That’s basically it. Apple went big because the target process allowed it. To someone out of the ASIC industry, it is a set of interestingly scaled but pedestrian design choices coupled with some exaggeration (realizable memory bandwidth per core on the Max is a fraction of what you’d expect based on Apple’s aggregate memory bandwidth claim for the processor as a whole) and a very serious investment in performance/watt (legacy of the phone use case).
The Max has barely any improvement core-wise than the first M1. It’s going to be interesting to see what the real next generation looks like.
> The Max has barely any improvement core-wise than the first M1.
Isn't that what you would expect in two chips that use the same core design?
There is more memory bandwidth to the Max, and the system level cache is larger, so there are differences outside of the core, but the core itself didn't change.
The M1 also has old cores from the A14. The A15 isn't hugely faster than the A14 but it clocks faster and has other efficiency tweaks. Clock for clock, the M1 is slower than the iPhone 13 Pro.
That's not what you would expect if you look at the graph of six years of year-over-year SPEC performance gains on iPhone cores. Their history shows a pretty reliable 20% gain per year.
>Whilst in the past 5 years Intel has managed to increase their best single-thread performance by about 28%, Apple has managed to improve their designs by 198%, or 2.98x (let’s call it 3x) the performance of the Apple A9 of late 2015.
