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

[Tigerick]

Wildcat Lake (WCL) Specs

Intel Wildcat Lake (WCL) is upcoming mobile SoC replacing Raptor Lake-U. 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 Q1 2026.

		Intel Raptor Lake U	Intel Wildcat Lake 15W?	Intel Lunar Lake		Intel Panther Lake 4+0+4
Launch Date		Q1-2024	Q2-2026	Q3-2024		Q1-2026
Model		Intel 150U	Intel Core 7	Core Ultra 7 268V		Core Ultra 7 365
Dies		2	2	2		3
Node		Intel 7 + ?	Intel 18-A + TSMC N6	TSMC N3B + N6		Intel 18-A + Intel 3 + TSMC N6
CPU		2 P-core + 8 E-cores	2 P-core + 4 LP E-cores	4 P-core + 4 LP E-cores		4 P-core + 4 LP E-cores
Threads		12	6	8		8
Max Clock		5.4 GHz	?	5 GHz		4.8 GHz
L3 Cache		12 MB		12 MB		12 MB
TDP		15 - 55 W	15 W ?	17 - 37 W		25 - 55 W
Memory		128-bit LPDDR5-5200	64-bit LPDDR5	128-bit LPDDR5x-8533		128-bit LPDDR5x-7467
Size		96 GB		32 GB		128 GB
Bandwidth				136 GB/s
GPU		Intel Graphics	Intel Graphics	Arc 140V		Intel Graphics
RT		No	No	YES		YES
EU / Xe		96 EU	2 Xe	8 Xe		4 Xe
Max Clock		1.3 GHz	?	2 GHz		2.5 GHz
NPU		GNA 3.0	18 TOPS	48 TOPS		49 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.

 

[ajsdkflsdjfio]

The whole "death of x86" argument is really missing the forest for the trees. Noone is seriously arguing that x86 will cease to exist anywhere in the near future. x86 will live on in some form or another for many decades to come.

Someone else in this thread said ARM was "only" 10% of the client laptop market....as if ARM going from 0% to 10% marketshare in just 4 years in one of x86's last (of 2) markets isn't fairly remarkable growth.

I think you are the one missing the forest for the trees. You do realize that the 10% client laptop market is due to apple alone right? There are no other viable competitors using ARM and there have been multiple attempts to bring ARM to pc including Qualcomm's recent attempt which have all ended up in complete failure.

People switched from x86 to ARM because Mac/MacOS itself changed to ARM. They also got a nice performance boost with it as well, but who's to say whether that's ARM or Apple's design team. Regardless, they could have gotten a 0% performance boost over contemporary x86 and still have gotten 5-10% of the laptop market to switch to ARM.

The problem isn't ARM taking over, it's Apple taking over with their chips or some other player like Nvidia even. But so far I don't see that happening either since apple mainly plays it's own game in the corner. They rapidly shifted their portion of the market to ARM but I don't see them converting a large portion of the market anytime soon.

Also, AMD and Intel laptop chips are closer than they ever have been to apple since the M-series chips first debuted and I don't see this gap widening as recent competition between Intel and AMD have spurred rapid innovation between the two in addition to the fact that both AMD and Intel seem to be putting more focus in laptop chips than ever before. I mean look at lunar lake, meteor lake, hawk point, strix point, strix point HALO. They all saw Apple's success with their SOC designs and are looking to replicate that success.

 

[igor_kavinski]

Few users reporting artifacts on ARL iGPU: https://www.overclock.net/posts/29408015/

 

[511]

Few users reporting artifacts on ARL iGPU: https://www.overclock.net/posts/29408015/

They are using OCd ram of 8200MT/s and it is normal at stock classic OC causing artifacts

 

[igor_kavinski]

They are using OCd ram of 8200MT/s and it is normal at stock classic OC causing artifacts

GPU isn't getting overclocked. Never heard of memory overclocking causing issues with a Ryzen APU. This is one more problem for Intel.

