|
Vestnik Novosibirskogo Gosudarstvennogo Universiteta. Seriya Matematika, Mekhanika, Informatika, 2014, Volume 14, Issue 4, Pages 11–21
(Mi vngu351)
|
|
|
|
Mathematical Simulation of Electromagnetic Logging Data Using High-Performance Coprocessor Intel Xeon Phi
V. N. Glinskikha, Yu. O. Bulantsevab a A. A. Trofimuk Institute of Petroleum Geology and Geophysics, Siberian Branch of the Russian Academy of Sciences, Novosibirsk
b Novosibirsk State University
Abstract:
The article deals with mathematical simulation of electromagnetic logging data from oil-and-gas wells by using high-performance coprocessor Intel Xeon Phi. A computational algorithm to solve forward two-dimensional electromagnetic logging problems is developed. Its parallel realization is made through the use of OpenMP technology for Intel architectures, including MIC. The estimations of computational performance while using multi-core Intel architectures are given. The computational models describing different variants of host- and coprocessors usage are scrutinized. The performed mathematical simulation and comparative analysis of the results have shown that by means of coprocessor Intel Xeon Phi it is possible to increase a processing speed by a factor of hundreds as compared with widely available processors Intel Core.
Keywords:
mathematical simulation, electromagnetic logging, electrical conductivity, parallel algorithm, high-performance computing, coprocessor Intel Xeon Phi.
Received: 16.09.2014
Citation:
V. N. Glinskikh, Yu. O. Bulantseva, “Mathematical Simulation of Electromagnetic Logging Data Using High-Performance Coprocessor Intel Xeon Phi”, Vestn. Novosib. Gos. Univ., Ser. Mat. Mekh. Inform., 14:4 (2014), 11–21
Linking options:
https://www.mathnet.ru/eng/vngu351 https://www.mathnet.ru/eng/vngu/v14/i4/p11
|
Statistics & downloads: |
Abstract page: | 183 | Full-text PDF : | 68 | References: | 43 | First page: | 9 |
|