Emulating massively parallel computer architectures represents a very important tool for the parallel programmers. It allows them to implement and validate their algorithms. Due to the high cost of the massively paral...Emulating massively parallel computer architectures represents a very important tool for the parallel programmers. It allows them to implement and validate their algorithms. Due to the high cost of the massively parallel real machines, they remain unavailable and not popular in the parallel computing community. The goal of this paper is to present an elaborated emulator of a 2-D massively parallel re-configurable mesh computer of size n x n processing elements (PE). Basing on the object modeling method, we develop a hard kernel of a parallel virtual machine in which we translate all the physical properties of its different components. A parallel programming language and its compiler are also devel-oped to edit, compile and run programs. The developed emulator is a multi platform system. It can be installed in any sequential computer whatever may be its operating system and its processing unit technology (CPU). The size n x n of this virtual re-configurable mesh is not limited;it depends just on the performance of the sequential machine supporting the emulator.展开更多
This paper investigates the comparison problem of the reliability index between a parallel and a cold-standby system,both of which are consisting of two identical units.On the contrary to the general intuitive result,...This paper investigates the comparison problem of the reliability index between a parallel and a cold-standby system,both of which are consisting of two identical units.On the contrary to the general intuitive result,we proved that,under the condition that the system is shocked by a Poisson stream,the life time of the parallel system is longer than that of the cold-standby one in the sense of probability.展开更多
Fuzzy technology is a newly developed discipline based on fuzzy mathematics. In the recent years, it has been successfully applied into many areas, such as process control, diagnosis, evaluation, decision making and s...Fuzzy technology is a newly developed discipline based on fuzzy mathematics. In the recent years, it has been successfully applied into many areas, such as process control, diagnosis, evaluation, decision making and scheduling, especially in simulation where accurate mathematical models can not or very hard be established. In this paper, to meet the demands of fuzzy simulation, two fuzzy nets will first be presented, which are quite suitable for modeling the parallel or concurrent systems with fuzzy behavior. Then, a concept of active simulation will be introduced, in which the simulation model not only can show its fuzzy behavior, but also has a certain ability which can actively perform many very useful actions, such as automatic warning, realtime monitoring, simulation result checking, simulation model self-adapting, error recovery, simulating path tracing, system states inspecting and exception handling, by a unified approach while some specified events occur. The simulation model described by this powerful simulation modeling tool is concurrently driven by a network interpreter and an event monitor that all can be implemented by software or hardware. Besides, some interesting applications are given in the paper.展开更多
In this paper a hybrid parallel multi-objective genetic algorithm is proposed for solving 0/1 knapsack problem. Multi-objective problems with non-convex and discrete Pareto front can take enormous computation time to ...In this paper a hybrid parallel multi-objective genetic algorithm is proposed for solving 0/1 knapsack problem. Multi-objective problems with non-convex and discrete Pareto front can take enormous computation time to converge to the true Pareto front. Hence, the classical multi-objective genetic algorithms (MOGAs) (i.e., non- Parallel MOGAs) may fail to solve such intractable problem in a reasonable amount of time. The proposed hybrid model will combine the best attribute of island and Jakobovic master slave models. We conduct an extensive experimental study in a multi-core system by varying the different size of processors and the result is compared with basic parallel model i.e., master-slave model which is used to parallelize NSGA-II. The experimental results confirm that the hybrid model is showing a clear edge over master-slave model in terms of processing time and approximation to the true Pareto front.展开更多
This paper presents an error modeling methodology that enables the tolerance design, assembly and kinematic calibration of a class of 3-DOF parallel kinematic machines with parallelogram struts to be integrated into a...This paper presents an error modeling methodology that enables the tolerance design, assembly and kinematic calibration of a class of 3-DOF parallel kinematic machines with parallelogram struts to be integrated into a unified framework. The error mapping function is formulated to identify the source errors affecting the uncompensable pose error. The sensitivity analysis in the sense of statistics is also carried out to investigate the influences of source errors on the pose accuracy. An assembly process that can effectively minimize the uncompensable pose error is proposed as one of the results of this investigation.展开更多
随着ChatGPT的问世,各种大模型(Large Language Model,LLM)产品不断涌现,一个属于大模型的时代正在来临。然而,由于大模型面临着参数规模大、训练时间长的难点,现有传统机器学习模型训练方法并不适用于大模型的训练,亟需探索新的分布式...随着ChatGPT的问世,各种大模型(Large Language Model,LLM)产品不断涌现,一个属于大模型的时代正在来临。然而,由于大模型面临着参数规模大、训练时间长的难点,现有传统机器学习模型训练方法并不适用于大模型的训练,亟需探索新的分布式训练方法与策略。针对这些问题,从三个方面综述大模型分布式训练方法在过去十几年里的进展,包含分布式训练的架构并行加速策略以及内存和计算优化方面的内容,最后提出了未来可以探索的研究方向。展开更多
文摘Emulating massively parallel computer architectures represents a very important tool for the parallel programmers. It allows them to implement and validate their algorithms. Due to the high cost of the massively parallel real machines, they remain unavailable and not popular in the parallel computing community. The goal of this paper is to present an elaborated emulator of a 2-D massively parallel re-configurable mesh computer of size n x n processing elements (PE). Basing on the object modeling method, we develop a hard kernel of a parallel virtual machine in which we translate all the physical properties of its different components. A parallel programming language and its compiler are also devel-oped to edit, compile and run programs. The developed emulator is a multi platform system. It can be installed in any sequential computer whatever may be its operating system and its processing unit technology (CPU). The size n x n of this virtual re-configurable mesh is not limited;it depends just on the performance of the sequential machine supporting the emulator.
