General purpose graphic processing unit （GPU） calculation technology is gradually widely used in various fields. Its mode of single instruction, multiple threads is capable of seismic numerical simulation which has ...General purpose graphic processing unit （GPU） calculation technology is gradually widely used in various fields. Its mode of single instruction, multiple threads is capable of seismic numerical simulation which has a huge quantity of data and calculation steps. In this study, we introduce a GPU-based parallel calculation method of a precise integration method （PIM） for seismic forward modeling. Compared with CPU single-core calculation, GPU parallel calculating perfectly keeps the features of PIM, which has small bandwidth, high accuracy and capability of modeling complex substructures, and GPU calculation brings high computational efficiency, which means that high-performing GPU parallel calculation can make seismic forward modeling closer to real seismic records.展开更多
In this study,insights into the effect of interfacial anisotropy on a complex hexagonal close-packed(hcp) dendritic growth during alloy solidification were gained by graphics processing unit(GPU)-accelerated three-dim...In this study,insights into the effect of interfacial anisotropy on a complex hexagonal close-packed(hcp) dendritic growth during alloy solidification were gained by graphics processing unit(GPU)-accelerated three-dimensional(3D) phase-field simulations,as demonstrated for a Mg-Gd alloy.An anisotropic phasefield model with finite interface dissipation was developed by incorporating the contribution of the anisotropy of interfacial energy into the total free energy functional.The modified spherical harmonic anisotropy function was then chosen for the hcp crystal.The GPU parallel computing algorithm was implemented in the present phase-field model,and a corresponding code was developed in the compute unified device architecture parallel computing platform.Benchmark tests indicated that the calculation efficiency of a single TESLA V100 GPU could be~80times that of open multi-processing(OpenMP) with eight central processing unit cores.By coupling the phase-field model with reliable thermodynamic and interfacial energy descriptions,the 3D phase-field simulation of α-Mg dendritic growth in the Mg-6Gd(in wt%) alloy during solidification was performed.Various two-dimensional dendrite morphologies were revealed by cutting the simulated 3D dendrite along different crystallographic planes.Typical sixfold equiaxed and butterflied microstructures observed in experiments were well reproduced.展开更多
The signal processing speed of spectral domain optical coherence tomography(SD-OCT)has become a bottleneck in a lot of medical applications.Recently,a time-domain interpolation method was proposed.This method can get ...The signal processing speed of spectral domain optical coherence tomography(SD-OCT)has become a bottleneck in a lot of medical applications.Recently,a time-domain interpolation method was proposed.This method can get better signal-to-noise ratio(SNR)but much-reduced signal processing time in SD-OCT data processing as compared with the commonly used zeropadding interpolation method.Additionally,the resampled data can be obtained by a few data and coefficients in the cutoff window.Thus,a lot of interpolations can be performed simultaneously.So,this interpolation method is suitable for parallel computing.By using graphics processing unit(GPU)and the compute unified device architecture(CUDA)program model,time-domain interpolation can be accelerated significantly.The computing capability can be achieved more than 250,000 A-lines,200,000 A-lines,and 160,000 A-lines in a second for 2,048 pixel OCT when the cutoff length is L=11,L=21,and L=31,respectively.A frame SD-OCT data(400A-lines×2,048 pixel per line)is acquired and processed on GPU in real time.The results show that signal processing time of SD-OCT can befinished in 6.223 ms when the cutoff length L=21,which is much faster than that on central processing unit(CPU).Real-time signal processing of acquired data can be realized.展开更多
Solute transport simulations are important in water pollution events.This paper introduces a finite volume Godunovtype model for solving a 4×4 matrix form of the hyperbolic conservation laws consisting of 2D shal...Solute transport simulations are important in water pollution events.This paper introduces a finite volume Godunovtype model for solving a 4×4 matrix form of the hyperbolic conservation laws consisting of 2D shallow water equations and transport equations.The model adopts the Harten-Lax-van Leer-contact(HLLC)-approximate Riemann solution to calculate the cell interface fluxes.It can deal well with the changes in the dry and wet interfaces in an actual complex terrain,and it has a strong shock-wave capturing ability.Using monotonic upstream-centred scheme for conservation laws(MUSCL)linear reconstruction with finite slope and the Runge-Kutta time integration method can achieve second-order accuracy.At the same time,the introduction of graphics processing unit(GPU)-accelerated computing technology greatly increases the computing speed.The model is validated against multiple benchmarks,and the results are in good agreement with analytical solutions and other published numerical predictions.The third test case uses the GPU and central processing unit(CPU)calculation models which take 3.865 s and 13.865 s,respectively,indicating that the GPU calculation model can increase the calculation speed by 3.6 times.In the fourth test case,comparing the numerical model calculated by GPU with the traditional numerical model calculated by CPU,the calculation efficiencies of the numerical model calculated by GPU under different resolution grids are 9.8–44.6 times higher than those by CPU.Therefore,it has better potential than previous models for large-scale simulation of solute transport in water pollution incidents.It can provide a reliable theoretical basis and strong data support in the rapid assessment and early warning of water pollution accidents.展开更多
