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.

 

[gaav87]

Well, it contains just the first page of the review.

you need to swap on bing every page ends with /1 /2 /3 etc.

"https://overclock3d.net/reviews/cpu_mainboard/intel-core-ultra-200s-cpu-review/6/" type this on bing then click the little arrow next to the link and click cached

Like this

Intel Core Ultra 200S CPU Review - OC3D

Aiming squarely at rectifying the problems of the recent Intel CPUs, the Core Ultra range are cool and efficient.

cc.bingj.com

 

[Thunder 57]

I was sort of laughing about the CB conspiracy theories that came up recently but maybe @Abwx was on to something. ARL looks amazing in CB. It seems to fall apart in everything else.

 

[gaav87]

I was sort of laughing about the CB conspiracy theories that came up recently but maybe @Abwx was on to something. ARL looks amazing in CB. It seems to fall apart in everything else.

Amazing ? its losing to 14900k and 9950x in R20

Intel Core Ultra 285K, 265K, and 245K CPU Review

Intel has fixed some BIG problems, but at what cost?

cc.bingj.com

 

[igor_kavinski]

Well, it contains just the first page of the review.

Did OC3D get a threatening call from their Intel handler?

"Take down that review! NOW! And release a statement tomorrow that you messed up by testing Arrow Lake improperly!".

OC3D: "Our main testing guy was on vacation and we hired this other guy not two days before and he last tested Athlon 64 when he was a teen but he didn't mention that on his resume and told us that he had experience reviewing 64-bit processors...".

 

[gaav87]

Did OC3D get a threatening call from their Intel handler?

"Take down that review! NOW! And release a statement tomorrow that you messed up by testing Arrow Lake improperly!".

OC3D: "Our main testing guy was on vacation and we hired this other guy not two days before and he last tested Athlon 64 when he was a teen but he didn't mention that on his resume and told us that he had experience reviewing 64-bit processors...".

Im reading whole review its horrible... i posted above how to read it all cached not just screenshots.

 

[Sunaiac]

Did OC3D get a threatening call from their Intel handler?

"Take down that review! NOW! And release a statement tomorrow that you messed up by testing Arrow Lake improperly!".

OC3D: "Our main testing guy was on vacation and we hired this other guy not two days before and he last tested Athlon 64 when he was a teen but he didn't mention that on his resume and told us that he had experience reviewing 64-bit processors...".

Well if he tested A64 he should feel like nothing much has changed with Intel still -25% perf for +25% power :whistling:

 

[Gideon]

Basically Admitting the design was wrong and CPU+IMC should have been in the same tile

Well that can't be the only reason. Zen apparently manages to do better, despite these being on separate dies (on a archaic packaging process)

 

[poke01]

I was sort of laughing about the CB conspiracy theories that came up recently but maybe @Abwx was on to something. ARL looks amazing in CB. It seems to fall apart in everything else.

It’s also amazing in Geekbench. But if we look deeper the 9950X is actually better in CB2024 for MT while using less power than the 285K.

My suspicion of it better than 9950X in ST in CB2024 is that it may use more power. Do we know the single thread power consumption at 5,7GHZ vs the 9950X?

 

[Abwx]

Amazing ? its losing to 14900k and 9950x in R20

Intel Core Ultra 285K, 265K, and 245K CPU Review

Intel has fixed some BIG problems, but at what cost?

cc.bingj.com

It doesnt, it s because those CPUs are on unlimited power in this review, actualy even in CB 2024 the 9950X is ahead of a 253W 14900K, or should i say a 275W since with a PL2 at 253W it still managed to pull 275W in Computerbase review.

And if you want to dig further look at the ST scores in CB R20/R23 and do the comparison with CB 2024.

AMD Ryzen 9 9900X und 9950X im Test: Benchmarks in neuen Anwendungstests

Ryzen 9 9950X & 9900X im Test: Benchmarks in neuen Anwendungstests / Intel-Instabilität und AGESA-Updates sind die (neue) Tagesordnung

www.computerbase.de

 

[gaav87]

It doesnt, it s because those CPUs are on unlimited power in this review, actualy even in CB 2024 the 9950X is ahead of a 253W 14900K, or should i say a 275W since with a PL2 at 253W it still managed to pull 275W in Computerbase review.

AMD Ryzen 9 9900X und 9950X im Test: Benchmarks in neuen Anwendungstests

Ryzen 9 9950X & 9900X im Test: Benchmarks in neuen Anwendungstests / Intel-Instabilität und AGESA-Updates sind die (neue) Tagesordnung

www.computerbase.de

Look at the power draw its 42W above 9950x

Intel Core Ultra 285K, 265K, and 245K CPU Review

Intel has fixed some BIG problems, but at what cost?

cc.bingj.com

 

[Abwx]

Look at the power draw its 42W above 9950x

Intel Core Ultra 285K, 265K, and 245K CPU Review

Intel has fixed some BIG problems, but at what cost?

cc.bingj.com

This review is not accurate, that s a full system power, beside they have the 9950X at a higher power than the 7950X, yet the latter has a 230W PPT while the former has a 200W PPT.

Also this would imply that the 14900K/KS are at 230W if the 9950X is at 200W, wich is impossible for those scores.

I edited my previous post, compare the ST scores in CB R20/23 to CB 2024,
i did so, Strix Point FI is quite ahead of LNL in R20/R23 and is quite behind in R 2024.

 

[poke01]

Re: Intel being 6% better in ST than the 9950X in CB2024, keep a look out for power consumption at 5.7GHz on a single core tomorrow.

