Re: BogoMIPS revisitied...MMX
Perry Harrington (pedward@sun4.apsoft.com)
Wed, 18 Mar 1998 15:22:48 -0800 (PST)
>
>
> On Wed, 18 Mar 1998 linker@nightshade.ml.org wrote:
>
> > Well.. What bogomips do tell you is that differnt processors optimize
> > differntly..
>
> Yours perhaps optimizes to much, since 2 'e' seems to have been lost. :-)
>
> > Two computers: P233 and PII-233 both running the same Linux kernel,
> > P233-400bogos PII233-200bogos.. DES2 client ran 15% faster on the P233
> > over the PII233.. :)
>
> The x86 architecture is crappy. Trying to optimize to much these shit
> seems to lead to tons of firmware bugs, IMO.
> I just cross fingers for the next generation of affordable processors
> to be clean.
> Do you have some results about the same algorithm running on some clean
> architecture as ALPHA (and using 64 bit calculations) ?
A 166Mhz 21066 w/256K (L3?) Cache will spit out ~814000 DES keys/s on that
test. A far cry from my 486-120 that did 245000 and 117000 RC5 (the alpha
did 95000). BTW, this is a UDB.
>
>
> Gerard.
>
--
Perry Harrington Linux rules all OSes. APSoft ()
email: perry@apsoft.com Think Blue. /\
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu