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
Based on the finite element method(FEM)in the frequency domain and particle-in-cell approach in the time domain,a hybrid domain multipactor threshold prediction algorithm is proposed in this paper.The proposed algorit...Based on the finite element method(FEM)in the frequency domain and particle-in-cell approach in the time domain,a hybrid domain multipactor threshold prediction algorithm is proposed in this paper.The proposed algorithm has the advantages of the frequency domain and the time domain algorithms at the same time in terms of high computational accuracy and considerable computational efficiency.In addition,the compute unified device architecture(CUDA)acceleration technique also can be employed to further enhance its simulation efficiency.Numerical examples are carried out to demonstrate the effectiveness of the proposed algorithm.The results indicate that the multipactor threshold can be accurately predicted and the computational efficiency can be improved.展开更多
The implementation and optimization of the traditional contour generation algorithms are always proposed for the common processor. When processing high resolution images, the performance often exists low efficiency. A...The implementation and optimization of the traditional contour generation algorithms are always proposed for the common processor. When processing high resolution images, the performance often exists low efficiency. A new graphics processing unit (GPU)-based algorithm is proposed to get the clear and integrated contour of leaves. Firstly we implement the classic Sobel operator of edge detection in GPU. Then a simple and effective method is designed to remove the fake edge and a heuristic algorithm is used to repair the broken edge. It is proved by the experiments that the results of our algorithm are natural and realistic in terms of morphology and can be good materials for the virtual plant.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
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 scenario simulation analysis of water environmental emergencies is very important for risk prevention and control,and emergency response.To quickly and accurately simulate the transport and diffusion process of hi...The scenario simulation analysis of water environmental emergencies is very important for risk prevention and control,and emergency response.To quickly and accurately simulate the transport and diffusion process of high-intensity pollutants during sudden environmental water pollution events,in this study,a high-precision pollution transport and diffusion model for unstructured grids based on Compute Unified Device Architecture(CUDA)is proposed.The finite volume method of a total variation diminishing limiter with the Kong proposed r-factor is used to reduce numerical diffusion and oscillation errors in the simulation of pollutants under sharp concentration conditions,and graphics processing unit acceleration technology is used to improve computational efficiency.The advection diffusion process of the model is verified numerically using two benchmark cases,and the efficiency of the model is evaluated using an engineering example.The results demonstrate that the model perform well in the simulation of material transport in the presence of sharp concentration.Additionally,it has high computational efficiency.The acceleration ratio is 46 times the single-thread acceleration effect of the original model.The efficiency of the accelerated model meet the requirements of an engineering application,and the rapid early warning and assessment of water pollution accidents is achieved.展开更多
Alias – Wavefront OBJ meshes are a common text file type for transferring 3D mesh data between applications made by different vendors.However, as the mesh complexity gets higher and denser, the files become larger an...Alias – Wavefront OBJ meshes are a common text file type for transferring 3D mesh data between applications made by different vendors.However, as the mesh complexity gets higher and denser, the files become larger and slower to import.This paper explores the use of GPUs to accelerate the importing and parsing of OBJ files by studying file read-time, runtime, and load resistance. We propose a new method of reading and parsing that circumvents GPU architecture limitations and improves performance, seeing the new GPU method outperforms CPU methods with a 6×– 8× speedup. When running on a heavily loaded system, the new method only received an 80% performance hit, compared to the160% that the CPU methods received. The loaded GPU speedup compared to unloaded CPU methods was3.5×, and, when compared to loaded CPU methods,8×. These results demonstrate that the time is right for further research into the use of data-parallel GPU acceleration beyond that of computer graphics and high performance computing.展开更多
