News Intel to Make 3nm Technology More Accessible to IFS Customers

Status
Not open for further replies.

ikjadoon

Distinguished
Feb 25, 2006
1,994
61
19,860
Only for the iGPU tile. I don't read much into that other than potential capacity offload at this stage. If that is the case in 3 generations then it's a different story

If IFS is worried about its CPUs exceeding IFS capacity, then external customers probably should be worried, too, though, right? That is, vendors might not be willing to trust Intel's capacity claims until Intel has a few generations of its nodes delivering capacity for Intel's own products.

Does anyone want to be "second", if Intel isn't ready to be first?

It took Apple more than a few generations to end its dual-sourcing from Samsung & TSMC, and commit to TSMC. I don't forget that Intel's entire GPU line-up is fabbed at TSMC, including all mobile, workstation, and desktop Arc dGPUs:

Intel Arc A310: TSMC N6
Intel Arc A380: TSMC N6
Intel Arc A750: TSMC N6
Intel Arc A770: TSMC N6
etc.

These GPUs are likely extremely low volume. Of course, maybe future Arc generations use Intel nodes? But, rumors indicate Intel will again use TSMC nodes for Intel's flagship-to-low-end Arc GPU products.


That would mean even in 2026, Intel backing TSMC for its GPU foundry needs. Of course, these are rumors. These are future generations, but I imagine Intel wants to promote any foundry wins, just as frequently as it promotes these ancillary updates (like the OP).
 
Apple is happy with TSMC why would it want to go with Intel when they have removed all Intel's chips from their gear?
Apple wants to pay as little as possible which is why they don't want to pay the overhead for a full intel CPU, but they do have to manufacture their M1 cpus somewhere anyway, so unless you can come up with a reason why Apple actively hates intel I don't see a reason why Apple would care whom they pay the money to manufacture their M1.
 
  • Like
Reactions: thisisaname
If IFS is worried about its CPUs exceeding IFS capacity, then external customers probably should be worried, too, though, right? That is, vendors might not be willing to trust Intel's capacity claims until Intel has a few generations of its nodes delivering capacity for Intel's own products.

Does anyone want to be "second", if Intel isn't ready to be first?
TSMC might be more efficient in making GPU tiles until intel makes a FAB that is special made for it.
As far as I understand it intel has only FABs that are 100% specialized towards CPUs now and it might be more expensive for them to make gpu tiles on a CPU FAB then to pay TSMC to make them.
Just a guess.
 
  • Like
Reactions: thestryker

thisisaname

Distinguished
Feb 6, 2009
934
520
19,760
Apple wants to pay as little as possible which is why they don't want to pay the overhead for a full intel CPU, but they do have to manufacture their M1 cpus somewhere anyway, so unless you can come up with a reason why Apple actively hates intel I don't see a reason why Apple would care whom they pay the money to manufacture their M1.
I have no proof they hate Intel.

As for why they would not swap the cost of changing design to work with Intel would be substantial.
Also having worked quite closely with TSMC I would be surprised if they have tailored their designs to be efficiently manufactured by them.
 
TSMC might be more efficient in making GPU tiles until intel makes a FAB that is special made for it.
As far as I understand it intel has only FABs that are 100% specialized towards CPUs now and it might be more expensive for them to make gpu tiles on a CPU FAB then to pay TSMC to make them.
Just a guess.
Anything they produced in house would have to take away from CPU production which undoubtedly is more profitable. I don't think they'll move GPUs in house until they have the majority of fabs producing 20a/18a or beyond.
 
I have no proof they hate Intel.

As for why they would not swap the cost of changing design to work with Intel would be substantial.
Also having worked quite closely with TSMC I would be surprised if they have tailored their designs to be efficiently manufactured by them.
Intel works hard with ARM to make ARM designs easily fabbable on intel FABs, it won't do anything for current designs probably but it will definitely make it easy for future products. The Apple CPUs are just ARM CPUs with Apple design.
Also in general intel might just pay the expense for any design changes themselves to get IFS going.
 
  • Like
Reactions: thisisaname
Status
Not open for further replies.