CUDA Environment Research Articles

A GPU accelerated three-dimensional ghost cell method with an improved implicit surface representation for complex rigid or flexible boundary flows

This paper presents an efficient and reliable three-dimensional (3D) ghost cell method for complex rigid or flexible boundary flows. An improved implicit interface representation method is developed to treat the arbitrary complex interfaces including the thin or sharp boundaries. This method is robust and avoids the solving of a large dense matrix, and thus the computational efficiency is greatly enhanced. The ghost cell method with a unified eight-node interpolation scheme is adopted to enforce the no-slip boundary conditions on complex boundaries. To perform 3D high-resolution simulation on a desktop computer, a GPU parallel framework in CUDA environment is developed to significantly accelerate the computational efficiency of the present solver. The horizontal oscillations of a two-dimensional (2D) cylinder and a 3D sphere in the rest fluid are simulated to validate the accuracy and computational performance of the present model. Spatial accuracy of near second-order on the boundary treatment and good grid convergence are confirmed. Also, the present solver can achieve hundreds of acceleration ratios for 2D grids and thousands of acceleration ratios for 3D grids. Then, uniform flows around a 3D arbitrary rigid or flexible object such as a stationary cylindrical cylinder, a stationary square cylinder, an oscillating airfoil, and a swimming carangiform are simulated. The accuracy and capability of the present model for 3D complex geometries with large-amplitude movement or deformation is satisfactorily validated. Moreover, typical 3D wake structures are well captured.

Spark Distributed Real-Time Data and GPU Parallel Computing Based on 5G Virtual Reality

5G virtual reality has attracted many manufacturers and users with its unique immersion, interactivity and imagination characteristics, which has become the focus of new markets. The purpose of this article is to use Spark distributed real-time data system and GPU parallel computing to quickly process and analyze data. This article mainly designs a general-purpose real-time data analysis and processing system based on Spark, which mainly includes new ETL and real-time processing engine modules, and is committed to achieving higher real-time performance than traditional Hadoop. And realize fast calculation. At the same time there is universality and stability. Includes real-time flow calculations. Fast batch processing and machine learning The various types of data computers are included in this article by preparing the cutting device and adjusting the cutting output. The device is ready to effectively terminate the CUDA environment. The cudamalloc function is used to allocate a linear space of bytes to the device, and then transfer the data from the host to the device to determine the number of GPU blocks and threads. GPU parallel computing can increase the data processing speed by 27%, while the secondary programming algorithm can reduce the optimization time of the cup by 12%.

Virtual Clinical Trials in 2D and 3D X-ray Breast Imaging and Dosimetry: Comparison of CPU-Based and GPU-Based Monte Carlo Codes.

Simple SummaryVirtual clinical trials in X-ray breast imaging may permit substantial reduction of the costs, times, and exposure risk to patient of clinical trials. Monte Carlo simulation techniques are increasingly adopted for VCT in breast imaging and dosimetry studies. This work aims to compare three different platforms for breast VCT studies, to develop real-time virtual DM, DBT and BCT examinations, where the in-silico image acquisition process takes a computational time comparable to that typical of a corresponding real clinical examination.Computational reproductions of medical imaging tests, a form of virtual clinical trials (VCTs), are increasingly being used, particularly in breast imaging research. The accuracy of the computational platform that is used for the imaging and dosimetry simulation processes is a fundamental requirement. Moreover, for practical usage, the imaging simulation computation time should be compatible with the clinical workflow. We compared three different platforms for in-silico X-ray 3D breast imaging: the Agata (University & INFN Napoli) that was based on the Geant4 toolkit and running on a CPU-based server architecture; the XRMC Monte Carlo (University of Cagliari) that was based on the use of variance reduction techniques, running on a CPU hardware; and the Monte Carlo code gCTD (University of Texas Southwestern Medical Center) running on a single GPU platform with CUDA environment. The tests simulated the irradiation of cylindrical objects as well as anthropomorphic breast phantoms and produced 2D and 3D images and 3D maps of absorbed dose. All the codes showed compatible results in terms of simulated dose maps and imaging values within a maximum discrepancy of 3%. The GPU-based code produced a reduction of the computation time up to factor 104, and so permits real-time VCT studies for X-ray breast imaging.

