The issue is likely that 3nm node was delayed. The A16 and A17 have the same codename internally (H15 and H15 Coll), it’s rumored that the A17 is what the A16 should have been if 3nm wasn’t delayed. Now they are basically a generation behind schedule, let’s see what happens next year. At least on the GPU side they have to improve power efficiency.
Yes, last year they had to roll back the GPU changes due to heat issues / 3nm being delayed. This year they were able to implement what they initially planned for the A16. I’m not sure how what you are saying contradicts my comment.
This isn’t just an Apple thing. Intel’s 12000 series should have launched in 2017. Instead, it got launched in 2021 FOUR YEARS late because of all their 10nm issues. In the interim, Intel backported whatever they thought would actually be economically feasible on 14nm.
Apple no doubt started designing what A16 should have been way back in 2017-2018. When it became apparent TSMC would miss targets, the most they could do was rapidly try to backport a few features to the old node which is basically what we got in A16.
Then, even though TSMC promised 1.7x scaling for non-SRAM transistors, their real scaling turned out to be around 1.2x (they didn’t change the size of the significant cache blocks, so they should have gotten a lot more of a shrink).
Apple is not Intel. They never tie their architectures to a particular node.
Under no circumstances could Intel 12th gen have launched earlier than 2021. The process was more or less fixed by Tiger Lake in 2020. If they had something better, they would have shipped that instead.
TSMC N3B really ruined Apple this year
The issue is likely that 3nm node was delayed. The A16 and A17 have the same codename internally (H15 and H15 Coll), it’s rumored that the A17 is what the A16 should have been if 3nm wasn’t delayed. Now they are basically a generation behind schedule, let’s see what happens next year. At least on the GPU side they have to improve power efficiency.
There was the same “rumor” last year. Sounds like nonsense at this point. Apple’s had plenty of time to adjust.
Yes, last year they had to roll back the GPU changes due to heat issues / 3nm being delayed. This year they were able to implement what they initially planned for the A16. I’m not sure how what you are saying contradicts my comment.
This isn’t just an Apple thing. Intel’s 12000 series should have launched in 2017. Instead, it got launched in 2021 FOUR YEARS late because of all their 10nm issues. In the interim, Intel backported whatever they thought would actually be economically feasible on 14nm.
Apple no doubt started designing what A16 should have been way back in 2017-2018. When it became apparent TSMC would miss targets, the most they could do was rapidly try to backport a few features to the old node which is basically what we got in A16.
Then, even though TSMC promised 1.7x scaling for non-SRAM transistors, their real scaling turned out to be around 1.2x (they didn’t change the size of the significant cache blocks, so they should have gotten a lot more of a shrink).
Apple is not Intel. They never tie their architectures to a particular node.
Under no circumstances could Intel 12th gen have launched earlier than 2021. The process was more or less fixed by Tiger Lake in 2020. If they had something better, they would have shipped that instead.
If I was Apple I would be pissed at TSMC
It’s not worse than N4, so that comparison does them no favors.