[RC5] Why does Pentium 3 process faster than Pentium 4?

Andrew MacKenzie andy at edespot.com
Wed Dec 11 11:24:33 EST 2002


> >Well, contrary to what Intel would have you believe, clockspeed isn't the
> >most important factor in determining a chips speed.  A lesser clocked
> >Athlon, or G4 can perform admirably against faster clocked P4's.  A lot of
> >this has to do with the depth of the chips pipe-line, and the number of
> >instructions executed per clock (IPC).
> >
> Honestly, I can't here this anymore...
<lotsa snippage>
Points taken.  You make good ones.  I was mearly giving examples for why a
faster clocked chip may not perform as quickly as a slower clocked chip.

I did not pretend to know *exactly* why RC5 is slower on a P4, so I
appologize if I gave that impression.  But my point still stands that (and
I *hate* to tout the Apple line) clockspeed is not everything. 

A G4 at the same clock speed as a P4 would solidly kick the P4's ass.  But
that won't happen because of the way the two chips are designed.  Don't
take this as Intel bashing.  An Athlon at the same speed as a P4 would also
kick the P4's ass.  But (unfortunatly for AMD) that isn't likely to happen
either.  (think all chips running at current max P4 clock rate).  

Things get more interesting when you consider the Alpha chips.  An 800Mhz
EV6.7 performs *very* nicely.  :-)

> >The P4 is also a slightly different architecture than the PIII.  Some
> >things have changed that effect dnet on it.
> >
> The P4 not completely different
(later changed to "is completely")

I was thinking of the instruction set.  But yes, the design is quite
different.  Poor choice of words on my part.

-- 
// Andrew MacKenzie  |  http://www.edespot.com
// With a PC, I always felt limited by the software available.
// On Unix, I am limited only by my knowledge.
//     --Peter J. Schoenster
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
Url : http://lists.distributed.net/pipermail/rc5/attachments/20021211/70f3f453/attachment-0001.bin


More information about the rc5 mailing list