Multiple‐GPU parallelization of three‐dimensional material point method based on single‐root complex

AbstractAs one of the arbitrary Lagrangian–Eulerian methods, the material point method (MPM) owns intrinsic advantages in simulation of large deformation problems by combining the merits of the Lagrangian and Eulerian approaches. Significant computational intensity is involved in the calculations of the MPM due to its very fine mesh needed to achieve a sufficiently high accuracy. A new multiple‐GPU parallel strategy is developed based on a single‐root complex architecture of the computer purely within a CUDA environment. Peer‐to‐Peer (P2P) communication between the GPUs is performed to exchange the information of the crossing particles and ghost element nodes, which is faster than the heavy send/receive operations between different computers through the infiniBand network. Domain decomposition is performed to split the whole computational task over the GPUs with a number of subdomains. The computations within each subdomain are allocated on a corresponding GPU using an enhanced “Particle‐List” scheme to tackle the data race during the interpolation from associated particles to common nodes. The acceleration effect of the parallelization is evaluated with two benchmarks cases, mini‐slump test after a dam break and cone penetration test in clay, where the maximum speedups with 1 and 8 GPUs are 88 and 604, respectively.

Research on fine tuning parameter insulator identification based on YOLOV4 algorithm

Aiming at the problem that the training network time of YOLOV4 algorithm is too long due to the large data set of aerial insulator images, a method based on YOLOV4 algorithm is proposed to shorten the training time by fine-tuning parameters without affecting the positioning detection accuracy. Based on the development of UBANTU virtual machine, through CUDA and CUDNN environment configuration, and through the detection and verification of insulator aerial photo data set, the feasibility of accurate positioning of insulators under the condition of fine tuning parameters of YOLOV4 algorithm is successfully proved.

A system architecture for parallel analysis of flux-balanced metabolic pathways

Elementary flux mode (EFM) analysis is a well-studied method in constraint-based modeling of metabolic networks. In EFM analysis, a network is decomposed into minimal functional pathways based on the assumption of balanced metabolic fluxes. In this paper, a system architecture is proposed that approximately models the functionality of metabolic networks. The AND/OR graph model is used to represent the metabolic network and each processing element in the system emulates the functionality of a metabolite. The system is implemented on a graphics processing unit (GPU) as the hardware platform using CUDA environment. The proposed architecture takes advantage of the inherent parallelism in the network structure in terms of both pathway and metabolite traversal. The function of each element is defined such that it can find flux-balanced pathways. Pathways in both small and large metabolic networks are applied to the proposed architecture and the results are discussed.

A divide-and-conquer approach for the computation of the Moore-Penrose inverses

In this paper, we present a divide-and-conquer method for computing the Moore-Penrose inverse of a bidiagonal matrix. Working together with the effective parallel algorithms for the reduction of a general matrix to the bidiagonal matrix, the proposed method provides a new parallel approach for the computation of the Moore-Penrose inverse of a general matrix. This new approach was implemented in the CUDA environment and a significant speedup was observed on randomly generated matrices.

A metaheuristic optimization algorithm for multimodal benchmark function in a GPU architecture

It is well known that the numerical solution of evolutionary systems and problems based on topological design requires a high computational power. In the last years, many parallel algorithms have been developed in order to improve its performance. Among them, genetic algorithms (GAs) are one of the most popular metaheuristic algorithms inspired by Darwin's evolution theory. From the High Performance Computing (HPC) point of view, the CUDA environment is probably the parallel computing platform and programming model that more heyday has had in recent years, mainly due to the low acquisition cost of graphics processing units (GPUs) compared to a cluster with similar functional characteristics. Consequently, the number of GPU-CUDAs present in the top 500 fastest supercomputers in the world is constantly growing. In this paper, a numerical algorithm developed in the NVIDIA CUDA platform capable of solving classical optimization functions usually employed as benchmarks is presented. The obtained results demonstrate that GPUs are a valuable tool for acceleration of GAs and may enable its use in much complex problems. Also, a sensitivity analysis is carried out in order to show the relative weight of each GA operator in the whole computational cost of the algorithm.

Stochastic first passage time accelerated with CUDA

The numerical integration of stochastic trajectories to estimate the time to pass a threshold is an interesting physical quantity, for instance in Josephson junctions and atomic force microscopy, where the full trajectory is not accessible. We propose an algorithm suitable for efficient implementation on graphical processing unit in CUDA environment. The proposed approach for well balanced loads achieves almost perfect scaling with the number of available threads and processors, and allows an acceleration of about 400× with a GPU GTX980 respect to standard multicore CPU. This method allows with off the shell GPU to challenge problems that are otherwise prohibitive, as thermal activation in slowly tilted potentials. In particular, we demonstrate that it is possible to simulate the switching currents distributions of Josephson junctions in the timescale of actual experiments.

