Leaked plan shows Intel will try to be more efficient than M1 Max by late 2023
A presentation slide claiming to show Intel's projected future roadmap includes plan for Arrow Lake processor to outperform Apple's M1 Max by late 2023 or early 2024.
Intel has already claimed to be producing processors that exceed the performance of Apple's M1 Max. However, the difference is within a margin of error while at the same time, Intel's processors require dramatically more power.
Now the company is reportedly aiming at a new processor that will beat Apple's 2021 chips by early 2024 at the latest.
The tweet from "Jim," aka AdoredTV, was in response to a thread discussing Intel's use of TSMC for 3 nanometer chip production. He says he got the slide "between 8-9 months ago," so plans may have changed.
Intel's slide says that it is about "targeting Apple compete 14" premium designs requiring high-touch OEM collaboration." And also that it is focused on how to "maximise performance."
Technology site WCCFtech, which previously reported on Apple using Intel for a 2022 Mac Pro update, Intel plans a 320 EU iGPU based on Battleimage architecture.
WCCFtech further says that according to the leaked slide, the forthcoming Arrow Lake-P (portable) processors will use 14 cores, while the desktop Arrow Lake-S will have up to 40 cores.
Apple's M2 chips are expected in the first half of 2022, and M2 Pro and M2 Max will ultimately follow. It's not yet clear what balance of power to performance they will have.
Read on AppleInsider
Intel has already claimed to be producing processors that exceed the performance of Apple's M1 Max. However, the difference is within a margin of error while at the same time, Intel's processors require dramatically more power.
Now the company is reportedly aiming at a new processor that will beat Apple's 2021 chips by early 2024 at the latest.
It wasn't a rumour, it was their plan. I talked with Intel engineers working on the project and I was also handed this slide a bit before then. If they are no longer doing TSMC 3nm its a decision made since the video. pic.twitter.com/zr0FojtCv6
-- Jim (@AdoredTV)
The tweet from "Jim," aka AdoredTV, was in response to a thread discussing Intel's use of TSMC for 3 nanometer chip production. He says he got the slide "between 8-9 months ago," so plans may have changed.
Intel's slide says that it is about "targeting Apple compete 14" premium designs requiring high-touch OEM collaboration." And also that it is focused on how to "maximise performance."
Technology site WCCFtech, which previously reported on Apple using Intel for a 2022 Mac Pro update, Intel plans a 320 EU iGPU based on Battleimage architecture.
WCCFtech further says that according to the leaked slide, the forthcoming Arrow Lake-P (portable) processors will use 14 cores, while the desktop Arrow Lake-S will have up to 40 cores.
Apple's M2 chips are expected in the first half of 2022, and M2 Pro and M2 Max will ultimately follow. It's not yet clear what balance of power to performance they will have.
Read on AppleInsider
Comments
Where was Intel's motivation when Apple was a dedicated customer all of those years? How long ago did the rumors of Apple's plans to make computer SOCs start flying? Why didn't Intel attempt to get into gear then? They had plenty of time to attempt to retain Apple as a customer, but kept dragging their feet. This is starting to sound a little like the Blackberry story, or was it called the Blueberry? Those are such a distant memory anymore.
What are you talking about?
However the leaked intel slide states: ARL-P is targeting Apple 14 premium inch designs. Nowhere does the intel slide claim that intel is targeting the 2021 m1 max with a 2023/24 product.
The only way Intel truly beats apple in single thread performance/watt is if they beat TSMC in process. There's no way Intel wins on equivalent process because x86 requires much higher clock speeds (and therefore voltage) to beat Apple's core design on single thread performance. I doubt that changes.
For multi-threaded performance/watt, Intel might stand a chance on equivalent process due to hyper threading. I'd still bet on Apple, but it's not impossible that Intel could eke out a win.
The gazillion dollar question, then, is -- can Intel recapture the process lead? It's not impossible. Gelsinger and Co. seem genuinely committed (ie, they're spending the money, hiring the people, telling the stock market to F-off). The geopolitical situation might help Intel, too. I'll say this -- if Intel actually releases 'Intel 4' products on time AND if the TSMC 3nm schedule slips, I'll buy Intel stock (not before that, though).
In most speed test it's only by 5%. Take note that Alder lake needs 4 more cores to do that . So Alder lake is slow.