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.

 

[jpiniero]

Being Intel it could easily be a lot of hot air with nothing really said.

 

[uzzi38]

The biggest variant. I'm not talking about Igor, I'm talking about the Intel slide. And mobile MTL is limited to 6+8 not 6+16.

Never mind this post I misread.

 

[nicalandia]

Wrong thread.

 

[dullard]

Friday's a good day to dump bad news?

I'll take back what I said about details coming soon. Looks like the webinar was postponed to Jan 12 due to Covid. https://www.intel.com/content/www/u...tform-roadmap-investor-webinar.html#gs.kqvqe2

But, it is now scheduled for a Thursday. Does that suddenly mean it must be good news since it isn't on a Friday? Or does the fact that they delayed the meeting override the fact that it isn't on a Friday. I get confused regarding conspiracy theories and which rule takes precedence. Either way, feel free to resume the Meteor Lake is delayed past the end of 2023 rumors again.

 

[jpiniero]

I'll take back what I said about details coming soon. Looks like the webinar was postponed to Jan 12 due to Covid. https://www.intel.com/content/www/u...tform-roadmap-investor-webinar.html#gs.kqvqe2

Guessing they got cold feet. The new date btw is approx 2 weeks from Q4 earnings report so they definately won't say anything interesting now.

 

[Hitman928]

Guessing they got cold feet. The new date btw is approx 2 weeks from Q4 earnings report so they definately won't say anything interesting now.

A little strange you would need to postpone a webinar due to covid policies. Unless a bunch of people on the production team all got Covid?

 

[Hulk]

I'll take back what I said about details coming soon. Looks like the webinar was postponed to Jan 12 due to Covid. https://www.intel.com/content/www/u...tform-roadmap-investor-webinar.html#gs.kqvqe2

But, it is now scheduled for a Thursday. Does that suddenly mean it must be good news since it isn't on a Friday? Or does the fact that they delayed the meeting override the fact that it isn't on a Friday. I get confused regarding conspiracy theories and which rule takes precedence. Either way, feel free to resume the Meteor Lake is delayed past the end of 2023 rumors again.

Yes now it's good news. MTL must be ahead of schedule and early samples are hitting 8GHz @ 105 Watts.




Yes, sarcasm!

 

[Doug S]

A little strange you would need to postpone a webinar due to covid policies. Unless a bunch of people on the production team all got Covid?

And I'm sure scheduling it for AFTER the holidays when people have been flying around all over the country will be just fine, covid wise.

 

[Exist50]

A little strange you would need to postpone a webinar due to covid policies. Unless a bunch of people on the production team all got Covid?

Or just one of the key speakers. It's supposed to be live, after all.

 

[nicalandia]

No MTL Before 2024. Fight Me

 

[DrMrLordX]

Does that suddenly mean it must be good news since it isn't on a Friday?

God only knows. Why wouldn't they just release some slides or text if they can't do the full presentation? If it's THAT important.

 

[Hulk]

No MTL Before 2024. Fight Me

The fact that we have a Raptor refresh is a good indication that there is some trepidation with Intel 4. Rocket Lake part deux. Well not really, it's a not a half-baked new fill in, but you know what I mean. Meteor can only work on Intel 4 so Intel is in a holding pattern until that happens.

 

[igor_kavinski]

Maybe investors are demanding that Intel come clean regarding Intel 4 progress. If true, they will tell us all the benefits Intel 4 brings and then give some not-so-great news about it and quickly move on to how great 13900KS will be and what we can expect to see with Raptor Lake Refresh and cheering all around when they confirm Z790 will accept the new CPUs. I'm guessing cache will see an increase again.

 

[Joe NYC]

God only knows. Why wouldn't they just release some slides or text if they can't do the full presentation? If it's THAT important.

The info and spin must be delivered together.

 

[DrMrLordX]

The info and spin must be delivered together.

Guess they can't spin with a sore throat and cough.

 

[Exist50]

God only knows. Why wouldn't they just release some slides or text if they can't do the full presentation? If it's THAT important.

