소개

세미나

홈 > 학술행사 > 세미나 68

[세미나] 2014.11.07 계산과학 초청세미나 공지(updated)
계산과학전공   2014.11.03   1562

11월 7일(금요일)
오전 10시-12시 / 14-15시에 CST 세미나실(25동 114호)에서
초청세미나가 있으니 많은 참여 바랍니다.
초록은 아래와 같습니다.

======================================================
10시 - 11시
연사 : Yuusuke Iso (Kyoto University)

제목 : Stability of the CIP scheme applied to advection equations
초록 : The cubic interpolated pseudoparticle (CIP) scheme is one of the Japanese algorithms for solving partial differential equations, and it is proposed by Prof. Takashi Yabe. He has proposed various types of numerical schemes with the same name "CIP", and we discuss the original scheme proposed in 1985. The scheme is intended to be a highly accurate one for solving hyperbolic equations and is widely used in computational mechanics. It is well known as an accurate scheme but its stability analysis has been unsolved for long time. We give a weak stability estimate for the scheme applied to linear advection equations and also show that it is not strongly stable in L^2. This research is a joint work with Dr. Daiki Tanaka, Prof. Hiroshi Fujiwara and Prof Takaaki Nishida.

======================================================
11시 - 12시
연사 : Hiroshi Fujiwara (Kyoto University, Graduate School of Informatics)

제목 : Hybrid Parallelization and GPGPU for Fast Computation of the Radiative Transport Equation
초록 : We discuss an efficient parallel computation of the stationary radiative transport equation (RTE) in the three dimensions by using GPU (Graphics rocessing Unit). RTE is an integro-differential equation and it appears as a mathematical model of light propagation in human bodies. Its discretization is essentially a five dimentional large scale problem, since light intensity in RTE depends on the position and the velocity. 
We employ two techniques for fast computations : GPU to accelerate calculation of the integral term in RTE, and software pipelining with OpenMP to hide transfer delays between the host memory and GPU device memory. The finite difference also appears in discretization of RTE. Its memory access pattern is quite different from that of numerical integration, and CPU processes it simultaneously by software pipelining techniques in the proposed algorithm. In the presentation, we show the current hybrid parallel implementation on a PC cluster with GPUs, 
and discuss efficiency of the propolsed parallel computing. 
This talk is based on a project with Prof. Y. Iso and Human Brain Research Center in Kyoto University.

======================================================
14시 - 15시
연사 : 전영목 교수 (아주대학교)

제목 : Hybrid difference methods for PDEs

======================================================








댓글







admin
2017-09-21
dasdfasd



목록


69 [세미나] 2014.12.12(금) 계산과학 초청세미나 공지(Updated) 2014.12.09
68 [세미나] 2014.11.07 계산과학 초청세미나 공지(updated) 2014.11.03
67 [세미나] 2012.07.12 계산과학 세미나 공지 2013.07.11
66 CST Seminar (CST Program) 2012.05.21