GPU fuzzy c-means algorithm implementations: performance analysis on medical image segmentation

Image segmentation in the medical imagery such as MRI, is an essential step to the sensitive analysis of human tissues lesions with the objective to improve the partition of different parts of the image according to their specific characteristics. Fuzzy c-means (FCM) is one of the widely used algorithms in literature regarding image segmentation. Indeed, it offers performances to the precision level in many medical fields of applications. However, the main limitation of FCM algorithm is time consuming during the image segmentation by clustering. In order to improve and to reduce the time delay of image data processing, we implemented three methods inspired from the FCM on GPU GT 740 m by using the CUDA environment. This latter is well adapted to the new architectures of processing, and its sequential migration towards the parallel approach through the SIMD architecture as GPU cards solves this time constraint. Furthermore, we have improved, via the two current developed implementations methods, the speed up of the processing acquisition in comparison with the reference methods. The efficiency evaluation such as strengths and weaknesses of each implemented method will be evaluated on medical images segmentation according to the size of the modelled brain tumours.

Research on Parallelization of GPU-based K-Nearest Neighbor Algorithm

Based on the analysis of the K-Nearest Neighbor Algorithm, the feasibility of parallelization is studied from the steps of the algorithm, the operation efficiency and the data structure of each step, and the part of parallel execution is determined. A K-Nearest Neighbor Algorithm parallelization scheme is designed and the parallel G-KNN algorithm is implemented in the CUDA environment. The experimental results show that the K-Nearest Neighbor Algorithm has a significant improvement in efficiency after parallelization, especially on large-scale data.

GPU-based parallelization for bubble mesh generation

PurposeIn FEM computations, the mesh quality improves the accuracy of the approximation solution and reduces the computation time. The dynamic bubble system meshing technique can provide high-quality meshes, but the packing process is time-consuming. This paper aims to improve the running time of the bubble meshing by using the advantages of parallel computing on graphics processing unit (GPU).Design/methodology/approachThis paper is based on the analysis of the processing time on CPU. A massively parallel computing-based CUDA architecture is proposed to improve the bubble displacement and database updating. Constraints linked to hardware considerations are taken into account. Finally, speedup factors are provided on test cases and real scale examples.FindingsThe numerical experiences show the efficiency of parallel performance reaches a speedup of 35 compared to the serial implementation.Research limitations/implicationsThis contribution is so far limited to two-dimensional (2D) geometries although the extension to three-dimension (3D) is straightforward regarding the meshing technique itself and the GPU implementation. The authors’ works are based on a CUDA environment which is widely used by developers. C\\C++ and Java were the programming languages used. Other languages may of course lead to slightly different implementations.Practical implicationsThis approach makes it possible to use bubble meshing technique for both initial design and optimization, as excellent meshes can be built in few seconds.Originality/valueCompared to previous works, this contribution shows that the scalability of the bubble meshing technique needs to solve two key issues: reach a T(N) global cost of the implementation and reach a very fast size map interpolation strategy.

GPU-accelerated algorithms for many-particle continuous-time quantum walks

Many-particle continuous-time quantum walks (CTQWs) represent a resource for several tasks in quantum technology, including quantum search algorithms and universal quantum computation. In order to design and implement CTQWs in a realistic scenario, one needs effective simulation tools for Hamiltonians that take into account static noise and fluctuations in the lattice, i.e. Hamiltonians containing stochastic terms. To this aim, we suggest a parallel algorithm based on the Taylor series expansion of the evolution operator, and compare its performances with those of algorithms based on the exact diagonalization of the Hamiltonian or a 4th order Runge–Kutta integration. We prove that both Taylor-series expansion and Runge–Kutta algorithms are reliable and have a low computational cost, the Taylor-series expansion showing the additional advantage of a memory allocation not depending on the precision of calculation. Both algorithms are also highly parallelizable within the SIMT paradigm, and are thus suitable for GPGPU computing. In turn, we have benchmarked 4 NVIDIA GPUs and 3 quad-core Intel CPUs for a 2-particle system over lattices of increasing dimension, showing that the speedup provided by GPU computing, with respect to the OPENMP parallelization, lies in the range between 8x and (more than) 20x, depending on the frequency of post-processing. GPU-accelerated codes thus allow one to overcome concerns about the execution time, and make it possible simulations with many interacting particles on large lattices, with the only limit of the memory available on the device. Program summaryProgram Title: cuQuWaLicensing provisions: GNU General Public License, version 3Program Files doi:http://dx.doi.org/10.17632/vjpnjgycdj.1Programming language: CUDA CNature of problem: Evolution of many-particle continuous-time quantum-walks on a multidimensional grid in a noisy environment. The submitted code is specialized for the simulation of 2-particle quantum-walks with periodic boundary conditions.Solution method: Taylor-series expansion of the evolution operator. The density-matrix is calculated by averaging multiple independent realizations of the system.External routines: cuBLAS, cuRANDUnusual features: Simulations are run exclusively on the graphic processing unit within the CUDA environment. An undocumented misbehavior in the random-number generation routine (cuRAND package) can corrupt the simulation of large systems, though no problems are reported for small and medium-size systems. Compiling the code with the -arch=sm_30 flag for compute capability 3.5 and above fixes this issue.

