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.

 

[511]

They better make it happen! I don't care if they have to take their server core and splice it into the consumer design.

Lion Cove doesn't have HT only Panther Cove has HT possibility we get NVL with HT

 

[igor_kavinski]

Page 211 - Question - Raptor Lake - Official Thread

Page 211 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

forums.anandtech.com

big.LITTLE optimizer, working for RPL at least. May work on MTL and ARL.

 

[Thibsie]

It's not crappy validation teams. At one point they canned the entire team. That's why it got delayed, and why it struggled.

Also on a device as complex as a modern high end CPU core, there's no such thing as pure copy and paste. It's not Windows Paint.

They used Photoshop content aware copy/paste 🤪

 

[Hulk]

Context switching latency between a Lion Cove core and a Skymont cluster is much higher. Also, the virtual thread in SMT is just an illusion. To the core, it's just two instruction streams in flight so the core will just crunch through those instructions as quickly as possible because SMT works by boosting resource utilization to the max, ensuring there is no idle time betweens loads, stores etc.

Intel probably has data showing how idle Lion Cove core resources get during certain workloads but of course they won't share that publicly because just like their stupid E-core marketing spiel, this time they are doing the world a "favor" by dropping HT and concentrating on ST performance which by the way still didn't get to be the best in the world. Really looking forward to them releasing a refresh with HT enabled.

So since SMT is essentially just using the extra width of the physical core to keep track of two threads, is there any thread scheduling priority even required for SMT/HT?

 

[igor_kavinski]

is there any thread scheduling priority even required for SMT/HT?

Priority is required to pin new threads to available real cores so they can have full access to the core's resources. Once the OS scheduler runs out of real cores, it will start assigning new threads to virtual cores and every thread on a real core having to live with the virtual thread will see some throughput loss due to cache contention and partitioning of core resources but overall, the idle moments of the individual core resources will be minimized resulting in higher total MT throughput.

 

[SiliconFly]

.

 

[Nothingness]

Ok, all this talk of x86 death is meaningless without some hard numbers .... which none of you have provided. Anecdotal evidence is silly. I don't understand for the life of me why people do it.

"George Burns smoked his entire live and lived to 100 years old, therefore smoking is good for you".

"I use a mac at work therefore x86 is doomed"

Here is a fact. 98% of corporate computers world wide use x86. The market is price conscious, and risk adverse. The insanely high amount of dependent applications on x86 presents a virtually insurmountable barrier to any other ISA. Shy of a federal LAW (which will never happen), x86 will remain dominant for at least another 10 years. My guess is 20 ..... or more.


... and you represent how much of the market again?

You're barking at the wrong tree. I've only given my personal point of view.

I didn't pretend macOS/Arm/WoA was gaining a significant momentum or that x86 is dying; all I can say is that *I* see many more mac in enterprise and that macOS on Arm fits *my* needs. For x86 death, I've been wanting it ever since I was confronted to it almost 30 years ago, but I'm not naive enough to think it will happen before my retirement (even though in my work environment I almost never use any x86 HW). Again a *personal* preference that I don't turn into a generality.

 

[Doug S]

The entire world is not going to port all their software to ARM just because Microsoft says so.

They would if Microsoft did what Apple did and said "we're dropping x86 and going ARM". Obviously I'm not suggesting that as a realistic scenario, and there would be a lot of outrage directed at Microsoft. In the end most people would eventually go along with it. The average consumers wouldn't even notice the difference unless theyhad some old games that didn't work under emulation.

Being "forced" is really the only reason the entire world ported Mac software to ARM. If instead of dropping x86 Apple continued selling and supporting both architectures then most developers wouldn't have bothered porting to ARM. If the x86 version would continue to work and Apple continued to sell new x86 Macs, why bother? Maybe some would have got on board once they saw ARM Macs outperforming x86 Macs, but even then it only matters if your application is performance sensitive. If you're Intuit for instance, I think you would consider porting a waste of time and continue building x86 only versions (because the ARM Macs could run that, while presumably even if this alternate history there would not be another version of Rosetta 2 that translated ARM to x86) because no one is saying "damn this tax application I have to use only once a year needs to run faster!"

 

[SiliconFly]

.

 

[OneEng2]

Almost of Top 100 US companies provide an employee with either a ARM MacBook or Windows laptop.

