Non-ARM optimized plugins in a ARM hosts
- KVRAF
- Topic Starter
- 1748 posts since 2 Jul, 2018
https://www.pro-tools-expert.com/produc ... at-we-know
A great article. It sums up all pitfalls and trouble that we will be dealing with the M1 chipsets
A great article. It sums up all pitfalls and trouble that we will be dealing with the M1 chipsets
-
Zaphod (giancarlo) Zaphod (giancarlo) https://www.kvraudio.com/forum/memberlist.php?mode=viewprofile&u=111268
- KVRAF
- 2596 posts since 23 Jun, 2006
I had a lot of issues in Rosetta traslated code, especially when code is loaded from ram
I had good performances in native mode, around 1/3 of Intel desktops (i9) but
1) stable
2) the computer is cold and running for weeks!!! Completely cold
Waiting for M1 now...
I had good performances in native mode, around 1/3 of Intel desktops (i9) but
1) stable
2) the computer is cold and running for weeks!!! Completely cold
Waiting for M1 now...
-
Zaphod (giancarlo) Zaphod (giancarlo) https://www.kvraudio.com/forum/memberlist.php?mode=viewprofile&u=111268
- KVRAF
- 2596 posts since 23 Jun, 2006
YesFigBug wrote: ↑Fri Nov 13, 2020 4:32 pm Just got confirmation from Apple Developer forum that all dylib in the same process must be the same architecture. I assume that means AU plugins run in their own process? So if ARM hosts want to run Intel plugins, they must have a plugin bridge, similar to the bridges used for running 32 bit plugins in 64 bit processes.
-
Zaphod (giancarlo) Zaphod (giancarlo) https://www.kvraudio.com/forum/memberlist.php?mode=viewprofile&u=111268
- KVRAF
- 2596 posts since 23 Jun, 2006
The memory performance bottleneck is more or less my experience
Edit: my bad, this is the correct link
https://www.anandtech.com/show/16252/ma ... -m1-tested
Edit: my bad, this is the correct link
https://www.anandtech.com/show/16252/ma ... -m1-tested
-
Richard_Synapse Richard_Synapse https://www.kvraudio.com/forum/memberlist.php?mode=viewprofile&u=245936
- KVRian
- 1136 posts since 20 Dec, 2010
I can confirm there's a performance hit, should be in that ballpark roughly at first glance, but need to experiment more. Anyway it looks like we won't get around making custom versions for the M1 processors, using native code+NEON.syntonica wrote: ↑Fri Nov 13, 2020 9:45 pm Ow! That's a bigger hit than I've heard before. 37.5%. I'm surprised since most ARM substitutions look to be one-to-one, clock-speed wise. It's probably in the SIMD, where they may be substituting code loops for vector calls. It's been a while since I compared NEON to Intel.
Richard
Synapse Audio Software - www.synapse-audio.com