Eight Core Mac Pro - Performance test results.

tacvbo83 · Post by **tacvbo83** » Fri May 25, 2007 12:12 am

RobertX wrote:
tacvbo83 wrote:although 35C is too hot, gonna wait for a cooler Mac Pro
So far the test has been going for almost 5 hours and the temp is still at 35°. The fans are barely moving and the computer is making no noise at all.

I have a Core 2 Duo rig at home and that damn thing sounds like a leaf-blower.

When the new 45nm Intel chips [Penryn, Wolfdale & Yorkfield] come out they should run quite a bit cooler than present models.

Thats when I will think of buying. I bought one of the first MBP batch and it was the best purchase I have ever made except for the extreme heat it produces. I hear new ones run cooler which is what I will be looking for when I buy a new Mac.

knotkranky · Post by **knotkranky** » Fri May 25, 2007 4:01 am

nebulae wrote:
knotkranky wrote:piggy instrument plugs
How many of these piggies could a quad-core handle?

wow, that made me have a pull.

noisetonepause · Post by **noisetonepause** » Fri May 25, 2007 4:04 am

m:o wrote:What, you can route several tracks to a specific cpu? Or have i misunderstood?

No, it's all handled internally.

As I understand it, though, with certain routing settings, several tracks need to be processed together on the same CPU. In some cases, this will mean that you will see less or no benefit from multiple cores.

rydan · Post by **rydan** » Fri May 25, 2007 9:25 am

Is there any "official" performance test set for Live? If so, where do I find it?

nebulae · Post by **nebulae** » Fri May 25, 2007 1:13 pm

I think it's time for a newer, harder Liveset. I'll try to put one together after this weekend's deathmatch.

alvaro · Post by **alvaro** » Fri May 25, 2007 4:08 pm

I promise post my results here if anyone upload it.

Would be pretty interesting

RobertX · Post by **RobertX** » Fri May 25, 2007 5:13 pm

I got the RAM [8 GIG] and drives [150GB 10k] in this morning and repeated the test...

Same results as before.

nebulae · Post by **nebulae** » Fri May 25, 2007 5:17 pm

RobertX wrote:I got the RAM [8 GIG] and drives [150GB 10k] in this morning and repeated the test...

Same results as before.

holy crap, 8gb of ram???!?!?!!

JACKAL & HYDE · Post by **JACKAL & HYDE** » Sat May 26, 2007 1:34 am

RobertX wrote:I got the RAM [8 GIG] and drives [150GB 10k] in this morning and repeated the test...

Same results as before.

Thats pretty shocking.

Johnisfaster · Post by **Johnisfaster** » Sat May 26, 2007 1:47 am

JACKAL & HYDE wrote:
RobertX wrote:I got the RAM [8 GIG] and drives [150GB 10k] in this morning and repeated the test...

Same results as before.

Thats pretty shocking.

if I recall correctly the live performance test uses very little if any streamed audio from the harddisk so ram and harddrive speed isn't going to matter very much if I understand that stuff right. ram and harddisk speed are going to matter alot when you have large wav files and samples in your set.

nebulae · Post by **nebulae** » Sat May 26, 2007 2:00 am

actually, there's an even simpler explanation...the way Live's multi-threading works is that each audio/midi track in Live is set to a specific processor. Meaning that the load of any particular track is tied to one processor only. So for example, you can run a heavy Operator patch with a very long decay, and the CPU usage can get up to like 80% on Live's meter...in the system manager, it'll show up as 80% of only one of your physical processors. Now if you duplicated that same track, Live would still read 80%, while the system would now show 80% x 2.

Ok, so now we go back to the Live 5 test, which was created when Live was not set of multi-threading. It doesn't surprise me at all if the load on an 8-cpu machine reads the same as the load on a 2-cpu machine. I suspect that not every one of the CPUs is being used...please confirm this for us, so I can be corrected if I'm mistaken.

I think that a new Live 6 test is in order, and I'll try to get it done by the end of the weekend. Basically, we should have at least 8 tracks, each playing a different audio loop, each piped into 8 additional tracks, with about 8 reverb sends as well. Anyone have other suggestions to give it a good baseline test that would be a good indicator of modern processors?

Johnisfaster · Post by **Johnisfaster** » Sat May 26, 2007 2:12 am

nebulae wrote:Anyone have other suggestions to give it a good baseline test that would be a good indicator of modern processors?

if I were making a test I'd definetly put at least 1 of each of lives plugs including all fx and all instruments (operator, simpler, sampler, impulse) as well as a bunch of audio tracks. alot of reverbs and alot of delays and even some clever track routing. basically, use all of the features available including midi effects and track routing and the works.

sparklepuff · Post by **sparklepuff** » Sat May 26, 2007 2:14 am

And complex warp all those little audio critters. C'mon Neb, maybe you can git'er done before 7 comes out!!

nebulae · Post by **nebulae** » Sat May 26, 2007 2:26 am

Johnisfaster wrote:
nebulae wrote:Anyone have other suggestions to give it a good baseline test that would be a good indicator of modern processors?
if I were making a test I'd definetly put at least 1 of each of lives plugs including all fx and all instruments (operator, simpler, sampler, impulse) as well as a bunch of audio tracks. alot of reverbs and alot of delays and even some clever track routing. basically, use all of the features available including midi effects and track routing and the works.

The issue with this is that not everyone has all of the plugs, so a large portion would miss out on a true benchmark. I'd say Simpler and Impulse for sure.

The other issue is that true trackcount has always been hard because I can't put out a 1gb project that streams 50 tracks...

spiral · Post by **spiral** » Sat May 26, 2007 5:08 am

knotkranky wrote:
nebulae wrote:
knotkranky wrote:piggy instrument plugs
How many of these piggies could a quad-core handle?

wow, that made me have a pull.

where are the other teats?