Re: [ccp4bb]: Some naive questions about AltiVec

[James Stroud <James.Stroud@colorado.edu>]

***  For details on how to be removed from this list visit the  ***
***          CCP4 home page http://www.ccp4.ac.uk         ***

By all accounts, vectorized code running on G4s is the way to go if you can
do it and though it would be nice to have high speed crystallography
computation "on the go" with a G4 laptop, I must provide an independent
confirmation of Bill Scott's observations.

I have had a similar experience with Absoft. Namely, their fortran compiler
doesn't work, so don't waste your money. I've watched it choke on even on
the most standard code. Inexpensive Linux machines are the way to go unless
Apple provides its own vectorizing preprocessor.

Though we probably could have gotten more bang per buck with AMD CPUs, we
get screaming results with a stack of dual P4 Xeons running Linux using the
intel ICC and IFC compilers to compile our code.

--------------------------------------------------------
"Research: If it worked the first time,
they would just call it 'search'."     -Roy Garcia
--------------------------------------------------------
 James C. Stroud
 Department of Chemistry and Biochemistry
 University of Colorado at Boulder
 Boulder, CO 80309

 Tel: 303-492-4503      Fax: 303-735-1347
--------------------------------------------------------