From: Stephen Hemminger <[EMAIL PROTECTED]>
Date: Thu, 15 Dec 2005 15:36:08 -0800

> $ ./croot 10000000
> 
> Opteron 2.0 Ghz
> math 9671505106 1.230814
> old 9676503359 1.287217
> bisect 9666502089 1.074139
> newton 9671507303 1.168087
> 
> Xeon (32bit) 2.4 Ghz
> math 9671505106 3.047887
> old 9676503359 5.917374
> bisect 9666502089 5.337120
> newton 9671507303 2.433769
> 
> Pentium III 700 Mhz
> math 9671505106 7.038867
> old 9676503359 9.055317
> bisect 9666502089 7.904939
> newton 9671507303 4.867410

I hacked it up to work on Sparc64, and got similar results:

UltraSPARC-III 750Mhz
math 9671505106 13.981894
old 9676503359 14.733434
bisect 9666502089 9.803103
newton 9671507303 6.047052

UltraSPARC-IIIi 1.5Ghz
math 9671505106 6.605714
old 9676503359 6.818648
bisect 9666502089 4.493193
newton 9671507303 2.549662

On platforms without hardware integer multiply and divide newton does
especially well.  The following results are after recompiling to do
multiply and divide via software library calls:

UltraSPARC-III 750Mhz
math 9671505106 13.814611
old 9676503359 79.915000
bisect 9666502089 67.882641
newton 9671507303 10.131326

UltraSPARC-IIIi 1.5Ghz
math 9671505106 6.431173
old 9676503359 39.667685
bisect 9666502089 33.510414
newton 9671507303 4.565952
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to