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]

Bleh, not even going to give those hacks a click.

You can always click this

 

[SiliconFly]

.

 

[igor_kavinski]

It should be well above 70% or even 80% by now.

The problem is product. Intel needs to show actual working 18A product to regain consumer and investor confidence and then ship said product within 6 months to at least their priority customers if they want to stay in the game.

 

[SiliconFly]

.

 

[igor_kavinski]

Hope they do a Panther Lake desktop refresh of Arrow Lake to fix the horrible latencies and I/O performance issues.

 

[DAPUNISHER]

Hope they do a Panther Lake desktop refresh of Arrow Lake to fix the horrible latencies and I/O performance issues.

Have they released the big arrow lake fix promised weeks ago? It was supposed to be the end of last month or beginning of this.

 

[igor_kavinski]

Have they released the big arrow lake fix promised weeks ago? It was supposed to be the end of last month or beginning of this.

Nothing for my mobo as of today

I'm suffering from task paralysis due to tons of ideas on benchmarking coz once I take out 12700K, don't want to put it together again just for some test.

 

[Win2012R2]

You can always benchmark the install time of Win2012R2...

 

[igor_kavinski]

You can always benchmark the install time of Win2012R2...

If you have an easy to run data intensive real world benchmark in mind, I'm all ears

 

[SiliconFly]

.

 

[Win2012R2]

If you have an easy to run data intensive real world benchmark in mind, I'm all ears

Sadly all I've got is proprietary code that I can't share

 

[FlameTail]

Intel 18A hits record 99% yield rate.

https://twitter.com/x/status/1864988793041723872

Take the news with a grain of salt.

 

[Hitman928]

Intel 18A hits record 99% yield rate.

https://twitter.com/x/status/1864988793041723872

Take the news with a grain of salt.

It’s a joke to make a point. Look at the die size he’s using.

 

[511]

It’s a joke to make a point. Look at the die size he’s using.

Same joke media is pulling with 800+ mm2 die 🤪

 

[Win2012R2]

Same joke media is pulling with 800+ mm2 die 🤪

But that's where the big money is and will be for some time - Nvidia Rubin, huge 1600 gbe switch silicon etc. Who is Intel going to get for small 18A chiplets - Apple?

 

[511]

But that's where the big money is and will be for some time - Nvidia Rubin, huge 1600 gbe switch silicon etc. Who is Intel going to get for small 18A chiplets - Apple?

Getting this Size to yield before HVM is impossible even for TSMC.
TSMC start with 100-120mm2 Apple A series as a lead vehicle and than yield goes up you can't expect a process that is not in HVM ready yet to do 800mm2 also the only fab that has problem with this size is Samsung not Intel (EMR/GNR/SRF is proof)

 

[Win2012R2]

Getting this Size to yield before HVM is impossible even for TSMC.

Yep, you know it and I know it, but the market wants magical customers like Nvidia, Broadcom that will allow Intel to capture some of that sweet AI money, so who is going to pay top dollar for the first smaller dies like Apple does for TSMC? So that's basically no serious big fab customers till when, 2027? Pat would not have lasted that long.

Frankly if 18A was really doing well then Intel would have been shouting about it from the rooftops.

 

[511]

Yep, you know it and I know it, but the market wants magical customers like Nvidia, Broadcom that will allow Intel to capture some of that sweet AI money, so who is going to pay top dollar for the first smaller dies like Apple does for TSMC? So that's basically no serious big fab customers till when, 2027? Pat would not have lasted that long.

It won't happen before 2026 even if some magic is to happen

Frankly if 18A was really doing well then Intel would have been shouting about it from the rooftops.

They are shouting 18A every conference call 😂

 

[Win2012R2]

They are shouting 18A every conference call 😂

Apologies, I meant to say - provide some real verifiable information, not making claims how great it is - lots of shouting indeed, seems like not a lot of substance, and if it was so good why fire Pat now? Maybe the yields are good - but at what price? Something rotten is clearly there, guess not long left to wait and find out.

 

[511]

Apologies, I meant to say - provide some real verifiable information, not making claims how great it is - lots of shouting indeed, seems like not a lot of substance, and if it was so good why fire Pat now? Maybe the yields are good - but at what price? Something rotten is clearly there, guess not long left to wait and find out.

Maybe but the board needs firing as well especially the yeary guy he has been at the board since the bean counter period begin

 

[Win2012R2]

Maybe but the board needs firing as well especially the yeary guy he has been at the board since the bean counter period begin

Totally agree, I actually think firing Pat was a big mistake - he should have fought this, gone to shareholders and get whole board fired.

 

[511]

Totally agree, I actually think firing Pat was a big mistake - he should have fought this, gone to shareholders and get whole board fired.

Well wish we could file a class action lawsuit against the board for dragging the share down 😂

 

[511]

If pat firing was a good thing stock wouldn't have gone down like it does for CEO's the market knows it is difficult to find someone to handle fhe mess Intel is

 

[OneEng2]

Considering those losses include 3 years worth of deferred tax assets (~$10B), and $billions more in impairment and accelerated depreciation, I don't see how it's physically possible they could report quarterly losses this high again in the next few quarters.

I agree that I don't expect their losses to be as big as last quarter where I concur they have brought in everything and the kitchen sink to make the future look better.

My concern is that the fundamentals of their strategy don't lead to a profitable business. You can't just keep buying 10bn, then 15bn, then 25bn new equipment every 18-24 months and then put up with the low yield rates while they ramp up only to be hit with the cycle again.... at least not if your intent is to pay it off with so few customers (or one customer being Intel).

Ahh yes, the fun of a bad financial report. You see that you're going to miss your numbers by a large margin, you decide to take ALL of your pain pills at once. You know that you're going to get butchered by the markets anyway, so you pull in all sorts of bad news to go in one dump. Then, in following quarters, you don't have all the bad stuff hanging over you, so any improvements look better in context...

Yep. I have done, and recommended on more than one occasion . Common in all industries.

The problem is product. Intel needs to show actual working 18A product to regain consumer and investor confidence and then ship said product within 6 months to at least their priority customers if they want to stay in the game.

Agree. Customers need certainty. This is why TSMC's more regimented approach is used vs. Intel's "no-holes-barred" approach to process advantage.

Yep, you know it and I know it, but the market wants magical customers like Nvidia, Broadcom that will allow Intel to capture some of that sweet AI money, so who is going to pay top dollar for the first smaller dies like Apple does for TSMC? So that's basically no serious big fab customers till when, 2027? Pat would not have lasted that long.

Frankly if 18A was really doing well then Intel would have been shouting about it from the rooftops.

This is sadly the tricky wicket that exists. The desktop/laptop (and mobile for that matter) markets can't contain the uber high cost of a large die on a new process. The markets that can only want a big die.

 

[MoistOintment]

so who is going to pay top dollar for the first smaller dies like Apple does for TSMC?

Intel Design is with PTL-U/P/H