Title :
Application of GPU to Three Computational Models
Author :
Qiangqiang Shi ; Yiyang Yang ; Xiaolin Li
Author_Institution :
Dept. of Appl. Math. & Stat., Stony Brook Univ., Stony Brook, NY, USA
Abstract :
In this paper, we report three applications of Graphics Processing Unit (GPU) based algorithms for high performance computation of mathematical models with the Fron Tier++ code. In the first set of simulations, the system of one-dimensional gas dynamics equations is solved by the Weighed Essentially Non-Oscillatory (WENO) scheme, we achieved 7-20 times speedup for different mesh sizes on one GPU device. In the second case, the spring model for fabric dynamics is studied, the GPU code is about 10-20 times faster than the pure CPU code for different mesh sizes. In the last case, a GPU enhanced numerical algorithm for American option pricing under the generalized hyperbolic distribution is studied. Using one GPU device, we have achieved 2 times speedup for the price of single option and 100 times speedup for multiple options.
Keywords :
graphics processing units; 1D gas dynamics equations; American option pricing; CPU code; Fron Tier++ code; GPU based algorithms; GPU code; GPU device; GPU enhanced numerical algorithm; WENO scheme; fabric dynamics; generalized hyperbolic distribution; graphics processing unit; high performance computation; mathematical models; spring model; three computational models; weighed essentially nonoscillatory scheme; Capacitance; Clocks; Electronic mail; Logic gates; MOS devices; Monitoring; Transistors; American option pricing; GPGPU; gas dynamics; spring model;
Conference_Titel :
Embedded Multicore/Manycore SoCs (MCSoc), 2014 IEEE 8th International Symposium on
Conference_Location :
Aizu-Wakamatsu
DOI :
10.1109/MCSoC.2014.44