ni...@lysator.liu.se (Niels Möller) writes:
Trying
$ ./speed -o cycles-broken -s 1-30,100,200 -r mpn_mullo_n mpn_binvert
it appears binvert is up to 5 times slower than mullo for just a few
limbs, 2 times slower for n = 10, and roughly 50% slower in the range
between 20 and 200
Torbjorn Granlund t...@gmplib.org writes:
* Which function uses submul_1? I thought neither the old nor the new
bdiv functions used that.
You're right. I thought current sb_pi1_bdiv_qr used submul_1, but when I
look I remember that it uses addmul_1 and then it negates q on the fly.
* I