Organic reefs, the targets of deep-water petro- leum exploration, developed widely in Xisha area. However, there are concealed igneous rocks undersea, to which organic rocks have nearly equal wave impedance. So the ig...Organic reefs, the targets of deep-water petro- leum exploration, developed widely in Xisha area. However, there are concealed igneous rocks undersea, to which organic rocks have nearly equal wave impedance. So the igneous rocks have become interference for future explo- ration by having similar seismic reflection characteristics. Yet, the density and magnetism of organic reefs are very different from igneous rocks. It has obvious advantages to identify organic reefs and igneous rocks by gravity and magnetic data. At first, frequency decomposition was applied to the free-air gravity anomaly in Xisha area to obtain the 2D subdivision of the gravity anomaly and magnetic anomaly in the vertical direction. Thus, the dis- tribution of igneous rocks in the horizontal direction can be acquired according to high-frequency field, low-frequency field, and its physical properties. Then, 3D forward model- ing of gravitational field was carried out to establish the density model of this area by reference to physical properties of rocks based on former researches. Furthermore, 3D inversion of gravity anomaly by genetic algorithm method of the graphic processing unit （GPU） parallel processing in Xisha target area was applied, and 3D density structure of this area was obtained. By this way, we can confine the igneous rocks to the certain depth according to the density of the igneous rocks. The frequency decomposition and 3D inversion of gravity anomaly by genetic algorithm method of the GPU parallel processing proved to be a useful method for recognizing igneous rocks to its 3D geological position. So organic reefs and igneous rocks can be identified, which provide a prescient information for further exploration.展开更多
On-line transient stability analysis of a power grid is crucial in determining whether the power grid will traverse to a steady state stable operating point after a disturbance. The transient stability analysis involv...On-line transient stability analysis of a power grid is crucial in determining whether the power grid will traverse to a steady state stable operating point after a disturbance. The transient stability analysis involves computing the solutions of the algebraic equations modeling the grid network and the ordinary differential equations modeling the dynamics of the electrical components like synchronous generators, exciters, governors, etc., of the grid in near real-time. In this research, we investigate the use of time-parallel approach in particular the Parareal algorithm implementation on Graphical Processing Unit using Compute Unified Device Architecture to compute solutions of ordinary differential equations. The numerical solution accuracy and computation time of the Parareal algorithm executing on the GPU are demonstrated on the single machine infinite bus test system. Two types of dynamic model of the single synchronous generator namely the classical and detailed models are studied. The numerical solutions of the ordinary differential equations computed by the Parareal algorithm are compared to that computed using the modified Euler’s method demonstrating the accuracy of the Parareal algorithm executing on GPU. Simulations are performed with varying numerical integration time steps, and the suitability of Parareal algorithm in computing near real-time solutions of ordinary different equations is presented. A speedup of 25× and 31× is achieved with the Parareal algorithm for classical and detailed dynamic models of the synchronous generator respectively compared to the sequential modified Euler’s method. The weak scaling efficiency of the Parareal algorithm when required to solve a large number of ordinary differential equations at each time step due to the increase in sequential computations and associated memory transfer latency between the CPU and GPU is discussed.展开更多
Fluid-structure interaction （FSI） problems in microchannels play a prominent role in many engineering applications. The present study is an effort toward the simulation of flow in microchannel considering FSI. The b...Fluid-structure interaction （FSI） problems in microchannels play a prominent role in many engineering applications. The present study is an effort toward the simulation of flow in microchannel considering FSI. The bottom boundary of the microchannel is simulated by size-dependent beam elements for the finite element method （FEM） based on a modified cou- ple stress theory. The lattice Boltzmann method （LBM） using the D2Q13 LB model is coupled to the FEM in order to solve the fluid part of the FSI problem. Because of the fact that the LBM generally needs only nearest neighbor information, the algorithm is an ideal candidate for parallel computing. The simulations are carried out on graphics processing units （GPUs） using computed unified device architecture （CUDA）. In the present study, the governing equations are non-dimensionalized and the set of dimensionless groups is exhibited to show their effects on micro-beam displacement. The numerical results show that the displacements of the micro-beam predicted by the size-dependent beam element are smaller than those by the classical beam element.展开更多
Large eddy simulation （LES） using the Smagorinsky eddy viscosity model is added to the two-dimensional nine velocity components （D2Q9） lattice Boltzmann equation （LBE） with multi-relaxation-time （MRT） to simul...Large eddy simulation （LES） using the Smagorinsky eddy viscosity model is added to the two-dimensional nine velocity components （D2Q9） lattice Boltzmann equation （LBE） with multi-relaxation-time （MRT） to simulate incompressible turbulent cavity flows with the Reynolds numbers up to 1 × 10^7. To improve the computation efficiency of LBM on the numerical simulations of turbulent flows, the massively parallel computing power from a graphic processing unit （GPU） with a computing unified device architecture （CUDA） is introduced into the MRT-LBE-LES model. The model performs well, compared with the results from others, with an increase of 76 times in computation efficiency. It appears that the higher the Reynolds numbers is, the smaller the Smagorinsky constant should be, if the lattice number is fixed. Also, for a selected high Reynolds number and a selected proper Smagorinsky constant, there is a minimum requirement for the lattice number so that the Smagorinsky eddy viscosity will not be excessively large.展开更多
