This not a complaint, It's an observation.
Yesterday, I was served two a9 core WUs in a row on my Apple M4 CPU (the first was about a week ago during the WU shortage).
Is it just me or in other words is it normal that they process at around 60K PPD compared to 220K PPD average ?
OK it's a sample of only 3 but it shows I had never seen lower that 120K.
An other related question :
What is the benchmark CPU / GPU ?
Core a9 on Apple silicon
Moderators: Site Moderators, FAHC Science Team
-
- Posts: 1930
- Joined: Sun Dec 16, 2007 6:22 pm
- Hardware configuration: 9950x, 9950x3D, 5950x, 5800x3D
7900xtx, RX9070, Radeon 7, 5700xt, 6900xt, Intel B580 - Location: London
- Contact:
Re: Core a9 on Apple silicon
Benchmark CPUs and GPUs are all CPUs and GPUs in possession of internal testers.
-
- Site Admin
- Posts: 8189
- Joined: Tue Apr 21, 2009 4:41 pm
- Hardware configuration: Mac Studio M1 Max 32 GB smp6
Mac Hack i7-7700K 48 GB smp4 - Location: W. MA
Re: Core a9 on Apple silicon
My observation is similar, but tied to specific projects. Those ones may not be properly configured for A9, that lab has more experience using the A8 folding core. I see the same lower PPD on A9 projects for that lab when they get assigned to my Intel macOS system.
It is also possible the core was compiled with the wrong optimizations for macOS. The A8 folding core does give about the same PPD as projects running under Linux.
It is also possible the core was compiled with the wrong optimizations for macOS. The A8 folding core does give about the same PPD as projects running under Linux.
-
- Posts: 33
- Joined: Tue Jun 08, 2021 1:14 pm
- Hardware configuration: Mac Studio M1 Max
Mac Mini M4 Pro
M2 Macbook Air
Folding since 2005 - Location: Atlantic County, NJ
Re: Core a9 on Apple silicon
Same. The difference is pretty stark on some of the A9 WUs. It seems to hit the Intel CPUs on MacOS as well, but not as much as on the M-series systems.