[ksec]

Every time I criticise Intel, Or more like pointing out facts , supporters will always use Jim Keller as the excuse, as if he was the silver bullet.

Intel's struggle has nothing to do with is processors' design. Sunny Cove and Willow Cove ( aka Icelake and TigerLake ) were close to design complete before Jim Keller joined. Intel's problem is with their manufacturing, both technical and economical. And Jim Keller is not a Fab guy, nothing he could do to fix this.

[wmf]

The great man theory of chip design. In a few months we'll get a ton of the "Xe sucks because Raja's GPUs are always too hot" theory.

[CoolGuySteve]

He lovingly lays each atom and then kisses each box gently before it heads out the door.

[tw04]

Process didn’t cause all the security holes implemented as performance hacks, architecture did. AMD caught up through architecture, process was just icing on the cake.

[etaioinshrdlu]

No one thought of speculative execution and hypertheading as performance hacks until the last few years. They were brilliant techniques. They still are, they just were found to have a cost. They are still used now but more carefully.

Intel Management Engine and SGX on the other hand, are basically user-hostile parts of the hardware, with some bugs mixed in.

[wolfgke]

> No one thought of speculative execution and hypertheading as performance hacks until the last few years.

"Everybody" who has some knowledge in security (espcially with respect to side channels) knew from beginning that these CPU features were a ticking time bomb in terms of potential side channels.

What was unclear was how this (at this time played down by CPU vendors) potential threat could be used to create real attacks.

Going from potential threat (that "everybody" knew about) to real attack is the central achievement of the authors of the Spectre and Meltdown attacks (and their successors).

[legulere]

That’s not the impression that I got. Research on side channels were basically limited to timing side channels in cryptography. Everything else was not seen as practically exploitable.

[wolfgke]

> Everything else was not seen as practically exploitable.

For a concrete blog post, see https://cyber.wtf/2017/07/28/negative-result-reading-kernel-...

Note that according to https://en.wikipedia.org/w/index.php?title=Spectre_(security... Spectre was published January 2018, i.e. this blog post is indeed older.

As I wrote: It was unclear how this potential threat could be used to create real attacks.

[majewsky]

ME is exactly what Intel's data center customers want. It's only present in consumer CPUs because it doesn't scale to have separate ME and non-ME SKUs.

[jimbob45]

Why do you say their problem is based in manufacturing?

[The_Colonel]

They have been working on the 10nm manufacturing process for ages and it's still not completely finished. That gave AMD huge opportunity to catch up (which it did).

[londons_explore]

Nothing stops Intel manufacturing their designs with third parties. Yet they don't.

Either it isn't worth it (too much coupling between fab and designs - not the right abstractions), or institutional inertia stops them doing it.

[jabl]

IIRC most of Intel's expenses are related to the fabs and semiconductor R&D. The chip designs (the computer architecture part that gets computer people excited) is almost a rounding error on top of that. From that perspective Intel designs chips so that they can sell the silicon real estate they manufacture, not the other way around (that they have fabs so they can realize their chip design ambitions).

So if they would fab their chips somewhere else, they would be sitting on a huge expensive asset producing nothing. If they couldn't find a productive use for their fabs it would likely mean the end of the company. And if they can't produce their own chips in their own fabs, why would anyone else want to use Intel fabs?

Further, the vertical integration of fab process and chip design is something Intel regards as a competitive advantage. For a long time this was very much true, but it seems the hard work by TSMC and others have made it possible to make top-end chip designs on a merchant foundry process nowadays.

Intel at some point tried to play the merchant foundry game, but it seems it wasn't successful and they shut it down. Which perhaps isn't that unsurprising, considering TSMC, and to a lesser extent Globalfoundries, have been at that game for decades and they're good at it.

So all in all, I don't think fabbing their chips at some third party is a viable approach for Intel. Either they fix their process or they go under. "Go under" not necessarily meaning bankruptcy, it could also mean a massively, hugely downsized company doing chip designs to be fabbed at some third party. I think they're still far away from such a drastic step.

[theevilsharpie]

> Nothing stops Intel manufacturing their designs with third parties. Yet they don't.

It wouldn't surprise me if the reason Keller left is because he wanted to outsource manufacturing to a competitive third party fab, and got denied.

Keller is an a computer architect, but architecture doesn't matter if you can't physically build the thing.

[olliej]

I'm not a hardware engineer/cpu designer/electrical engineer, but my understanding is that designing high end cpus requires engineering and designing towards the specific manufacturing process of the fabs you're using. Even if intel did decide to, I don't think they could just send their designs to tsmc/global foundries or what have you.

[jabl]

Not my expertise either, but it seems that the advantages of vertical integrations between fabbing and chip design being large was the "common wisdom" in the industry for a long time. But it seems that lately AMD/NVIDIA/TSMC and others have demonstrated that fabless chip companies and merchant foundries is a model capable of producing the highest end chips as well.

And yes, if for some reason Intel would want to fab their chips at some merchant foundry (see my sibling answer to yours why I think that's unlikely, but just for the sake of argument), I'm quite sure they couldn't just email the RTL's to the foundry and get chips back. It would take a lot of work to adapt the chips to the merchant foundry's process.

[ksec]

They cant, they will need to redesign the whole thing with new rules, mask and testing. Not to mention using tools that likely Intel is extremely unfamiliar with. ( At least their CPU teams.)

It is more of a cost/ economical issues, which jabl above provides a decent explanation.

[fomine3]

Ice Lake outperforms Zen2 in IPC but it can't run on higher clock speed (on efficiently) and can't ship many chips. Many of it is due to 10nm manufacturing.

[ReticentVole]

Intel's problem is that they fired expensive, older American workers and replaced them with H1B contractors.

There's a video on AdoredTV about the topic: https://www.youtube.com/watch?v=agxSclh27uo

[markus_zhang]

But, but it's good for the stock price!