The simulation is an important means of performance evaluation of the computer architecture. Nowadays, the serial simulation of general purpose graphics processing unit(GPGPU) architecture is the main bottleneck for t...The simulation is an important means of performance evaluation of the computer architecture. Nowadays, the serial simulation of general purpose graphics processing unit(GPGPU) architecture is the main bottleneck for the simulation speed. To address this issue, we propose the intra-kernel parallelization on a multicore processor and the inter-kernel parallelization on a multiple-machine platform. We apply these two methods to the GPGPU-sim simulator. The intra-kernel parallelization method firstly parallelizes the serial simulation of multiple compute units in one cycle. Then it parallelizes the timing and functional simulation to reduce the performance loss caused by the synchronization between different compute units. The inter-kernel parallelization method divides multiple kernels of a CUDA program into several groups and distributes these groups across multiple simulation hosts to perform the simulation. Experimental results show that the intra-kernel parallelization method achieves a speed-up of up to 12 with a maximum error rate of 0.009 4% on a 32-core machine, and the inter-kernel parallelization method can accelerate the simulation by a factor of up to 3.9 with a maximum error rate of 0.11% on four simulation hosts. The orthogonality between these two methods allows us to combine them together on multiple multi-core hosts to get further performance improvements.展开更多
Personal desktop platform with teraflops peak performance of thousands of cores is realized at the price of conventional workstations using the programmable graphics processing units(GPUs).A GPU-based parallel Euler/N...Personal desktop platform with teraflops peak performance of thousands of cores is realized at the price of conventional workstations using the programmable graphics processing units(GPUs).A GPU-based parallel Euler/Navier-Stokes solver is developed for 2-D compressible flows by using NVIDIA′s Compute Unified Device Architecture(CUDA)programming model in CUDA Fortran programming language.The techniques of implementation of CUDA kernels,double-layered thread hierarchy and variety memory hierarchy are presented to form the GPU-based algorithm of Euler/Navier-Stokes equations.The resulting parallel solver is validated by a set of typical test flow cases.The numerical results show that dozens of times speedup relative to a serial CPU implementation can be achieved using a single GPU desktop platform,which demonstrates that a GPU desktop can serve as a costeffective parallel computing platform to accelerate computational fluid dynamics(CFD)simulations substantially.展开更多
Compared with the conventional X-ray absorption imaging, the X-ray phase-contrast imaging shows higher contrast on samples with low attenuation coefficient like blood vessels and soft tissues. Among the modalities of ...Compared with the conventional X-ray absorption imaging, the X-ray phase-contrast imaging shows higher contrast on samples with low attenuation coefficient like blood vessels and soft tissues. Among the modalities of phase-contrast imaging, the grating-based phase contrast imaging has been widely accepted owing to the advantage of wide range of sample selections and exemption of coherent source. However, the downside is the substantially larger amount of data generated from the phase-stepping method which slows down the reconstruction process. Graphic processing unit(GPU) has the advantage of allowing parallel computing which is very useful for large quantity data processing. In this paper, a compute unified device architecture(CUDA) C program based on GPU is introduced to accelerate the phase retrieval and filtered back projection(FBP) algorithm for grating-based tomography. Depending on the size of the data, the CUDA C program shows different amount of speed-up over the standard C program on the same Visual Studio 2010 platform. Meanwhile, the speed-up ratio increases as the size of data increases.展开更多
Graphics processing units(GPUs)employ the single instruction multiple data(SIMD)hardware to run threads in parallel and allow each thread to maintain an arbitrary control flow.Threads running concurrently within a war...Graphics processing units(GPUs)employ the single instruction multiple data(SIMD)hardware to run threads in parallel and allow each thread to maintain an arbitrary control flow.Threads running concurrently within a warp may jump to different paths after conditional branches.Such divergent control flow makes some lanes idle and hence reduces the SIMD utilization of GPUs.To alleviate the waste of SIMD lanes,threads from multiple warps can be collected together to improve the SIMD lane utilization by compacting threads into idle lanes.However,this mechanism induces extra barrier synchronizations since warps have to be stalled to wait for other warps for compactions,resulting in that no warps are scheduled in some cases.In this paper,we propose an approach to reduce the overhead of barrier synchronizat ions induced by compactions,In our approach,a compaction is bypassed by warps whose threads all jump to the same path after branches.Moreover,warps waiting for a compaction can also bypass this compaction when no warps are ready for issuing.In addition,a compaction is canceled if idle lanes can not be reduced via this compaction.The experimental results demonstrate that our approach provides an average improvement of 21%over the baseline GPU for applications with massive divergent branches,while recovering the performance loss induced by compactions by 13%on average for applications with many non-divergent control flows.展开更多
