Calculation of [A] of the FS solver should be parallelized on the CPU and the GPU

Suyash1989 / cfd-with-cuda

Automatically exported from code.google.com/p/cfd-with-cuda

0 stars 0 forks source link

Calculation of [A] of the FS solver should be parallelized on the CPU and the GPU #25

Open GoogleCodeExporter opened 8 years ago

GoogleCodeExporter commented 8 years ago

In Step 1 of the Fractional Step solver [A] matrix is calculated at the first 
iteration of each time step. This is quite time consuming and should be 
parallelized on the CPU and the GPU.

Original issue reported on code.google.com by cuneytsert on 10 Jun 2014 at 12:04

GoogleCodeExporter commented 8 years ago

A reference paper for parallel FE assmebly on the CPU and the GPU is

G. R. Markall1, A. Slemmer, D. A Ham, P. H. J. Kelly1, C. D. Cantwell, and
S. J. Sherwin, "Finite element assembly strategies on multi- and many-core 
architectures", Int. J. Numer. Meth. Fluids 2011; 00:1–18

Original comment by cuneytsert on 10 Jun 2014 at 12:15