Discussion Intel Meteor, Arrow, Lunar & Panther Lakes + WCL Discussion Threads

[Tigerick]

Wildcat Lake (WCL) Preliminary Specs

Intel Wildcat Lake (WCL) is upcoming mobile SoC replacing ADL-N. WCL consists of 2 tiles: compute tile and PCD tile. It is true single die consists of CPU, GPU and NPU that is fabbed by 18-A process. Last time I checked, PCD tile is fabbed by TSMC N6 process. They are connected through UCIe, not D2D; a first from Intel. Expecting launching in Q2/Computex 2026. In case people don't remember AlderLake-N, I have created a table below to compare the detail specs of ADL-N and WCL. Just for fun, I am throwing LNL and upcoming Mediatek D9500 SoC.

		Intel Alder Lake - N	Intel Wildcat Lake	Intel Lunar Lake		Mediatek D9500
Launch Date		Q1-2023	Q2-2026 ?	Q3-2024		Q3-2025
Model		Intel N300	?	Core Ultra 7 268V		Dimensity 9500 5G
Dies		2	2	2		1
Node		Intel 7 + ?	Intel 18-A + TSMC N6	TSMC N3B + N6		TSMC N3P
CPU		8 E-cores	2 P-core + 4 LP E-cores	4 P-core + 4 LP E-cores		C1 1+3+4
Threads		8	6	8		8
Max Clock		3.8 GHz	?	5 GHz
L3 Cache		6 MB	?	12 MB
TDP		7 W	Fanless ?	17 W		Fanless
Memory		64-bit LPDDR5-4800	64-bit LPDDR5-6800 ?	128-bit LPDDR5X-8533		64-bit LPDDR5X-10667
Size		16 GB	?	32 GB		24 GB ?
Bandwidth			~ 55 GB/s	136 GB/s		85.6 GB/s
GPU		UHD Graphics		Arc 140V		G1 Ultra
EU / Xe		32 EU	2 Xe	8 Xe		12
Max Clock		1.25 GHz		2 GHz
NPU		NA	18 TOPS	48 TOPS		100 TOPS ?

As Hot Chips 34 starting this week, Intel will unveil technical information of upcoming Meteor Lake (MTL) and Arrow Lake (ARL), new generation platform after Raptor Lake. Both MTL and ARL represent new direction which Intel will move to multiple chiplets and combine as one SoC platform.

MTL also represents new compute tile that based on Intel 4 process which is based on EUV lithography, a first from Intel. Intel expects to ship MTL mobile SoC in 2023.

ARL will come after MTL so Intel should be shipping it in 2024, that is what Intel roadmap is telling us. ARL compute tile will be manufactured by Intel 20A process, a first from Intel to use GAA transistors called RibbonFET.

 

[511]

There is no benefit of Pat's work thus far so giving him any credit right now is premature. All we know for the time being is that Pat keeps hyping the next big thing (right now it's 18A and Panther Lake/Nova Lake) and people keep defending him by saying that everything Intel has delivered since he stepped in as CEO was already decided before he took the helm.

Fine. I better not hear these excuses by December 2025. I mean it!

I never said he delivered everything on time but at least give him credit where it is due 🫠🫠

 

[mzocyteae]

All we know for the time being is that Pat keeps hyping the next big thing (right now it's 18A and Panther Lake/Nova Lake) .

18A is the big thing, while Panther Lake/Nova Lake are minor.
The only thing relevant is that Panther/Nova should be get more blocks built from intel foundry.

 

[igor_kavinski]

I never said he delivered everything on time but at least give him credit where it is due 🫠🫠

Wait for Q42024 results

 

[MoistOintment]

All we know for the time being is that Pat keeps hyping the next big thing (right now it's 18A and Panther Lake/Nova Lake)

18A is the thing Pat has been hyping before Intel 4 was even in customer hands. It's the most important thing Intel has done (for Intel) for as long as I've been following hardware. It's the make-it-or-break-it measurement of his entire tenure as CEO. Everything between when he took office until 18A has been mostly projects already in the pipeline and him cutting costs to tread water.

18A is not simply "the next thing he's hyping". It will determine if he still has a job or not. He still has a job because the most important change he's enacted can't be measured until 18A launches.

 

[igor_kavinski]

18A is not simply "the next thing he's hyping". It will determine if he still has a job or not. He still has a job because the most important change he's enacted can't be measured until 18A launches.

If you say so

 

[igor_kavinski]

Lunar Lake is doing well, I guess: https://www.notebookcheck.net/Tence...glasses-free-3D-gaming-handheld.923541.0.html

 

[OneEng2]

18A is the thing Pat has been hyping before Intel 4 was even in customer hands. It's the most important thing Intel has done (for Intel) for as long as I've been following hardware. It's the make-it-or-break-it measurement of his entire tenure as CEO. Everything between when he took office until 18A has been mostly projects already in the pipeline and him cutting costs to tread water.

18A is not simply "the next thing he's hyping". It will determine if he still has a job or not. He still has a job because the most important change he's enacted can't be measured until 18A launches.

Agree.

I still wonder about this strategy though. Put everything on the line to pay for an exponentially more expensive and complex process. Hmm.

Lets say it works and 18A is all that and a bag of chips. It isn't like it is going to blow N2 out of the water like some historic Intel nodes have in the past. In fact, it will be better than N2 in some respects and worse in others from what I can gather. Still, the point remains, what then? Mortgage the company again for the next node which may be even more expensive?

 

[dttprofessor]

Intel=fab,pat is right.

