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.

 

[poke01]

oh come on this isn't 2012 anymore.

? Still happens today. Take a good look at any OEM.

 

[adroc_thurston]

Still happens today. Take a good look at any OEM.

They offer piles of different gaming(tm) laptops aimed at different segments of the market?

 

[poke01]

They offer piles of different gaming(tm) laptops aimed at different segments of the market?

I’ll narrow it down. The Framework Strix Halo 385 desktop is cheaper than their FW laptop 13 with a AI 7 350.

Many such cases where mini PCs are much cheaper than laptops.

 

[adroc_thurston]

I’ll narrow it down. The Framework Strix Halo 385 desktop is cheaper than their FW laptop 13 with a AI 7 350.

Framework is a lolcow meme, pretend they do not exist.

Many such cases where mini PCs are much cheaper than laptops.

all the halo NUCs start like like 1.5 kilobuck.

 

[fastandfurious6]

what a fail (Halo)

framework miniPC has a waitlist since it got announced

AMD is bottlenecked by TSMC capacity (apple renting whole factories lol)

 

[inquiss]

framework miniPC has a waitlist since it got announced

AMD is bottlenecked by TSMC capacity (apple renting whole factories lol)

AMD isn't bottlenecked by TSMC

 

[poke01]

all the halo NUCs start like like 1.5 kilobuck.

And halo laptops will be more expensive for less specs than the halo NUCs.

You can already see this with the HP halo laptop. Laptops are higher volume and higher margins for OEMs and AMD, Intel.

 

[adroc_thurston]

And halo laptops will be more expensive for less specs than the halo NUCs.

They're more expensive because they're expensive laptops, not because they have halo inside.
Again, barebones NUCs with stxH start at like 1.5 kilobuck.
That's bananas expensive.

 

[ToTTenTranz]

Intel released a video yesterday about Panther Lake's iGPU:

They specifically namedrop handhelds. I wonder if we're getting a MSI Claw with Panther Lake as one of the first PTL devices out there.

 

[CouncilorIrissa]

PTL gets Xe3 IP, but will be sold under Battlemage branding.

https://videocardz.com/newz/intel-updates-gpu-roadmap-panther-lakes-graphics-confirmed-as-b-series-xe3p-listed-for-next-arc-family

They've lost the plot lol

 

[511]

PTL gets Xe3 IP, but will be sold under Battlemage branding.

https://videocardz.com/newz/intel-updates-gpu-roadmap-panther-lakes-graphics-confirmed-as-b-series-xe3p-listed-for-next-arc-family

They've lost the plot lol

Outsourcing to AI

 

[poke01]

PTL gets Xe3 IP, but will be sold under Battlemage branding.

https://videocardz.com/newz/intel-updates-gpu-roadmap-panther-lakes-graphics-confirmed-as-b-series-xe3p-listed-for-next-arc-family

They've lost the plot lol

I don’t get this. Now I really want to see 3D mark results time spy and Steel nomad 4K and cyberpunk benchmarks

 

[ToTTenTranz]

PTL gets Xe3 IP, but will be sold under Battlemage branding.

https://videocardz.com/newz/intel-updates-gpu-roadmap-panther-lakes-graphics-confirmed-as-b-series-xe3p-listed-for-next-arc-family

They've lost the plot lol

Does it matter at all whether they're calling it "Arc" or "Arc-B"?
This is probably happening because Xe3 discrete GPUs are still far away and they don't want to Osborne their current and future Battlemage lineup.


Besides, videocardz' table is wrong. Arrow Lake uses an Alchemist Xe LPG GPU, not a Battlemage Xe2 like the one in Lunar Lake. Intel is already mixing up two GPU architectures within mobile processors under the same branding. And yet, performance and capabilities are similar so most people don't care.

 

[CouncilorIrissa]

I don’t get this. Now I really want to see 3D mark results time spy and Steel nomad 4K and cyberpunk benchmark

https://videocardz.com/newz/intel-details-xe3-gpu-architecture-for-panther-lake-up-to-12-xe-cores-and-50-performance-vs-lunar-lake

You'll be waiting for actual performance figures for a while I guess.

 

[511]

50% faster than LNL like i said sadly bottlenecked by memory

 

[CouncilorIrissa]

Does it matter at all whether they're calling it "Arc" or "Arc-B"?
This is probably happening because Xe3 discrete GPUs are still far away and they don't want to Osborne their current and future Battlemage lineup.

It does, because Xe3 is supposedly a much more capable IP that shouldn't have to carry BMG's baggage (CPU overhead was fixed, but the damage has been done).

 

[poke01]

https://videocardz.com/newz/intel-details-xe3-gpu-architecture-for-panther-lake-up-to-12-xe-cores-and-50-performance-vs-lunar-lake

You'll be waiting for actual performance figures for a while I guess.

So like what’s new standard here?

It’s underwhelming so far.

 

[poke01]

50% faster than LNL like i said sadly bottlenecked by memory

It’s not bottlenecked by memory. There’s barely any core improvement.

No wonder it’s under Battlemage still.

Edit: maybe I’ll just wait for tests.

 

[eek2121]

framework miniPC has a waitlist since it got announced

AMD is bottlenecked by TSMC capacity (apple renting whole factories lol)

Only the top tier has a wait list.

 

[511]

It’s not bottlenecked by memory. There’s barely any core improvement.

No wonder it’s under Battlemage still

there is improvement you can see it in the micros

 

[CouncilorIrissa]

It’s not bottlenecked by memory. There’s barely any core improvement.

No wonder it’s under Battlemage still.

Edit: maybe I’ll just wait for tests.

 

[WCCF-HMS]

Page 878 - Discussion - Intel Meteor, Arrow, Lunar & Panther Lakes + WCL Discussion Threads

Page 878 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

This isn't Xe2 vs Xe3. It's Xe2 (Arv 140V) with the power tuning patch on MSI Claw.

 

[DavidC1]

Who said there were no core improvements on Cougar Cove? I think Adroc was one of them.

The front end has been reworked to deliver a steadier instruction flow, while the scheduler issues work to the execution units with fewer stalls. Internal structures such as the dispatch and allocation queues have been slightly widened to balance throughput and energy use. Together these adjustments yield roughly five to ten percent higher performance per clock at the same frequency.

The earlier leaks saying 5-8% were right.

Darkmont improves:
-Branch prediction
-Dynamic Prefetcher controls
-Bigger Nanocode coverage
-Better memory disambiguation

Pantherlake also finally balances it so more power is given to GPU rather than CPU. This will improve standing compared to competition. Previous architectures would often give too much power to CPU, starving the GPU core.

 

[ToTTenTranz]

It does, because Xe3 is supposedly a much more capable IP that shouldn't have to carry BMG's baggage (CPU overhead was fixed, but the damage has been done).

It doesn't because ~99% of the people using Intel graphics aren't using an Intel dGPU.
Heck, the vast majority of people using a modern Intel GPU for gaming aren't using an Intel dGPU, either. They're using a Xe1 140T or a Xe2 140V.
Intel kept the iGPU Xe2's branding under A-series despite being architecturally similar to dGPU B-series, and now they're doing the same with Xe3 under B-series.

50% faster than LNL like i said sadly bottlenecked by memory

There's a whopping 16MB L2 in there meaning they increased the L2 per core by 50%, and then it can access up to 18MB L3 on the Compute Tile.





Plus, the NPU can also access the L3. Although Intel doesn't mention this, it probably means Panther Lake could efficiently offload the upscaler to the NPU, unlike AMD's SoCs.

 

[poke01]

Overall, PTL looks great. These laptops will sell very well