Well if the information was extremely time sensitive, you'd figure they would, right? Feels like people are really making a mountain out of a molehill here...

 

[BorisTheBlade82]

No MTL Before 2024. Fight Me

I am not ready for giving up MTL in 23. I am expecting an IceLake kind of thing in late H2 with only a few OEM designs and not being better than the predecessor in every way. Nevertheless from a design strategy it is the right way to go for Intel IMHO.

 

[witeken]

No MTL Before 2024. Fight Me

The production stepping of MTL has already been taped out. Intel literally said Intel 4 production has started.

 

[BorisTheBlade82]

The production stepping of MTL has already been taped out. Intel literally said Intel 4 production has started.

Even if - MTL is so much more than just an Intel4 CPU chiplet.
Everything needs to come together for this first version, while successors will be much less prone for delays.

 

[igor_kavinski]

It boggles the mind that with all their R&D budget, Intel didn't prioritize testing the waters of chiplet based CPU dies. They must have had monolithic dies planned for the next 10 to 15 years before AMD burst their complacent bubble with Ryzen.

 

[nicalandia]

The production stepping of MTL has already been taped out. Intel literally said Intel 4 production has started.

We all know that. But MTL is much more than Intel4

At first MTL was to be released after Alder Lake in late 2022, but it was not going to be ready and Intel designed Raptor Lake and MTL was moved to late 2023...But now they will have Raptor Lake Refresh so there is that....

 

[Tigerick]

	Process Node	Transistors	Die Size		Execution Units	ALU	RT units	TGP	Graphics Clock	FP32 (TFlops)
A370M	N6	7.2 B	157 mm2	8 Xe Cores	128 EU	1024 ALU	8	35 - 50W	1550 MHz	4.2 TF
GT2	N5	?	?	4 Xe Cores	64 EU	512 ALU	?	?	?	?
GT3	N5	?	?	8 Xe Cores	128 EU	1024 ALU	?	?	?	?
AMD PHX	N4	25 B	178 mm2	6 WGP	768 SP	1536 ALU	NA	35-54W	3 GHz	9.2 TF

Since Kepler leaks the tGPU info on upcoming Meteor Lake, I have compiled the comparison chart of tGPU and A370M, make me think how much power MTL's tGPU needed, any ideas?

 

[BorisTheBlade82]

It boggles the mind that with all their R&D budget, Intel didn't prioritize testing the waters of chiplet based CPU dies. They must have had monolithic dies planned for the next 10 to 15 years before AMD burst their complacent bubble with Ryzen.

They had KabyLake-R, Lakefield and they were supposed to have SPR up and running by now. So in theory more than enough playground for chiplets. They admittedly wanted to leapfrog AMD by leaving out an interconnect via organic package and this may still work out if AMD does not come to terms.

 

[Hulk]

Intel does have some experience putting more than one die on a package with the P4 D, C2D quad, etc..

 

[mikk]

	Process Node	Transistors	Die Size		Execution Units	ALU	RT units	TGP	Graphics Clock	FP32 (TFlops)
A370M	N6	7.2 B	157 mm2	8 Xe Cores	128 EU	1024 ALU	8	35 - 50W	1550 MHz	4.2 TF
GT2	N5	?	?	4 Xe Cores	64 EU	512 ALU	?	?	?	?
GT3	N5	?	?	8 Xe Cores	128 EU	1024 ALU	?	?	?	?

Since Kepler leaks the tGPU info on upcoming Meteor Lake, I have compiled the comparison chart of tGPU and A370M, make me think how much power MTL's tGPU needed, any ideas?

There is no indication of a GT3 for Meteor Lake, github only has GT2 entries for mobile. It makes no sense, otherwise we would have to assume MTL only comes with 64EUs against 96 EUs on the previous generation. Kepler also claimed RDNA3 ships with a broken Shader Pre-Fetching which AMD denied. Kepler is not a good source. He claims something without any source and people believe in him.