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.

 

[maddie]

The board probably wanted him to fire some of his buddies at high positions and he must've opposed that. I foresee more departures in quick succession.

Psychic? How can one deduce this from Pat's release.

 

[AcrosTinus]

This year has been a movie.
From politics to tech, a clowns show...

 

[igor_kavinski]

Psychic? How can one deduce this from Pat's release.

A board member previously resigned over Pat's refusal to fire middle managers: https://www.tomshardware.com/tech-i...intels-stock-dropped-6-since-the-announcement

So now the board is going to sharpen their knife for some much needed culling...

 

[GTracing]

Can we move this discussion to it's own thread?

 

[The Hardcard]

It's a bad news they have put finance guys as CEOs it's bad as Swan and Kranzich were not enough

One of Intel’s most successful CEOs was a finance guy. They just need someone who can lead and direct technical progress, regardless of previous education and role.

 

[igor_kavinski]

Can we move this discussion to it's own thread?

It's a here: https://forums.anandtech.com/thread...let-the-door-hit-you-on-your-way-out.2623948/

 

[GTracing]

It's a here: https://forums.anandtech.com/thread...let-the-door-hit-you-on-your-way-out.2623948/

It might be better to put it in the CPU subforum if the mods allow it. It won't be very visible there and I don't want to shut down discussion on it.

 

[Hitman928]

It might be better to put it in the CPU subforum if the mods allow it. It won't be very visible there and I don't want to shut down discussion on it.

It’s being discussed in the Intel 3Q earnings results thread.

 

[fastandfurious6]

it's joever!

 

[fastandfurious6]

Cope Ultra 2% !!!! (dancing for the stakeholders)

View attachment 108932

https://twitter.com/x/status/1843598034250412141

one last dance.... 🕺🪩

 

[511]

Well Pat took blame for Swan decision and left someone will take his credit or blame depending on 18A and Their products

 

[fastandfurious6]

intel will never recover from this, pat is leaving a sinking ship

 

[adroc_thurston]

intel will never recover from this, pat is leaving a sinking ship

He's not leaving, this is BoD cracking the whip and forcing him out.

 

[Kepler_L2]

So uhh, is that a plan for the next 5 years is done kinda retirement or an impending doom kinda retirement?

It's a "oopsie I bet the entire company on 18A and nobody wants to use it" kind of retirement.

 

[adroc_thurston]

It's a "oopsie I bet the entire company on 18A and nobody wants to use it" kind of retirement.

Because it's not very good

 

[511]

Because it's not very good

Its not 18A it's the capital Investment that he made to achieve it

 

[Saylick]

Its not 18A it's the capital Investment that he made to achieve it

I suppose the Board didn't like how that capital investment isn't getting recouped since they don't have as many 18A customers as they wanted. Fiduciary duty to shareholders, that kind of jazz.

 

[igor_kavinski]

It's a "oopsie I bet the entire company on 18A and nobody wants to use it" kind of retirement.

Probably some major customer bailed out after witnessing 18A health...

I mean, think about it. Why wouldn't Nvidia, AMD and Qualcomm get onboard since they badly need lower prices than what TSMC is offering?

 

[Saylick]

Probably some major customer bailed out after witnessing 18A health...

I mean, think about it. Why wouldn't Nvidia, AMD and Qualcomm get onboard since they badly need lower prices than what TSMC is offering?

The customers that would want 18A wouldn't care for it unless it had the performance to back it up. A customer like Nvidia isn't concerned about the price of the node, hence Jensen's comment about wholeheartedly supporting TSMC jacking up the node price since only they, not their competitors, would be able to afford it. Cutting edge, high performance and high profit parts require cutting edge nodes to give it that performance. No performance means no sales. No sales means no profit. No profit means no one buys the node.

 

[igor_kavinski]

The customers that would want 18A wouldn't care for it unless it had the performance to back it up.

This!

 

[mzocyteae]

A customer like Nvidia isn't concerned about the price of the node, hence Jensen's comment about wholeheartedly supporting TSMC jacking up the node price since only they, not their competitors, would be able to afford it. Cutting edge, high performance and high profit parts require cutting edge nodes to give it that performance. No performance means no sales. No sales means no profit. No profit means no one buys the node.

Then why NV picked cheap node and Apple doesn't pick n2 eagerly?

 

[Saylick]

Then why NV picked cheap node and Apple doesn't pick n2 eagerly?

You think N4P is cheap? It ain't cheap.

 

[adroc_thurston]

A customer like Nvidia isn't concerned about the price of the node

Yeah they are lol.
But everyone is.

 

[Saylick]

Yeah they are lol.
But everyone is.

If 18A offered 20% lower PPA than TSMC's equivalent but also 20% cheaper, Nvidia wouldn't use it. Nvidia's profit margins are so filthy that 18A could be 40% cheaper and I still wouldn't believe they'd use it if it didn't offer equivalent performance. With the AI market being so dang lucrative, I think Nvidia would gladly pay a premium on the node if it meant they hold onto their lead.

 

[gdansk]

Depends on the product. Ampere already showed Nvidia will use a cheap node when they know it'll be good enough.

But I somehow doubt 18A is good enough for big chips like Samsung's so-called 8nm.