 

[CouncilorIrissa]

You do realsiy it is a bug in windows power plan which is causing this ona ASUS laptop? cause it is not even boosting to its peak

It's not a bug, it's intentional. Without limiting boost clocks LNL wouldn't have any battery life to boast about (other than when idling -- PMIC helps with that a lot)
It's reproducible on Lenovo as well.
And Acer laptops.

 

[511]

GPU isn't getting overclocked. Never heard of memory overclocking causing issues with a Ryzen APU. This is one more problem for Intel.

I don't think oc memory issues can be blamed on Manufacturers if it was stock it would be an issues it's not stock it's your own fault neither AMD/Nvidia or Intel will do anything regards to it it can be soem some driver problem as well cause.
Manufacture warrant is for stock settings

It's not a bug, it's intentional. Without limiting boost clocks LNL wouldn't have any battery life to boast about (other than when idling -- PMIC helps with that a lot)
It's reproducible on Lenovo as well.
And Acer laptops.

You can watch this he tested it unplugged even phoronix had issues with LNL

 

[CouncilorIrissa]

I don't think oc memory issues can be blamed on Manufacturers if it was stock it would be an issues it's not stock it's your own fault neither AMD/Nvidia or Intel will do anything regards to it or maybe some driver problem cause according to manufacture it's not their stock setting

You can watch this he tested it unplugged even phoronix had issues with LNL

Thanks for proving my point: on 1:24 he sets the power profile to High Performance, which is what I said in the earlier post.
The battery life tests are done on Balanced, but performance is measured on High Performance. Different amount of work done, different performance.

A quick sanity check: you can't have 15 hours of battery life from a 55Wh battery if your device boosts to 17-18w in 1t workloads (which is what will happen once you run a web browser, or Discord, or Slack, or any other Electron-based / PWA app), period.

 

[511]

Thanks for proving my point: on 1:24 he sets the power profile to High Performance, which is what I said in the earlier post.
The battery life tests are done on Balanced, but performance is measured on High Performance. Different amount of work done, different performance.

A quick sanity check: you can't have 15 hours of battery life from a 55Wh battery if your device boosts to 17-18w in 1t workloads (which is what will happen once you run a web browser, or Discord, or Slack, or any other Electron-based / PWA app), period.

You have to sustain 17W for a hour to drain a considerable amount for a few seconds it won't matter much as for high performance i didn't notice that it happened on linux as well with Phoronix this is certainly a bug imo unless someone officially confirms it

 

[CouncilorIrissa]

You have to sustain 17W for a hour to drain a considerable amount for a few seconds it won't matter much as for high performance i didn't notice that it happened on linux as well with Phoronix this is certainly a bug imo unless someone officially confirms it

You severely underestimate the amount of time web pages spend being re-rendered. They will keep your CPU busy.

 

[poke01]

Speedometer also seems to be very finicky even varying by +-10% based on the browser you are using. In the first place it seems to heavily favor apple even in scenarios where their CPUs are actually weaker than their competitors

This benchmark seems to like specific high IPC and high cache designs.

desktop raptor-lake and zen4 owners report and you see that there is clearly something different about MacOS that causes speedometer to perform better

Speedometer doesn’t favour any OS,
See 8 Elite Android scores , it’s on par with A18 Pro.

This was around the typical score I found for zen4 AMD users and it's still on par/weaker than my M1 Macbook air which has around a 10-20% weaker 1T performance and much slower ram among other things.

This is a Zen4 desktop with a very large L3 cache. Cache also plays a role but so do clocks.

Here’s Zen4 7700X which as higher clocks.

Desktop Zen5 scores even higher, especially if you tune it.

But this is irrelevant to the fact that these benchmarks themselves are flawed for a CPU to CPU comparison. Pugetbench is also heavily reliant upon the GPU and therefore will have its scores differ significantly even on the same CPU using different GPUs. With the M3 chip having around a 20% stronger GPU, the Puget bench scores you referenced aren't reliable.