A graphic processing unit (GPU)-accelerated biological species recognition method using partially connected neural evolutionary network model is introduced in this paper. The partial connected neural evolutionary netw...A graphic processing unit (GPU)-accelerated biological species recognition method using partially connected neural evolutionary network model is introduced in this paper. The partial connected neural evolutionary network adopted in the paper can overcome the disadvantage of traditional neural network with small inputs. The whole image is considered as the input of the neural network, so the maximal features can be kept for recognition. To speed up the recognition process of the neural network, a fast implementation of the partially connected neural network was conducted on NVIDIA Tesla C1060 using the NVIDIA compute unified device architecture (CUDA) framework. Image sets of eight biological species were obtained to test the GPU implementation and counterpart serial CPU implementation, and experiment results showed GPU implementation works effectively on both recognition rate and speed, and gained 343 speedup over its counterpart CPU implementation. Comparing to feature-based recognition method on the same recognition task, the method also achieved an acceptable correct rate of 84.6% when testing on eight biological species.展开更多
Mutual information （MI）-based image registration is effective in registering medical images, but it is computationally expensive. This paper accelerates MI-based image registration by dividing computation of mutual ...Mutual information （MI）-based image registration is effective in registering medical images, but it is computationally expensive. This paper accelerates MI-based image registration by dividing computation of mutual information into spatial transformation and histogram-based calculation, and performing 3D spatial transformation and trilinear interpolation on graphic processing unit （GPU）. The 3D floating image is downloaded to GPU as flat 3D texture, and then fetched and interpolated for each new voxel location in fragment shader. The transformed resuits are rendered to textures by using frame buffer object （FBO） extension, and then read to the main memory used for the remaining computation on CPU. Experimental results show that GPU-accelerated method can achieve speedup about an order of magnitude with better registration result compared with the software implementation on a single-core CPU.展开更多
The newly emerging neural radiance fields(NeRF)methods can implicitly fulfill three-dimensional(3D)reconstruction via training a neural network to render novel-view images of a given scene with given posed images.The ...The newly emerging neural radiance fields(NeRF)methods can implicitly fulfill three-dimensional(3D)reconstruction via training a neural network to render novel-view images of a given scene with given posed images.The Instant Neural Graphics Primitives(Instant-NGP)method further improves the position encoding of NeRF.It obtains state-of-the-art efficiency.However,only a local pixel-wised loss is considered when training the Instant-NGP while overlooking the nonlocal structural information between pixels.Despite a good quantitative result,it leads to a poor visual effect,especially the completeness.Inspired by the stochastic structural similarity(S3IM)method that exploits nonlocal structural information of groups of pixels,this paper proposes a new method to improve the completeness of fast novel view synthesis.The proposed method first extends the thread-wised processing of the Instant-NGP to the processing in a customthread block(i.e.,a group of threads).Then,the relative dimensionless global error in synthesis,i.e.,Erreur Relative Globale Adimensionnelle de Synthese(ERGAS),of a group of pixels corresponding to a group of threads is computed and incorporated into the loss function.Extensive experiments validate the proposed method.It can obtain better quantitative results than the original Instant-NGP with fewer iteration steps.PSNR is increased by 1%.Amazing qualitative results are obtained,especially for delicate structures and details such as lines and continuous structures.With the dramatic improvements in the visual effects,our method can boost the practicability of implicit 3D reconstruction in applications such as self-driving and augmented reality.展开更多
稀疏矩阵向量乘(SpMV)是稀疏线性系统的计算核心和瓶颈,其运算效率会影响迭代求解器的整体性能,其优化研究一直是科学计算和工程应用领域中的研究热点之一。偏微分方程的离散化会产生稀疏对角矩阵,由于其多样的非零元分布,导致没有一种...稀疏矩阵向量乘(SpMV)是稀疏线性系统的计算核心和瓶颈,其运算效率会影响迭代求解器的整体性能,其优化研究一直是科学计算和工程应用领域中的研究热点之一。偏微分方程的离散化会产生稀疏对角矩阵,由于其多样的非零元分布,导致没有一种方法能够在所有矩阵中取得最优时间性能。针对上述问题,提出一种面向图形处理单元(GPU)的稀疏对角矩阵自适应SpMV优化方法AST(Adaptive SpMV Tuning)。该方法通过设计特征空间,构建特征提取器,提取矩阵结构精细特征,通过深入分析特征和SpMV方法的相关性,建立可扩展的候选方法集合,形成特征和最优方法的映射关系,构建性能预测工具,实现矩阵最优方法的高效预测。实验结果表明,AST能够取得85.8%的预测准确率,平均时间性能损失为0.09,相比于DIA(Diagonal)、HDIA(Hacked DIA)、HDC(Hybrid of DIA and Compressed Sparse Row)、DIA-Adaptive和DRM(Divide-Rearrange and Merge),能够获得平均20.19、1.86、3.06、3.72和1.53倍的内核运行时间加速和1.05、1.28、12.45、1.94和0.97倍的浮点运算性能加速。展开更多
基金supported by the National Natural Science Foundation of China (Nos 40974066 and 40821062)National Basic Research Program of China (No 2007CB209602)
文摘General purpose graphic processing unit （GPU） calculation technology is gradually widely used in various fields. Its mode of single instruction, multiple threads is capable of seismic numerical simulation which has a huge quantity of data and calculation steps. In this study, we introduce a GPU-based parallel calculation method of a precise integration method （PIM） for seismic forward modeling. Compared with CPU single-core calculation, GPU parallel calculating perfectly keeps the features of PIM, which has small bandwidth, high accuracy and capability of modeling complex substructures, and GPU calculation brings high computational efficiency, which means that high-performing GPU parallel calculation can make seismic forward modeling closer to real seismic records.
