Some comments about graphic processing unit (GPU) architectures applied to finite-difference time-domain (FDTD) room acoustics simulation: Present and future trends

2013 ◽  
Author(s):  
Jose J. Lopez ◽  
Juan M. Navarro ◽  
Diego Carnicero ◽  
Jose Escolano
Keyword(s):  
Finite Difference ◽  
Time Domain ◽  
Finite Difference Time Domain ◽  
Graphic Processing Unit ◽  
Room Acoustics ◽  
Processing Unit ◽  
Future Trends ◽  
Gpu Architectures ◽  
Difference Time ◽  
Graphic Processing

scholarly journals Acceleration of split-field finite difference time-domain method for anisotropic media by means of graphics processing unit computing

2013 ◽  
Vol 53 (1) ◽  
pp. 011005 ◽  
Author(s):  
Jorge Francés ◽  
Sergio Bleda ◽  
Mariela Lázara Álvarez ◽  
Francisco Javier Martínez ◽  
Andres Márquez ◽  
...  
Keyword(s):  
Finite Difference ◽  
Time Domain ◽  
Finite Difference Time Domain ◽  
Graphics Processing Unit ◽  
Anisotropic Media ◽  
Time Domain Method ◽  
Processing Unit ◽  
Split Field ◽  
Graphics Processing ◽  
Difference Time

scholarly journals Parallelization of the finite-difference time-domain method for room acoustics modelling based on CUDA

2013 ◽  
Vol 57 (7-8) ◽  
pp. 1822-1831 ◽  
Author(s):  
José J. López ◽  
Diego Carnicero ◽  
Néstor Ferrando ◽  
José Escolano
Keyword(s):  
Finite Difference ◽  
Time Domain ◽  
Finite Difference Time Domain ◽  
Time Domain Method ◽  
Room Acoustics ◽  
Domain Method ◽  
Difference Time

PARALLEL 3D FINITE-DIFFERENCE TIME-DOMAIN METHOD ON MULTI-GPU SYSTEMS

2011 ◽  
Vol 22 (02) ◽  
pp. 107-121 ◽  
Author(s):  
LIU-GE DU ◽  
KANG LI ◽  
FAN-MIN KONG ◽  
YUAN HU
Keyword(s):  
Finite Difference ◽  
Time Domain ◽  
Finite Difference Time Domain ◽  
Data Exchange ◽  
Programming Model ◽  
Perfect Match ◽  
Absorbing Boundary Conditions ◽  
Processing Unit ◽  
Computation Efficiency ◽  
Difference Time

Finite-difference time-domain (FDTD) is a popular but computational intensive method to solve Maxwell's equations for electrical and optical devices simulation. This paper presents implementations of three-dimensional FDTD with convolutional perfect match layer (CPML) absorbing boundary conditions on graphics processing unit (GPU). Electromagnetic fields in Yee cells are calculated in parallel millions of threads arranged as a grid of blocks with compute unified device architecture (CUDA) programming model and considerable speedup factors are obtained versus sequential CPU code. We extend the parallel algorithm to multiple GPUs in order to solve electrically large structures. Asynchronous memory copy scheme is used in data exchange procedure to improve the computation efficiency. We successfully use this technique to simulate pointwise source radiation and validate the result by comparison to high precision computation, which shows favorable agreements. With four commodity GTX295 graphics cards on a single personal computer, more than 4000 million Yee cells can be updated in one second, which is hundreds of times faster than traditional CPU computation.

Sign in / Sign up

Export Citation Format

Share Document