[Arkham_c]

This looks promising:

From XLR8YourMac:

Code:
"I work at a university, and our dual 2Ghz G5 just arrived.  I just did  a quick iTunes benchmark, converting "Moment's Notice" (Coltrane) from  AIFF, on the hard drive: 

I just watched for the highest reached conversion speed factor: 

Dual 2Ghz G5:
 converting to 160 MP3:     45.6x
 converting to 160 AAC:     33.5x
 
 My 12" PowerBook G4 867Mhz:
 converting to 160 MP3:     11.5x
 converting to 160 AAC:     8.8x 

The G5 is standard factory configuration.
 The PowerBook is running Panther 7B53. 

Both systems had nothing but iTunes running, and were not playing the  tracks while converting them.

[skyman]

Originally posted by Arkham_c:
This looks promising:

From XLR8YourMac:

Code:
"I work at a university, and our dual 2Ghz G5 just arrived.  I just did  a quick iTunes benchmark, converting "Moment's Notice" (Coltrane) from  AIFF, on the hard drive: 

I just watched for the highest reached conversion speed factor: 

Dual 2Ghz G5:
 converting to 160 MP3:     45.6x
 converting to 160 AAC:     33.5x
 
 My 12" PowerBook G4 867Mhz:
 converting to 160 MP3:     11.5x
 converting to 160 AAC:     8.8x 

The G5 is standard factory configuration.
 The PowerBook is running Panther 7B53. 

Both systems had nothing but iTunes running, and were not playing the  tracks while converting them.

It's a Dual G5 running against a single 867MHz G4.

NOT a good comparison at all!!

Did you read the rest of the specs? The G5 benchmarks were not that good. I am not impressed.

[Arkham_c]

Originally posted by skyman:
It's a Dual G5 running against a single 867MHz G4.

NOT a good comparison at all!!

Did you read the rest of the specs? The G5 benchmarks were not that good. I am not impressed.

Well, the Cinebench test is worthless. Cinebench's authors have said that they expect G5 optimizations to significantly increase the speed on a G5.

As to the speed difference, first, you only benefit from the second processor if you rip two tracks at once. if you extrapolate the G4 to the equivalent speed of the G5, you get a 2.12GHz G4, so the G5 is much faster at an equivalent clock speed.

[skyman]

Originally posted by Arkham_c:
Well, the Cinebench test is worthless. Cinebench's authors have said that they expect G5 optimizations to significantly increase the speed on a G5.

As to the speed difference, first, you only benefit from the second processor if you rip two tracks at once. if you extrapolate the G4 to the equivalent speed of the G5, you get a 2.12GHz G4, so the G5 is much faster at an equivalent clock speed.

Even though iTunes is not optimized for dual processors, OS X controls the task distribution among processors. Applications that aren't SMP optimized (because their code isn't divided into threads properly) still benefit from dual processors because the OS executes them on whichever processor is free.

So, I would expect a Dual 2Ghz G5 to perform far better than it did in the above itunes test. Especially compared with the slower version of the 867Mhz G4. Like I said I am not impressed at all with the performance of the dual 2Ghz G5.

It looks like the dual 2Ghz G5 performs just as well as a dual 2Ghz G4 would.

[skyman]

What I would like to see is a 1.6GHz G5 vs a 1.4 GHz G4 in REAL would performance tests.

[Graymalkin]

Originally posted by skyman:
Even though iTunes is not optimized for dual processors, OS X controls the task distribution among processors. Applications that aren't SMP optimized (because their code isn't divided into threads properly) still benefit from dual processors because the OS executes them on whichever processor is free.

So, I would expect a Dual 2Ghz G5 to perform far better than it did in the above itunes test. Especially compared with the slower version of the 867Mhz G4. Like I said I am not impressed at all with the performance of the dual 2Ghz G5.

It looks like the dual 2Ghz G5 performs just as well as a dual 2Ghz G4 would.

No matter how good OSX's SMP capabilities are a processor can only do so much work in a given period of time. The single encoding thread got the full attention of one of the processors, it ripped the song at more than twice the speed of the single G4. That means a single G5 chips at roughly twice the clock speed of a G4 got about four times the performance. The second processor in the G5 system didn't do a whole lot to boost the encoding speed of iTunes. Stop with the "G5 isn't that impressive" crap. The G4 was actually a fairly impressive chip and the G5 is much much stronger.

[skyman]

Originally posted by Graymalkin:
The single encoding thread got the full attention of one of the processors

How do you know this? Did you guess? Where is your proof? And please don't tell me you watched the CPU monitor as this little app is nothing more than a ROUGH gauge.

it ripped the song at more than twice the speed of the single G4. That means a single G5 chips at roughly twice the clock speed of a G4 got about four times the performance. The second processor in the G5 system didn't do a whole lot to boost the encoding speed of iTunes. Stop with the "G5 isn't that impressive" crap. The G4 was actually a fairly impressive chip and the G5 is much much stronger.

STOP comparing the G5 to the G4 in the PowerBook. This is NOT the same G4 chip in the PowerMac G4. Again you are comparing a G5 to the slower version 867MHz G4.

Let's see REAL world tests of a 1.4GHz G4 vs. a 1.6 GHz G5. This would be a more Realistic and comparable test.