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

Tigerick · Aug 22, 2022

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.

Comparison of upcoming Intel's U-series CPU: Core Ultra 100U, Lunar Lake and Panther Lake

Model	Code-Name	Date	TDP	Node	Tiles	Main Tile	CPU	LP E-Core	LLC	GPU	Xe-cores
Core Ultra 100U	Meteor Lake	Q4 2023	15 - 57 W	Intel 4 + N5 + N6	4	tCPU	2P + 8E	2	12 MB	Intel Graphics	4
?	Lunar Lake	Q4 2024	17 - 30 W	N3B + N6	2	CPU + GPU & IMC	4P + 4E	0	12 MB	Arc	8
?	Panther Lake	Q1 2026 ?	?	Intel 18A + N3E	3	CPU + MC	4P + 8E	4	?	Arc	12

Comparison of die size of Each Tile of Meteor Lake, Arrow Lake, Lunar Lake and Panther Lake

	Meteor Lake	Arrow Lake (N3B)	Lunar Lake	Panther Lake
Platform	Mobile H/U Only	Desktop & Mobile H&HX	Mobile U Only	Mobile H
Process Node	Intel 4	TSMC N3B	TSMC N3B	Intel 18A
Date	Q4 2023	Desktop-Q4-2024 H&HX-Q1-2025	Q4 2024	Q1 2026 ?
Full Die	6P + 8P	8P + 16E	4P + 4E	4P + 8E
LLC	24 MB	36 MB ?	12 MB	?
tCPU	66.48
tGPU	44.45
SoC	96.77
IOE	44.45
Total	252.15

Intel Core Ultra 100 - Meteor Lake

As mentioned by Tomshardware, TSMC will manufacture the I/O, SoC, and GPU tiles. That means Intel will manufacture only the CPU and Foveros tiles. (Notably, Intel calls the I/O tile an 'I/O Expander,' hence the IOE moniker.)

csbin · Jan 9, 2025

ARL-S Game Over

https://twitter.com/x/status/1877506376550789594

511 · Jan 9, 2025

MoistOintment said:
Of course. We'll order a few hundred PTL-U Dell Pro's or whatever they're calling the Latitude 5000 series replacement. They'll be an improvement over the Core 100U's we're currently deploying, which are already more than sufficient for office work.

As for the quick replacement: I'm also doubtful. Maybe one or two PTL laptops in December to claim 2025 launch date metrics were met - but expect most PTL-H laptops to be announced / launched at next year's CES.

It's same amount of LNL imo around 2million PTL

MoistOintment said:
PTL-H is a replacement to ARL-H. PTL-U is a replacement to ARL-U. Packaging changes (improvements) don't change the market segments they're operating in.

Yup

DrMrLordX · Jan 10, 2025

csbin said:
ARL-S Game Over

Let's hope Dr. Su remembers to send both Intel co-CEOs "Thank you" cards for the OS update.

511 · Jan 10, 2025

Thanks Swan and whoever was with you on delivering meh Architecture of series of product (MTL/ARL) for

DAPUNISHER · Jan 10, 2025

csbin said:
ARL-S Game Over

https://twitter.com/x/status/1877506376550789594

Please refrain from posting content that trashes a vendor in that vendor's threads. This post was reported, and it is indeed flame bait. Posting this in an AMD thread is okay, as throwing some shade at the competition is expected.

Mod DAPUNISHER.

igor_kavinski · Jan 10, 2025

511 said:
Thanks Swan and whoever was with you on delivering meh Architecture of series of product (MTL/ARL) for

Pat should take responsibility for both. With his technical background, he should never have let MTL see the light of day. It was so easy to kill a mediocre product as soon as the first tapeout samples were in their hands and they found out that it would underperform. But instead, they went full steam ahead and delivered V2.0 of MTL, which was arguably much better but still had the basic teething issues with tiles. No matter what kind of mental gymnastics people play to blame Intel's current situation on Pat's predecessors, it's really Pat who has to take full responsibility because his job was to UNDO the damage, not create even more of a mess.

