On 27.02.2012 18:01, Matthew Knepley wrote:
On Mon, Feb 27, 2012 at 10:55 AM, Barry Smith <bsmith@mcs.anl.gov> wrote:

  I'm afraid the sudden appearance of the blas dot for complex numbers problem is my fault.

  Traditionally since 199x we never used the complex dot product from blas because of the return complex type problem. VecDot_Seq() used #ifdef for complex and a simple loop.

  Since some blas norm suck I off-hand told Shri to use dot for norm and wasn't thinking the complex case.

  Since then, of course, the complex dot problem has been coming up.

  Maybe it is best to continue to never use complex blas dot and just change the VecNorm_ routines to use norm for complex and not dot.? Just throw away this silly problem and time sink?

Why is this such a problem? Just use PetscScalar for the BLASdot_() return type and its fine.

For instance MKL's BLAS returns result for zdot in the first argument and PETSc's BLASdot_() fails there.


   Matt
 

   Barry




--
What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.
-- Norbert Wiener


-- 
Regards,
Alexander