speed of unbalanced multiplication

[bodrato at mail.dm.unipi.it]

Ciao Torbjorn,

Il Gio, 7 Febbraio 2013 11:22 am, Torbjorn Granlund ha scritto:
> It would be nice to understand the slowdown of before, though...

I agree, but ... the only difference I could see on my netbook is not
memory alignment, but "position".

Before the patch, I obtain:

$ tune/speed -o addrs -s 800000 mpn_mul_n
[...]
dst 01BF0B00 src 7F90B1F75040 7F90B195A040   (cf sp approx 7FFF797BF61C)
^C
$ tune/speed -o addrs -s 800000 mpn_mul
[...]
dst 01F97B00 src 02BCCB40 7FE0D0C9A040   (cf sp approx 7FFF8D1D3F3C)
^C

... and mpn_mul seem slower.

After it:

$ tune/speed -o addrs -s 800000 mpn_mul_n
[...]
dst 017A4B00 src 7FA7F3A85040 7FA7F346A040   (cf sp approx 7FFF9C81A24C)
^C
$ tune/speed -o addrs -s 800000 mpn_mul
[...]
dst 01005B00 src 7F2E273C8040 7F2E26DAD040   (cf sp approx 7FFF19656F2C)
^C

... and I get the same speed.

Regards,
m

-- 
http://bodrato.it/papers/