• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Intel Makes Jilted Reference to Apple in its Internal "Arrow Lake" Slide

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
47,677 (7.43/day)
Location
Dublin, Ireland
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard Gigabyte B550 AORUS Elite V2
Cooling DeepCool Gammax L240 V2
Memory 2x 16GB DDR4-3200
Video Card(s) Galax RTX 4070 Ti EX
Storage Samsung 990 1TB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) ASUS SupremeFX S1220A
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Gamdias Hermes E2
Software Windows 11 Pro
Intel is designing a "Halo" SKU of a future generation of mobile processors with a goal to match Apple's in-house silicon of the time. Slated for tape-out some time in 2023, with mass-production expected in 2024, the 15th Generation Core "Arrow Lake-P Halo" processor is being designed specifically to compete with Apple's "premium 14-inch laptop" (presumably the MacBook Pro) that the company could have around 2024, based on an in-house Apple silicon. This is to essentially tell its notebook partners that they will have an SoC capable of making their devices in the class truly competitive. Apple relies on a highly scaled out Arm-based SoC based on in-house IP blocks, with a software that's closely optimized for it. Intel's effort appears to chase down its performance and efficiency.

The Core "Arrow Lake" microarchitecture succeeds the 14th Gen "Meteor Lake." It is a multi-chip module (MCM) of three distinct dies built on different fabrication nodes, in line with the company's IDM 2.0 strategy. These nodes are Intel 4 (comparable to TSMC N7 or N6), Intel 20A (comparable to TSMC N5), and an "external" 3 nm-class node that's just the TSMC N3. The compute tile, or the die which houses the CPU cores, combines a hybrid CPU setup of 6 P-cores, and 8 E-cores. The performance cores are likely successors of the "Redwood Cove" P-cores powering the "Meteor Lake" compute tiles. Intel appears to be using one kind of E-cores across two generations (eg: Gracemont across Alder Lake and Raptor Lake). If this is any indication, Arrow Lake could continue to use "Crestmont" E-cores. Things get interesting with the Graphics tile.



With Meteor Lake, Intel is disaggregating the iGPU out of both the "processor die" and the platform tile. The company understands the importance of having a fast iGPU in the wake of competition from not just Apple, but also AMD tapping into its latest RDNA-series IP to create powerful iGPUs. The graphics tile of Arrow Lake-P Halo will very likely be based on the node with the highest transistor density (our money is on TSMC N3). This tile features a whopping 320 execution units (EUs), which work out to 2,560 unified shaders. Intel is designating the iGPU its highest performance designation in the series, "GT3." The least advanced node of the three, Intel 4, could be used for the platform or I/O tiles, which house the memory controllers, PCIe root-complexes, and various SoC I/O interfaces.

View at TechPowerUp Main Site | Source
 
A lot of words and very. very little info. As is the norm when discussing products that are two years away.
 
I'm guessing: Only 100 will be made for sending to reviewers & the rest would come 12months later & still use 2x the power except for a few selected benchmarks that virtually nobody cares about.
 
I'm guessing: Only 100 will be made for sending to reviewers & the rest would come 12months later & still use 2x the power except for a few selected benchmarks that virtually nobody cares about.
I'm guessing: you can't actually name a situation when Intel actually did what you seem to be expecting them to do (again?).
 
I know it's in fashion to shit on Intel regardless of what the context/conversion is, but Intel is still the 800lb gorilla of the semiconductor market. They get lazy when there is no competition, but Intel has time and again delivered in spades whenever presented with an existential threat.

90% of Intel's current defecit is because of the Fab inferiority. With them leading the way in terms of High-NA EUV orders, I expect them to be able to close the gap to TSMC in terms of fabrication, and then Intel's architecture talents will shine through.
 
I know it's in fashion to shit on Intel regardless of what the context/conversion is, but Intel is still the 800lb gorilla of the semiconductor market. They get lazy when there is no competition, but Intel has time and again delivered in spades whenever presented with an existential threat.

90% of Intel's current defecit is because of the Fab inferiority. With them leading the way in terms of High-NA EUV orders, I expect them to be able to close the gap to TSMC in terms of fabrication, and then Intel's architecture talents will shine through.
I do my best to not crap on anyone, but there are several aspects to any business, be it Intel, AMD, Nvidia or whoever:
- Engineering: everybody employs smart guys, smarter than anyone lurking some random internet forum
- Marketing: this I hate with a passion; nothing but hollow words, often released years before you're supposed to be buying an actual product
- Business: this is what people usually get mixed with morals; to this, I'm applying the "hate the game, don't hate the player" mantra.
 
One question, wherein Lies the jilted reference?!

I'm not seeing it!?.
 
Last edited:
Given the timeframe and the 3nm TSMC process, it is most likely to be Battlemage based, also GT3 320EUs suggest that probably will be HBM3 in package, it seems difficult that even a 128bit LPDDR5X 8533Mbps (136.5GB/s) can support the 320EUs design+CPU memory needs
 
One question, wherein Les the jilted reference?!

I'm not seeing it!?.
Hi,
Maybe it was the name of the person that sent the memo people name children interesting names lol
It's the only blacked out area :cool:
 
I think that just make sense to make larger APU for laptop. I thought neither Intel or AMD had interest in doing this. They would prefer to sell GPU instead but this is interesting from Intel. They are trying to take market share and get a foothold in the GPU market and this would indeed help.

They have the relationship with OEM to ensure they push those laptop.

Intel and AMD can murder themselves on the GPU front, but the real company to take over is Nvidia. I think it would be easy to steal market share from AMD but there isn't that much. Stealing market share from Nvidia is where the money is and a design like this can make a huge dent in the laptop market.

But i am surprised that it's Intel that will do it first in the x86 market. That is the kind of thing that a leader would do and that probably mean that AMD is still not a leader on the laptop market. (techwise i mean, not market share wise).
 
No, ARL uses Skymont rather than Crestmont as its E-Cores architecture:

If you look at the picture carefully, you can see that "Introduces LNC+SKT on N3". LNC is short for Lion Cove, and SKT is for Skymont. That matches older rumors.
 
Throwing shade,….
 
Imagine bragging about a product that's years away with no chance of being on time that's to compete with an already 1+ year old product LOL
 
Speculation. Need to see the product with Intel or it's just talk and wishful thinking. History shows that navel gazing is a speciality for them.
 
Imagine bragging about a product that's years away with no chance of being on time that's to compete with an already 1+ year old product LOL
Imagine reading about a product that's years away and already knowing what it's going to compete with. Oh, wait, you don't have to...
 
Imagine reading about a product that's years away and already knowing what it's going to compete with. Oh, wait, you don't have to...
I don't have to. Intel vomits bullshit slides full of lies and fantasies and is years behind as usual.

Man, Arc is gonna be amazing, Intel said so 2 yrs ago. It's totally gonna be great and compete...with 2016 GPUs.

Add 1-2 yrs min to everything and cut performance to LOL levels and you have an accurate Intel product forecast.
I'm still waiting on those 7nm products from last year that might come in 1.5 more yrs (I expect a couple token mobile chips just like the sad ramp of 10nm).
 
Last edited:
its good to have goals intel, and necessary to make plans, but be confident you can meet those goals before releasing them to the public
make a decent CPU for a thin and light laptop that doesn't run nuclear hot and is impossible to cool, and you might have something
your previous statements and product schedule about 10nm are still present in everyone's mind
 
Back
Top