文摘This paper investigates the comparison problem of the reliability index between a parallel and a cold-standby system,both of which are consisting of two identical units.On the contrary to the general intuitive result,we proved that,under the condition that the system is shocked by a Poisson stream,the life time of the parallel system is longer than that of the cold-standby one in the sense of probability.
文摘Fuzzy technology is a newly developed discipline based on fuzzy mathematics. In the recent years, it has been successfully applied into many areas, such as process control, diagnosis, evaluation, decision making and scheduling, especially in simulation where accurate mathematical models can not or very hard be established. In this paper, to meet the demands of fuzzy simulation, two fuzzy nets will first be presented, which are quite suitable for modeling the parallel or concurrent systems with fuzzy behavior. Then, a concept of active simulation will be introduced, in which the simulation model not only can show its fuzzy behavior, but also has a certain ability which can actively perform many very useful actions, such as automatic warning, realtime monitoring, simulation result checking, simulation model self-adapting, error recovery, simulating path tracing, system states inspecting and exception handling, by a unified approach while some specified events occur. The simulation model described by this powerful simulation modeling tool is concurrently driven by a network interpreter and an event monitor that all can be implemented by software or hardware. Besides, some interesting applications are given in the paper.
文摘In this paper a hybrid parallel multi-objective genetic algorithm is proposed for solving 0/1 knapsack problem. Multi-objective problems with non-convex and discrete Pareto front can take enormous computation time to converge to the true Pareto front. Hence, the classical multi-objective genetic algorithms (MOGAs) (i.e., non- Parallel MOGAs) may fail to solve such intractable problem in a reasonable amount of time. The proposed hybrid model will combine the best attribute of island and Jakobovic master slave models. We conduct an extensive experimental study in a multi-core system by varying the different size of processors and the result is compared with basic parallel model i.e., master-slave model which is used to parallelize NSGA-II. The experimental results confirm that the hybrid model is showing a clear edge over master-slave model in terms of processing time and approximation to the true Pareto front.
基金This work was supported by the National Natural Science Foundation of China (Grant No.50075006) the Royal Society UK-China Joint Research Grant and Tianjin Scientce and Technology Commission(Grant No.003802111).
文摘This paper presents an error modeling methodology that enables the tolerance design, assembly and kinematic calibration of a class of 3-DOF parallel kinematic machines with parallelogram struts to be integrated into a unified framework. The error mapping function is formulated to identify the source errors affecting the uncompensable pose error. The sensitivity analysis in the sense of statistics is also carried out to investigate the influences of source errors on the pose accuracy. An assembly process that can effectively minimize the uncompensable pose error is proposed as one of the results of this investigation.
文摘随着ChatGPT的问世,各种大模型(Large Language Model,LLM)产品不断涌现,一个属于大模型的时代正在来临。然而,由于大模型面临着参数规模大、训练时间长的难点,现有传统机器学习模型训练方法并不适用于大模型的训练,亟需探索新的分布式训练方法与策略。针对这些问题,从三个方面综述大模型分布式训练方法在过去十几年里的进展,包含分布式训练的架构并行加速策略以及内存和计算优化方面的内容,最后提出了未来可以探索的研究方向。
