RT Conference Proceedings
T1 Toward GPU-accelerated Traffic Simulation and Its Real-Time Challenge
A1 Hirabayashi, Manato
A1 Kato, Shinpei
A1 Edahiro, Masato
A1 Sugiyama, Yuki
A2 García Valls, Marisol
A2 Cucinotta, Tommaso
AB Traffic simulation is a growing domain of computationalphysics. Many life and industrial applications would benefitfrom traffic simulation to establish reliable transportationsystems. A core challenge of this science research, however,is its unbounded scale of computation. This paper exploresan advantage of using the graphics processing unit (GPU)for this computational challenge. We study two schemes ofmaximizing GPU performance in the context of traffic simulation,and provide some basic experiments. The experimentalresults show that our GPU implementation improvessimulation speed by five times over the traditional CPU implementation.We also discuss that additional orders-ofmagnitudeimprovements could be achieved by overcomingthe current hardware limitation of the GPU.
PB Universidad Carlos III de Madrid
YR 2012
FD 2012-12-04
LK https://hdl.handle.net/10016/17925
UL https://hdl.handle.net/10016/17925
LA eng
NO REACTION 2012. 1st International workshop on Real-time and distributed computing in emerging applications. December 4th, 2012, San Juan, Puerto Rico.
NO This work was supported by Grant-in-Aid for Scientific Research 24500058.
DS e-Archivo
RD 19 may. 2024