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.

 

[adroc_thurston]

Lunar Lake-U

Lunar Lake is an -M, which is tablet.

Memory is different thus they are not related at all, no follow up, Lunar Lake is a one off

indeed.

 

[mikk]

I'm sorry, but Anandtech has spoken. Holthaus is incorrect. There is absolutely no way that an ultra-low power 4+4 Panther Lake-U can be a successor to an ultra-low power 4+4 Lunar Lake-U. Memory is different thus they are not related at all, no follow up, Lunar Lake is a one off. See below for proof (And this is just from the first page of a search).

Razor Lake-M maybe.

 

[SiliconFly]

.

 

[SiliconFly]

.

 

[511]

True. I myself posted the same saying LNL is a one off.

But according to Intel co-CEO Holthaus, PTL-H has more similarities to LNL than ARL-H. Not sure exactly what she means by that, but it has to mean something cos she's Intel co-CEO who oversees PTL-H directly.

My take is, PTL-H may not share many similarities with ARL-H.

Well the only thing PTL /ARL share is the upgradable RAM/Soldered Ram and no MOP
PTL and LNL share many similarities
> SLC
> Quad Cluster LPE Cores
> Everything into one tile except the GPU

 

[dullard]

Well the only thing PTL /ARL share is the upgradable RAM/Soldered Ram and no MOP
PTL and LNL share many similarities
> SLC
> Quad Cluster LPE Cores
> Everything into one tile except the GPU

PTL-U / LNL also are more focused on iGPU and NPU than just pure CPU power. And PTL-U / LNL have similar power levels (15 W vs 17 W due to the memory on LNL). And similar target market segments. So, therefore Panther Lake has nothing to do with the one-off Lunar Lake.

 

[SiliconFly]

.

 

[Joe NYC]

Intel co-CEO Michelle Johnston Holthaus just reiterated on X/Twitter what she said during the CES keynote, that Panther Lake is a follow up to Lunar Lake (not ARL-H).

Maybe in some spiritual form, but Gelsinger reiterated that Lunar Lake is a one off, with no direct successor.

 

[gdansk]

It doesn't matter if its successor is spiritual. It'll probably be good enough...

But LNL was seemingly on the right path so I had hoped its successor was more LNL but better.

 

[DKR]

Maybe in some spiritual form, but Gelsinger reiterated that Lunar Lake is a one off, with no direct successor.

I believe it's more of a comment on Memory on Package. That's very bad for Intel's margins and also affects the OEM's profit and flexibility. so that will not be repeated. Everything else in LNL likely comes to PTL - I think that's what MJH means when wrote that post in X.

 

[The Hardcard]

Maybe in some spiritual form, but Gelsinger reiterated that Lunar Lake is a one off, with no direct successor.

Then he got bounced, so…

While I think it was a mistake that he got fired, I think he was making a mistake by not following up LNL. Maybe that part is getting reversed.

EDIT: I mean the whole point of ending his era was to change some of his plans, right? Why not keep him if everything he said will still be true?

 

[igor_kavinski]

EDIT: I mean the whole point of ending his era was to change some of his plans, right? Why not keep him if everything he said will still be true?

Seeing how bad Arrow Lake turned out and that he killed Royal Core and Beast Lake, I don't think he was PAYING attention to any consumer CPU other than with the express intent of trying to funnel any money he could from them into the process/fab side. He had NO client plans. Good riddance.

 

[DavidC1]

Seeing how bad Arrow Lake turned out and that he killed Royal Core and Beast Lake, I don't think he was PAYING attention to any consumer CPU other than with the express intent of trying to funnel any money he could from them into the process/fab side. He had NO client plans. Good riddance.

Well, since the BoD has been known to make questionable decisions, and that development take long time, you can't say this with any certainty.

Clearly he made mistakes, and one big one is over-investing during the covid era, almost making you think if they did that knowing the lockdowns would persist eternally, and in that case the revenue case would have worked.

Once that failed, the rest of the decisions are explained by the fallout of drastically reduced revenue.

This is beside the massive toxic culture that has existed in Intel for a long time. Like someone said, Intel is a different company. They have incredible internal sabotaging and competitions within the company. It would require overhauling 3 decades of culture rot, which is a daunting task even if the CEO was the best you could get.

Neither Lisa Su nor Jensen Huang would have been able to fix this.

