GMP 6 the incomatible GMP?

Torbjorn Granlund tg at gmplib.org
Tue Jan 8 12:50:01 CET 2013


Marc Glisse <marc.glisse at inria.fr> writes:

  Then we might as well always put it in _mp_d[-1], no? IIRC that's what
  mpfr does.

I see some problems with that:

* There is a serial memory dependency problem, making the allocation
  check at least one more cache latency away.  I don't think OoO
  execution will be able to hide that, as this is used.

* There is a slight type error mixing limbs and sizes.  The ASL patch by
  Per Olofsson will require many limbs to represent a size.  But this is
  a testing feature, which should not get in they way of an otherwise
  desirable change.

-- 
Torbjörn


More information about the gmp-devel mailing list