News Modular AMD Chips to Enhance Customization With 3rd Party Chiplets

dehjomz

Distinguished
Dec 31, 2007
69
48
18,560
So this is similar in concept to intel foundry services that will allow developers to mix and match various ip on the same chip. So AMD chiplet services… and rather than having to manufacture the chip itself, on a node that may or may not be delayed or constrained in some other form, AMD can farm production out to TSMC.

Seems like a very smart strategy. I wonder what types of IP blocks we’ll start to see on these custom chips? What would be the benefit, if any, of a chip with both arm and x86 cores? Wouldn’t windows and Linux need to be updated to fully account for and optimally utilize various types of cores spanning different ISAs on the same package?
 
Jul 20, 2021
63
35
1,560
So this is similar in concept to intel foundry services that will allow developers to mix and match various ip on the same chip. So AMD chiplet services… and rather than having to manufacture the chip itself, on a node that may or may not be delayed or constrained in some other form, AMD can farm production out to TSMC.

Seems like a very smart strategy. I wonder what types of IP blocks we’ll start to see on these custom chips? What would be the benefit, if any, of a chip with both arm and x86 cores? Wouldn’t windows and Linux need to be updated to fully account for and optimally utilize various types of cores spanning different ISAs on the same package?

Depends on application. For instance, all AMD processors already include a teeny tiny Arm core (AMD's Secure Processor) that's not exposed to the system and handles internal chip security. Software will naturally need to evolve to handle all the different ISAs, but we're already on that road (windows on Arm, app developers having to code for both x86 on windows and Arm on MacOS, etc).
 
Seems like a very smart strategy. I wonder what types of IP blocks we’ll start to see on these custom chips? What would be the benefit, if any, of a chip with both arm and x86 cores? Wouldn’t windows and Linux need to be updated to fully account for and optimally utilize various types of cores spanning different ISAs on the same package?
I would argue operating systems are aware of this in a sense. For instance, the commands that games send to video cards to render something are actually microprograms called shaders. They get compiled by the drivers before being sent to the card to run.

The OS wouldn't run on multiple ISAs, it'll just run on one and see the other as some other hardware to send executable data to if need be.
 

Latest posts