China
Africa
Explore chapters and articles related to this topic
Parallel Computing Architecture Basics
Published in Vivek Kale, Parallel Computing Architectures and APIs, 2019
The degree of parallelism is simply the index of the number of computations that can be executed concurrently. Suppose that the application allows the development of processing algorithms with a degree of parallelism A; the language used to code the algorithm allows the representation of algorithms with a degree of parallelism L; the compilers produce an object code that retains a degree of parallelism C; and the hardware structure of the machine has a degree of parallelism H. Then, for processing to be most efficient: H≥C≥L≥A
Advanced Signal Processing Resources in FPGAs
Published in Juan José Rodríguez Andina, Eduardo de la Torre Arnanz, María Dolores Valdés Peña, FPGAs, 2017
Juan José Rodríguez Andina, Eduardo de la Torre Arnanz, María Dolores Valdés Peña
How can the same problem be solved using FPGAs? Thanks to the availability of abundant logic resources and the possibility of configuring them to operate in parallel, several approaches are feasible, from a fully series architecture (requiring N clock cycles to generate new output data) to a fully parallel one, like the one shown in Figure 4.1b, capable of generating new output data every clock cycle, or intermediate series-parallel solutions. This provides the designer with the flexibility to define different performance–complexity trade-offs by choosing a particular degree of parallelism. In addition, by using design techniques such as pipelining or retiming, extremely high-performance signal processing systems can be obtained.
A prediction model for complex equipment remaining useful life using gated recurrent unit complex networks
Published in Enterprise Information Systems, 2023
Sheng Tong, Jie Yang, Haohua Zong
Traditional GRU networks use a stochastic gradient descent algorithm to optimise each parameter, and the execution efficiency is low. The genetic algorithm is a commonly used parallel random global optimisation search algorithm that simulates the genetic and evolutionary process of organisms in nature, and it has good execution efficiency. This algorithm draws on the basic law of survival of the fittest in genetics and expresses the optimisation problem to be solved as the chromosome competition and survival process. Through the chromosome duplication, crossover and mutation processes, satisfactory conditional individuals are finally output. Thereby, the global optimal solution is obtained. The GA is an optimisation algorithm with a high degree of parallelism, strong generalisation ability and adaptability (Goldberg,1988); and its implementation process is shown in Figure 4.