 

[511]

Well, since the BoD has been known to make questionable decisions, and that development take long time, you can't say this with any certainty.

Clearly he made mistakes, and one big one is over-investing during the covid era, almost making you think if they did that knowing the lockdowns would persist eternally, and in that case the revenue case would have worked.

Once that failed, the rest of the decisions are explained by the fallout of drastically reduced revenue.

This is beside the massive toxic culture that has existed in Intel for a long time. Like someone said, Intel is a different company. They have incredible internal sabotaging and competitions within the company. It would require overhauling 3 decades of culture rot, which is a daunting task even if the CEO was the best you could get.

Neither Lisa Su nor Jensen Huang would have been able to fix this.

Definitely not an easy task but it's easy if a person can just clean the house and leave

 

[511]

Seeing how bad Arrow Lake turned out and that he killed Royal Core and Beast Lake, I don't think he was PAYING attention to any consumer CPU other than with the express intent of trying to funnel any money he could from them into the process/fab side. He had NO client plans. Good riddance.

I have heard Raichu and Bionic Squash tweet it was not feasible the area cost was too much and the MT/mm2 was bad as well

 

[Thunder 57]

Well, since the BoD has been known to make questionable decisions, and that development take long time, you can't say this with any certainty.

Clearly he made mistakes, and one big one is over-investing during the covid era, almost making you think if they did that knowing the lockdowns would persist eternally, and in that case the revenue case would have worked.

Once that failed, the rest of the decisions are explained by the fallout of drastically reduced revenue.

This is beside the massive toxic culture that has existed in Intel for a long time. Like someone said, Intel is a different company. They have incredible internal sabotaging and competitions within the company. It would require overhauling 3 decades of culture rot, which is a daunting task even if the CEO was the best you could get.

Neither Lisa Su nor Jensen Huang would have been able to fix this.

Probably why they supposedly have a hard time finding people who wanto to be the CEO.

 

[511]

Probably why they supposedly have a hard time finding people who wanto to be the CEO.

I think the issues is they treat you very expendable and they want results in short term if that's the case it's never going to improve

 

[511]

Promised Copimum

 

[gdansk]

Promised Copimum
View attachment 114470

Which reviewer config? CB 2024 1T shows 140+ in most reviews. Based on this chart I'm supposed to expect 210?

 

[DrMrLordX]

They did: https://www.anandtech.com/show/13405/intel-10nm-cannon-lake-and-core-i3-8121u-deep-dive-review (enhanced version of this 10nm process was later renamed to Intel 7 because Intel insists their 10nm is as good as TSMC N7)

Intel 10nm, 10nm+, 10SF, and 10ESF/Intel 7 are not 7nm nodes. N7, N7p, N7+, and N6 aren't 7nm nodes either.

 

[desrever]

Which reviewer config? CB 2024 1T shows 140+ in most reviews. Based on this chart I'm supposed to expect 210?

did any reviewer test on Windows 11 24H2 because thats what I assume the baseline is from?

 

[gdansk]

did any reviewer test on Windows 11 24H2 because thats what I assume the baseline is from?

No because the reviewer guide told them not to (yet).

 

[cannedlake240]

PTL-U / LNL also are more focused on iGPU and NPU than just pure CPU power. And PTL-U / LNL have similar power levels (15 W vs 17 W due to the memory on LNL). And similar target market segments. So, therefore Panther Lake has nothing to do with the one-off Lunar Lake.

PTL-U iGP is a puny 4Xe3 config on Intel 3. If it was a direct LNL successor they wouldn't have split the igpu and instead doubled down on reducing soc, idle power usage. PTL from rumors sounds like it actually regresses from LNL a bit in that regard. Intel doesn't have the right mindset and culture to pursue Apple level efficiency because they aren't in the mobile business

 

[511]

PTL-U iGP is a puny 4Xe3 config on Intel 3. If it was a direct LNL successor they wouldn't have split the igpu and instead doubled down on reducing soc, idle power usage. PTL from rumors sounds like it actually regresses from LNL a bit in that regard. Intel doesn't have the right mindset and culture to pursue Apple level efficiency because they aren't in the mobile business

PTL-U is a replacement for ARL-U/MTL-U for cheaper market there is no reason for cost adder on such inexpensive devices.These sell for $700-800

 

[511]

also MTL-U vs ARL-U the difference is big for a refresh