Hitman928 · Jan 10, 2025

igor_kavinski said:
Pat should take responsibility for both. With his technical background, he should never have let MTL see the light of day. It was so easy to kill a mediocre product as soon as the first tapeout samples were in their hands and they found out that it would underperform. But instead, they went full steam ahead and delivered V2.0 of MTL, which was arguably much better but still had the basic teething issues with tiles. No matter what kind of mental gymnastics people play to blame Intel's current situation on Pat's predecessors, it's really Pat who has to take full responsibility because his job was to UNDO the damage, not create even more of a mess.

I think Pat made some major mistakes while being CEO (he did good things too but the mistakes cost him his job), but MTL and even ARL are not on him. They were way too far along in development for him to make meaningful change with them. It also would not have been wise to cancel them. It may seem counter-intuitive, but it is almost always better to release something new, even if it under performs, as new goes a long way in the OEM market which is the main customer and lets you get real feedback which is very important, even when you know you will be underperforming. Products wise, Pat should be judged on the next gen that comes after this one in terms of his influence really being on the products.

511 · Jan 10, 2025

igor_kavinski said:
Pat should take responsibility for both. With his technical background, he should never have let MTL see the light of day. It was so easy to kill a mediocre product as soon as the first tapeout samples were in their hands and they found out that it would underperform. But instead, they went full steam ahead and delivered V2.0 of MTL, which was arguably much better but still had the basic teething issues with tiles. No matter what kind of mental gymnastics people play to blame Intel's current situation on Pat's predecessors, it's really Pat who has to take full responsibility because his job was to UNDO the damage, not create even more of a mess.

He fixed GNR lol otherwise it would have underperformed he fixed their freaking process that kranzich and Swan threw under the bus they would rather give TSMC Money than to fund Intel lmao if Swan had thrown some money at Intel Meteor Lake wouldn't have been horrible he fixed the most difficult issue also MTL 2.0 exists in term of ARL-U if you want to see Improvements

igor_kavinski · Jan 10, 2025

511 said:
also MTL 2.0 exists in term of ARL-U if you want to see Improvements

You can't be selective. How come ARL-S is not Pat's fault but ARL-U improvements are totally his doing?

Are you saying Pat cared more about the laptop market than desktop?

Oh gee, that explains everything!

Screwed Raptor Lake with via oxidation in the fabs to fast track MTL shipments. Then neglected to care about ARL-S because ARL-U was a definite improvement over the paltry MTL parts.

cannedlake240 · Jan 10, 2025

igor_kavinski said:
You can't be selective. How come ARL-S is not Pat's fault but ARL-U improvements are totally his doing?

Are you saying Pat cared more about the laptop market than desktop?

Oh gee, that explains everything!

Screwed Raptor Lake with via oxidation in the fabs to fast track MTL shipments. Then neglected to care about ARL-S because ARL-U was a definite improvement over the paltry MTL parts.

It's not being selective though? ARL-U is a "fixed" MTL-U 2+8 arriving a whole year later. It's not even a proper fix, just a compute tile swap that slightly improves perf/W, while broader MTL/ARL platform issues are still not addressed. This fix doesn't even apply to ARL since it doesn't have an Fmax problem. Truth is MTL/ARL have inherent flaws in the soc architecture that'd take a year or two to address, and by that point that's on NVL and PTL to solve those flaws

511 · Jan 10, 2025

igor_kavinski said:
You can't be selective. How come ARL-S is not Pat's fault but ARL-U improvements are totally his doing?

