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.

 

[inf64]

I think there's a small difference between ES & final silicon.

Hope dies last.

 

[cebri1]

It’s because it’s a 16 in… wait, what?

 

[Hitman928]

View attachment 108381

It’s because it’s a 16 in… wait, what?

Again, that is just 1 element at play. Look at the below example for the Proart and Zehpyrus; same size screens, same CPUs, same battery size, very different battery life results.



It is not unreasonable to have CPUs in completely different laptops drawing the same amount of power, but the system as a whole has wildly different power consumption.

The CB results in JT’s review show the 28W limit is correctly in place, so pointing at system level consumption to try and prove the 28W limit isn’t working is just not good enough when direct performance measurement shows it is working and the difference in system level consumption is explainable.

Edit: it’s probably not a coincidence that the model showing high system power consumption in JT’s review is the same one showing significantly worse battery life in the above screenshot.

 

[coercitiv]

It’s because it’s a 16 in… wait, what?

Food for thought:

 

[cebri1]

Food for thought:
View attachment 108383
View attachment 108385

15W TDP vs 28W TDP, I’d say is very aligned.

 

[KompuKare]

Recent Geekbench 6 runs dont support the hammering part at all.

285K - Geekbench 6 CPU Search - Geekbench

265K - Geekbench 6 CPU Search - Geekbench

Don't forget that in the best/worst (take your pick) tradition of sensational "journalism" any time one product beats another by even 1-5% it is usually referred to as "stomps", or "destroys", or similar hyperbole.

 

[Hitman928]

15W TDP vs 28W TDP, I’d say is very aligned.

TDP is basically meaningless now. What matters is what the PL2/PL1 are set at. According to NBC, the Zenbook 14 with the 155h has a lower PL1 (20 W) than the Yoga with the 125u (29 W) but a higher PL2 (64 W vs 41 W). The big reason the Zenbook has such worse battery life is that it has a higher resolution, higher refresh rate, OLED display which will draw way more power than the IPS panel in the Yoga, despite the Yoga having a bigger screen size.

https://www.notebookcheck.net/Core-Ultra-5-125U-performance-debut-Lenovo-Yoga-7-2-in-1-16IML9-convertible-review.830675.0.html

https://www.notebookcheck.net/Asus-Zenbook-14-OLED-review-The-1-2-kg-subnotebook-with-120-Hz-OLED-and-Core-Ultra-7.805236.0.html

 

[poke01]

If it hasn’t been obvious outlets and YouTubers promote the latest and the current product they are reviewing in the best light possible unless of course the product is so bad they can’t do so.

That being said there a few decent outlets that test everything. So how will Lion Cove hammer Zen5? Probably only in ST and memory support even then most DIY users will pick the X3D parts and creators Intel.

 

[coercitiv]

15W TDP vs 28W TDP, I’d say is very aligned.

I'd say the days when Intel U chips had chipset on package while H chips did not are gone since MTL. AFAIK the SoCs are functionally the same, hence the difference in power under very light loads is only attributable to the rest of the system (components & firmware).

 

[511]

If it hasn’t been obvious outlets and YouTubers promote the latest and the current product they are reviewing in the best light possible unless of course the product is so bad they can’t do so.

That being said there a few decent outlets that test everything. So how will Lion Cove hammer Zen5? Probably only in ST and memory support even then most DIY users will pick the X3D parts and creators Intel.

Well the efficiency problem will be solved as well so it will be even difficult Choice to prioritise what now Unless you have a drop in mobo upgrade

 

[SiliconFly]

.

 

[gdansk]

As far as I can tell neither Arrow Lake nor Zen 5 have changed anything. Based on Geekbench they both look like very unimpressive improvements for typical PCs. And it took both far too long to deliver.

Even process parity with LNL wasn't enough to match the year old M3 in some ways. At this point it really does look like the ARM and Apple yearly cadence - afforded by the smartphone market - will win and remain on top.

 

[KompuKare]

When team red's advocates were spreading the *exact same* hyperbole for the past couple of years, it was okay. But now the tables have turned, it isn't okay anymore? Thats hilarious! Thats hyperbole.

Reading comprehension? Because I said no such thing - just that I have a very low opinion of what passes for tech "journalism".

 

[AcrosTinus]

Reading comprehension? Because I said no such thing - just that I have a very low opinion of what passes for tech "journalism".

Just a curious time and place to make that criticism...

