According to John Caron:
>
>
> I would assume that the cost of writing large float arrays on the cray
> comes from:
> 1) converting the floats to ieee format
> 2) the xdr overhead, especially array loops.
>
> On point one, there might be a system library to do this fast. I also
> heard a rumor that Cray is going to change to ieee format (???)
Look up the command and subroutine "assign." This can be used to write
out files in ieee format and whatever it is doing the conversion is supposed
to have been optimized by Cray. I don't know how well this can be applied
to netcdf libraries.
--
Matt Hughes, Graphics and Visualization Coordinator
University of Minnesota Supercomputer Institute
1200 Washington Avenue South Ph: (612) 626-1765
Minneapolis, MN 55415 hughes@xxxxxxxxxxx