 

[511]

18A is the thing Pat has been hyping before Intel 4 was even in customer hands. It's the most important thing Intel has done (for Intel) for as long as I've been following hardware. It's the make-it-or-break-it measurement of his entire tenure as CEO. Everything between when he took office until 18A has been mostly projects already in the pipeline and him cutting costs to tread water.

18A is not simply "the next thing he's hyping". It will determine if he still has a job or not. He still has a job because the most important change he's enacted can't be measured until 18A launches.

Apparently Daniel nenni from semi wiki think 18A is good from the sources he has inside industr

Intel 18A "too good" but design lags

Got this from X but too interesting to let it go by: "The design service and design enablement is still fairly weak at Intel right now, but the technology is just way too good." He noted Samsung's MOL had issues, but no comments on TSMC.

semiwiki.com

 

[mzocyteae]

In fact, it will be better than N2 in some respects and worse in others from what I can gather. Still, the point remains, what then? Mortgage the company again for the next node which may be even more expensive?

If 18a is that good, intel will get decent foundry orders. Then next nodes would be less harsh.
The real question would be if 18a can compete with n3 with quality+cost.

 

[MoistOintment]

Agree.

I still wonder about this strategy though. Put everything on the line to pay for an exponentially more expensive and complex process. Hmm.

Lets say it works and 18A is all that and a bag of chips. It isn't like it is going to blow N2 out of the water like some historic Intel nodes have in the past. In fact, it will be better than N2 in some respects and worse in others from what I can gather. Still, the point remains, what then? Mortgage the company again for the next node which may be even more expensive?

Why external customers are so important. Gotta spread those costs across more volume than Intel Products can provide alone. But that's inevitable: Each new node will be more expensive than the last.

What hurts Intel the most is years or proprietary tooling and older nodes focused on HPC over density. Intel would be in a much better spot financially if Intel 7 was based around industry standard tooling and they could open it up as a high volume, low cost legacy node to keep the DUV lines active as they move on to 18A / Intel 3. Securing Intel 16 customers is a critical component of this strategy that's, imo, under discussed. Keeping DUV lines filled after Intel Products moves on is an important step.

 

[igor_kavinski]

Intel=fab,pat is right.

Come on. Intel is never leaping ahead of the fab industry again. The other competitors (mainly TSMC) gained wayyy too much experience and expertise during the languishing era of Krzanich.

 

[igor_kavinski]

The real question would be if 18a can compete with n3 with quality+cost.

Short answer: After their Intel 4 troubles, it looks more and more like "fat chance".

But I would be happy to be proven wrong.

 

[SiliconFly]

.

 

[GTracing]

My take, if 18A pans out, Intel won't have nearly as much of a cash flow problem in the future.

Right now they're playing catch-up. They're financing multiple nodes at once.
Their nodes prior to "Intel 4" are dated, and they can't really sell capacity on those older nodes because they don't use industry standard tooling.

Intel doesn't have to surpass TSMC or even catch them. If 18A is 2-3 years behind in PPA, has good yields, and gets a few customers, Intel will be fine.

 

[SiliconFly]

.

 

[maddie]

Node, node, node.

Materials/chemistry? If I remember correctly, it wasn't node size that mainly sank 10nm, but chemical incompatibilities.

Having a similar node size as the competitor is a good start, but definitely not the final word.

 

[moinmoin]

Apparently Daniel nenni from semi wiki think 18A is good from the sources he has inside industr

I recall positive impressions like this having happened in the past as well so consider me sceptical. In the past I attributed this potential mismatch to Intel's seemingly excellent foundry PR.

 

[SiliconFly]

.

 

[maddie]

Well, it all boils down to who has the best transistors. Remember the time when Pat kept singing on stage about how wonderful their RibbonFET transistors are and was comparing them to Mona Lisa. It matters. 18A I think has excellent transistors. Expected to clock higher than N2 (possible higher Fmax due to BSPDN).

And according to Daniel Nenni, 18A is better than N3B, N3, N3E & N3X and is close to N2. Pat himself said 18A is very close to N2 in density & better than N2 in performance. Its pretty clear 18A is on par with N2 in most aspects.

If they can get yields up & hit decent volume on time, 2025 would be an amazing year for Intel.

He has been singing, dancing & praying for a long time now, but somehow, it keeps getting worse. Falling for the same fantastical message repeatedly is not wise. A smart person will think to see the actual physical product after so many false predictions the past several years. I want a strong company but will not dance to the PR spin.

 

[SiliconFly]

.

 

[maddie]

Thats why smart people don't take PR words for granted. Neither AMD's nor Intel's. It's never wise. Independent views/reviews matter. And they have good things to say about 18A. Either way, Intel is all set to release 18A details in a couple of months. Don't worry.

Pot calling kettle?

 

[DavidC1]

And according to Daniel Nenni, 18A is better than N3B, N3, N3E & N3X and is close to N2. Pat himself said 18A is very close to N2 in density & better than N2 in performance. Its pretty clear 18A is on par with N2 in most aspects.

When did Pat say it'll be close in density to N2?

By the way IEDM presentations already revealed SRAM size. 18A is 0.021um2 and N2 is 0.0175um2. 18A's SRAM size is same as N3E. Now logic might be different, but my estimations with Crestmont says 18A should be around N3 in density.

Page 138 - Discussion - Leading Edge Foundry Node advances (TSMC, Samsung Foundry, Intel) - [2020 - 2025]

Page 138 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

18A should lead in performance but lose in density.

 

[SiliconFly]

.

 

[SiliconFly]

.