A lot of people in these comments don't seem to be really engaging with what was said. The unified memory architecture is fantastic, everything is in one place, easy and fast to access, up to the limit of the size of memory and compute you can fit on one chip it's massively advantageous. There is obviously a point where you reach the limit of how much you can pack in, but the disadvantages of having to shovel data back and forth mean you need a really powerful GPU before it becomes worth having.
But let's assume you really want more compute Apple has to first design a standalone GPU, then it has to do a PCI or CXL core or some custom interconnect, then it has to redesign it's OS for non-uniform memory doing all that fun stuff hiding the memory communication, then it has to add the primitives to it's languages for you to manage memory (because to get performance you have to actively design for it) and then you need to get all your performance critical applications to re-write their stacks with this in mind.
It's a massive lift! And for what? Only Desktop can take advantage of it, and in Apple's product line only the Mac Pro. And that's assume you execute well and the device ends up more capable than just using the SoC. And all of this we're talking about on top of the massive lift Apple literally just finished moving all their products onto Apple silicon. It's just a crazy ask for a v1 of a product.
> then it has to redesign it's OS for non-uniform memory doing all that fun stuff hiding the memory communication, then it has to add the primitives to it's languages for you to manage memory (because to get performance you have to actively design for it) and then you need to get all your performance critical applications to re-write their stacks with this in mind.
Yeah, it's not like their OS and Languages already support this model given that everything before the switch to Arm worked this way
Before it was just like on windows with a graphics card that holds the compute relevant data.
Now they have two cards with different memory bandwidths and ideally you would want to combine them of some sorts instead of wasting the whole m2 ultra gpu
Since macOS Sonoma will continue to support discrete GPUs on intel Macs, is there a fundamental technical reason why it would be impossible to support them on Apple Silicon Macs?
But let's assume you really want more compute Apple has to first design a standalone GPU, then it has to do a PCI or CXL core or some custom interconnect, then it has to redesign it's OS for non-uniform memory doing all that fun stuff hiding the memory communication, then it has to add the primitives to it's languages for you to manage memory (because to get performance you have to actively design for it) and then you need to get all your performance critical applications to re-write their stacks with this in mind.
It's a massive lift! And for what? Only Desktop can take advantage of it, and in Apple's product line only the Mac Pro. And that's assume you execute well and the device ends up more capable than just using the SoC. And all of this we're talking about on top of the massive lift Apple literally just finished moving all their products onto Apple silicon. It's just a crazy ask for a v1 of a product.