基金supported by the Natural Science Foundation of Hunan Province for Distinguished Young Scholars (No. 2021JJ10062)National Key Research and Development Program of China (No. 2016YFB0301101)+2 种基金Science and Technology Program of Guangxi province, China (No. AB21220028)the financial support from the Fundamental Research Funds for the Central Universities of Central South University (No. 2019zzts050)Postgraduate Scientific Research Innovation Project of Hunan Province (No. CX20190106)。
文摘In this study,insights into the effect of interfacial anisotropy on a complex hexagonal close-packed(hcp) dendritic growth during alloy solidification were gained by graphics processing unit(GPU)-accelerated three-dimensional(3D) phase-field simulations,as demonstrated for a Mg-Gd alloy.An anisotropic phasefield model with finite interface dissipation was developed by incorporating the contribution of the anisotropy of interfacial energy into the total free energy functional.The modified spherical harmonic anisotropy function was then chosen for the hcp crystal.The GPU parallel computing algorithm was implemented in the present phase-field model,and a corresponding code was developed in the compute unified device architecture parallel computing platform.Benchmark tests indicated that the calculation efficiency of a single TESLA V100 GPU could be~80times that of open multi-processing(OpenMP) with eight central processing unit cores.By coupling the phase-field model with reliable thermodynamic and interfacial energy descriptions,the 3D phase-field simulation of α-Mg dendritic growth in the Mg-6Gd(in wt%) alloy during solidification was performed.Various two-dimensional dendrite morphologies were revealed by cutting the simulated 3D dendrite along different crystallographic planes.Typical sixfold equiaxed and butterflied microstructures observed in experiments were well reproduced.
基金supported by National High Technology R&D project of China(2008AA02Z422)The Instrument Developing Project of The Chinese Academy of Sciences,Institute of Optics and Electronic,Chinese Academy of Sciences.
文摘The signal processing speed of spectral domain optical coherence tomography(SD-OCT)has become a bottleneck in a lot of medical applications.Recently,a time-domain interpolation method was proposed.This method can get better signal-to-noise ratio(SNR)but much-reduced signal processing time in SD-OCT data processing as compared with the commonly used zeropadding interpolation method.Additionally,the resampled data can be obtained by a few data and coefficients in the cutoff window.Thus,a lot of interpolations can be performed simultaneously.So,this interpolation method is suitable for parallel computing.By using graphics processing unit(GPU)and the compute unified device architecture(CUDA)program model,time-domain interpolation can be accelerated significantly.The computing capability can be achieved more than 250,000 A-lines,200,000 A-lines,and 160,000 A-lines in a second for 2,048 pixel OCT when the cutoff length is L=11,L=21,and L=31,respectively.A frame SD-OCT data(400A-lines×2,048 pixel per line)is acquired and processed on GPU in real time.The results show that signal processing time of SD-OCT can befinished in 6.223 ms when the cutoff length L=21,which is much faster than that on central processing unit(CPU).Real-time signal processing of acquired data can be realized.
基金Project supported by the National Natural Science Foundation of China(Nos.52009104 and 52079106)the Shaanxi Provincial Department of Water Resources Project(No.2017slkj-14)the Shaanxi Provincial Department of Science and Technology Project(No.2017JQ3043),China。
文摘Solute transport simulations are important in water pollution events.This paper introduces a finite volume Godunovtype model for solving a 4×4 matrix form of the hyperbolic conservation laws consisting of 2D shallow water equations and transport equations.The model adopts the Harten-Lax-van Leer-contact(HLLC)-approximate Riemann solution to calculate the cell interface fluxes.It can deal well with the changes in the dry and wet interfaces in an actual complex terrain,and it has a strong shock-wave capturing ability.Using monotonic upstream-centred scheme for conservation laws(MUSCL)linear reconstruction with finite slope and the Runge-Kutta time integration method can achieve second-order accuracy.At the same time,the introduction of graphics processing unit(GPU)-accelerated computing technology greatly increases the computing speed.The model is validated against multiple benchmarks,and the results are in good agreement with analytical solutions and other published numerical predictions.The third test case uses the GPU and central processing unit(CPU)calculation models which take 3.865 s and 13.865 s,respectively,indicating that the GPU calculation model can increase the calculation speed by 3.6 times.In the fourth test case,comparing the numerical model calculated by GPU with the traditional numerical model calculated by CPU,the calculation efficiencies of the numerical model calculated by GPU under different resolution grids are 9.8–44.6 times higher than those by CPU.Therefore,it has better potential than previous models for large-scale simulation of solute transport in water pollution incidents.It can provide a reliable theoretical basis and strong data support in the rapid assessment and early warning of water pollution accidents.
