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

Page 259 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Tigerick

Senior member
Apr 1, 2022
676
558
106






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

ModelCode-NameDateTDPNodeTilesMain TileCPULP E-CoreLLCGPUXe-cores
Core Ultra 100UMeteor LakeQ4 202315 - 57 WIntel 4 + N5 + N64tCPU2P + 8E212 MBIntel Graphics4
?Lunar LakeQ4 202417 - 30 WN3B + N62CPU + GPU & IMC4P + 4E08 MBArc8
?Panther LakeQ1 2026 ??Intel 18A + N3E3CPU + MC4P + 8E4?Arc12



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

Meteor LakeArrow Lake (20A)Arrow Lake (N3B)Arrow Lake Refresh (N3B)Lunar LakePanther Lake
PlatformMobile H/U OnlyDesktop OnlyDesktop & Mobile H&HXDesktop OnlyMobile U OnlyMobile H
Process NodeIntel 4Intel 20ATSMC N3BTSMC N3BTSMC N3BIntel 18A
DateQ4 2023Q1 2025 ?Desktop-Q4-2024
H&HX-Q1-2025
Q4 2025 ?Q4 2024Q1 2026 ?
Full Die6P + 8P6P + 8E ?8P + 16E8P + 32E4P + 4E4P + 8E
LLC24 MB24 MB ?36 MB ??8 MB?
tCPU66.48
tGPU44.45
SoC96.77
IOE44.45
Total252.15



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.)

 

Attachments

  • PantherLake.png
    283.5 KB · Views: 23,965
  • LNL.png
    881.8 KB · Views: 25,436
Last edited:

adroc_thurston

Platinum Member
Jul 2, 2023
2,335
3,232
96
There is no architecture-specific restriction on the size of the L2 in this approach.
Yes there are, only so many ways/sets possible until power goes boom.
Zen5 may take the overall performance crown, but not by much I guess. The difference should be in single digit. I'm thinking like 5% maximum.
You're funny I'll give you that.
 

cortexa99

Senior member
Jul 2, 2018
319
505
136
After seeing MLID's claim, a guy called bullsh1tbuster on X shared his view on weibo #1 #2 (have same avatar, ya same guy) after complete testing LionCove IPC.

Lion Cove IPC and general architecture testing completed
Hmm... It's a long story
It is a tock.
But like Meteor Lake
I think these two core are more inclined to power
Instead of peak performance
It is also necessary to carry the latency penalty of chiplet D2D FDI.

It means that the score running, especially the desktop end, may not be obvious.
However, the overall experience (heat dissipation, noise, responsiveness, weight) of the mobile terminal will be significantly improved due to the increase in perf/w.

Even the endurance may need to be added with some oil....
I think MTL/ARL will be very good lesson

So LionCove would have major archtecture changes which would be enough to make ARL being a "tock" and more IPC but still heavily inclined to efficiency. Sounds like clock regression is inevitable. Would MLID's "25%-35% more perf on same core count" being true?
 

coercitiv

Diamond Member
Jan 24, 2014
6,225
12,022
136
So LionCove would have major archtecture changes which would be enough to make ARL being a "tock" and more IPC but still heavily inclined to efficiency. Sounds like clock regression is inevitable. Would MLID's "25%-35% more perf on same core count" being true?
If only Intel told us that Lion Cove would be optimized for power efficiency, then we would not have to do all this guessing games based on MLID beads and tarot cards. Like, they could have mentioned it casually somewhere, even in a leaked slide for some other product. /s
 

tamz_msc

Diamond Member
Jan 5, 2017
3,825
3,654
136
Yes there are, only so many ways/sets possible until power goes boom.
So if you're going for a fatter -mont core without being as fat as -Cove, then just readjust the core count accordingly while increasing L2$, within bounds of course.

That is what the Hot Chips slide is essentially saying.
 
