Regarding superopt-va

[Torbjorn Granlund]

  i have an interest on computer architecture (specifying my own 
  architectures, their implementations -- soft cores -- and tools) and 
  recently i had a specific need for optimizing code sequences (integer 
  arithmetic library development for my processor). This where gmp and the 
  recently announced (by Tobjorn) superopt-va come in place.

I doubt superopt-va is useful for that, as it is not specific to any
processor.

You may want to port the GNU superopt to your processor.

  To my understanding the superopt-va is written from scratch, and some 
  things that where implemented in the GNU superopt, are not there (yet) 
  in superopt-va.

Well, they do and will always do quite different things.

The "va" in superopt-va is for Vector Algebra.

  2) Is it possible to specify unsigned words (assuming that the default 
  is signed words), e.g. via the regular type casting? I remember this was 
  available for the GNU superopt.

Be my guest.

  3) What is this Toom arithmetic? I have never heard about it yet. Where 
  is it used (this might be a little OT, but it seems that Toom functions 
  are the only benchmark that the new superopt has been exercised on.)

I mean the arithmetic needed in Toom's multiplication algorithm.  (Or
specifically the polynomial evaluation needed therein, the
interpolation does not fit, but there has been other work in that
area, see www.bodrato.it.)

  4) Is "superopt-va" going to be included in tests/devel directory of the 
  gmp release? I have added the related files to this dir in my own copy. 
  Or is it considered very alpha for that?

I don't have any plans for including in GMP.

-- 
Torbjörn