts, achieving substantial speedups and consistently surpassing the highly optimized multithreaded CPU implementation in terms of computation time and scalability as the problem size increases. Therefore, this work evaluates the trade-offs between different hardware platforms and underscores the potential of GPU-based parallelism for accelerating SNE solvers.

Heterogeneous many-core optimization for Monte Carlo path-tracing on new generation Sunway HPC system

We present swRender, a new parallel rendering pipeline based on the new Sunway many-core architecture (SW26010P) for the Monte Carlo path-tracing algorithm. Previous parallel rendering schemes are unsuitable for our task due to issues such as vast differences in hardware architectures and bottlenecks in I/O communication efficiency. To that end, we create a new two-level parallel tile rendering framework to fully utilize the Sunway computing resources, a practical tile-grouping load-balancing method to maintain the framework’s stability, and a novel many-core acceleration optimization to improve the rendering performance at the pixel level. Our method achieves (1) an average speedup of 16x in multiple benchmarks when compared to the baseline path-tracing model on the Sunway architecture, and (2) an average speedup of 2x when compared to state-of-the-art CPU, co-processor, and GPU-based parallel rendering approaches. Moreover, we scale swRender to run on 15 million cores and obtain high scalable parallel efficiency of 92%.

Dynamic numerical simulation of ice-propeller milling based on GPU parallel computing

To integrate high-performance GPU parallel computing with the peridynamics method and enhance the computational efficiency of numerical simulations for ice-propeller milling, thus providing better data support for the design of propellers in ice-covered areas, a GPU-based parallel peridynamics computational approach was developed on CUDA in this study. The approach was built upon the bond-based peridynamics theory and CUDA programming framework, and its validity was confirmed using test cases involving an airfoil cutting ice and an ice ball impacting a rigid wall. A corresponding three-dimensional GPU parallel computational program was created for the ice-propeller milling process, and the computational code was optimized, resulting in a 24-fold increase in computational efficiency. Utilizing the high-performance computational code, the influence of sea ice elastic modulus and propeller pitch on the mechanical performance of the blades was investigated. The computational results revealed that the ice loads on the blades increased with rising elastic modulus and decreased with increasing pitch, and a larger pitch led to more sea ice being milled away.

High-spatiotemporal resolution microwave-induced thermoacoustic tomography for imaging biological dynamics in deep tissue

Biological systems undergo constant dynamic changes across various spatial and temporal scales. To investigate the intricate biological dynamics in living organisms, there is a strong need for high-speed and high-resolution imaging capabilities with significant imaging depth. In this work, we present high-spatiotemporal resolution microwave-induced thermoacoustic tomography (HR-MTAT) as a method for imaging biological dynamics in deep tissues. HR-MTAT utilizes nanosecond pulsed microwave excitation and ultrasound detection, with appropriate spatial configurations, to achieve high coupling of the sample to the microwaves, to produce images in soft tissue with dielectric contrast and sub-millimeter spatial resolution (230 μm), to a depth of a few centimeters. Notably, by employing a 128-channel parallel signal acquisition and digitization strategy, the field programmable gate array module manages data synthesis, and GPU-based parallel pixel reconstruction facilitates HR-MTAT to accomplish single-frame image reconstruction in an impressive 50 μs. The practical feasibility of HR-MTAT was evaluated in live mice. The results show that HR-MTAT can noninvasively image whole-body small animals (up to 60 mm in depth) with clear resolution of internal organ structures at a frame rate of 100 Hz, without the need for labeling. At this high spatiotemporal resolution, HR-MTAT can capture respiration, heartbeat, and arterial pulse propagation without motion artifacts and track bio-nanoprobes in livers and tumors. These findings demonstrate HR-MTAT's ability to perform dynamic imaging with high contrast and resolution in deep tissues.

Efficient Parallel Processing of R-Tree on GPUs

R-tree is an important multi-dimensional data structure widely employed in many applications for storing and querying spatial data. As GPUs emerge as powerful computing hardware platforms, a GPU-based parallel R-tree becomes the key to efficiently port R-tree-related applications to GPUs. However, traditional tree-based data structures can hardly be directly ported to GPUs, and it is also a great challenge to develop highly efficient parallel tree-based data structures on GPUs. The difficulty mostly lies in the design of tree-based data structures and related operations in the context of many-core architecture that can facilitate parallel processing. We summarize our contributions as follows: (i) design a GPU-friendly data structure to store spatial data; (ii) present two parallel R-tree construction algorithms and one parallel R-tree query algorithm that can take the hardware characteristics of GPUs into consideration; and (iii) port the vector map overlay system from CPU to GPU to demonstrate the feasibility of parallel R-tree. Experimental results show that our parallel R-tree on GPU is efficient and practical. Compared with the traditional CPU-based sequential vector map overlay system, our vector map overlay system based on parallel R-tree can achieve nearly 10-fold speedup.

