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

[Stefaan Cottenier]

> Also, I noticed that the best performance on P4 systems was achieved
> by using MKL. This is strange because normally Goto's lib is faster 
> than MKL.

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.

Stefaan