 

[SiliconFly]

.

 

[DavidC1]

you missed @Josh128 post? https://forums.anandtech.com/thread...akes-discussion-threads.2606448/post-41306858

View attachment 108378

Here HX 370 has longer battery life. Different models so yet not a proper comparison, but more accurate than an usseless 14" vs 16"

Lunarlake system has 1800p 120Hz OLED display while Ryzen HX 370 system has 1200p 60Hz OLED display.

Lunarlake is a lot lower power but not enough to make up for that difference.

 

[Hitman928]

I'd be interested to see how LNL performs at 20 W or lower, especially in gaming. It probably can't run AAA games well, even it minimal settings, but for light or medium weight games, it should do well and I'm guessing nothing else can keep up with it at the lower power levels.

 

[Josh128]

Lunarlake system has 1800p 120Hz OLED display while Ryzen HX 370 system has 1200p 60Hz OLED display.

Lunarlake is a lot lower power but not enough to make up for that difference.

Precisely, and that was point-- to show how much the display impacts the battery life. Others were implying that I was making it up.

The chart I posted even shows the Strix system beating the Snapdragon X Lenovo system with 14.50 inch 16:10, 2944 x 1840 pixel 239 PPI, Capacitive, OLED,90 Hz display.

 

[SiliconFly]

.

 

[itsmydamnation]

Battlemage supports upscaling for ray-tracing perf using XeSS. Offers excellent quality (comparable to DLSS). But it still lacks FG. I think frame-gen uses less than half the gpu compute to generate a frame rather than rendering it. Intel did mention that it's coming out with its own FG a.k.a ExtraSS soon. But when it'll reach the masses and/or whether it'll get adopted by popular games is still a question.

Once they release it, LNL should be able to handle AAA titles at a good frame rate with normal settings.

You can use FSR 3.1 FG with XeSS on anything , XeSS is not as good as good DLSS 3.7 generally speaking, you might find specific situations but not overall, not in motion , its probably a bit better then FSR 3.1 upscale overall ( most games better some not). FSR 3.1 FG is basically the best FG so unless intel has something really good cooking I wouldn't bother re-inventing the wheel.

 

[DrMrLordX]

I thought you didn’t care about battery, there are outlets everywhere.

That was @Markfw not @MarkPost

 

[511]

As far as I can tell neither Arrow Lake nor Zen 5 have changed anything. Based on Geekbench they both look like very unimpressive improvements for typical PCs. And it took both far too long to deliver.

Even process parity with LNL wasn't enough to match the year old M3 in some ways. At this point it really does look like the ARM and Apple yearly cadence - afforded by the smartphone market - will win and remain on top.

The x86 duo has been focusing Clock Speed for decades and now Apple//ARM is following the suite with M1->M2->M3->M4 soon apple/Arm will hit the wall of clockspeed meanwhile Intel/AMD should focus on their ST Perf/ lower power levels LNL is a very nice step they need to keep improving it

 

[SiliconFly]

.

 

[Nothingness]

Well, in the grand scheme of things, those are all mostly ES. Now this looks like a QS. And it's killing it...

Intel Core Ultra 7 265K Shows Strong Multi-Core Performance In New Benchmark Leak: 16% Faster Than 14700K, Beats Ryzen 9 9950X & 14900KS Too

Latest benchmarks of Intel's Core Ultra 7 265K "Arrow Lake" CPU have leaked & showcase much better performance, even beating 9950X & 14900KS.

wccftech.com

And it says: "it's 8.4% faster than Ryzen 9 9950X" in multi-threading! And this is just a 265K.

It's pretty much clear now that ARL-S 285K is clearly the leader this gen. Both in ST & MT.

Have we reached the point where we take wccftech seriously? What about waiting for release? Or let's switch this to a "8.4% over 9950x!!!!!!11111" hype train thread. Or even 10% (or even more!) because it's a QS (which is not even proven) so final will go through the roof when released.

 

[cebri1]

Have we reached the point where we take wccftech seriously? What about waiting for release? Or let's switch this to a "8.4% over 9950x!!!!!!11111" hype train thread. Or even 10% (or even more!) because it's a QS (which is not even proven) so final will go through the roof when released.

I agree with you in principle, but this thread is thrash (like the other Intel threads) thanks to the the usual suspects. I think wccfftech has higher standards than most posters here.

Edit: The GB6 entry: https://browser.geekbench.com/v6/cpu/8030562