基金financially supported by the National Natural Science Foundation of China (No.41174085)
文摘Organic reefs, the targets of deep-water petro- leum exploration, developed widely in Xisha area. However, there are concealed igneous rocks undersea, to which organic rocks have nearly equal wave impedance. So the igneous rocks have become interference for future explo- ration by having similar seismic reflection characteristics. Yet, the density and magnetism of organic reefs are very different from igneous rocks. It has obvious advantages to identify organic reefs and igneous rocks by gravity and magnetic data. At first, frequency decomposition was applied to the free-air gravity anomaly in Xisha area to obtain the 2D subdivision of the gravity anomaly and magnetic anomaly in the vertical direction. Thus, the dis- tribution of igneous rocks in the horizontal direction can be acquired according to high-frequency field, low-frequency field, and its physical properties. Then, 3D forward model- ing of gravitational field was carried out to establish the density model of this area by reference to physical properties of rocks based on former researches. Furthermore, 3D inversion of gravity anomaly by genetic algorithm method of the graphic processing unit （GPU） parallel processing in Xisha target area was applied, and 3D density structure of this area was obtained. By this way, we can confine the igneous rocks to the certain depth according to the density of the igneous rocks. The frequency decomposition and 3D inversion of gravity anomaly by genetic algorithm method of the GPU parallel processing proved to be a useful method for recognizing igneous rocks to its 3D geological position. So organic reefs and igneous rocks can be identified, which provide a prescient information for further exploration.
文摘On-line transient stability analysis of a power grid is crucial in determining whether the power grid will traverse to a steady state stable operating point after a disturbance. The transient stability analysis involves computing the solutions of the algebraic equations modeling the grid network and the ordinary differential equations modeling the dynamics of the electrical components like synchronous generators, exciters, governors, etc., of the grid in near real-time. In this research, we investigate the use of time-parallel approach in particular the Parareal algorithm implementation on Graphical Processing Unit using Compute Unified Device Architecture to compute solutions of ordinary differential equations. The numerical solution accuracy and computation time of the Parareal algorithm executing on the GPU are demonstrated on the single machine infinite bus test system. Two types of dynamic model of the single synchronous generator namely the classical and detailed models are studied. The numerical solutions of the ordinary differential equations computed by the Parareal algorithm are compared to that computed using the modified Euler’s method demonstrating the accuracy of the Parareal algorithm executing on GPU. Simulations are performed with varying numerical integration time steps, and the suitability of Parareal algorithm in computing near real-time solutions of ordinary different equations is presented. A speedup of 25× and 31× is achieved with the Parareal algorithm for classical and detailed dynamic models of the synchronous generator respectively compared to the sequential modified Euler’s method. The weak scaling efficiency of the Parareal algorithm when required to solve a large number of ordinary differential equations at each time step due to the increase in sequential computations and associated memory transfer latency between the CPU and GPU is discussed.
文摘Fluid-structure interaction （FSI） problems in microchannels play a prominent role in many engineering applications. The present study is an effort toward the simulation of flow in microchannel considering FSI. The bottom boundary of the microchannel is simulated by size-dependent beam elements for the finite element method （FEM） based on a modified cou- ple stress theory. The lattice Boltzmann method （LBM） using the D2Q13 LB model is coupled to the FEM in order to solve the fluid part of the FSI problem. Because of the fact that the LBM generally needs only nearest neighbor information, the algorithm is an ideal candidate for parallel computing. The simulations are carried out on graphics processing units （GPUs） using computed unified device architecture （CUDA）. In the present study, the governing equations are non-dimensionalized and the set of dimensionless groups is exhibited to show their effects on micro-beam displacement. The numerical results show that the displacements of the micro-beam predicted by the size-dependent beam element are smaller than those by the classical beam element.
基金supported by College of William and Mary,Virginia Institute of Marine Science for the study environment
文摘Large eddy simulation （LES） using the Smagorinsky eddy viscosity model is added to the two-dimensional nine velocity components （D2Q9） lattice Boltzmann equation （LBE） with multi-relaxation-time （MRT） to simulate incompressible turbulent cavity flows with the Reynolds numbers up to 1 × 10^7. To improve the computation efficiency of LBM on the numerical simulations of turbulent flows, the massively parallel computing power from a graphic processing unit （GPU） with a computing unified device architecture （CUDA） is introduced into the MRT-LBE-LES model. The model performs well, compared with the results from others, with an increase of 76 times in computation efficiency. It appears that the higher the Reynolds numbers is, the smaller the Smagorinsky constant should be, if the lattice number is fixed. Also, for a selected high Reynolds number and a selected proper Smagorinsky constant, there is a minimum requirement for the lattice number so that the Smagorinsky eddy viscosity will not be excessively large.
