Has Apple deliberately nerfed the M3 Pro CPU? And for what reason?
From Apple’s slides starting at 10:29:
M3 = 35% faster CPU than M1; 20% faster than M2
M3 Pro = 20% faster CPU than M1 Pro; No comparison to M2 Pro was given! 🤔
M3 Max = 80% faster than M1 Max; 50% faster than M2 Max
When Apple announced the M2 Pro they claimed it was 20% faster than M1 Pro. So are we to assume M3 Pro has no performance improvement this gen?
They’ve reduced the number of performance cores from eight to six, and as per the OP memory bandwidth at 150GB/sec is lower than the 200GB/sec of the M1 Pro.
It seems reducing the number of performance cores in favour of efficiency cores has eliminated any overall performance uplift M3 Pro had over M2 Pro. We’ll have to wait for benchmarks to be certain, but I’m sure Apple’s omission of a comparison to M2 Pro is very telling.
These things already had incredible battery life, I’m not sure why Apple would choose to sacrifice performance for more battery life? The people buying these machines, myself included, are pros that need performance, and the rest of the M3 family has CPU performance improvements, so why not M3 Pro?
Honestly I think Apple went the wrong way with the Pro/Max line-up.
I think instead of the linear progression they have been trying to chase with Mx -> Mx Pro -> Mx Max -> Mx Ultra I think instead they should have had the Pro and Max be separate branches in the product line to differentiate between different professional use cases.
Take my use case for instance. I work in IT so most of my usage is in browsers, light development, and virtualization. All CPU bound tasks, and very little GPU apart from what’s required to run lots of monitor real-estate and anything that leans on the GPU for secondary acceleration like video decoding. So my ideal system is going to be lopsided to CPU performance and not care much for GPU at all.
On the other side take someone who is doing 3d modeling, image manipulation or GPU accelerated scientific computing. They’re going to want at least an equal balance of CPU and GPU, or even a slight GPU bias.
So it seems like it would make more sense to do something like:
Base Mx cpu 4p/4e. A good balance between performance and efficiency for basic tasks.
Mx Pro 10-12p/2-4e. Lots of single-threaded CPU performance for people that just need that. Leave the graphics only a moderate upgrade from the base M chip. E-cores just for times you need to do idle tasks in the background.
Mx Max 6p/12-16e. Focus more on efficiency cores and GPU core counts. The logic here is that most workloads that lean heavily on GPU will be more easily multithreaded, which while the e-cores are slower, they are more energy efficient per unit of work done. So if your workload is easy to multithread, you can lean on high amounts of e-cores to do your CPU work, which makes more efficient use of your power budget and die space.
Then, you can do the same with your even bigger SKUs:
“Big” Mx Pro with 20-24p/4-8e that’s effectively just two Pros glued together with gobs of CPU cores for that kind of workload.
“Big” Mx Max with 12p/24-32e and a huge GPU.
It muddles up the marketing which is why Apple probably wouldn’t do it, but it allows a bit more customization for what real-world workloads would require.