Is asm code selection optimal?

Torbjörn Granlund tg at
Wed May 17 01:01:05 UTC 2017

tg at (Torbjörn Granlund) writes:

  And in the case you quote I'd assume the default is actually the C code,
  i.e., that the config did not pick up any asm.
Alas, that's not the case.

I don't know what's going on.  For a normalised divisor, timings match

I fixed some problems with the tables, the result should start
apppearing with next set of runs.

The C code you suggested is still missing.

There will be some duplicates related too include_mpn.  Suppressing
duplicates isn't as easy as one might think as just excluding
include_mpn files misses many things we do want to measure.

Please encrypt, key id 0xC8601622

More information about the gmp-devel mailing list