A tremendous amount of data has been generated by global financial markets everyday,and such time-series data needs to be analyzed in real time to explore its potential value.In recent years,we have witnessed the succ...A tremendous amount of data has been generated by global financial markets everyday,and such time-series data needs to be analyzed in real time to explore its potential value.In recent years,we have witnessed the successful adoption of machine learning models on financial data,where the importance of accuracy and timeliness demands highly effective computing frameworks.However,traditional financial time-series data processing frameworks have shown performance degradation and adaptation issues,such as the outlier handling with stock suspension in Pandas and TA-Lib.In this paper,we propose HXPY,a high-performance data processing package with a C++/Python interface for financial time-series data.HXPY supports miscellaneous acceleration techniques such as the streaming algorithm,the vectorization instruction set,and memory optimization,together with various functions such as time window functions,group operations,down-sampling operations,cross-section operations,row-wise or column-wise operations,shape transformations,and alignment functions.The results of benchmark and incremental analysis demonstrate the superior performance of HXPY compared with its counterparts.From MiBs to GiBs data,HXPY significantly outperforms other in-memory dataframe computing rivals even up to hundreds of times.展开更多
As an established spatial analytical tool,Geographically Weighted Regression(GWR)has been applied across a variety of disciplines.However,its usage can be challenging for large datasets,which are increasingly prevalen...As an established spatial analytical tool,Geographically Weighted Regression(GWR)has been applied across a variety of disciplines.However,its usage can be challenging for large datasets,which are increasingly prevalent in today’s digital world.In this study,we propose two high-performance R solutions for GWR via Multi-core Parallel(MP)and Compute Unified Device Architecture(CUDA)techniques,respectively GWR-MP and GWR-CUDA.We compared GWR-MP and GWR-CUDA with three existing solutions available in Geographically Weighted Models(GWmodel),Multi-scale GWR(MGWR)and Fast GWR(FastGWR).Results showed that all five solutions perform differently across varying sample sizes,with no single solution a clear winner in terms of computational efficiency.Specifically,solutions given in GWmodel and MGWR provided acceptable computational costs for GWR studies with a relatively small sample size.For a large sample size,GWR-MP and FastGWR provided coherent solutions on a Personal Computer(PC)with a common multi-core configuration,GWR-MP provided more efficient computing capacity for each core or thread than FastGWR.For cases when the sample size was very large,and for these cases only,GWR-CUDA provided the most efficient solution,but should note its I/O cost with small samples.In summary,GWR-MP and GWR-CUDA provided complementary high-performance R solutions to existing ones,where for certain data-rich GWR studies,they should be preferred.展开更多
Low-Density Parity-Check (LDPC) codes are powerful error correcting codes. LDPC decoders have been implemented as efficient error correction codes on dedicated VLSI hardware architectures in recent years. This paper...Low-Density Parity-Check (LDPC) codes are powerful error correcting codes. LDPC decoders have been implemented as efficient error correction codes on dedicated VLSI hardware architectures in recent years. This paper describes two strategies to parallelize min-sum decoding of irregular LDPC codes. The first implements min-sum LDPC decoders on multicore platforms using OpenMP, while the other uses the Compute Unified Device Architecture (CUDA) to parallelize LDPC decoding on Graphics Processing Units (GPUs). Empirical studies on data with various scales show that the performance of these decoding processes is improved by these parallel strategies and the GPUs provide more efficient, fast implementation decoder.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
The network switches in the data plane of Software Defined Networking (SDN) are empowered by an elementary process, in which enormous number of packets which resemble big volumes of data are classified into specific f...The network switches in the data plane of Software Defined Networking (SDN) are empowered by an elementary process, in which enormous number of packets which resemble big volumes of data are classified into specific flows by matching them against a set of dynamic rules. This basic process accelerates the processing of data, so that instead of processing singular packets repeatedly, corresponding actions are performed on corresponding flows of packets. In this paper, first, we address limitations on a typical packet classification algorithm like Tuple Space Search (TSS). Then, we present a set of different scenarios to parallelize it on different parallel processing platforms, including Graphics Processing Units (GPUs), clusters of Central Processing Units (CPUs), and hybrid clusters. Experimental results show that the hybrid cluster provides the best platform for parallelizing packet classification algorithms, which promises the average throughput rate of 4.2 Million packets per second (Mpps). That is, the hybrid cluster produced by the integration of Compute Unified Device Architecture (CUDA), Message Passing Interface (MPI), and OpenMP programming model could classify 0.24 million packets per second more than the GPU cluster scheme. Such a packet classifier satisfies the required processing speed in the programmable network systems that would be used to communicate big medical data.展开更多
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This work was supported by the National Natural Science Foundation of China(61571022,61971022)the National Key laboratory Foundation(HTKJ2019KI504013,61424020305).