Amazon, Nvidia, Google, Microsoft, Netflix, Adobe to list some of top US companies.

Heck even the medium sized company in Australia which is not even on the AUS stock exchange provides MacBooks to some devs and executives.

AMD is not huge in the client space, especially OEM desktops and laptops. It’s been 6 months since Zen5 mobile launched and the majority of laptops are still from ASUS.


Some here need to get rid of the x86 only mindset. By the end of this decade the laptop landscape will change drastically. Qualcomm launched with a different variety of OEMs on day 1!!

Again, these are not statistics, but rather anecdotal evidence. "Some", "Either", "Not huge" .... surely you can see the difference.

In laptops, x86 currently holds over 90% of the market (statistic). What I pulled up in the US market was ~94.2% x86 vs 5.8% ARM. In the corporate market, it is MUCH lower (figure I found was 98% x86).

Overall, globally, yes, ARM will make big inroads to laptops; however, expect this to be primarily in developing countries and as a low cost alternative to x86, not an Apple Mac Book Pro. See this slide: https://www.tomshardware.com/laptop...ll-power-40-percent-of-notebooks-sold-in-2029

Also "Notebooks" vs "Laptops" should be noted. Sure, more mobile-ish PC devices will be ARM; however, more "Laptops", especially "Corporate Laptops" will continue to be x86.

I think Intel and AMD are going to be just fine on the x86 market, but your point is valid that some erosion of marketshare will occur over the next decade largely outside of corporate while even some corporate market will be lost.

It does not constitute the end of x68 though. That is just silly thinking at this point IMO.

They would if Microsoft did what Apple did and said "we're dropping x86 and going ARM". Obviously I'm not suggesting that as a realistic scenario, and there would be a lot of outrage directed at Microsoft. In the end most people would eventually go along with it. The average consumers wouldn't even notice the difference unless theyhad some old games that didn't work under emulation.

Being "forced" is really the only reason the entire world ported Mac software to ARM. If instead of dropping x86 Apple continued selling and supporting both architectures then most developers wouldn't have bothered porting to ARM. If the x86 version would continue to work and Apple continued to sell new x86 Macs, why bother? Maybe some would have got on board once they saw ARM Macs outperforming x86 Macs, but even then it only matters if your application is performance sensitive. If you're Intuit for instance, I think you would consider porting a waste of time and continue building x86 only versions (because the ARM Macs could run that, while presumably even if this alternate history there would not be another version of Rosetta 2 that translated ARM to x86) because no one is saying "damn this tax application I have to use only once a year needs to run faster!"

I suspect that it would spell the end of the road for Microsoft were they to do this. Already, Windows 11 is only 20% of the market while the very old Windows 10 is still 80%. Imagine how many hacks would pop up over night to keep 10 and 11 running in corporate? It would still be another 20 years IMO before x86 dropped below 50% even in the worst imaginable circumstances.

 

[Hulk]

One issue for software vendors is that there are so many applications that have "topped out" or nearly so in terms of evolution. The bread and butter applications like spreadsheets, word processors, database, presentation, web browsing, mail clients, vector illustration, photo editing, and others are in many cases on their 20th plus version. For example, I started with Coreldraw at version 3. By version 10 or 11 it was nearly what it is today and now we're on version 24. Even relatively new applications like DAW's and video editors are quite advanced these days. All of the action with new software seems to revolve around AI and games.

So how do software developers continue to sell software in which a large percentage of the user base sees no need to upgrade?

1. Don't allow software to be moved from one computer to another. Moving to a new computer and you have to repurchase the software. This is of course what MS does with OEM versions of Windows and Office. This would be pretty annoying for expensive software.

2. Don't sell standalone versions and force subscriber based licenses. We, as consumers hate this and will go to almost any means to avoid it. If that means using an inferior application that is not subscriber based then so be it. We'll deal with the inferior application or someone will come out with a good alternative. The market is brutal in this regard. Adobe is the 800lb gorilla with Photoshop and they are throwing their weight around in a big way with subscriptions. Much as I love Photoshop, I'll move to another editor before I go subscription. I think subcriber only models are going to find enormous resistance.

Or, the good old standby, lobby and beg Microsoft to release a new version of Window that requires a new codebase, or just build some BS into it that won't allow older applications to run.