基金the National Natural Science Foundation of China(Nos.61572508,61272144,61303065and 61202121)the National High Technology Research and Development Program(863)of China(No.2012AA010905)+2 种基金the Research Project of National University of Defense Technology(No.JC13-06-02)the Doctoral Fund of Ministry of Education of China(No.20134307120028)the Research Fund for the Doctoral Program of Higher Education of China(No.20114307120013)
文摘The simulation is an important means of performance evaluation of the computer architecture. Nowadays, the serial simulation of general purpose graphics processing unit(GPGPU) architecture is the main bottleneck for the simulation speed. To address this issue, we propose the intra-kernel parallelization on a multicore processor and the inter-kernel parallelization on a multiple-machine platform. We apply these two methods to the GPGPU-sim simulator. The intra-kernel parallelization method firstly parallelizes the serial simulation of multiple compute units in one cycle. Then it parallelizes the timing and functional simulation to reduce the performance loss caused by the synchronization between different compute units. The inter-kernel parallelization method divides multiple kernels of a CUDA program into several groups and distributes these groups across multiple simulation hosts to perform the simulation. Experimental results show that the intra-kernel parallelization method achieves a speed-up of up to 12 with a maximum error rate of 0.009 4% on a 32-core machine, and the inter-kernel parallelization method can accelerate the simulation by a factor of up to 3.9 with a maximum error rate of 0.11% on four simulation hosts. The orthogonality between these two methods allows us to combine them together on multiple multi-core hosts to get further performance improvements.
基金supported by the National Natural Science Foundation of China (No.11172134)the Funding of Jiangsu Innovation Program for Graduate Education (No.CXLX13_132)
文摘Personal desktop platform with teraflops peak performance of thousands of cores is realized at the price of conventional workstations using the programmable graphics processing units(GPUs).A GPU-based parallel Euler/Navier-Stokes solver is developed for 2-D compressible flows by using NVIDIA′s Compute Unified Device Architecture(CUDA)programming model in CUDA Fortran programming language.The techniques of implementation of CUDA kernels,double-layered thread hierarchy and variety memory hierarchy are presented to form the GPU-based algorithm of Euler/Navier-Stokes equations.The resulting parallel solver is validated by a set of typical test flow cases.The numerical results show that dozens of times speedup relative to a serial CPU implementation can be achieved using a single GPU desktop platform,which demonstrates that a GPU desktop can serve as a costeffective parallel computing platform to accelerate computational fluid dynamics(CFD)simulations substantially.
基金the National Basic Research Program(973) of China(No.2010CB834300)the Biomedical Engineering Cross-Research Fund of Shanghai Jiao Tong University(Nos.YG2011MS49 and YG2013MS65)
文摘Compared with the conventional X-ray absorption imaging, the X-ray phase-contrast imaging shows higher contrast on samples with low attenuation coefficient like blood vessels and soft tissues. Among the modalities of phase-contrast imaging, the grating-based phase contrast imaging has been widely accepted owing to the advantage of wide range of sample selections and exemption of coherent source. However, the downside is the substantially larger amount of data generated from the phase-stepping method which slows down the reconstruction process. Graphic processing unit(GPU) has the advantage of allowing parallel computing which is very useful for large quantity data processing. In this paper, a compute unified device architecture(CUDA) C program based on GPU is introduced to accelerate the phase retrieval and filtered back projection(FBP) algorithm for grating-based tomography. Depending on the size of the data, the CUDA C program shows different amount of speed-up over the standard C program on the same Visual Studio 2010 platform. Meanwhile, the speed-up ratio increases as the size of data increases.
基金the National Natural Science Foundation of China(No.61702521)the Natural Science Foundation of Tianjin(No.18JCQNJC00400)+1 种基金the Scientific Research Foundation of Civil Aviation University of China(No.2017QD12S)the Fundamental Research Funds for the Central Universities of Civil Aviation University of China(Nos.3122018C023 and 3122018C021)。
文摘Graphics processing units(GPUs)employ the single instruction multiple data(SIMD)hardware to run threads in parallel and allow each thread to maintain an arbitrary control flow.Threads running concurrently within a warp may jump to different paths after conditional branches.Such divergent control flow makes some lanes idle and hence reduces the SIMD utilization of GPUs.To alleviate the waste of SIMD lanes,threads from multiple warps can be collected together to improve the SIMD lane utilization by compacting threads into idle lanes.However,this mechanism induces extra barrier synchronizations since warps have to be stalled to wait for other warps for compactions,resulting in that no warps are scheduled in some cases.In this paper,we propose an approach to reduce the overhead of barrier synchronizat ions induced by compactions,In our approach,a compaction is bypassed by warps whose threads all jump to the same path after branches.Moreover,warps waiting for a compaction can also bypass this compaction when no warps are ready for issuing.In addition,a compaction is canceled if idle lanes can not be reduced via this compaction.The experimental results demonstrate that our approach provides an average improvement of 21%over the baseline GPU for applications with massive divergent branches,while recovering the performance loss induced by compactions by 13%on average for applications with many non-divergent control flows.
