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.

 

[biostud]

I threw in towel AND THUS SOLD or returned on any 13th or 14th Gen part because of stability and degradation issues. SO never really tested it,
I have a 7800X3D right now.

But if they have a 12 P core on a single ring bus Raptor Lake and it has stability issues fixed (I would think given new die or otherwise Intel will not make it), I am for sure a buyer. If it has the 8 + 16 RPL die stability and degradation issues, a hard pass despite me wanting such a product.

Would you trust Intel enough to buy such a 12P processor at launch? Or how many months would you wait?

 

[Wolverine2349]

Would you trust Intel enough to buy such a 12P processor at launch? Or how many months would you wait?

I will play that by ear. I think I would trust it at launch as long as it's determined that the issue is with the current stepping and not a design flaw in Raptor Lake itself.

Cause Alder Lake stepping are reliable and stable also on same 10nm node.

If there is some flaw with cache or ring structure of RPL (have heard rumors there may be and not just a stepping issue) and it is not stepping than no unless intel makes it Alder Lake based. Those I suppose its possible those flaws are based on the current die or they could be based on Raptor Cove cores and the ring and cache not sure. If its the latter its a hard pass.

Not sure what to do. Given its coming out in 1 year, hard to wait a few months. If it was out like now then yes I would wiat a few minutes. Hope to have more data for a good informed decision by then given its tardy release date.

 

[ondma]

Yep. If any reviewers are using some special settings in benchmarks that casual users don't understand or able to replicate, then it amounts to cheating.

Its not cheating really, but they should make clear they are using some special settings.

 

[511]

Reviewer using XMP they should compare JEDEC as well cause freaking 90% of users run it

 

[Doug S]

Reviewer using XMP they should compare JEDEC as well cause freaking 90% of users run it

Maybe they need two results, one is "this is the performance typical users who mostly use defaults will see" and "this is the best you can get if you perform the full list of optimizations/tweaks listed in the footnotes".

It is really no different than if they overclocked the CPU by 500 MHz in their results. Just like core parking, buying faster RAM and tweaking it, and so forth, that's just another optimization to get more performance, right? But I have a feeling more people would find that to be "cheating" than the stuff they're currently doing. Not sure why.

 

[dullard]

Maybe they need two results, one is "this is the performance typical users who mostly use defaults will see" and "this is the best you can get if you perform the full list of optimizations/tweaks listed in the footnotes".

Exactly. All good reviews do this. Spec memory/clocks/settings (which is what almost all users will see when they buy a Dell, HP, Lenovo, or similar). Then max everything (which throws money and power consumption concerns out the window).

 

[jdubs03]

Hot off the press:

Intel Core Ultra 9 285K, the flagship Arrow Lake-CPU spotted on Geekbench with 5.7 GHz clock - VideoCardz.com

Core Ultra 9 285K finally on Geekbench The next-gen desktop flagship is almost here. Intel is expected to unveil its new desktop series in a few weeks. The development process is advanced, and most board partners already have access to nearly final silicon known as Qualification Samples. These...

videocardz.com

Based on the chart within, ST is about 11% higher than the 14900K and MT is about 10% higher.

 

[Det0x]

*already posted*

As a comparison, this is my OC'ed 9950X

 

[DokiDoki]

*already posted*

As a comparison, this is my OC'ed 9950X
View attachment 105867

Bleurgh...you cannot even beat the competition with a ~300 MHz advantage in the most commonly used tasks from the end-user perspective.

ASUS System Product Name vs ASUS System Product Name - Geekbench

browser.geekbench.com

 

[cebri1]

So 11% faster than the 14900K? Seems off.

edit: sorry, already mentioned.

 

[H433x0n]

There’s some really good news in these results. If you dig into the subtests, ARL gets wins in text processing and HTML5. It’s only real big losses are object detection and background blur both of which are accelerated by AVX512.

So if you go by just the int performance, ARL looks promising against Zen 5.

 

[poke01]

So 11% faster than the 14900K? Seems off.

why? Its supposed be higher in ST, lacks HT(increases ST) and is on a much better node.

 

[cebri1]

why? Its supposed be higher in ST, lacks HT(increases ST) and is on a much better node.

If you take into account the IPC increase and the clock regression should be under 10%. People were expecting close to 3-5% improvement.

 

[coercitiv]

Sinners rejoice, the E-core voltage rail deliverance is finally upon us!

https://twitter.com/x/status/1826072744120955299

PS: in case anyone is confused, Asus managed to leak Intel Z890 footage in an article meant to support the AMD x870e chipset launch.

 

[SiliconFly]

-

 

[Abwx]

Yours is overclocked. Normal 9950X will be 3.5% slower than Core Ultra 9 285K.

This change nothing, 14900K and 9950X score 3236 and 3427 in ST respectively, both using stock speed RAM at 5600, this 285K GB submission use 6400 RAM and 5.7GHz ST frequency, so the 9950X is certainly not 3.5% slower in ST at stock RAM speeds.

 

[511]

This change nothing, 14900K and 9950X score 3236 and 3427 in ST respectively, both using stock speed RAM at 5600, this 285K GB submission use 6400 RAM and 5.7GHz ST frequency, so the 9950X is certainly not 3.5% slower in ST at stock RAM speeds.

6400MT/s is the supposedly official speed for Ultra 9 285K,9950X is 5600 according to AMD so both running at STOCK

 

[Tup3x]

Hot off the press:

Intel Core Ultra 9 285K, the flagship Arrow Lake-CPU spotted on Geekbench with 5.7 GHz clock - VideoCardz.com

Core Ultra 9 285K finally on Geekbench The next-gen desktop flagship is almost here. Intel is expected to unveil its new desktop series in a few weeks. The development process is advanced, and most board partners already have access to nearly final silicon known as Qualification Samples. These...

videocardz.com

Based on the chart within, ST is about 11% higher than the 14900K and MT is about 10% higher.

Looks pretty nice. Now it all comes down to power usage.

 

[SiliconFly]

.

 

[TwistedAndy]

Also, there are some results for Geekbench 5. The P-core in Intel Core 285K matches the one in Apple M4:



That's not a fully fair comparison because of the Geekbench Windows tax, but it is pretty interesting.

 

[Det0x]

Also, there are some results for Geekbench 5. The P-core in Intel Core 285K matches the one in Apple M4:

View attachment 105879

That's not a fully fair comparison because of the Geekbench Windows tax, but it is pretty interesting.

Seems like the 285K does alittle worse in GB5 ST than GB6 ST in comparison against the same OC'ed 9950X (?)

ASUS System Product Name vs ASUS System Product Name - Geekbench

browser.geekbench.com

ASUS System Product Name vs ASUS System Product Name - Geekbench

browser.geekbench.com

 

[Abwx]

6400MT/s is the supposedly official speed for Ultra 9 285K,9950X is 5600 according to AMD so both running at STOCK

Supposedly...

And the submission was made at JEDEC lose timings for DDR 6400 you think.?.

Anyway even at 6400 it score a paltry 0.67% better than the 9950X at 5600.

It matters a lot. Looks like Zen5 isn't that good compared to ARL. Seems both are actually running at stock.

9950X run within 200W while ARL is at 250W, and Intel already made a reservation for 297W/329W PL2/PL4 in case 250W still falling short in a lot of benches, wich will be likely the case if we look at the 43118 pts CB R23 score at 250W.

 

[SiliconFly]

.

 

[DokiDoki]

Seems like the 285K does alittle worse in GB5 ST than GB6 ST in comparison against the same OC'ed 9950X (?)

Yawn...same integer score as your OC'd 9950X ES.

Next.

 

[SiliconFly]

.