[Wien] performance problem using ifort + Goto's lib

[Christopher Homes]

>
>
>I did a few non-systematic tests some time ago, from which I concluded 
>that goto is faster than mkl 6.0, but slower than mkl 6.1. This seems 
>to be confirmed by the benchmark page, where e.g.:
>
>P4, 3.2 GHz, dual channel mem.   258 sec    ifc7, mkl6
>P4, 3.2 GHz, 400MHz dual ch.mem. 228 sec    ifort8.0, mkl6.1
>
>Not really a clean comparison (ifc vs ifort as well), but this gain of 
>30 s is less than the estimated gain of goto over mkl 6.0. If this 
>conclusion is true (do other users find the same?), then this explains 
>your above question.
>
I did the original benchmark on our workstation that yielded the 258 sec
result.  This benchmark actually involved the ifc 7.1 compiler and the
mkl 6.1 libraries.  I have since applied the latest update to the mkl
libraries and recompiled with the ifort 8.0 compiler and I find no change
in the benchmark time - with some optimization, I now get a benchmark
time of 256 sec, and if you kill absolutely ever process, then you can
trim it down to 254 sec.  Compiling with the Goto blas routines also
didn't seem to make much of a difference (on the order of seconds).
I think this result is consistent with benchmark time of 258 secs that
was quoted earlier in this thread.
 
  Chris.

======================================================================
Christopher Homes, Rm. 1-17            Email: homes at bnl.gov
Department of Physics - Bldg. 510B     Tel: (631) 344-7579 (Office)
Brookhaven National Laboratory              (631) 344-3537 (Lab)
20 Pennsylvania Street                      (631) 344-5510 (NSLS/U10A)
P.O. Box 5000                          FAX: (631) 344-2739
Upton, New York, USA 11973-5000

Physics Infrared - http://infrared.phy.bnl.gov
NSLS U10A - http://infrared.phy.bnl.gov/u10a.htm
Personal - http://infrared.phy.bnl.gov/homes.htm
======================================================================