Cause Intel 3 never existed. GNR/SRF/MTL all were defined for original Intel 7nm which got scraped.
Pat made Intel 7nm+ and 7nm++ (Intel 4 and Intel 3). MTL was on Intel 4 but GNR/SRF moved to I3 and it is forward compatible with I4 and apparently I3 turned out to be good and they ported the MTL-U die to I3 as well to fill in the gap in their products and minimize cost issues due to TSMC you can think of it as an big refresh. they simply improved upon the process one such example in BEOL

igor_kavinski said:
Are you saying Pat cared more about the laptop market than desktop?

Oh gee, that explains everything!

Yes Desktop is low priority for them

igor_kavinski said:
Screwed Raptor Lake with via oxidation in the fabs to fast track MTL shipments. Then neglected to care about ARL-S because ARL-U was a definite improvement over the paltry MTL parts.

Oxidation issue is not a process issue just to be clear and it has nothing to do with fast tracking MTL cause the fabs (Arizona for the oxidation issue and Oregon/Ireland for Meteor Lake) are entirely different its more like an accident cause by someone's negligence whoever that was and as for last part you are most likely correct they are gaining +500 Mhz Boost clock and such high base clocks without raising power to the moon lol.

Intel Delivers Leading-Edge Foundry Node with Intel 3 Technology; on Path Back to Process Leadership

Editor’s Note: Welcome to the new Intel Foundry blog! We're launching this resource as a new way to peek inside our systems foundry for the AI era with some of the experts making it happen. We're thrilled to launch the blog with this exciting look at the Intel 3 node’s performance gains from...

community.intel.com

https://vlsi24.mapyourshow.com/mys_shared/vlsi24/handouts/T1-1_Hafez.pdf

dttprofessor · Jan 10, 2025

TSMC N3 delay》》intel MTL /ARW delay 1year.
Intel is destined to lose the desktop gaming market this year. Even if amd all 9000X products combined cannot sell 9800X3d, changing the new ARL of all tiles will not help. pat said that "all bets are on 18A", which does not only refer to silicon nodes, but also to products.

DavidC1 · Jan 10, 2025

igor_kavinski said:
Pat should take responsibility for both. With his technical background, he should never have let MTL see the light of day. It was so easy to kill a mediocre product as soon as the first tapeout samples were in their hands and they found out that it would underperform. But instead, they went full steam ahead and delivered V2.0 of MTL, which was arguably much better but still had the basic teething issues with tiles.

Processes are built upon the learnings of previous generation, which Meteorlake was basically a learning vehicle for it. Without it, neither Intel 3, or 18A would exist. This is a common mistake, which by now I would have hoped you learned from it. Only way for Meteorlake to not exist is for fabs to be completely thrown in the garbage by now.

Just like Intel's graphic driver development went full steam only after launch of their dGPU, despite having iGPU for almost 3 decades, only real world learnings matter in the end.

Arrowlake was supposed to launch BEFORE Lunarlake. And predecessor to Arrowlake is Meteorlake. Which means by the time Gelsinger got in, both were in pretty advanced stages. The only thing you can do is to prevent any further delays.

Back then when it was known as Intel 7nm, it was announced it was delayed at least 6 months, which meant they had to delay Meteorlake. Hence Raptorlake as the replacement.

DrMrLordX · Jan 10, 2025

igor_kavinski said:
Pat should take responsibility for both. With his technical background, he should never have let MTL see the light of day. It was so easy to kill a mediocre product as soon as the first tapeout samples were in their hands and they found out that it would underperform. But instead, they went full steam ahead and delivered V2.0 of MTL, which was arguably much better but still had the basic teething issues with tiles. No matter what kind of mental gymnastics people play to blame Intel's current situation on Pat's predecessors, it's really Pat who has to take full responsibility because his job was to UNDO the damage, not create even more of a mess.

Intel had nothing else. Also they did kill Meteor Lake-S which is where it would have been (apparently) quite bad. That got us Raptor Lake Refresh and see how well that worked out . . .