Graph analysis using a GPU-based parallel algorithm: quantum clustering

Graph analysis using a GPU-based parallel algorithm: quantum clustering

Outlier Detection Using a GPU-Based Parallel Algorithm: Quantum Clustering

We introduce a novel hypothesis in the field of outlier detection, suggesting that normal data tend to be distributed in regions where the density changes smoothly or is less pronounced, whereas abnormal data often exhibit distribution in areas characterized by abrupt changes in data density. Relying on this hypothesis, we develop a novel density-based unsupervised outlier detection method, referred to as Quantum Clustering (QC). This approach addresses the processing of unlabeled data and employs a potential function to identify the centroids of clusters and outliers effectively. Experimental results demonstrate that the potential function can accurately detect hidden outliers within data points. Furthermore, by adjusting the parameter [Formula: see text], QC enables the identification of more subtle outliers. Additionally, our method is evaluated on several benchmarks from diverse research areas, affirming its broad applicability.

GPU-based parallel programming for FEM analysis in the optimization of steel frames

ABSTRACT Optimization of large-scale frame structures consumes a vast amount of time since the analysis of such complex systems contains several iterative processes. Mitigating computational burden and reducing this time to a reasonable level is possible by running GPU (Graphical Processing Unit) processors, which can be found on standard computers. This study presents an algorithm for the acceleration of size optimization of steel frames by using the BBO (Biogeography-Based Optimization) method that is suitable for GPU architecture. The GPU-based parallel algorithm, designed for FEM (Finite Element Method) analysis, is applied to three hypothetical steel-frame case structures with different numbers of members and nodes; and processed on four different computers which are available on the market. The presented case studies revealed that the proposed solution’s efficiency increases as the number of members increases and confirmed the ability of the acceleration algorithm for optimization of large-scale frame structures and provided time efficiency.

Method for GPU-based spectral data cube reconstruction of integral field snapshot imaging spectrometers.

In this paper, the principles of spectral data cube reconstruction based on an integral field snapshot imaging spectrometer and GPU-based acceleration are presented. The primary focus is on improving the reconstruction algorithm using GPU parallel computing technology to enhance the computational efficiency for real-time applications. And the computational tasks of the spectral reconstruction algorithm were transferred to the GPU through program parallelization and memory optimization, resulting in significant performance gains. Experimental results indicate that the average processing time of the GPU-based parallel algorithm is approximately 29.43 ms, showing a substantial acceleration ratio of about 14.27 compared to the traditional CPU serial algorithm with an average processing time of around 420.46 ms. The study aims to refine the GPU parallelization algorithm for continued improvement in computational efficiency and overall performance. The anticipated applications of this research include providing crucial technical support for the perception and monitoring of crop growth traits in agricultural production, contributing to the modernization and advancement of intelligence in the field.

GPU-Based Parallel Processing Techniques for Enhanced Brain Magnetic Resonance Imaging Analysis: A Review of Recent Advances.

The approach of using more than one processor to compute in order to overcome the complexity of different medical imaging methods that make up an overall job is known as GPU (graphic processing unit)-based parallel processing. It is extremely important for several medical imaging techniques such as image classification, object detection, image segmentation, registration, and content-based image retrieval, since the GPU-based parallel processing approach allows for time-efficient computation by a software, allowing multiple computations to be completed at once. On the other hand, a non-invasive imaging technology that may depict the shape of an anatomy and the biological advancements of the human body is known as magnetic resonance imaging (MRI). Implementing GPU-based parallel processing approaches in brain MRI analysis with medical imaging techniques might be helpful in achieving immediate and timely image capture. Therefore, this extended review (the extension of the IWBBIO2023 conference paper) offers a thorough overview of the literature with an emphasis on the expanding use of GPU-based parallel processing methods for the medical analysis of brain MRIs with the imaging techniques mentioned above, given the need for quicker computation to acquire early and real-time feedback in medicine. Between 2019 and 2023, we examined the articles in the literature matrix that include the tasks, techniques, MRI sequences, and processing results. As a result, the methods discussed in this review demonstrate the advancements achieved until now in minimizing computing runtime as well as the obstacles and problems still to be solved in the future.

Development of a GPU-based multisphere DE–FE coupling method for interaction simulations between an off-road tire and a gravel terrain

For decades, growing interest has been devoted to simulating the tire–soil interaction phenomena using discrete element/finite element (DE–FE) coupling methods. In contrast to the widely used approach that idealizes soils as spherical DEs, a newly developed multisphere DE–FE method has been demonstrated to be more accurate in reproducing such phenomena; however, it requires considerable computational cost for large-scale tire–soil interaction simulations. Therefore, this study aims to develop an efficient graphics processing unit (GPU)-based multisphere DE–FE method based on a CUDA FORTRAN programming environment. To this end, two-level grids are introduced for the parallelization of contact detection for targeted multisphere DEs and subspheres, which helps to find contact pairs for the targeted subspheres of a multisphere DE in an efficient manner. In contrast to existing GPU-based parallelization techniques, which typically use atomic operations to avoid memory access conflicts, this study presents a parallelization strategy to process a contact pair between bounding spheres using one GPU thread to efficiently handle with owner-member relationships between multisphere DEs and their subspheres. In the parallelization for force calculation, our method introduces an efficient technique that utilizes one GPU thread to process a contact pair between subspheres, or between subspheres and FE segments, to reduce the number of repeated calculations. Finally, the developed GPU-based method is applied to analyze the travelling behaviors of a complex-patterned off-road tire on a gravel terrain, and the effectiveness and computational efficiency of this method are validated via indoor soil-bin experimental outcomes as well as serial and parallel simulation results. It is found that a speedup of approximately 38 has been achieved with the aid of the developed method.

GPU parallel computing based on PF-LBM method for simulating dendrites growth under natural convection conditions

This study introduces a GPU-based parallel computing approach that combines the phase-field model (PF) and the lattice Boltzmann model (LBM). By establishing a coupled multiphase field model incorporating physical external fields such as flow field, temperature field, and solute field, the research simulates the growth of single grains and multiple grains under the influence of natural convection. The variations in dendritic morphology, flow field, and solute field during dendritic solidification processes are observed. Initially, the study analyzes the morphology of equiaxed dendrites and the growth patterns of primary dendrites arms under natural convection conditions. The evolution of equiaxed dendrites in single grains and multiple grains under various conditions is investigated. Furthermore, the study explores the impact of different anisotropy strengths on the growth of single grains and multiple grains under natural convection. Notably, a distinct “necking” phenomenon is observed when the anisotropy strength of a single grain is 0.05. In the case of multiple grains, where competition between dendrites is present in addition to the influence of natural convection, a pronounced “necking” phenomenon is evident at an anisotropy strength of 0.03. Moreover, OpenCL parallel technology is designed on the GPU platform to accelerate the solution of the model. The parallelization of the phase-field model coupled with the LBM model on the GPU demonstrates a clear advantage. The parallel computation based on GPU not only exhibits absolute superiority but also shows more significant acceleration effects as the computational domain increases.

A GPU-Based Parallel Region Classification Method for Continuous Constraint Satisfaction Problems

Abstract Continuous constraint satisfaction is prevalent in many science and engineering fields. When solving continuous constraint satisfaction problems, it is more advantageous for practitioners to derive all feasible regions (i.e., the solution space) rather than a limited number of solution points, since these feasible regions facilitate design concept generation and design tradeoff evaluation. Several central processing unit (CPU)-based branch-and-prune methods and geometric approximation methods have been proposed in prior research to derive feasible regions for continuous constraint satisfaction problems. However, these methods have not been extensively adopted in practice, mainly because of their high computational expense. To overcome the computational bottleneck of extant CPU-based methods, this paper introduces a GPU-based parallel region classification method to derive feasible regions for continuous constraint satisfaction problems in a reasonable computational time. Using interval arithmetic, coupled with the computational power of GPU, this method iteratively partitions the design space into many subregions and classifies these subregions as feasible, infeasible, and indeterminate regions. To visualize these classified regions in the design space, a planar visualization approach that projects all classified regions into one figure is also proposed. The GPU-based parallel region classification method and the planar visualization approach are validated through two case studies about the bird function and the welded beam design. These case studies show that the method and the approach can solve the continuous constraint satisfaction problems and visualize the results effectively and efficiently. A four-step procedure for implementing the method and the approach in practice is also outlined.

