Edge Intelligence with Distributed Processing of DNNs:A Survey

Withthe rapiddevelopment of deep learning,the size of data sets anddeepneuralnetworks(DNNs)models are also booming.As a result,the intolerable long time for models’training or inference with conventional strategies can not meet the satisfaction of modern tasks gradually.Moreover,devices stay idle in the scenario of edge computing(EC),which presents a waste of resources since they can share the pressure of the busy devices but they do not.To address the problem,the strategy leveraging distributed processing has been applied to load computation tasks from a single processor to a group of devices,which results in the acceleration of training or inference of DNN models and promotes the high utilization of devices in edge computing.Compared with existing papers,this paper presents an enlightening and novel review of applying distributed processing with data and model parallelism to improve deep learning tasks in edge computing.Considering the practicalities,commonly used lightweight models in a distributed system are introduced as well.As the key technique,the parallel strategy will be described in detail.Then some typical applications of distributed processing will be analyzed.Finally,the challenges of distributed processing with edge computing will be described.

Research on Decalcification Degradation Process of Cement Stone

An accelerated laboratory method（saturated ammonium nitrate solution immersion method） was used to analyze the degradation of cement decalcification process. By studying the changes of intensity, volume, elastic modulus, quality, p H value, the Ca/Si, and mineral phase, it could be found that the first cement decalcification degradation process was the decalcification of calcium hydroxide, and then CSH gel, AFm, etc. The secondary ettringite deposition happened and the decalcification degradation depth was proportional to the square root of time. Moreover, the corresponding strength of cement would be gradually reduced, cement rock volume shrinkage occurred, p H values decreased, the surface elastic modulus decreased down to a certain level, and slightly changed and the Ca/Si was 3.1 from the beginning and lasted down to 1.3.

Improvements of the Analytical Model of Monte Carlo

By extending the conduction band structure, we set up a new analytical model in ZnS. Compared the results with both the old analytical model and the full band model, it is found that they are possibly in reasonable agreement with the full band method and we can improve the calculation precision. Another important work is to reduce the programme computation time using the method of data fitting scattering rate curves.

A graphics processing unit-based robust numerical model for solute transport driven by torrential flow condition

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.

A non-uniform grid approach for high-resolution flood inundation simulation based on GPUs

In view of the frequent occurrence of floods due to climate change, and the fact that a large calculation domain, with complex land types, is required for solving the problem of the flood simulations, this paper proposes an optimized non-uniform grid model combined with a high-resolution model based on the graphics processing unit (GPU) acceleration to simulate the surface water flow process. For the grid division, the topographic gradient change is taken as the control variable and different optimization criteria are designed according to different land types. In the numerical model, the Godunov-type method is adopted for the spatial discretization, the TVD-MUSUL and Runge-Kutta methods are used to improve the model’s spatial and temporal calculation accuracies, and the simulation time is reduced by leveraging the GPU acceleration. The model is applied to ideal and actual case studies. The results show that the numerical model based on a non-uniform grid enjoys a good stability. In the simulation of the urban inundation, approximately 40%–50% of the urban average topographic gradient change to be covered is taken as the threshold for the non-uniform grid division, and the calculation efficiency and accuracy can be optimized. In this case, the calculation efficiency of the non-uniform grid based on the optimized parameters is 2–3 times of that of the uniform grid, and the approach can be adopted for the actual flood simulation in large-scale areas.

Procedural generation and real-time rendering of a marine ecosystem

Underwater scene is one of the most marvelous environments in the world. In this study, we present an efficient procedural modeling and rendering system to generate marine ecosystems for swim-through graphic applications. To produce realistic and natural underwater scenes, several techniques and algorithms have been presented and introduced. First, to distribute sealife naturally on a seabed, we employ an ecosystem simulation that considers the influence of the underwater environment. Second, we propose a two-level procedural modeling system to generate sealife with unique biological features. At the base level, a series of grammars are designed to roughly represent underwater sealife on a central processing unit(CPU). Then at the fine level, additional details of the sealife are created and rendered using graphic processing units(GPUs). Such a hybrid CPU-GPU framework best adopts sequential and parallel computation in modeling a marine ecosystem, and achieves a high level of performance.Third, the proposed system integrates dynamic simulations in the proposed procedural modeling process to support dynamic interactions between sealife and the underwater environment, where interactions and physical factors of the environment are formulated into parameters and control the geometric generation at the fine level. Results demonstrate that this system is capable of generating and rendering scenes with massive corals and sealife in real time.

A TensorFIow-based new high-performance computational framework for CFD

In this study,a computational framework in the field of artificial intelligence was applied in computational fluid dynamics(CFD)field.This Framework,which was initially proposed by Google Al department,is called"TensorFlow".An improved CFD model based on this framework was developed with a high-order difference method,which is a constrained interpolation profile(CIP)scheme for the base flow solver of the advection term in the Navier-Stokes equations,and preconditioned conjugate gradient(PCG)method was implemented in the model to solve the Poisson equation.Some new features including the convolution,vectorization,and graphics processing unit(GPU)acceleration were implemented to raise the computational efficiency.The model was tested with several benchmark cases and shows good performance.Compared with our former CIP-based model,the present Tensor Flow-based model also shows significantly higher computational efficiency in large-scale computation.The results indicate TensorFlow could be a promising framework for CFD models due to its ability in the computational acceleration and convenience for programming.