[RC5] Speed

dan carter motion at es.co.nz
Tue Apr 21 18:38:06 EDT 1998


On Mon, 20 Apr 1998 19:39:25 -0700 (PDT), Dan Sugalski wrote:

>> And I was saying, that is a calculated value.  It is calculated from 
>> taking some refference processor (in X86 case it was P100), calculating 
>> how many of those processors would be doing current load of X86es, and 
>> than multiplying it with the number of known FLOPS of P100.  That was 
>> done by D.Net staff (http://www.distributed.net/statistics/stats.html.
>> I know that D.Net processing does NOT involve fp ops to be measured...
>
>You can't scale the numbers at all meaningfully, though.

You can't translate the numbers exactly. But that you can't translate meaninfully is yet to proven.

To me, it does meaning something to say 'if all the x86 chips were i586-100s, and all the PPCs were 604es and .... then 
our FLOPS would be X'.

Of course some x86s are AM80386es which will have a different RC5 to FLOPS speed ratio, so it is only a rough figure, 
but it's already weighted with processor type values so it's not that rough.

> I've got a couple of Alpha CPUs involved, and their numbers, relatively speaking, suck.
That doesn't matter because rc5 blocks completed by Alphas are translated to what an alpha gets in FLOPs, not what it 
gets in i586-100 flops.

Are you sure you've looked at that page? I was confused until i'd seen how they did it.


--
To unsubscribe, send 'unsubscribe rc5' to majordomo at lists.distributed.net
rc5-digest subscribers replace rc5 with rc5-digest



More information about the rc5 mailing list