A GPU-Based Approach for Automatic Segmentation of White Matter Lesions

ABSTRACT White matter lesions (WMLs) in the human brain are generally diagnosed by using magnetic resonance (MR) images. Doctors working on WMLs generally need to calculate the volume of lesions for each patient at regular intervals in order to observe the course of diseases and manage the treatment process. This paper introduces an unsupervised automatic approach for segmentation of WMLs in the human brain. The approach consists of skull stripping, preprocessing, and lesion detection steps. Three skull stripping methods are proposed to increase successful stripping probability on various qualities of MR image data. After preprocessing and segmenting lesions, the system applies volumetric calculation and 3D visualization of lesions. This volumetric information can be used by doctors to observe changes in the lesions against regularly scanned MR images of patients. GPU-based parallel image processing techniques are utilized on Nvidia CUDA environment in order to improve performance by 40–50 times. Therefore, the developed system saves the time of doctors by providing them a fast automatic segmentation method for WMLs.

GPU-based computational modeling of magnetic resonance imaging of vascular structures

Magnetic resonance imaging (MRI) is one of the most important diagnostic tools in modern medicine. Since it is a high-cost and highly-complex imaging modality, computational models are frequently built to enhance its understanding as well as to support further development. However, such models often have to be simplified to complete simulations in a reasonable time. Thus, the simulations with high spatial/temporal resolutions, with any motion consideration (like blood flow) and/or with 3D objects usually call for using parallel computing environments. In this paper, we propose to use graphics processing units (GPUs) for fast simulations of MRI of vascular structures. We apply a CUDA environment which supports general purpose computation on GPU (GPGPU). The data decomposition strategy is applied and thus the parts of each virtual object are spread over the GPU cores. The GPU cores are responsible for calculating the influence of blood flow behavior and MRI events after successive time steps. In the proposed approach, different data layouts, memory access patterns, and other memory improvements are applied to efficiently exploit GPU resources. Computational performance is thoroughly validated for various vascular structures and different NVIDIA GPUs. Results show that MRI simulations can be accelerated significantly thanks to GPGPU. The proposed GPU-based approach may be easily adopted in the modeling of other flow related phenomena like perfusion, diffusion or transport of contrast agents.

GPU-based parallel method of temperature field analysis in a floor heater with a controller

Abstract A parallel method enabling acceleration of the numerical analysis of the transient temperature field in an air floor heating system is presented in this paper. An initial-boundary value problem of the heater regulated by an on/off controller is formulated. The analogue model is discretized using the implicit finite difference method. The BiCGStab method is used to compute the obtained system of equations. A computer program implementing simultaneous computations on CPUand GPU(GPGPUtechnology) was developed. CUDA environment and linear algebra libraries (CUBLAS and CUSPARSE) are used by this program. The time of computations was reduced eight times in comparison with a program executed on the CPU only. Results of computations are presented in the form of time profiles and temperature field distributions. An influence of a model of the heat transfer coefficient on the simulation of the system operation was examined. The physical interpretation of obtained results is also presented.Results of computations were verified by comparing them with solutions obtained with the use of a commercial program - COMSOL Mutiphysics.