基金National Natural Science Foundation of China (No. 60975084)Natural Science Foundation of Fujian Province,China (No.2011J05159)
文摘A graphic processing unit (GPU)-accelerated biological species recognition method using partially connected neural evolutionary network model is introduced in this paper. The partial connected neural evolutionary network adopted in the paper can overcome the disadvantage of traditional neural network with small inputs. The whole image is considered as the input of the neural network, so the maximal features can be kept for recognition. To speed up the recognition process of the neural network, a fast implementation of the partially connected neural network was conducted on NVIDIA Tesla C1060 using the NVIDIA compute unified device architecture (CUDA) framework. Image sets of eight biological species were obtained to test the GPU implementation and counterpart serial CPU implementation, and experiment results showed GPU implementation works effectively on both recognition rate and speed, and gained 343 speedup over its counterpart CPU implementation. Comparing to feature-based recognition method on the same recognition task, the method also achieved an acceptable correct rate of 84.6% when testing on eight biological species.
基金Supported by National High Technology Research and Development Program("863"Program)of China(No.863-306-ZD13-03-06)
文摘Mutual information （MI）-based image registration is effective in registering medical images, but it is computationally expensive. This paper accelerates MI-based image registration by dividing computation of mutual information into spatial transformation and histogram-based calculation, and performing 3D spatial transformation and trilinear interpolation on graphic processing unit （GPU）. The 3D floating image is downloaded to GPU as flat 3D texture, and then fetched and interpolated for each new voxel location in fragment shader. The transformed resuits are rendered to textures by using frame buffer object （FBO） extension, and then read to the main memory used for the remaining computation on CPU. Experimental results show that GPU-accelerated method can achieve speedup about an order of magnitude with better registration result compared with the software implementation on a single-core CPU.
基金supported in part by National Natural Science Foundation of China under Grant No.62473013Key Project of Science and Technology Innovation and Entrepreneurship of TDTEC(No.2022-TDZD004).
文摘The newly emerging neural radiance fields(NeRF)methods can implicitly fulfill three-dimensional(3D)reconstruction via training a neural network to render novel-view images of a given scene with given posed images.The Instant Neural Graphics Primitives(Instant-NGP)method further improves the position encoding of NeRF.It obtains state-of-the-art efficiency.However,only a local pixel-wised loss is considered when training the Instant-NGP while overlooking the nonlocal structural information between pixels.Despite a good quantitative result,it leads to a poor visual effect,especially the completeness.Inspired by the stochastic structural similarity(S3IM)method that exploits nonlocal structural information of groups of pixels,this paper proposes a new method to improve the completeness of fast novel view synthesis.The proposed method first extends the thread-wised processing of the Instant-NGP to the processing in a customthread block(i.e.,a group of threads).Then,the relative dimensionless global error in synthesis,i.e.,Erreur Relative Globale Adimensionnelle de Synthese(ERGAS),of a group of pixels corresponding to a group of threads is computed and incorporated into the loss function.Extensive experiments validate the proposed method.It can obtain better quantitative results than the original Instant-NGP with fewer iteration steps.PSNR is increased by 1%.Amazing qualitative results are obtained,especially for delicate structures and details such as lines and continuous structures.With the dramatic improvements in the visual effects,our method can boost the practicability of implicit 3D reconstruction in applications such as self-driving and augmented reality.
文摘稀疏矩阵向量乘(SpMV)是稀疏线性系统的计算核心和瓶颈,其运算效率会影响迭代求解器的整体性能,其优化研究一直是科学计算和工程应用领域中的研究热点之一。偏微分方程的离散化会产生稀疏对角矩阵,由于其多样的非零元分布,导致没有一种方法能够在所有矩阵中取得最优时间性能。针对上述问题,提出一种面向图形处理单元(GPU)的稀疏对角矩阵自适应SpMV优化方法AST(Adaptive SpMV Tuning)。该方法通过设计特征空间,构建特征提取器,提取矩阵结构精细特征,通过深入分析特征和SpMV方法的相关性,建立可扩展的候选方法集合,形成特征和最优方法的映射关系,构建性能预测工具,实现矩阵最优方法的高效预测。实验结果表明,AST能够取得85.8%的预测准确率,平均时间性能损失为0.09,相比于DIA(Diagonal)、HDIA(Hacked DIA)、HDC(Hybrid of DIA and Compressed Sparse Row)、DIA-Adaptive和DRM(Divide-Rearrange and Merge),能够获得平均20.19、1.86、3.06、3.72和1.53倍的内核运行时间加速和1.05、1.28、12.45、1.94和0.97倍的浮点运算性能加速。
