The thoughts of reviewers based on their claims is that likely you will get something that is competitive with current gen ryzen mobile (4900h on the high end) on power usage/perf and competitive with m1 on perf, but not power usage. However, I don't see them drawing even with Apple on power efficiency, and AMD have their Zen 3 mobile chips in the near future, so it's more a holding on in technical quality. Likely they will outsell both though, given the M1's Mac exclusivity and the limited range of AMD laptops (and limited stock of TSMC 7nm everything currently) - try buy a 4900H system vs a 108xxH, it's much harder.

Their perfromance claims will result in M1 multicore level probably with more cores but nowhere close in single core regardless of their shockingly false single core claims.

Intel getting TSMC to build some of its chips is also I think a way to constrict AMD supply rather than them actually needing the production

Well if this is the case it would not be inconsistent with Intel's usual AMD sabotage.

While I can totally believe Intel doing it for that reason alone - Isn't Intel only buying 7nm capacity while AMD is already moving to 5nm?

No, Apple have exclusivity on TSMC 5nm currently

The news back in September was that Apple had exclusivity on TSMC 5nm to the end of last year: https://www.digitimes.com/news/a20200917PD210.html

It seems that this year Apple has only secured 80% of TSMC 5nm production: https://wccftech.com/apple-secured-80-tsmc-5nm-production-ca...

This specific announcement is an incredibly run of the mill "Intel produced a new larger variant of a chip they already make". It's still produced at 10nm, this is not any kind of big step forward to catching up with Apple.

So if I was gonna try to interpret tea leaves, did yields finally increase to where 8 cores on a die was viable or was it just limited to 4 cores before to maximize capacity?

I would put it more as "Intel didn't do poorly this round" if all holds true to the information we have so far. AMD still hasn't overtaken them in low core count performance in the laptop space and this should hold them off from doing that until at least Zen 4 (late Fall-ish or so) or open Intel up more time to continue changing its momentum if Zen 4 falters any. In this space the M1 is still miles ahead both (i.e. AMD/Intel can generally match the performance or the power budget with their latest designs but the M1 can do both at the same time). On the desktop side the Rocket Lake S should just eek out Zen 3 on single core performance albeit ~6 months (or about half a product cycle) later. Certainly good news for Intel as it keeps them from being steamrolled in a single year but that means AMD still has higher momentum, a time advantage on the next release, a guarantee that TSMCs new 5nm process they want to use works (as used in the M1), and a significantly better many core position.

AMD has their presentation shortly but I wouldn't expect more than news on Zen 3 mobiles (which may dampen Intel's presentation a bit but probably won't outdo them) and Zen 3 Epyc (server, likely to wipe the floor) this early into it on the CPU side.

It’s great to see competition in the sector.

WCCFtech has a better article with image summaries. https://wccftech.com/intel-launches-tiger-lake-h-tgl-h-mobil...

> Fastest Laptop Processor (Single Thread) On The 10nm SuperFin Process

That last part of the title would seem to imply that it's not the fastest overall.

Wonder what are:

1. the fastest overall

2. the fastest overall single thread

3. the fastest overall on the 10nm SuperFin process

Currently (and for laptop CPUs specifically)

1. AMD Ryzen 4900H

2. Apple M1, though the Intel 10875H is pretty much the same perf (though at 3x the power usage)

3. Only Intel uses this, so whatever Intel's fastest chip on this process is.

That said, it varies by use cases, and M1 leans heavily on accelerators so has big wins in some and big losses in others when compared the 4900H or 10875H, which are closer to each other in single threaded benchmarks.

> 2. Apple M1, though the Intel 10875H is pretty much the same perf (though at 3x the power usage)

In single core? At least by Geekbench (clearly not the best test) it is shown to be more than 25% slower than M1.

Assuming Intel is sticking to Specint2017 for that claim, the M1's lead isn't that big: https://www.anandtech.com/show/16252/mac-mini-apple-m1-teste...

So per that the M1 is 8% faster in single-core than the 28W i7-1185G7 (side note: Intel fix your naming yeesh). It would not at all be surprising if Intel claws that back, that's well within "typical" generational IPC gains.

Doesn’t hyperthreding gain about 25% extra perf per core?

Is geekbech single core test a single thread test or two threads pinned to one core (if the cpu supports HT)?

I assume some could actually answer your question with respect to designm but you would be asking the wrong question. Intel's main competitor is not ARM or AMD. It is TSMC's ecosystem. Which is ex-CEO Morris Chang calls it the Grand Alliance.