Электронный каталог

Книга (аналит. описание)

Hristov, I.
Parallelizing Multiple Precision Taylor Series Method for Integrating the Lorenz System / I.Hristov, T.Puzynina, Z.Sharipov, Z.Tukhliev, [a.o.] // Advanced Computing in Industrial Mathematics [Electronic resource] : 15th Annual Meeting of the Bulgarian Section of SIAM, Sofia, Bulgaria, December 15–17, 2020 : Revised Selected Papers / Ed.: I.Georgiev, H.Kostadinov, E.Lilkova. – Cham : Springer, 2023. – P. 56-66. – URL: https://doi.org/10.1007/978-3-031-20951-2_6. – Bibliogr.: 25.

A hybrid MPI+OpenMP strategy for parallelizing multiple precision Taylor series method is proposed, realized and tested. To parallelize the algorithm we combine MPI and OpenMP parallel technologies together with GMP library (GNU Multiple Precision library) and the tiny MPIGMP library. The details of the parallelization are explained on the paradigmatic model of the Lorenz system. We succeed to obtain a correct reference solution in the rather long time interval - [0,7000]. The solution is verified by comparing the results for 2700-th order Taylor series method and precision of 3374 decimal digits, and those with 2800-th order and precision of 3510 decimal digits. With 192 CPU cores in Nestum cluster, Sofia, Bulgaria, the 2800-th order computation lasted 145 h with speedup 105. – (Studies in Computational Intelligence ; Vol. 1076) .



ОИЯИ = ОИЯИ (JINR)2023
Спец.(статьи,препринты) = Ц 84 а2 - Многомашинные комплексы вычислительных средств. Вычислительные системы и сети. Параллельные вычисления. Квантовые компьютеры