Diva with Rosetta2 on Apple M1

Official support for: u-he.com
Post Reply New Topic
RELATED
PRODUCTS

Post


Post

How does it run under Rosetta? I heard the numbers are very impressive with Rosetta as well.

Post

tony10000 wrote: Thu Dec 03, 2020 8:46 pm How does it run under Rosetta? I heard the numbers are very impressive with Rosetta as well.
See the first post of this thread

Post

pdxindy wrote: Thu Dec 03, 2020 9:26 pm
tony10000 wrote: Thu Dec 03, 2020 8:46 pm How does it run under Rosetta? I heard the numbers are very impressive with Rosetta as well.
See the first post of this thread
They were still using the Reaper Apple Silicon Beta. I wanted to see stats for the Intel 6.18 version.

Post

Could you please update first post with Daw/Version in case of both tests.
Also exact test project is interesting or at least more details on how it is done (diva preset etc).
tony10000 wrote: Thu Dec 03, 2020 10:01 pm They were still using the Reaper Apple Silicon Beta. I wanted to see stats for the Intel 6.18 version.
Yes it's interesting to compare with MBP I7/I9 etc
Murderous duck!

Post

Jon Sine did some videos with the MacBook Air M1 version in Rosetta mode and got impressive results. He is now selling his top of the line MacBook Pro and using the Air.

https://www.youtube.com/watch?v=JkH77jQvm7A

https://www.youtube.com/watch?v=w-KOVdlVYUU

https://www.youtube.com/watch?v=r4HRHJgl23w

Post

tasmaniandevil wrote: Thu Dec 03, 2020 2:48 pmOtoh this first test indicates that on those amazing new chips, there seems to be way less need for a multicore option than on traditional Intel chips.
That seems extraordinarily promising to me. Those numbers are outstanding under the circumstances.

Post

tasmaniandevil wrote: Thu Dec 03, 2020 2:48 pm Since many of you are curious (we, too) about the performance of the new Apple Silicon M1, here are the results of our very first test on the M1 MacBook Pro.

This was just a quick, unscientific "it's late at night but I can't wait any longer and need to know how good it is" test, but since the results are more than promising, we thought we should share them with you.

Test setup:

* Apple 2020 MacBook Pro M1
* Reaper, native Silicon beta
* 48kHz, buffer size 512 samples
* Diva 1.4.4, rev. 9709 (no ARM support), running bridged via Rosetta2
* "BS Deep Space Diva" preset (accuracy: great), playing six voices

We simply duplicated the track again and again, until the CPU bellyflopped.
And to have something to compare it to, we did the same test on an old, trustworthy MacBook Pro from 2015 with a 2.2GHz Intel i7 (this is starting to feel a bit like on an episode of Mythbusters).

Diva_Reaper_Rosetta2_M1.png

Results:

Multicore option in Diva disabled:

On the 2015 Intel MBP, 3 instances with 18 voices ran without glitches. The fourth instance already produced too many dropouts to continue working.

On the 2020 M1 MBP, 20 instances with 120 voices ran glitch free. With one more instance and 126 voices, there were some dropouts, and it finally glitched heavily when adding instance 22. :o

Our jaws dropped collectively at that moment.

With Diva's multicore option enabled in each instance:

On the 2015 Intel MBP, six instances with 36 voices ran glitch free, a seventh instance produced occasional dropouts, and the eighth instance brought it to its knees.

On the 2020 M1 MBP, only five instances with 30 voices played without glitches, the sixth instance already produced heavy crackling.

This is not exactly the result we were hoping for, but we are still in the process of porting our plugins to run natively (i.e. without Rosetta2) on the new Silicon chips, and we expect to see some better numbers by then.

Otoh this first test indicates that on those amazing new chips, there seems to be way less need for a multicore option than on traditional Intel chips.

I'm sure we will conduct way more tests, but right now we are simply elated and relieved to see our plugins performing so incredibly well under Rosetta2.

Rest assured, after these initial results, we are more motivated than ever to port our plugins to the new Silicon platform. Please be patient, though. The porting will still take quite some time, as it turns out to be more complex than anticipated.

Cheers,
Tas
Nice.

Im curious have you tried to compare same setting performance with processors (if you have any of those): ryzen 3600x,3700x,3800x, 5600x, 5700x 5800x?

Post

As written in the initial post, this was just a quick first test.
We compared it to the machine that was at hand, which was a 2015 MacBook Pro.
We will conduct lots more tests over time, but we simply don't have that many different systems with all kinds of CPUs we could compare it with (especially not during Covid times, when the majority of people is working from home office).
That QA guy from planet u-he.

Post

Are you actually planning to adjust all plugins for Apple Silicon? Also less selling products like ACE and Bazille?

Post

tslays wrote: Sat Dec 05, 2020 4:43 pm Are you actually planning to adjust all plugins for Apple Silicon? Also less selling products like ACE and Bazille?
Of course.

Post

Does this have implications for AU vs VST3 performance?

I can only get parameter automation (via Ableton's "configure" button) working with the VST3 versions. The mapping correctly identifies the parameter with the Audio Unit version, but there appears to be no communication in either direction of the value. That's a bit off-topic, but I'm hoping I will able to continue using the VST3 versions with Apple Silicon without a performance hit.

Post

neuromod wrote: Mon Dec 07, 2020 6:07 pm I can only get parameter automation (via Ableton's "configure" button) working with the VST3 versions.
This has nothing to do with Apple Silicon, it's a problem with the AU versions under Big Sur.
You can read about the current state of Big Sur compatibility here: viewtopic.php?f=31&t=550513
The next updates will include fixes for all those AU related issues.
That QA guy from planet u-he.

Post

Small update, we successfully built our first version that runs natively on the M1, using the Neon instruction set.

Just for fun we repeated the test from last week, and this time we could run up to 32 instances of Diva with 192 voices without dropouts in Reaper, compared to 20 instances with 120 voices with the Rosetta2 version of the plugin. :hyper:

A word of caution about those numbers: This was just a very simple lab test, running the same preset, playing the same notes in each instance (see the setup notes in the first post).
It remains to be seen how the plugins actually perform in real world projects in different hosts.

We also have a hunch about the weak performance when using Diva's multicore switch, and we hope to improve this over the next weeks.

Exciting times ahead.
That QA guy from planet u-he.

Post

51% Improvement...... Nice.

Exciting Times ahead indeed.

I really was not looking forward to this move from Apple. (Why Apple, why?).

But it seems to be turning out completely opposite to what I expected.

Thanks for the update Tas.

rsp
sound sculptist

Post Reply

Return to “u-he”