Jos R Bergervoet wrote:
>
> Also, the newer (commercial) codes, might be somewhat faster or
> slower. But the above should be a fair indication.
Many times commercial codes are not really better in the computational
core, but rather in the GUI: that's what sells and that's what is
seen.
On a C240+ our FDTD code written by a guy here, a 79 x 94 x 184 cells
makes about 1 s / iteration or 731 ns / iteration / cell (pretty close
to Jos' value for psufdtd if it was also on a C240+). However, the
domain is bordered by PMLs so that the pipeline of the processor (the
HPPA 2.0 processors can handle pipelining) is restarted several times
per iteration. If the domain were bordered by PEC or PMC, the
computation would be faster as the pipelining needs no restart.
The same code is about 3 to 6 times slower on modern PCs like K6, K7
oder similar Pentiums.
cheers
juergen
Received on Thu Feb 17 2000 - 04:03:17 EST
This archive was generated by hypermail 2.2.0 : Sat Oct 02 2010 - 00:10:40 EDT