A18 Pro … your thoughts?

I assume this chip will go into the regular iPad and, if there is one, the iPad Mini 7. On those 4 platforms, having that much GPU power sounds to me like Apple is aiming toward turning those devices into the real alternative to portable gaming devices. Why else would they need that much power?
 
First iPhone 16 Geekbench score? Seems a little low. It could be the 16 and not the Pro/Max. Obvious caveat that background work can initially lower scores.
1725966274348.png
 
Lots more scores.

1726057960761.png
 
My biggest open question is how much more cache the A18 Pro has versus A18. And what the topology of it is. I imagine it’s only the SLC cache that’s bigger and not L1/2
 
I assume this chip will go into the regular iPad and, if there is one, the iPad Mini 7. On those 4 platforms, having that much GPU power sounds to me like Apple is aiming toward turning those devices into the real alternative to portable gaming devices. Why else would they need that much power?
Pro apps that can do hardware accelerated RT like CAD or blender? Given the larger chips use the same basic core architecture, building such things for the M series means that the A series kinda get it (In advance as they lead M) "for free"; they're just smaller, architecture leading core count versions of the later M chips.
 
Srouji interview.



What an outstanding interview, providing some insight into processor development and overall goals as they relate to Apple products. It's a shame many at the other place will never see it and continue to blather on about how Apple "doesn't innovate anymore."
 
What an outstanding interview, providing some insight into processor development and overall goals as they relate to Apple products. It's a shame many at the other place will never see it and continue to blather on about how Apple "doesn't innovate anymore."
I think the other place has already dismissed the video as weak sauce…
 
What an outstanding interview, providing some insight into processor development and overall goals as they relate to Apple products. It's a shame many at the other place will never see it and continue to blather on about how Apple "doesn't innovate anymore."

IMO the questions were weak and not very interesting, and Srouji had no difficulty diplomatically side-stepping them without revealing much technical information. You can’t ask an Apple exec for technical detail, they won’t answer. It would be much more interesting to ask about vision and strategy.
 
IMO the questions were weak and not very interesting, and Srouji had no difficulty diplomatically side-stepping them without revealing much technical information. You can’t ask an Apple exec for technical detail, they won’t answer. It would be much more interesting to ask about vision and strategy.

Weak questions, yes... but anything deeper, including long range company or product vision/strategy, I don't think Srouji would have spoken to other than in generalities.
 
He reiterated a point I’ve raised before - Apple doesn’t give a rat’s ass about designing chips to win artificial benchmarks, because they don’t have to sell chips. Other than that, my main thought was they must train these guys on how to respond, at Apple University. Engineers don’t naturally answer questions the way Srouji did
 
He reiterated a point I’ve raised before - Apple doesn’t give a rat’s ass about designing chips to win artificial benchmarks, because they don’t have to sell chips. Other than that, my main thought was they must train these guys on how to respond, at Apple University. Engineers don’t naturally answer questions the way Srouji did

I think that was his strongest point, and in combination with the factors beyond/besides compute performance considered during the systems engineering phase of Apple processor development. And also being mindful of right-sizing (my choice of words) what's required, so as not to adversely impact other goals (thermals, etc).
 
Weak questions, yes... but anything deeper, including long range company or product vision/strategy, I don't think Srouji would have spoken to other than in generalities.
Yeah as I wrote at the other place these kinds of short 15 minute video interviews are rarely more than for vision/strategy. I thought the questions were fine and the answers largely expected.

The parts that were interesting that I would have liked expanded on included what differences between A- and M- series GPUs (my guess is L1 cache size) and more details about the data they use to prioritize performance optimizations.
 
What an outstanding interview, providing some insight into processor development and overall goals as they relate to Apple products. It's a shame many at the other place will never see it and continue to blather on about how Apple "doesn't innovate anymore."

Yeah, I like how he stressed that apple doesn't design to win benchmarks, but they do as a side effect.

WE know they could likely push the chips in the Mac, iPad, etc. further to go faster, but they'd make for crappier products due to heat, battery life, etc.
 
Back
Top