OCTSharp: an open-source and real-time OCT imaging software based on C.

Optical coherence tomography (OCT) demands massive data processing and real-time displaying during high-speed imaging. Current OCT imaging software is predominantly based on C++, aiming to maximize performance through low-level hardware management. However, the steep learning curve of C++ hinders agile prototyping, particularly for research purposes. Moreover, manual memory management poses challenges for novice developers and may lead to potential security issues. To address these limitations, OCTSharp is developed as an open-source OCT software based on the memory-safe language C#. Within the managed C# environment, OCTSharp offers synchronized hardware control, minimal memory management, and GPU-based parallel processing. The software has been thoroughly tested and proven capable of supporting real-time image acquisition, processing, and visualization with spectral-domain OCT systems equipped with the latest advanced hardware. With these enhancements, OCTSharp is positioned to serve as an open-source platform tailored for various applications.

Accurate Global Point Cloud Registration Using GPU-Based Parallel Angular Radon Spectrum.

Accurate robot localization and mapping can be improved through the adoption of globally optimal registration methods, like the Angular Radon Spectrum (ARS). In this paper, we present Cud-ARS, an efficient variant of the ARS algorithm for 2D registration designed for parallel execution of the most computationally expensive steps on Nvidia™ Graphics Processing Units (GPUs). Cud-ARS is able to compute the ARS in parallel blocks, with each associated to a subset of input points. We also propose a global branch-and-bound method for translation estimation. This novel parallel algorithm has been tested on multiple datasets. The proposed method is able to speed up the execution time by two orders of magnitude while obtaining more accurate results in rotation estimation than state-of-the-art correspondence-based algorithms. Our experiments also assess the potential of this novel approach in mapping applications, showing the contribution of GPU programming to efficient solutions of robotic tasks.

Parallel inference for cross-collection latent generalized Dirichlet allocation model and applications

Existing cross-collection topic models with document-topic representation encounter performance bottlenecks in large-scale datasets due to their reliance on Dirichlet priors and conventional inference schemes. These constraints become noticeable in models derived from the Latent Dirichlet Allocation (LDA) framework. To address these challenges, this paper introduces the GPU-accelerated cross-collection latent generalized Dirichlet allocation (gccLGDA) model. This innovative approach integrates the benefits of generalized Dirichlet (GD) distribution with the computational prowess of GPU-based parallel inference, offering enhanced cross-collection topic modeling. The gccLGDA employs the GD distribution presenting a more flexible prior with a comprehensive covariance structure, enabling a more nuanced capture of relationships between latent topics across different collections. Leveraging GPU for parallel inference, our model promises scalable and efficient training for expansive datasets, making it apt for large-scale data challenges. Through empirical evaluations in comparative text mining and document classification, we demonstrate the enhanced performance of the gccLGDA, highlighting its advantages over existing cross-collection topic models.

Optimized Implementation of Argon2 Utilizing the Graphics Processing Unit

In modern information technology systems, secure storage and transmission of personal and sensitive data are recognized as important tasks. These requirements are achieved through secure and robust encryption methods. Argon2 is an advanced cryptographic algorithm that emerged as the winner in the Password Hashing Competition (PHC), offering a concrete and secure measure. Argon2 also provides a secure mechanism against side-channel attacks and cracking attacks using parallel processing (e.g., GPU). In this paper, we analyze the existing GPU-based implementation of the Argon2 algorithm and further optimize the implementation by improving the performance of the hashing function during the computation process. The proposed method focuses on enhancing performance by distributing tasks between CPU and GPU units, reducing the data transfer cost for efficient GPU-based parallel processing. By shifting several stages from the CPU to the GPU, the data transfer cost is significantly reduced, resulting in faster processing times, particularly when handling a larger number of passwords and higher levels of parallelism. Additionally, we optimize the utilization of the GPU’s shared memory, which enhances memory access speed, especially in the computation of the hash value generation process. Furthermore, we leverage the parallel processing capabilities of the GPU to perform efficient brute-force attacks. By computing the H function on the GPU, the proposed implementation can generate initial blocks for multiple inputs in a single operation, making brute-force attacks in an efficient way. The proposed implementation outperforms existing methods, especially when processing a larger number of passwords and operating at higher levels of parallelism.

