Title :
Performance analysis of parallel master-slave Evolutionary strategies (μ,λ) model python implementation for CPU and GPGPU
Author :
Zubanovic, D. ; Hidic, Alisa ; Hajdarevic, A. ; Nosovic, Novica ; Konjicija, Samim
Author_Institution :
Fac. of Electr. Eng., Univ. of Sarajevo, Sarajevo, Bosnia-Herzegovina
Abstract :
Evolutionary strategies is a heuristic, guided-search based evolutionary algorithm, widely used as optimization technique for computationally intensive problems. Python is a high-level programming language known for code readability, reusability and the ease of use, making it preferable choice for quick and robust software development, although it is lacking in performance and concurrency area. Emerging technologies such as Anaconda Accelerate Python compiler attempt to combine Python´s ease of use with both declarative and explicit parallelization and high performance in computationally intensive problems. In this paper an example of master - slave parallel Evolutionary strategy ES(μ,λ) implementation in Python is given, and its performance on CPU and GPU are analyzed.
Keywords :
evolutionary computation; graphics processing units; high level languages; mathematics computing; parallel processing; program compilers; search problems; software reusability; Anaconda Accelerate Python compiler; CPU; ES(μ,λ); GPGPU; Python parallel master-slave evolutionary strategy (μ,λ) model; code readability; code reusability; concurrency area; heuristic guided-search based evolutionary algorithm; high-level programming language; optimization technique; performance analysis; robust software development; Acceleration; Computational modeling; Graphics processing units; Heuristic algorithms; Master-slave; Sociology; Statistics; GPU; Heuristic algorithms; Multithreading; Parallel computing; Python-Anaconda; Test functions for optimization;
Conference_Titel :
Information and Communication Technology, Electronics and Microelectronics (MIPRO), 2014 37th International Convention on
Conference_Location :
Opatija
Print_ISBN :
978-953-233-081-6
DOI :
10.1109/MIPRO.2014.6859822
