It is currently Fri Mar 29, 2024 1:29 am


Hauptwerk 7 - Mac M1 Max polyphony test - Max quality

Buying or building computers for Hauptwerk, recommendations, troubleshooting computer hardware issues.
  • Author
  • Message
Offline
User avatar

mwdiers

Member

  • Posts: 95
  • Joined: Wed Oct 11, 2006 11:33 pm

Hauptwerk 7 - Mac M1 Max polyphony test - Max quality

PostFri Jan 28, 2022 11:21 am

Here are the results of a polyphony test on my Macbook Pro M1 Max.
The specific model is the MacBook Pro (16-inch, 2021), M1 Max, 64GB RAM, 4TB SSD.

My audio interface is a Focusrite Scarlett 8i6.

These tests were performed through Logic Pro X 10.7.2, using the Hauptwerk AU bridge for MIDI and audio return. I was playing the notes live, not sequencing. I also had my normal audio FX chain running, which includes FabFilter Pro C2 (for compression), and FabFilter Pro R (for reverb). Logic and the FabFilter plugins were running in native mode. Only Hauptwerk and the AU bridge were running through Rosetta. Consider this a worse-case test.

I will test again later using an alternate config setup for direct MIDI and Audio, with no effects processing involved.

Base Settings:
Engine Sample Rate: 96Khz
Engine Processing Quality: Higher
Model Quality: Higher
Wind Supply Model: Enabled


Buffer 0128 X 1:
1750

Buffer 0128 X 2:
1750

Buffer 0256 X 1:
2000

Buffer 0256 X 1:
2000

Buffer 0256 X 2:
2000

Buffer 0512 X 1:
2125

Buffer 0512 X 2:
2125

Here's where it gets interesting.

Buffer 1024 X 1:
2000

Buffer 1024 X 2:
2125

Buffer 2048 X 1:
1000

Buffer 2048 X 2:
2125

Buffer 4096 X 1:
500

Buffer 4096 X 2:
2125

Increasing the buffer count did not increase polyphony for any given buffer size, so I only reported the results with 1 and 2 buffers.

Note that this is through Rosetta2, which does not support any AVX extensions, so the above results are achievable even without those vector optimizations.

I'll be really interested to see how this might change once Hauptwerk is running ARM-native, with Neon vector code.

Note that these results should also represent what is achievable on an M1 Pro CPU. The chief difference between the Pro and the Max is that the Max has double the memory bandwidth @ 400GB/s. However, the CPU is not able to saturate the memory bandwidth even on the Pro @ 200GB/s. The overhead is there for the use of the GPU, and Hauptwerk does not use the GPU.

NOTE: It just occurred to me that the above test is the result of a buffer interaction between Hauptwerk and Logic. My Logic buffer was set to 512 for all of the above tests. That would explain the weird results above 0512. It also invalidates the buffer size results lower than 512.
Last edited by mwdiers on Fri Jan 28, 2022 12:59 pm, edited 1 time in total.
Offline
User avatar

mdyde

Moderator

  • Posts: 15444
  • Joined: Fri Mar 14, 2003 1:19 pm
  • Location: UK

Re: Hauptwerk 7 - Mac M1 Max polyphony test - Max quality

PostFri Jan 28, 2022 12:05 pm

Thanks, Martin.

[Topic moved here.]

I suspect you'll find that the achievable polyphony will be quite a bit higher than that if you use direct audio output from Hauptwerk (rather than via a sequencer/DAW).
Best regards, Martin.
Hauptwerk software designer/developer, Milan Digital Audio.
Offline

RaymondList

Member

  • Posts: 223
  • Joined: Sun Mar 11, 2018 2:46 pm
  • Location: North Carolina, US

Re: Hauptwerk 7 - Mac M1 Max polyphony test - Max quality

PostFri Jan 28, 2022 12:25 pm

I have the "Pro" chip and not the "Max", but as you point out, they are really the same when talking about processing power. I have not done a polyphony test yet. However, I did install V7 and changed both settings you mention to "Higher". Playing the SP Bellevue Casavant with all stops out and with added reverb, playing as fast as I could with the most notes that I could play (as a quick and very dirty test) did not put the CPU meter into the yellow. In fact the iStat Menu app which I use for monitoring the box showed the 10 cpu's cruising at about 50%. As an aside, I've not as yet been able to get the computer fans to turn on! I hope they work if needed! I know that a test like this is sad, but it was quick to do and made me happy.

