Dual 2.0GHz G5 PowerMac Pictures and Benchmarks

[barabics]

Re: I'm so excited and I just can't hide it

Originally posted by trilogic
the delivery status of my dual G5 order is beeing assembled, delivery sept 7th. Hope it stays like this. 😀

okay so i ordered a dual G5, where do i look and find when my G5 is being assembled?
i just wanna know.

 

[MacBandit]

Re: Re: I'm so excited and I just can't hide it

Originally posted by barabics
okay so i ordered a dual G5, where do i look and find when my G5 is being assembled?
i just wanna know.

You go to your account in the Apple store and check the order status of the open order.

 

[mark_wilkins]

Originally posted by eatme8888
Software can be optimized for the G5's differences, but we won't see a speed increase on the level of 35-40%, which is what we would need to see in Cinebench for it to overtake the dual Xeon.

Actually, one of the developers of Cinebench posted on Ars Technica that they thought the dual 2 GHz G5 might end up "over 500" after optimization.

Note also that better optimization can yield tremendous performance improvements. One guy tested the same MP3 compression code compiled with GCC 3.3 and with IBM's 970-specific compiler for OS X (currently available as a public beta) and found that its execution doubled in speed when using IBM's compiler.

-- Mark

 

[mark_wilkins]

Originally posted by eatme8888
Compiler, yes, optimizations, no.

What do you think the difference between the compilers is, other than difference in optimization?

Take a look at the Shark tools described in the "Tuning for G5" technical note:

http://developer.apple.com/technotes/tn/tn2086.html

...and you'll see that they expose to the programmer all kinds of information about instruction issuing, where to expect pipeline stalls, and so on. With these kinds of tools, manual optimizations actually do have a reasonable hope of wringing out extremely strong performance improvements on top of what the compiler can achieve.

(Of course, that's a *hope* not a *guarantee.* 😀)

-- Mark