文摘Based on the finite element method(FEM)in the frequency domain and particle-in-cell approach in the time domain,a hybrid domain multipactor threshold prediction algorithm is proposed in this paper.The proposed algorithm has the advantages of the frequency domain and the time domain algorithms at the same time in terms of high computational accuracy and considerable computational efficiency.In addition,the compute unified device architecture(CUDA)acceleration technique also can be employed to further enhance its simulation efficiency.Numerical examples are carried out to demonstrate the effectiveness of the proposed algorithm.The results indicate that the multipactor threshold can be accurately predicted and the computational efficiency can be improved.
基金Project supported by the Shanghai Leading Academic Discipline Project(Grant No.J50103)the National Natural Science Foundation of China(Grant No.60970150)
文摘The implementation and optimization of the traditional contour generation algorithms are always proposed for the common processor. When processing high resolution images, the performance often exists low efficiency. A new graphics processing unit (GPU)-based algorithm is proposed to get the clear and integrated contour of leaves. Firstly we implement the classic Sobel operator of edge detection in GPU. Then a simple and effective method is designed to remove the fake edge and a heuristic algorithm is used to repair the broken edge. It is proved by the experiments that the results of our algorithm are natural and realistic in terms of morphology and can be good materials for the virtual plant.
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 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supported by the National Key Research and Development Program of China(Grant No.2022YFC3202004)the National Natural Science Foundation of China(Grant No.51979105).
文摘The scenario simulation analysis of water environmental emergencies is very important for risk prevention and control,and emergency response.To quickly and accurately simulate the transport and diffusion process of high-intensity pollutants during sudden environmental water pollution events,in this study,a high-precision pollution transport and diffusion model for unstructured grids based on Compute Unified Device Architecture(CUDA)is proposed.The finite volume method of a total variation diminishing limiter with the Kong proposed r-factor is used to reduce numerical diffusion and oscillation errors in the simulation of pollutants under sharp concentration conditions,and graphics processing unit acceleration technology is used to improve computational efficiency.The advection diffusion process of the model is verified numerically using two benchmark cases,and the efficiency of the model is evaluated using an engineering example.The results demonstrate that the model perform well in the simulation of material transport in the presence of sharp concentration.Additionally,it has high computational efficiency.The acceleration ratio is 46 times the single-thread acceleration effect of the original model.The efficiency of the accelerated model meet the requirements of an engineering application,and the rapid early warning and assessment of water pollution accidents is achieved.
文摘Alias – Wavefront OBJ meshes are a common text file type for transferring 3D mesh data between applications made by different vendors.However, as the mesh complexity gets higher and denser, the files become larger and slower to import.This paper explores the use of GPUs to accelerate the importing and parsing of OBJ files by studying file read-time, runtime, and load resistance. We propose a new method of reading and parsing that circumvents GPU architecture limitations and improves performance, seeing the new GPU method outperforms CPU methods with a 6×– 8× speedup. When running on a heavily loaded system, the new method only received an 80% performance hit, compared to the160% that the CPU methods received. The loaded GPU speedup compared to unloaded CPU methods was3.5×, and, when compared to loaded CPU methods,8×. These results demonstrate that the time is right for further research into the use of data-parallel GPU acceleration beyond that of computer graphics and high performance computing.