This is the Photoshop benchmark, it barely uses the GPU. It’s more of a CPU benchmark.

I understand that, my point was that speedometer having a better result for meteor lake compared to Strix Point doesn't really give much creedence to the accuracy or usefulness of that benchmarking program. Zen5 mobile was obviously nerfed vs desktop, but so is meteor lake which is a trash and older product regardless. The HX 370 has around a 20-30% 1T performance lead over the 185H and is monolithic to boot.

Strix point doesn’t perform well in web benchmarks and it’s not the only benchmark to be behind in. Jetstream 2.0 is the same.


MTL 155H is better than Strix point HX 370 here. So the 185H being better in Speedometer 3.0 isn’t an anomaly.

 

[SiliconFly]

.

 

[511]

This just in:

Intel Core Ultra 9 285H Geekbench scores have leaked. And it beats AMD top-end mobile offerings (AMD Ryzen AI 9 HX 370 & HX 375) by a mile! https://videocardz.com/newz/intel-core-ultra-225h-255h-and-285h-arrow-lake-h-cpus-appear-on-geekbench And this is just the mainstream H series. The top-end HX series should totally blow the competition out of the water! Arrow Lake mobile series appears to be very strong!

Only if we knew the Power consumption hoping it's 45W

 

[SiliconFly]

.

 

[511]

Typically, H series has always been 45W (and HX 55W).

I meant the actual power consumption not the TDP which is strictly governed by PL1/PL2

 

[CouncilorIrissa]

Typically, H series has always been 45W (and HX 55W).

45W figure is kind of a meme.
Actual burst and sustained power is much higher in pretty much everything.

 

[511]

45W figure is kind of a meme.
Actual burst and sustained power is much higher in pretty much everything.

100% PL1 is the most ideal figure

 

[SiliconFly]

.

 

[511]

U9 185H at 45W

Alienware Alienware m16 R2 - Geekbench

Benchmark results for an Alienware Alienware m16 R2 with an Intel Core Ultra 9 185H processor.

browser.geekbench.com

 

[LightningZ71]

This just in:

Intel Core Ultra 9 285H Geekbench scores have leaked. And it beats AMD top-end mobile offerings (AMD Ryzen AI 9 HX 370 & HX 375) by a mile!

https://videocardz.com/newz/intel-core-ultra-225h-255h-and-285h-arrow-lake-h-cpus-appear-on-geekbench

And this is just the mainstream H series. The top-end HX series should totally blow the competition out of the water!

Arrow Lake mobile series appears to be very very strong!

I'm not shocked that it's beating Strix Point. That's effectively a desktop processor vs. a mobile first. It'll be interesting to see how it does against Fire Range.

 

[511]

I'm not shocked that it's beating Strix Point. That's effectively a desktop processor vs. a mobile first. It'll be interesting to see how it does against Fire Range.

It is 6+8 vs 16C/32T desktop chip ofc Fire Range is going to win

 

[LightningZ71]

Fire range should span from single CCD parts with as few as 6 cores to dual CCD parts with up to 16 cores. I'm looking forward to the test results. AMD has a variety of SKUs for customers with different needs.

 

[SiliconFly]

.

 

[511]

Fire range should span from single CCD parts with as few as 6 cores to dual CCD parts with up to 16 cores. I'm looking forward to the test results. AMD has a variety of SKUs for customers with different needs.

They will be up against ARL-HX in laptop i am pretty sure ARL is going to win due to the limited power/thermals

 

[SiliconFly]

.

 

[igor_kavinski]

Alleged Fire Range ES Geekbench AI ONNX CPU score

Mostly performing pretty well against 285K: https://browser.geekbench.com/ai/v1/compare/167394?baseline=169229

Roughly 30% slower than 9950X: https://browser.geekbench.com/ai/v1/compare/167394?baseline=167511