Distributed multi-scale muscle simulation in a hybrid MPI–CUDA computational environment

We present Mexie, an extensible and scalable software solution for distributed multi-scale muscle simulations in a hybrid MPI–CUDA environment. Since muscle contraction relies on the integration of physical and biochemical properties across multiple length and time scales, these models are highly processor and memory intensive. Existing parallelization efforts for accelerating multi-scale muscle simulations imply the usage of expensive large-scale computational resources, which produces overwhelming costs for the everyday practical application of such models. In order to improve the computational speed within a reasonable budget, we introduce the concept of distributed calculations of multi-scale muscle models in a mixed CPU–GPU environment. The concept is applied to a two-scale muscle model, in which a finite element macro model is coupled with the microscopic Huxley kinetics model. Finite element calculations of a continuum macroscopic model take place strictly on the CPU, while numerical solutions of the partial differential equations of Huxley’s cross-bridge kinetics are calculated on both CPUs and GPUs. We present a modular architecture of the solution, along with an internal organization and a specific load balancer that is aware of memory boundaries in such a heterogeneous environment. Solution was verified on both benchmark and real-world examples, showing high utilization of involved processing units, ensuring high scalability. Speed-up results show a boost of two orders of magnitude over any previously reported distributed multi-scale muscle models. This major improvement in computational feasibility of multi-scale muscle models paves the way for new discoveries in the field of muscle modeling and future clinical applications.

Solving engineering models using hyperbolic matrix functions

In this paper a method for computing hyperbolic matrix functions based on Hermite matrix polynomial expansions is outlined. Hermite series truncation together with Paterson–Stockmeyer method allow to compute the hyperbolic matrix cosine efficiently. A theoretical estimate for the optimal value of its parameters is obtained. An efficient and highly-accurate Hermite algorithm and a MATLAB implementation have been developed. The MATLAB implementation has been compared with the MATLAB function funm on matrices of different dimensions, obtaining lower execution time and higher accuracy in most cases. To do this we used an NVIDIA Tesla K20 GPGPU card, the CUDA environment and MATLAB. With this implementation we get much better performance for large scale problems.

A GPU OpenCL based cross-platform Monte Carlo dose calculation engine (goMC)

Monte Carlo (MC) simulation has been recognized as the most accurate dose calculation method for radiotherapy. However, the extremely long computation time impedes its clinical application. Recently, a lot of effort has been made to realize fast MC dose calculation on graphic processing units (GPUs). However, most of the GPU-based MC dose engines have been developed under NVidia’s CUDA environment. This limits the code portability to other platforms, hindering the introduction of GPU-based MC simulations to clinical practice. The objective of this paper is to develop a GPU OpenCL based cross-platform MC dose engine named goMC with coupled photon–electron simulation for external photon and electron radiotherapy in the MeV energy range. Compared to our previously developed GPU-based MC code named gDPM (Jia et al Phys. Med. Biol. 57 7783–97), goMC has two major differences. First, it was developed under the OpenCL environment for high code portability and hence could be run not only on different GPU cards but also on CPU platforms. Second, we adopted the electron transport model used in EGSnrc MC package and PENELOPE’s random hinge method in our new dose engine, instead of the dose planning method employed in gDPM. Dose distributions were calculated for a 15 MeV electron beam and a 6 MV photon beam in a homogenous water phantom, a water-bone-lung-water slab phantom and a half-slab phantom. Satisfactory agreement between the two MC dose engines goMC and gDPM was observed in all cases. The average dose differences in the regions that received a dose higher than 10% of the maximum dose were 0.48–0.53% for the electron beam cases and 0.15–0.17% for the photon beam cases. In terms of efficiency, goMC was ~4–16% slower than gDPM when running on the same NVidia TITAN card for all the cases we tested, due to both the different electron transport models and the different development environments. The code portability of our new dose engine goMC was validated by successfully running it on a variety of different computing devices including an NVidia GPU card, two AMD GPU cards and an Intel CPU processor. Computational efficiency among these platforms was compared.

CUDA 환경에서 CUSUM 검증의 병렬화

We have parallelized the cumulative sum (CUSUM) test of NIST's statistical random number test suite in a CUDA environment. Storing random walks in an array instead of in scalar variables eliminates data dependence. The change in data structure makes it possible to apply parallel scans, scatters, and reductions at each stage of the test. In addition, serial data exchanges between CPU and GPU are removed by migrating CPU's tasks to GPU. Finally we have optimized global memory accesses. The overall speedup is 23 times over the sequential version. Our results contribute to improving security of random numbers for cryptographic keys as well as reducing the time for evaluation of randomness.