文摘A tremendous amount of data has been generated by global financial markets everyday,and such time-series data needs to be analyzed in real time to explore its potential value.In recent years,we have witnessed the successful adoption of machine learning models on financial data,where the importance of accuracy and timeliness demands highly effective computing frameworks.However,traditional financial time-series data processing frameworks have shown performance degradation and adaptation issues,such as the outlier handling with stock suspension in Pandas and TA-Lib.In this paper,we propose HXPY,a high-performance data processing package with a C++/Python interface for financial time-series data.HXPY supports miscellaneous acceleration techniques such as the streaming algorithm,the vectorization instruction set,and memory optimization,together with various functions such as time window functions,group operations,down-sampling operations,cross-section operations,row-wise or column-wise operations,shape transformations,and alignment functions.The results of benchmark and incremental analysis demonstrate the superior performance of HXPY compared with its counterparts.From MiBs to GiBs data,HXPY significantly outperforms other in-memory dataframe computing rivals even up to hundreds of times.
基金supported by National Key Research and Development Program of China[grant num-ber 2021YFB3900904]the National Natural Science Foundation of China[grant numbers 42071368,U2033216,41871287].
文摘As an established spatial analytical tool,Geographically Weighted Regression(GWR)has been applied across a variety of disciplines.However,its usage can be challenging for large datasets,which are increasingly prevalent in today’s digital world.In this study,we propose two high-performance R solutions for GWR via Multi-core Parallel(MP)and Compute Unified Device Architecture(CUDA)techniques,respectively GWR-MP and GWR-CUDA.We compared GWR-MP and GWR-CUDA with three existing solutions available in Geographically Weighted Models(GWmodel),Multi-scale GWR(MGWR)and Fast GWR(FastGWR).Results showed that all five solutions perform differently across varying sample sizes,with no single solution a clear winner in terms of computational efficiency.Specifically,solutions given in GWmodel and MGWR provided acceptable computational costs for GWR studies with a relatively small sample size.For a large sample size,GWR-MP and FastGWR provided coherent solutions on a Personal Computer(PC)with a common multi-core configuration,GWR-MP provided more efficient computing capacity for each core or thread than FastGWR.For cases when the sample size was very large,and for these cases only,GWR-CUDA provided the most efficient solution,but should note its I/O cost with small samples.In summary,GWR-MP and GWR-CUDA provided complementary high-performance R solutions to existing ones,where for certain data-rich GWR studies,they should be preferred.
基金Agilent Technology Foundation(No.912-CHN09)National Natural Science Foundation of China(No.61175110)+1 种基金National Key Basic Research and Development(973)Program of China(No.2012CB316305)National Key Projects of Science and Technology of China(No.2011ZX02101-004)
文摘Low-Density Parity-Check (LDPC) codes are powerful error correcting codes. LDPC decoders have been implemented as efficient error correction codes on dedicated VLSI hardware architectures in recent years. This paper describes two strategies to parallelize min-sum decoding of irregular LDPC codes. The first implements min-sum LDPC decoders on multicore platforms using OpenMP, while the other uses the Compute Unified Device Architecture (CUDA) to parallelize LDPC decoding on Graphics Processing Units (GPUs). Empirical studies on data with various scales show that the performance of these decoding processes is improved by these parallel strategies and the GPUs provide more efficient, fast implementation decoder.
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.
文摘The network switches in the data plane of Software Defined Networking (SDN) are empowered by an elementary process, in which enormous number of packets which resemble big volumes of data are classified into specific flows by matching them against a set of dynamic rules. This basic process accelerates the processing of data, so that instead of processing singular packets repeatedly, corresponding actions are performed on corresponding flows of packets. In this paper, first, we address limitations on a typical packet classification algorithm like Tuple Space Search (TSS). Then, we present a set of different scenarios to parallelize it on different parallel processing platforms, including Graphics Processing Units (GPUs), clusters of Central Processing Units (CPUs), and hybrid clusters. Experimental results show that the hybrid cluster provides the best platform for parallelizing packet classification algorithms, which promises the average throughput rate of 4.2 Million packets per second (Mpps). That is, the hybrid cluster produced by the integration of Compute Unified Device Architecture (CUDA), Message Passing Interface (MPI), and OpenMP programming model could classify 0.24 million packets per second more than the GPU cluster scheme. Such a packet classifier satisfies the required processing speed in the programmable network systems that would be used to communicate big medical data.