Due to the current gap in continued funding from the U.S. National Science Foundation (NSF), the NSF Unidata Program Center has temporarily paused most operations. See NSF Unidata Pause in Most Operations for details.

Efficiency on a CRAY

Hello,

I am converting CRAY floating-point binaries to NetCDF's, but it is very
expensive.  For example, A loop of 6 ncvarput's (FORTRAN binding) processing
a total of 0.5 Megawords costs about 10 CPU seconds.  I suspect that function
calls to XDR are inhibiting vectorization.  Has anyone dealt with this 
problem before?

-- 
  William Weibel                        |  weibel@xxxxxxxxxxxxxx
  Department of Atmospheric Sciences    |
  UCLA                                  |  Tel. (310)206-4441
  Los Angeles, CA  90024-1565           |  Fax  (310)206-5219
  U.S.A.                                |


  • 1993 messages navigation, sorted by:
    1. Thread
    2. Subject
    3. Author
    4. Date
    5. ↑ Table Of Contents
  • Search the netcdfgroup archives: