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]

PTL will outship Qualcomm in 2026 for Windows laptops. That's for sure. Inertia.

But over the next few years? Intel is going to lose marketshare and have to drop prices to compete against Qualcomm. They're the lower tier compared to Qualcomm chips, which are significantly faster and more efficient.

Bait used to be believable

 

[511]

PTL will outship Qualcomm in 2026 for Windows laptops. That's for sure. Inertia.

But over the next few years? Intel is going to lose marketshare and have to drop prices to compete against Qualcomm. They're the lower tier compared to Qualcomm chips, which are significantly faster and more efficient.

Not happening tbh PTL-H 12Xe3 is a balanced config and they have cheaper PTL-U Which is the main volume and more cheaper and available than QCOM SKU.
If you see the GPU Benchmark You will say the opposite thay Intel will kill QCOM.
NVL is not a SUS as well AMD/Intel are in same boat in Client ST.

 

[adroc_thurston]

AMD/Intel are in same boat in Client ST.

Nope

 

[511]

Nope

Vs ARM Yes what do you expect for Zen 6 ST ?
I expect 20-24% improvement vs Zen 5

 

[Meteor Late]

Holy cow that's bad ST for 2026.

Qualcomm's upcoming Oyron Windows SoCs are going to destroy Intel.

I remember when people said Lunar Lake killed Qualcomm's WoA effort. I think Qualcomm is going to absolutely kill Intel in the next few years on Windows.

WoA needs to mature much more, people need to be able to run all of their apps without issues, also people want their devices to work, if there are no drivers for printers and other things, it's not going to take off.

 

[adroc_thurston]

ARM Yes what do you expect for Zen 6 ST ?

Idk somewhere there.

I expect 20-24% improvement vs Zen 5

25% poverty N3p parts and 35-40% proper N2p 48M L3 stuff.
If we take 2850pts as the baseline STX1/KRK1 .gb6 score, we'll get 3560 (kinda slow) and circa 4k which is good nuff.

 

[511]

Idk somewhere there.

25% poverty N3p parts and 35-40% proper N2p 48M L3 stuff.
If we take 2850pts as the baseline STX1/KRK1 .gb6 score, we'll get 3560 (kinda slow) and circa 4k which is good nuff.

40% Ain't happening for ST improvements

 

[adroc_thurston]

40% Ain't happening for ST improvements

Two shrinks, a tock and 3x the L3? Piss easy.
But that only applies to STX1 vs MDS1 hi, others get proportionally less juice.

 

[Nothingness]

Ha I missed the 40% hype train so much.

 

[adroc_thurston]

Ha I missed the 40% hype train so much.

It's 30%.
10% is the CCD freebie you can get now with something like 9955HX.

 

[Magio]

All this and then we'll get Zen 6%.

Also Zen6 will more meaningfully compete with Coyote Cove anyway, not Cougar Cove which won't be the lead mobile core (or not for long) by the time Zen 6 mobile rolls out.

 

[adroc_thurston]

Also Zen6 will more meaningfully compete with Coyote Cove anyway

CYC is like 15% more perf

 

[Magio]

CYC is like 15% more perf

Rumors are 10/15% IPC but it's also gonna be on N2/P which even Intel optimists agree will offer moe raw performance than 18A. So 20 to 30% total perf gain over PTL in ST is my guess.

 

[adroc_thurston]

Rumors are 10/15% IPC but it's also gonna be on N2/P which even Intel optimists agree will offer moe raw performance than 18A.

Yeah but Intel physdes teams are lolcow stuff.

So 20 to 30% total perf gain over PTL in ST is my guess

It's 15% PTL-H to NVL-H, both 4+8.

 

[poke01]

Qualcomm ain’t getting any meaningful market share with those pathetic iGPUs.

No Nvidia option or any big iGPU. Why would any sane person buy a 18 core cpu and pair it with a weak iGPU?

They still don’t get it. Panther lake despite its okay cpu is still a better buy thanks to its iGPU.

 

[Magio]

It's 15% PTL-H to NVL-H, both 4+8.

If that's the case (in ST) despite new core + N2P I want everyone to hand apologies to 18A.

Qualcomm ain’t getting any meaningful market share with those pathetic iGPUs.

No Nvidia option or any big iGPU. Why would any sane person buy a 18 core cpu and pair it with a weak iGPU?

They still don’t get it. Panther lake despite its okay cpu is still a better buy thanks to its iGPU.

And having to deal with Windows on ARM (and no Linux support, for the 8 people it matters to (I'm one of them)).

 

[adroc_thurston]

Qualcomm ain’t getting any meaningful market share with those pathetic iGPUs.

Irrelevant metric.
QC sucks at building a product stack and building a platform that OEMs can swallow, cost-wise.

No Nvidia option or any big iGPU. Why would any sane person buy a 18 core cpu and pair it with a weak iGPU?

Me.
But WoA is dinky and Linux support on QC SoCs even with Glymur moving to full proper ACPI is shaky.

They still don’t get it. Panther lake despite its okay cpu is still a better buy thanks to its iGPU.

PTL is ok because it's being shipped at platform costs OEMs can swallow.

 

[adroc_thurston]

If that's the case (in ST) despite new core + N2P I want everyone to hand apologies to 18A.

18A isn't the issue. Intel CPU IP flat out sucks.

And having to deal with Windows on ARM (and no Linux support, for the 8 people it matters to (I'm one of them)).

Glymur should be better, but knowing QC.

 

[Doug S]

PTL will outship Qualcomm in 2026 for Windows laptops. That's for sure. Inertia.

But over the next few years? Intel is going to lose marketshare and have to drop prices to compete against Qualcomm. They're the lower tier compared to Qualcomm chips, which are significantly faster and more efficient.

But they are x86, and that's still the only first class citizen for Windows. Windows on ARM is like a ball and chain around Qualcomm's ankles that will limit them forever.

 

[poke01]

QC sucks at building a product stack and building a platform that OEMs can swallow, cost-wise.

Ehh. NUVIA got wasted at Qualcomm. Mid hardware.
They make SKUs only for benchmarks, not for actual real world cases.

 

[adroc_thurston]

Ehh. NUVIA got wasted at Qualcomm. Mid hardware.

The hardware (CPU/fabric/etc) is good.

They make SKUs only for benchmarks, not for actual real world cases.

Yes the stack and the platform both suck.
Glymur being 192b to ship in a single MoP SKU is just a waste of effort.

 

[poke01]

Glymur being 192b to ship in a single MoP SKU is just a waste of effort

Good luck selling that in 2026

 

[adroc_thurston]

Good luck selling that in 2026

It has a single laptop win iirc.

 

[mvprod123]

Ehh. NUVIA got wasted at Qualcomm. Mid hardware.
They make SKUs only for benchmarks, not for actual real world cases.

Gerard Williams III was very keen to make server chips, but as we can see, almost five years have passed since the acquisition of Nuvia, and not a single server product with Oryon architecture has been made.

 

[adroc_thurston]

Gerard Williams III was very keen to make server chips, but as we can see, almost five years have passed since the acquisition of Nuvia, and not a single server product with Oryon architecture has been made.

QC has a server BU and they talked about it a bit during that Saudi(?) announcement.