DP performance on Mac Pro??

[Frodo]

Test results:
132 tracks (90 seconds of audio/track, 132 audio files) with same three plug-ins as previous test. (396 plugins total)

Operating system and DP are on an internal SATA Samsung HD160JJ. Test project is on an internal SATA Western Digital WD2500JS.

The disk IO seems to be the limiting factor here (playback meter spikes at 133 tracks). CPU meter barely hits 1/2 FS and Activity Monitor show DP CPU usage at around 60%.

Phil

132 tracks
396 plugins
60% CPU

Those are still pretty remarkable numbers.

Thanks for sharing your data, Phil. I'm quite encouraged by this.

[grimepoch]

I created the DP benchmark back when 5.0 came out. Just a simple MIDI loop playing through groups of Modulo's using one of the default patchs. I do not remember the exact numbers, but between my Dual 1.8Ghz machine and my Quad 2.66Ghz machine, I saw a CPU to CPU gain in performance.

Meaning this: (4x2.66)/(2x1. = 2.96

Now, the reason I find this amazing is that typically CPU speed increases DO NOT normally scale. This is because bus speeds, drive speeds, video speeds, firewire speeds, etc normally play a huge role. Given this is mostly VI and no audio, I can see why though at least it would be more CPU intensive and scale with a CPU. That said, these are different architectures which made it even more strange.

So, as an additional test, I bought the update to Reaktor (5.2) for UB and ran stand-alone copies on each machine. I use the Dual FM Osc plugin that uses 64% on my G5. On the Intel, it used 23%.

Without doubt, the new machine really spanks the old machine.