GPU parallelization of particulate matter concentration modeling in indoor environment with cellular automata framework

Nowadays, the CFD approaches for modeling turbulent airflow and particulate matter (PM) concentration distribution are matured despite they all suffer from heavy computational demands. Particularly, in indoor PM concentration modeling, a novel cellular automata (CA) approach in “Modeling particulate matter concentration in indoor environment with cellular automata framework” is developed to achieve almost the same accuracy with improved efficiency as the Eulerian approach. To further enhance its efficiency, this study proposes two parallelization procedures. With the mechanism parallelization, the four PM transport mechanisms (flow advection, turbulent diffusion, gravitational settling, and boundary deposition) are simulated simultaneously instead of sequentially. Besides, using the GPU-based cell parallelization by adopting OpenCL 2.1 under Nvidia CUDA, the execution of all the PM transport mechanisms is performed parallelly on GPUs instead of sequentially on the CPU. Three parallelized CA scenarios, i.e., the parallelized CA approach with only the mechanism parallelization, with only the GPU-based cell parallelization, and with both the two parallelization procedures, are evaluated through two indoor PM concentration experiments. The three parallelized CA scenarios are found to maintain the accuracy but enhance the efficiency by 174%–210%, 1780%–5730%, and 2427%–7695%, respectively. Thus, the GPU-based cell parallelization obtains more efficiency enhancement than the mechanism parallelization. Furthermore, despite the simulations are performed on an i9 PC with an Intel UHD Graphics 630 graphic card, the parallelized CA approach with both the two parallelization procedures can enhance its efficiency up to 24–77 times, proving its considerable potentials as a useful tool for real-time 3D indoor PM distribution modeling.

An occupant-centric approach for spatio-temporal visual comfort assessment and optimization in daylit sports spaces

Most visual comfort analysis is based on glare detections in limited fixed view scenes, but sports spaces present challenges given occupants’ spatial and view directional variations in sports-related visual tasks. This paper proposes an occupant-centric approach for spatio-temporal visual comfort assessment and optimization (ST-VCAO) in daylit sports spaces by better considering the occupants’ movement behaviour. It introduces the movable view scenes (MVS) in glare simulations and further accelerates the ST-VCAO process using the GPU-based parallel simulation combining response surface methodology. The proposed approach was applied to a real case building in Harbin, China. Annual daylight and glare simulations in two tennis courts with a total of 500 MVS were performed using Perez all-weather sky model with Chinese standard weather data. Results indicate that the proposed approach could sufficiently clarify the spatial variance and temporal variation of visual comfort across all MVS, which is appropriate for sports spaces. Meanwhile, using the developed workflow, the total computational time could be saved by 27.08% (Case 1) or 71.25% (Case 2). Amongst all Pareto solutions, the optimum alternative upon the worst one observed 200% (Case 1) or 50.7% (Case 2) higher visual comfort.

Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments

We present <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Orbit</small> , a unified and modular framework for robot learning powered by <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Nvidia</small> Isaac Sim. It offers a modular design to easily and efficiently create robotic environments with photo-realistic scenes and high-fidelity rigid and deformable body simulation. With <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Orbit</small> , we provide a suite of benchmark tasks of varying difficulty– from single-stage cabinet opening and cloth folding to multi-stage tasks such as room reorganization. To support working with diverse observations and action spaces, we include fixed-arm and mobile manipulators with different physically-based sensors and motion generators. <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Orbit</small> allows training reinforcement learning policies and collecting large demonstration datasets from hand-crafted or expert solutions in a matter of minutes by leveraging GPU-based parallelization. In summary, we offer an open-sourced framework that readily comes with 16 robotic platforms, 4 sensor modalities, 10 motion generators, more than 20 benchmark tasks, and wrappers to 4 learning libraries. With this framework, we aim to support various research areas, including representation learning, reinforcement learning, imitation learning, and task and motion planning. We hope it helps establish interdisciplinary collaborations in these communities, and its modularity makes it easily extensible for more tasks and applications in the future. For videos, documentation, and code: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://isaac-orbit.github.io/</uri> .