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]

But the team behind Skymont shows that x64 isn't dead. "Throw more decoders at it bro, maybe it'll keep scaling." And lo, it did (so far).

They basically made an x86 Neoverse V3.

The main issue Intel has is Qualcomm shipping a few months earlier.

1Q earlier, really.

Anandtech has N3E for the compute tile - is that a typo?

Yeah, Hardwareluxx says N3b.
It's N3b.

 

[gdansk]

They basically made an x86 Neoverse V3.

Well I like it. Now put 8 in "Arrow Lake N" and sell it at cost.

 

[adroc_thurston]

Well I like it. Now put 8 in "Arrow Lake N" and sell it at cost.

Gotta wait for a usable in-house node for that. kek.

 

[del42sa]

Interestingly they put 8 ALU to x86 CPU ...

https://wccftech.com/intel-lunar-la...skymont-double-digit-ipc-new-thread-director/

 

[adroc_thurston]

Interestingly they put 8 ALU to x86 CPU ...

https://wccftech.com/intel-lunar-la...skymont-double-digit-ipc-new-thread-director/

Yeah, SKT is kinda, sorta x86 take on the likes of Neoverse V3/Cortex-X4.
Chungus decode, chungus rename, 8 ALU and have fun.
Dingus 4x128 SIMD too!

 

[H433x0n]

I'm super happy with the results. Lion Cove is definitively mid, Skymont exceeds expectations by a mile. Went from feeling bear-ish about Intel's future to optimistic about the next 2 years.

Intel definitely hangs onto the 1T performance crown for another 2 years.

 

[adroc_thurston]

Skymont exceeds expectations by a mile

It's good for a 12Q iteration but perf profile puts it around Z4c aka been-done-before.

 

[gdansk]

Lunar Lake is the only one rumored to have a fanless option so the choice is pretty much made for me. I think it'll be good enough to replace my M1 MBA (if it exists).

 

[adroc_thurston]

Lunar Lake is the only one rumored to have a fanless option so the choice is pretty much made for me. I think it'll be good enough to replace my M1 MBA (if it exists).

Why not just wait for a new MBA.
Unless you hate macOS like I do.

 

[H433x0n]

It's good for a 12Q iteration but perf profile puts it around Z4c aka been-done-before.

Huh? It's got better performance clock for clock and will also clock higher.

 

[poke01]

Lunar Lake is the only one rumored to have a fanless option so the choice is pretty much made for me. I think it'll be good enough to replace my M1 MBA (if it exists).

Funny thing is battery life is going to be similar between M1 and Lunar. It’s not going be an upgrade in that department

 

[adroc_thurston]

It's got better performance clock for clock

A few %% above GLC in specint is where Zen4 and bros dwell.

and will also clock higher.

Dingus on PHX2 goes to 3.7 and that's a mobile part.
Please.

 

[Hulk]

Does Lion Cove have HT? Anandtech seems to suggest yes, Tom's no.

 

[adroc_thurston]

Does Lion Cove have HT? Anandtech seems to suggest yes, Tom's no.

Client variant no.

 

[poke01]

I think for my laptop upgrade I’m going to wait till the holiday season. It’s either going to be a MacBook Air M3 or Lunar Lake Lenovo.

Depends on what gets revealed at WWDC next week. But for Windows folks only (good luck with Win 11 24H2), Lunar is great.

 

[TitanicFreak]

Does Lion Cove have HT? Anandtech seems to suggest yes, Tom's no.

It is optional. It can be added but it is removed in Lunar Lake for example.

 

[Ghostsonplanets]

Did he not even talk about Arrow lake or did I miss something ? (other than mentioning it before going on about Panther lake)

Guess I'll hit up the slides

Arrow Lake S time is on Innovation Days in September. Same for Battlemage dGPU.

 

[gdansk]

Unless you hate macOS like I do.

I upgraded to dual 4K monitors recently and still want my laptop screen.

Funny thing is battery life is going to be similar between M1 and Lunar. It’s not going be an upgrade in that department

I'm not too worried! If you're comparing it to M1 that's fantastic.

 

[Hulk]

This is a tough paragraph for me. HT IPC improved by 30%?

This Lion Cove architecture also aligns with performance increases, boasting a predicted double-digit bump in IPC over the older Redwood Cove generation. This uplift is noticed, especially in the betterment of its hyper-threading, whereby improved IPC by 30%, dynamic power efficiency improved by 20%, and previous technologies, in balancing, without increasing the core area, in a commitment of Intel to better performance, within existing physical constraints.

 

[majord]

Wow overwhelming. My personal take aways

(for Lion cove)
- Intel finally ditched the unified scheduler
-Finally moved to process agnostic/portable phy floorplan.

Considering these significant changes , Lion cove isn't bad.. I guess they've been honing this for a while now with the Mont's so it's too surprising . I am probably most surprised at the frequencies in the twitter (?) leak before given the changes, but where are the official numbers? is there an SKU chart? No regression on P core either speaks volumes for N3P , or intel's ability to scale frequency with this

Still confused overall though without seeing the SKU freq's and which have HT which Don't , etc.

Seems peak ST performance will be neck and neck for Zen 5 and Lion cove at the supposed frequencies?


The convergence in IPC and frequency capability of the Two cores, i'm starting to wonder if there's much point. How would a density optimised Lion cove core that tops out at ~4Ghz (yes, i.e like Zen c) compare to Skymont?


-50th edit; would LOVE to see a side by side full uARCH block diagram of Lion vs Sky , hopefully Chips n Cheese does them up soon based off the slides

 

[poke01]

I'm not too worried! If you're comparing it to M1 that's fantastic.

Yep, great see M1 level battery life in x86. It’s all in the design.

 

[gdansk]

This is a tough paragraph for me. HT IPC improved by 30%?

This Lion Cove architecture also aligns with performance increases, boasting a predicted double-digit bump in IPC over the older Redwood Cove generation. This uplift is noticed, especially in the betterment of its hyper-threading, whereby improved IPC by 30%, dynamic power efficiency improved by 20%, and previous technologies, in balancing, without increasing the core area, in a commitment of Intel to better performance, within existing physical constraints.

I couldn't make sense of it either but Saylick explained it

Page 327 - Discussion - Intel Meteor, Arrow, Lunar & Panther Lakes Discussion Threads

Page 327 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

 

[poke01]

I upgraded to dual 4K monitors recently and still want my laptop screen

lol, the bane of base Mx. limited I/O

 

[Ghostsonplanets]

Wait, I just realized: How TF will Intel sell Arrow Lake-U next year? Lunar Lake is straight up loads better and Skymont E core literally is faster than Redwood Cove P Core on ARL-U. Not even Intel 3 perf/W bump can save it.

From a consumer PoV, it makes no sense to choose such inferior SoC. Unless Intel prices it at mainstream/budget level.

 

[adroc_thurston]

How TF will Intel sell Arrow Lake-U next year?

That's the neat part. They basically won't.

Unless Intel prices it at mainstream/budget level.

RPL lives!