I don't know where this is going but the market will eventually work it out. We'll vote with out money.

 

[igor_kavinski]

Microsoft has an easy way of washing their hands off of x86. Once reasonably powerful ARM options become available, they can just opensource x86 compatible Win32 API and let the community shoulder the burden of keeping legacy software working.Then the reborn Microsoft can focus on Windows on ARM exclusively. AMD is probably on board. Only one left behind would be Intel. They may have 5 years to a decade to keep selling x86 compatible CPUs. But once the newest stuff is only available on Windows on ARM and most of the population except diehards are weaned off of x86, Intel will have no choice but to choose between ARM or RISC-V.

One thing some people may forget is that Microsoft has Visual Studio. They simply ditch the x86 version of Visual Studio and all their various languages (C#, ASP.NET etc.) and current and future business software developers will have no choice but to recompile their software with Visual Studio ARM edition.

 

[RNR_Forte]

I apologize to Intel. They put all they can on Lion Cove and the marvelous Skymont.

 

[poke01]

It does not constitute the end of x68 though. That is just silly thinking at this point IMO.

true. x86 won't end anytime soon if ever. But alternatives will arrive, thats point i'm trying to make. Lets see 2025/2026 is the years I think to make inroads from others

 

[Hulk]

As we know MS has a heck of a time these days getting users to move from one version to the next because the version they are on just works.
This isn't like moving from Windows 3.0 to 3.1, where one was pretty bad and the other one pretty good.
Or the 32bit move to Windows 95.
Or the move to XP.
Or Windows 7.
Having been on pretty much every version of Windows I think the major revisions were 3.1>95>XP>7. 1992 to 2012
So there you have 4 major releases in 20 years. From a 16 bit barely hiding DOS to full fledged 64 bit Windows with plug-and-play kind of being reality.

Now let's see what happened from 2012 to today. Windows 8>8.1>10>11 over a period of 12 years and counting. Started with 64bit Windows, still on 64bit Windows. Not a lot really happened other than MS really screwing up the GUI with Windows 8 and slowly walking all of that nonsense back. I doubt the kernal has really changed.

My point is there really isn't a big Windows feature we're all waiting for that will get us to upgrade. Not like moving from 16 to 32 bits, or 32 bits to 64 bits. They're pushing Cortana but it's not the Cortana we want, the one we want is the one in Halo!

 

[511]

Daniel have God on his side but still have bad luck.

Lion cove performance: Cb24 st: 225pts

Link

 

[techjunkie123]

Link

Here's a video with the record breaking lion cove 225 pts cb 24 run:

 

[511]

Here's a video with the record breaking lion cove 225 pts cb 24 run:

You didn't post the OG version -100 points for you
🤪

 

[OneEng2]

true. x86 won't end anytime soon if ever. But alternatives will arrive, thats point i'm trying to make. Lets see 2025/2026 is the years I think to make inroads from others

Alternatives will indeed arrive (and already have). I don't disagree that this is where things are heading, only that there is quite some time before x86 will be in danger of being supplanted ..... at least in corporate machines.

There are just too many apps and IT dependencies .... and training, etc, etc that need to be changed over.

I think that in consumer laptops, things will change earlier ... but there will still likely be a pretty steep resistance to changing from x86. My own personal cost to change would be unbearable.

 

[511]

LENOVO 83KF - Geekbench

Benchmark results for a LENOVO 83KF with an Intel Core Ultra 7 255H processor.

browser.geekbench.com

 

[SiliconFly]

.

 

[igor_kavinski]

LENOVO 83KF - Geekbench

Benchmark results for a LENOVO 83KF with an Intel Core Ultra 7 255H processor.

browser.geekbench.com

View attachment 113835

Nice uplift over 155H: https://browser.geekbench.com/v6/cpu/compare/9281202?baseline=9622999

 

[MarkizSchnitzel]

How expensive would it be for enterprise to switch to ARM? Who would pay for it? Would a Linux option become more cost effective and more desirable at that point?

Or the governments? They can barely maintain a semblance of support and good working order as is, and are relying on software decades old. This would be a prime chance for nepotism, corruption and clientelism.

 

[511]

what would you gain by switching to ARM ?

Absolutely nothing

 

[RNR_Forte]

My apologies to Intel and AMD. My sources know all but they do not would like create a war with AMD and Intel.