SM9 was established in 2016 as a Chinese ofcial identity-based cryptographic (IBC) standard, and became an ISO standard in 2021. It is well-known that IBC is suitable for Internet of Things (IoT) applications, since a...SM9 was established in 2016 as a Chinese ofcial identity-based cryptographic (IBC) standard, and became an ISO standard in 2021. It is well-known that IBC is suitable for Internet of Things (IoT) applications, since a centralized processing of client data (e.g. IoT cloud) is often done by gateways. However, due to limited computation resources inside IoT devices, the performance of SM9 becomes a bottleneck in practical usage. The existing SM9 implementa-tionsare often CPU-based, with relatively low latency and low throughput. Consequently, a pivotal challenge for SM9 in large-scale applications is how to reduce the latency while maximizing throughput for numerous concurrent inputs. After a systematic analysis of the SM9 algorithms, we apply optimization techniques including precomputa-tion,resource caching and parallelization to reduce the overhead of SM9. In this work, we introduce the frst prac-ticalimplementation of SM9 and its underlying SM9_P256 curve on GPU. Our GPU implementation combines multiple algorithms and low-level optimizations tailored for GPU’s single instruction, multiple threads architecture in order to achieve high throughput for SM9. Based on these, we propose GAPS, a high-performance Cryptog-raphyas a Service (CaaS) for SM9. GAPS adopts a heterogeneous computing architecture that fexibly schedules the inputs across two implementation platforms: a CPU for the low-latency processing of sporadic inputs, and a GPU for the high-throughput processing of batch inputs. According to our benchmark, GAPS only takes a few milliseconds to process a single SM9 request in idle mode. Moreover, when operating in its batch processing mode, GAPS can generate 2,038,071 private keys, 248,239 signatures or 238,001 ciphertexts per second. The results show that GAPS scales seamlessly across inputs of diferent sizes, preliminarily demonstrating the efcacy of our solution.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
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
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
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
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
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
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
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
基金supported by National Natural Science Foundation of China(Nos.62172411,62172404,61972094,and 62202458).
文摘SM9 was established in 2016 as a Chinese ofcial identity-based cryptographic (IBC) standard, and became an ISO standard in 2021. It is well-known that IBC is suitable for Internet of Things (IoT) applications, since a centralized processing of client data (e.g. IoT cloud) is often done by gateways. However, due to limited computation resources inside IoT devices, the performance of SM9 becomes a bottleneck in practical usage. The existing SM9 implementa-tionsare often CPU-based, with relatively low latency and low throughput. Consequently, a pivotal challenge for SM9 in large-scale applications is how to reduce the latency while maximizing throughput for numerous concurrent inputs. After a systematic analysis of the SM9 algorithms, we apply optimization techniques including precomputa-tion,resource caching and parallelization to reduce the overhead of SM9. In this work, we introduce the frst prac-ticalimplementation of SM9 and its underlying SM9_P256 curve on GPU. Our GPU implementation combines multiple algorithms and low-level optimizations tailored for GPU’s single instruction, multiple threads architecture in order to achieve high throughput for SM9. Based on these, we propose GAPS, a high-performance Cryptog-raphyas a Service (CaaS) for SM9. GAPS adopts a heterogeneous computing architecture that fexibly schedules the inputs across two implementation platforms: a CPU for the low-latency processing of sporadic inputs, and a GPU for the high-throughput processing of batch inputs. According to our benchmark, GAPS only takes a few milliseconds to process a single SM9 request in idle mode. Moreover, when operating in its batch processing mode, GAPS can generate 2,038,071 private keys, 248,239 signatures or 238,001 ciphertexts per second. The results show that GAPS scales seamlessly across inputs of diferent sizes, preliminarily demonstrating the efcacy of our solution.
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.
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 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 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.
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 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.
