On Mar 23, 12:29 am, "ah...clem" <[email protected]> wrote:
> On Mar 22, 11:57 am, Bruce Johnson <[email protected]>
> wrote:
>
> > Oh puleeeze. You're claiming a dual 1.25 Ghz G4 on a 333 mHz bus can 
> > compare to a Mac Pro (which at a MINIMUM has 2 2.66Ghz dual core Xeons with 
> > 667 Mhz memory bus) with a few COMPILER TWEAKS??? (which tweaks, BTW, 
> > Apple's dev tools pretty much apply automatically when you select PPC as a 
> > compile target)
>
> i never claimed any such thing!  re-read the post, bruce.  if you want
> to "win" the discussion so desperately that you will resort to putting
> words in my mouth, then you only underscore the weakness of your own
> position.  what i said was that PPC versus intel of comparable clock
> speeds was no contest.  given software well written for each, the PPC
> was damned near twice as fast as the intel on real world
> computationally intensive tasks.

Ok, I'll ask - I am well aware of how AltiVec functioned. And no
argument that an Intel-written SW may not properly run on a PPC to
take advantage. Honest question though - Doesn't Intel have a similar
functioning SIMD unit? Also 128bit wide? If that's the case, I'd
expect that a 4x2.8GHz machine to be 4.48X as fast as a 2x1.25GHz
machine, given the similarity between both SIMD units. The near 10X
improvement I see proves your point, to me, at least, that the code
was not optimized for PPC, specifically AltiVec. I have the latest DVD
rip I'm sending to a TiVo, will run on both machines to confirm exact
ratio I see.

-- 
You received this message because you are a member of G-Group, a group for 
those using G3, G4, and G5 desktop Macs - with a particular focus on Power Macs.
The list FAQ is at http://lowendmac.com/lists/g-list.shtml and our netiquette 
guide is at http://www.lowendmac.com/lists/netiquette.shtml
To post to this group, send email to [email protected]
For more options, visit this group at http://groups.google.com/group/g3-5-list

Reply via email to