I would love to see how these M1 chips would perform with Hauptwerk running native code, and not the interpreted version.
Ray
Offline
User avatar

mwdiers

Member

  • Posts: 95
  • Joined: Wed Oct 11, 2006 11:33 pm

Re: Hauptwerk 7 - Mac M1 Max polyphony test - Max quality

PostFri Jan 28, 2022 12:45 pm

Here is a test without Logic or any effects in the mix. Straight MIDI to Hauptwerk, audio out to my interface. The results are — strange.

I do not know how accurate the CPU meter is in this scenario. It sometimes behaves strangely, especially when more than 1 buffer is selected, spiking into the red, with no audible crackling. Therefore I am doing this test audibly, and reporting the polyphony at which there is no audible crackles/glitches at all.

Buffer 0128 X 1:
1250

Buffer 0256 X 1:
1625

Buffer 0512 X 1:
1875

Buffer 0512 X 3:
2125

Buffer 1024 X 1:
2000

Buffer 2048 X 1:
2125

Buffer 4096 X 1:
2125

And here is the same test repeated running through Logic, with Logic's buffer matching Hauptwerk's buffer. This time no effects are enabled:

Buffer 0128 X 1:
1750

Buffer 0256 X 1:
2000

Buffer 0512 X 1:
2125

Buffer 1024 X 1:
2125

NOTES: I was careful to have the absolute minimum number of processes running during this test. I find the results confusing. When running through Logic, I cannot achieve higher polyphony overall, but I can achiever higher polyphony at a lower latency than when running Hauptwerk by itself. I have no explanation for this, but the results were consistent.
Last edited by mwdiers on Fri Jan 28, 2022 1:41 pm, edited 1 time in total.
Offline
User avatar

mwdiers

Member

  • Posts: 95
  • Joined: Wed Oct 11, 2006 11:33 pm

Re: Hauptwerk 7 - Mac M1 Max polyphony test - Max quality

PostFri Jan 28, 2022 1:29 pm

RaymondList wrote:I have the "Pro" chip and not the "Max", but as you point out, they are really the same when talking about processing power. I have not done a polyphony test yet. However, I did install V7 and changed both settings you mention to "Higher". Playing the SP Bellevue Casavant with all stops out and with added reverb, playing as fast as I could with the most notes that I could play (as a quick and very dirty test) did not put the CPU meter into the yellow. In fact the iStat Menu app which I use for monitoring the box showed the 10 cpu's cruising at about 50%. As an aside, I've not as yet been able to get the computer fans to turn on! I hope they work if needed! I know that a test like this is sad, but it was quick to do and made me happy.

I would love to see how these M1 chips would perform with Hauptwerk running native code, and not the interpreted version.


The largest organ I have with a decent release tail is the Notre Dame de Metz. If I set my buffers to 512 and go full organ, all couplers, and push up the polyphony limit into the 3000s, and play a bunch of discordant noise with both hands rapidly moving about, I cannot get this to glitch, and I cannot get the CPU to climb into the yellow, no matter what I do.

The organ I normally use is the Masterworks Skinner. There are no release tails. My reverb comes from reverb plugins, so the CPU load there is constant no matter what I feed into it. There is no possible scenario that will break Hauptwerk on this machine at max quality.

But then, I don't have any of the really large instruments like the Willis or Bovenkerk, especially if it is multi-perspective like the Nancy. I'm sure one could hit the limit there easily enough.
Last edited by mwdiers on Fri Jan 28, 2022 6:01 pm, edited 1 time in total.
Offline
User avatar

mwdiers

Member

  • Posts: 95
  • Joined: Wed Oct 11, 2006 11:33 pm

Re: Hauptwerk 7 - Mac M1 Max polyphony test - Max quality

PostFri Jan 28, 2022 1:42 pm

mdyde wrote:Thanks, Martin.

[Topic moved here.]

I suspect you'll find that the achievable polyphony will be quite a bit higher than that if you use direct audio output from Hauptwerk (rather than via a sequencer/DAW).


One would think. I really don't understand why it turned out this way. Perhaps because it is passing audio to a DAW that is running native? Maybe there's a lot more overhead when a Rosetta2 process is directly accessing CoreAudio.

Return to Computer hardware / specs

Who is online

Users browsing this forum: No registered users and 4 guests