Decided to post here rather than make a new thread,
Considering what Apple has done with their M1 chips, is there a chance that future CPUs will have significantly larger "RAM"/cache on the/next to the processors. This would be alongside the standard DDR4/5 arrangement we have now.
I'm talking 1GB on Ryzen 3 and more the higher up you go. Say a Ryzen 7 sporting 4GB and threadrippers with 16GB on the low end and 64GB on the high end. How much would computational speed benefit from such an approach? Would we need to change how software is programmed to take advantage of this?
What about accelerators, will we see more HW accelerators for professional work?
Considering what Apple has done with their M1 chips, is there a chance that future CPUs will have significantly larger "RAM"/cache on the/next to the processors. This would be alongside the standard DDR4/5 arrangement we have now.
I'm talking 1GB on Ryzen 3 and more the higher up you go. Say a Ryzen 7 sporting 4GB and threadrippers with 16GB on the low end and 64GB on the high end. How much would computational speed benefit from such an approach? Would we need to change how software is programmed to take advantage of this?
What about accelerators, will we see more HW accelerators for professional work?