If you actually read the PDF document he refers to in his brilliant insight, you'll notice that Hyperthreading is only turned off on the dual processor systems. It is specifically turned ON for the single processor tests.
I don't think they were really trying to mislead anyone on the speed of the new Power Macs by decreasing the speed of the Dells. If they had been trying to do that, they could have easily left everything the way it was on the Dell by not updating the Red Hat software, or they could have run the tests under Windows.
What I saw in the G5 tests looked like optimizations more than anything else. They put in a couple of speed switches, similar to -O3 in that it would use memory less efficiently but make it run faster.
If you want a little extra information about Apple's new motherboards and the PPC 970, check out this press release:
http://www.apple.com/pr/library/2003/jun/23joint.h tml
The new iPods have the hardware to record and purportedly will have a microphone coming out in June.
Creative probably won't have all the parts for recording until June either.
But the real question is Does it record to AAC? What kind of encoding 'power' would that take to record in real time, and - if it is feasible - would it eat up the battery in just a couple hours?
Yes, I remember. If you take that same fact and think about it for a couple milliseconds longer you'd realize that Apple doesn't need AMD to get Hypertransport. And to expand on that, IBM's PPC 970 already has support for a 6.4 GB/s usable bandwidth bus, Hypertransport or not.
Slashdot Mirror
If you actually read the PDF document he refers to in his brilliant insight, you'll notice that Hyperthreading is only turned off on the dual processor systems. It is specifically turned ON for the single processor tests.
I don't think they were really trying to mislead anyone on the speed of the new Power Macs by decreasing the speed of the Dells. If they had been trying to do that, they could have easily left everything the way it was on the Dell by not updating the Red Hat software, or they could have run the tests under Windows.
What I saw in the G5 tests looked like optimizations more than anything else. They put in a couple of speed switches, similar to -O3 in that it would use memory less efficiently but make it run faster.
As with any benchmarks, YMMV.
If you want a little extra information about Apple's new motherboards and the PPC 970, check out this press release: http://www.apple.com/pr/library/2003/jun/23joint.h tml
Creative probably won't have all the parts for recording until June either.
But the real question is Does it record to AAC? What kind of encoding 'power' would that take to record in real time, and - if it is feasible - would it eat up the battery in just a couple hours?
Yes, I remember. If you take that same fact and think about it for a couple milliseconds longer you'd realize that Apple doesn't need AMD to get Hypertransport. And to expand on that, IBM's PPC 970 already has support for a 6.4 GB/s usable bandwidth bus, Hypertransport or not.