Maynard Handley (name99.delete@this.name99.org) on November 19, 2020 8:22 pm wrote:
> OK guys, M1 time is over. What's next?
>
> Something I just realized, and I think the timing works out beautifully:
> TSMC started N5P testing/Risk production in 2Q2020.
> Meaning that (and now that I think about it, it is so obvious!) the M1X will be on N5P!
> THAT is what's determining its schedule.
>
> There is a precedent. Remember that the A10 came out in Sept
> 2016, on 16nm. But the A10X came out in June 2017 on 10nm.
>
> This makes so much sense. It gives time Apple to improve some of the rushed bits of the M1, and gives
> a free 5% speed boost (which isn't much, sure, but may mean that M1X clocks at, say 3.5GHz)
> And gives Apple a second round of (totally justified!) "OMG, Apple is king, everyone else is doomed" publicity,
> say maybe in April or May, which should sustain them till the A15/iPhone next reveals in September.
>
> Well, six months or so to see if I'm right. tick tick tick


OK, let's say your thesis that Apple was pretty conservative with A14 (and thus the lesser IPC improvement compared with past years) is correct. If so I would submit the upcoming "8+4" chip will have A15 cores.

After all, we don't know Apple's schedule/cadence for the yearly SoC updates, only that they've lined up the new SoC design, new TSMC process, and new iPhone release to have millions of chips available by August to begin mass producing iPhones to make their traditional September ship date (delayed a bit this year, but understandable)

If they wanted to get A15 cores shipping months earlier than the usual September deadline, it would make sense their A14 schedule would end up compressed and the resulting improvements would seem a bit muted compared to past years. There's nothing stopping them from altering their schedule like this, if they do this they would have been planning it several years in advance. In fact, the rumor that the A14 taped out prior to September 2019 (versus previous generations which had taped out as late as December) does point to a potential "get this baby put to bed early so we can get to work on the next one" urgency.

Whether it lines up with N5P is unknown, but since this is much lower volume than iPhone it might be possible. Apple doesn't need too worry if N5P is ready or not. The design rules are the same, they will do their design and have it made with N5P if it is ready or N5 if it is not. They benefit from built in slack in the schedule, since they haven't announced exactly when these new Macs are coming. If they want to wait a month for N5P to be ready, they can and no one will care because they have not announced a date. They don't have that kind of freedom with the iPhone launch, if they are late with that the world notices (though they got a pass this year due to the pandemic)

So they may or may not get the 5% N5P bump, but would have a more typical generational IPC bump as well as bigger GPU improvements than A13->A14 provided. This would also help further differentiate between these higher end Mac laptops beyond just having more big cores and (presumably) more GPU cores.

There's really no reason they couldn't do this, since it doesn't depend on N5P at all, only on their own allocation of engineering resources that would have been planned several years in advance. The design rules for N5 and N5P are the same, a design that targets N5P could fall back to N5 if they were ready to go with their new design and didn't want to wait. I think shipping the new design earlier in the year would clearly be much more important to them than getting N5P.