SiliconFly · Jan 11, 2025

He needs to make up his mind. Last year, he said moore’s law is dead. And now this:

Exclusive: Nvidia CEO says his AI chips are improving faster than Moore's Law

Nvidia CEO Jensen Huang says the performance of his company's AI chips is advancing faster than historical rates set by Moore's Law, the rubric that drove

techcrunch.com

igor_kavinski · Jan 11, 2025

SiliconFly said:
He needs to make up his mind. Last year, he said moore’s law is dead. And now this:

Dementia setting in. Pretty soon he's gonna need AI assistance.

511 · Jan 11, 2025

SiliconFly said:
He needs to make up his mind. Last year, he said moore’s law is dead. And now this:

View attachment 114735

Exclusive: Nvidia CEO says his AI chips are improving faster than Moore's Law

Nvidia CEO Jensen Huang says the performance of his company's AI chips is advancing faster than historical rates set by Moore's Law, the rubric that drove

techcrunch.com

Are you doubting Captain Jensen and his Nvenger Squad?

On a side note his 5090 was following Moore's law in flesh vs 4090 and he still says Moore's Law is Dead bruh is still relying on Moore's law and TSMC for that matter and he doesn't want to

igor_kavinski · Jan 11, 2025

511 said:
Are you doubting Captain Jensen and his Nvenger Squad?

View attachment 114749

Don't care about that unless he's gifting that to me and he supports it with the latest drivers till the last Kavinski on this planet

maddie · Jan 11, 2025

SiliconFly said:
He needs to make up his mind. Last year, he said moore’s law is dead. And now this:

View attachment 114735

Exclusive: Nvidia CEO says his AI chips are improving faster than Moore's Law

Nvidia CEO Jensen Huang says the performance of his company's AI chips is advancing faster than historical rates set by Moore's Law, the rubric that drove

techcrunch.com

He needs to do what he's doing.

It's us dummies who repeat what he says reverently that is the problem. If a little intelligence and skepticism is used occasionally we'll be fine.

poke01 · Jan 11, 2025

Why do people take CEO marketing seriously??

Lots of CEOs say stupid or silly things it’s literally their job to defend their company from whatever

Saylick · Jan 12, 2025

poke01 said:
Why do people take CEO marketing seriously??

Lots of CEOs say stupid or silly things it’s literally their job to defend their company from whatever

They take his words seriously because he happened to be selling shovels during a gold rush. In America, we happen to obsess over the rich and successful as if being rich was a virtue.

poke01 · Jan 12, 2025

Saylick said:
They take his words seriously because he happened to be selling shovels during a gold rush. In America, we happen to obsess over the rich and successful as if being rich was a virtue.

its not just Amercian thing, its worldwide. Its a human thing. Anyway I don't get CEO worship, either from Nvidia fans, or AMD fans. I seen this countless times here and elsewhere.

Markfw · Jan 12, 2025

poke01 said:
its not just Amercian thing, its worldwide. Its a human thing. Anyway I don't get CEO worship, either from Nvidia fans, or AMD fans. I seen this countless times here and elsewhere.

You missed also using Intel fans. Its across all companies.

SiliconFly · Jan 12, 2025

Markfw said:
You missed also using Intel fans. Its across all companies.

Holthaus is the best. As good as Bob Swan. She's gonna take Intel where it's never been!

Nothingness · Jan 12, 2025

poke01 said:
its not just Amercian thing, its worldwide. Its a human thing. Anyway I don't get CEO worship, either from Nvidia fans, or AMD fans. I seen this countless times here and elsewhere.

In my country being rich makes many people jealous and dubious of how they got rich.

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

Senior member

Attachments

Senior member

Golden Member

Lifer

Golden Member

Super Moderator CPU Forum Mod and Elite Member

Lifer

Diamond Member

Golden Member

Lifer

Senior member

Golden Member

Member

Golden Member

Lifer

Golden Member

Lifer

Golden Member

Lifer

Diamond Member

Diamond Member

Diamond Member

Diamond Member

Moderator Emeritus, Elite Member

Golden Member

Diamond Member