The 9950X scores 139 at 5.7GHz while using 31 watts. Now if the 285K uses 6% or more power to deliver 6% more ST I don’t consider that a win.

Edit: it’s 6% not 8%.

 

[exquisitechar]

Re: Intel being 6% better in ST than the 9950X in CB2024, keep a look out for power consumption at 5.7GHz on a single core tomorrow.

The 9950X scores 139 at 5.7GHz while using 31 watts. Now if the 285K uses 6% or more power to deliver 6% more ST I don’t consider that a win.

Edit: it’s 6% not 8%.

6% more power for 6% higher ST performance is definitely a win.

 

[DavidC1]

Interesting to see some of his testing tools.

Steve is heavily implying that Arrow Lake uses more power from the motherboard connector and he hints that the power consumption figures in Intel's marketing materials don't take into account.

So not only Intel's own marketing materials disappoint, there's a possibility that it's still too optimistic and it may be a misleading result?

On top of that BSOD issues, platform instability, and varying performance from run to run? Why does a CPU need a matching software and OS update to perform like it was promised?

Maybe the Netburst comparison wasn't fit for Lion Cove but for the entire Arrowlake chip. Right now it reminds me of Prescott.

 

[gaav87]

So not only Intel's own marketing materials disappoint, there's a possibility that it's still too optimistic and it may be a misleading result?

On top of that BSOD issues, platform instability, and varying performance from run to run? Why does a CPU need a matching software and OS update to perform like it was promised?

Maybe the Netburst comparison wasn't fit for Lion Cove but for the entire Arrowlake chip. Right now it reminds me of Prescott.

They said 70-80W lower then 14900k it matches the OC3D review

 

[GTracing]

They said 70-80W lower then 14900k it matches the OC3D review

If OC3D is measuring power consumption using the 8-pin CPU cable then they wouldn't catch the higher power consumption.

 

[Hitman928]

So not only Intel's own marketing materials disappoint, there's a possibility that it's still too optimistic and it may be a misleading result?

On top of that BSOD issues, platform instability, and varying performance from run to run? Why does a CPU need a matching software and OS update to perform like it was promised?

Maybe the Netburst comparison wasn't fit for Lion Cove but for the entire Arrowlake chip. Right now it reminds me of Prescott.

TBF, we haven’t seen any real confirmation of the instability/crashing issues. Will be interesting to see if it’s mentioned by any reviewers tomorrow.

 

[Abwx]

They said 70-80W lower then 14900k it matches the OC3D review

Seriously, Computerbase has lower R20 scores for the 14900K/KS and they measure roughly 500W full system in Cinebench and 329W for the 7950X, beside the OCN review has 9% higher R20 score, wich point to an AIO cooling, if we are to trust their power numbers then RPL has as good perf/watt as the 7950X.

Intel Core i9-14900KS im Test: Anwendungs-Benchmarks, Leistungsaufnahme & Temperatur

Intel Core i9-14900KS im Test: Anwendungs-Benchmarks, Leistungsaufnahme & Temperatur / Testsystem und Testmethodik für Anwendungen

www.computerbase.de

 

[gaav87]

Seriously, Computerbase has lower R20 scores for the 14900K/KS and they measure roughly 500W full system in Cinebench and 329W for the 7950X, beside the OCN review has 9% higher R20 score, wich point to an AIO cooling, if we are to trust their power numbers then RPL has as good perf/watt as the 7950X.

Intel Core i9-14900KS im Test: Anwendungs-Benchmarks, Leistungsaufnahme & Temperatur

Intel Core i9-14900KS im Test: Anwendungs-Benchmarks, Leistungsaufnahme & Temperatur / Testsystem und Testmethodik für Anwendungen

www.computerbase.de

They have the test setup in the review i think at like page 4 or smt cba reading it again. Anyway huge copium even linus can't defend this.

 

[KompuKare]

Novalake will finally match raptor lake lmao

"And the starting bids for the Nova Lane hype-train are in!"

"First we have cannedlake240 starting bid of 'matches Raptor Lake'"

"Any other bids?"

 

[Hitman928]

This situation reminds me of a Key and Peele sketch in a gentlemen’s club where zen 5 is Peele and ARL is Key.

 

[Abwx]

They have the test setup in the review i think at like page 4 or smt cba reading it again. Anyway huge copium even linus can't defend this.

We ll see in 15H, Computerbase will have some power tests that can be trusted, for the rest their current bench suite is anemic quantity wise, there should be more numbers at Hardewareluxx.

 

[AcrosTinus]

So not only Intel's own marketing materials disappoint, there's a possibility that it's still too optimistic and it may be a misleading result?

On top of that BSOD issues, platform instability, and varying performance from run to run? Why does a CPU need a matching software and OS update to perform like it was promised?

Maybe the Netburst comparison wasn't fit for Lion Cove but for the entire Arrowlake chip. Right now it reminds me of Prescott.

I don't have the required knowledge to really know but the disaggregation of their chips spanning from mobile to low latency desktop does not work.

The desktop requires a dedicated approach not a unified one. AMD knows this and has been mastering this approach. If Intel can stay alive for 5 years, we might see the real tiles architecture optimized for gaming and low latency computing.

I just cannot believe that meteor lakes flaws were not corrected.
Welp, if this is really true I will be jumping on 24Core TR Zen5 or new package Zen6 mainstream.

 

[SiliconFly]

.

 

[Rheingold]

Steve is heavily implying that Arrow Lake uses more power from the motherboard connector

This was already discovered by der8auer two weeks ago, he talks about it here.