PPC vs x86 performance comparison

[filson]

I just read this (old news) from distributed.net.
Myself being bogged down by the MHz race, I thought it would be nice to see a computational comparison of the PPC/x86 processors to sort of iron out some of the doubts about the "slow" PPC's in the Pegasos and A1 boards.
Here's the snippet:

 we completed 86,950,894 workunits on our best day. This is 0.12% of the total keyspace meaning that at our peak rate we could expect to exhaust the keyspace in 790 days. Our peak rate of 270,147,024 kkeys/sec is equivalent to 32,504 800MHz Apple PowerBook G4 laptops or 45,998 2GHz AMD Athlon XP machines or (to use some rc5-56 numbers) nearly a half million Pentium Pro 200s.



so there is more to it after all. :-D  :-D

[filson]

being that i've been away for a while, i haven't been able to respond to your rants  :-D

One can not even compare the Pentium to an Athlon processor so what are you wining about??

I just brought this up to cheer up some moody faces, as in showing that even though the PPC's are "old" by todays standards, its not totaly useless.

And besides, most code are coded around the platform with its architecture in mind. data alignment, cache-miss prevention, instruction pipelining and so on.
No one code is the same on diferent machines, not ANSI C/C++, not Java, no nothing.

so cheer up! we can make this work if we realy want to.  :-)

[filson]

funny, i thought just the same when i saw you :-D  :-D

[filson]

my, oh my! i've made a monkey friend.  :-D
wanna continue in the DMZ? ;-)