Jul 27, 2020
16,513
10,524
106
My curiosity remains as to how Intel accomplishes the magic act of surpassing the raw performance of that CPU?
I would think Intel would only be concerned about surpassing 14900KS performance with the 15900KS. So they've got until March-April 2025 for that. Plenty of time. It also lets them sell more of their 14900KS stock for those who already have a Z690/790 mobo and it just makes more sense for them to upgrade rather than change the entire platform for almost no gain in 2024.
 
Reactions: Hulk

maddie

Diamond Member
Jul 18, 2010
4,758
4,714
136
Just went thru more RU stuff. It actually appears to be on track. Attached a RU patent filed in 2020. If RU appears in Nova Lake, and if it works as advertised, it might be huge. They casually claim an increase of 3X to 4X ST perf!

Link: https://file.io/yaUy4MhWhJJR
Work started on this in 2008. We should also remember that quite a few of the majors were invested in SoftMachines before Intel bought them outright. I would also think that if the tech is feasible, we will see it in some form in other company designs.

If I remember correctly, Intel was not one of the early investors.
 

Saylick

Diamond Member
Sep 10, 2012
3,199
6,511
136
Just great. Olrak put out a public Google Doc where everyone and their mothers can put in their guesses. There’s even a familiar person(s) whom we have in these forums. Now, all the Youtube “leakers” are going to be running around claiming “exclusive “ sources with this info…
 

Hulk

Diamond Member
Oct 9, 1999
4,251
2,047
136
I would think Intel would only be concerned about surpassing 14900KS performance with the 15900KS. So they've got until March-April 2025 for that. Plenty of time. It also lets them sell more of their 14900KS stock for those who already have a Z690/790 mobo and it just makes more sense for them to upgrade rather than change the entire platform for almost no gain in 2024.
True. But the 13900K was more performant than the 12900KS and the 14900K was more performant than the 13900KS (same ST frequency, faster MT).

I will be of the opinion that if the "15900K" is less performant than the 14900KS then ARL was a step back in terms of performance.
 
Reactions: Tlh97 and Elfear

Joe NYC

Platinum Member
Jun 26, 2021
2,013
2,457
106
Just great. Olrak put out a public Google Doc where everyone and their mothers can put in their guesses. There’s even a familiar person(s) whom we have in these forums. Now, all the Youtube “leakers” are going to be running around claiming “exclusive “ sources with this info…

From the spreadsheet:
RPC - I am assuming Raptor Cove - from Raptor Lake Refresh
LNC - I am assuming Lion Cove - which is expected to be the P-core of Lunar Lake

What is the name of the P-Core in Arrow Lake? I am assuming it is not LNC. I was assuming it is is a derivative of Redwood Cove...
But then, the name of the spreadsheet tab is: "Arrow Lake-S Speculation"

I am a little bit confused here...
 

FlameTail

Platinum Member
Dec 15, 2021
2,356
1,275
106
From the spreadsheet:
RPC - I am assuming Raptor Cove - from Raptor Lake Refresh
LNC - I am assuming is the Lion Cove - which is expected to be the P-core of Lunar Lake

What is the name of the P-Core in Arrow Lake? I am assuming it is not LNC. I was assuming it is is a derivative of Redwood Cove...
But then, the name of the spreadsheet tab is: "Arrow Lake-S Speculation"

I am a little bit confused here...

Arrow Lake P-core is Lion Cove aka LNC
 
Reactions: Tlh97 and Joe NYC

FlameTail

Platinum Member
Dec 15, 2021
2,356
1,275
106
Just great. Olrak put out a public Google Doc where everyone and their mothers can put in their guesses. There’s even a familiar person(s) whom we have in these forums. Now, all the Youtube “leakers” are going to be running around claiming “exclusive “ sources with this info…

They should also add a tab for upcoming ARM cores (Cortex X5, Apple A18, Oryon Pegasus etc...)
 

mikk

Diamond Member
May 15, 2012
4,151
2,164
136
Lenovo Yoga Pro 7 14 with Core Ultra 7 155H tested from Notebookcheck: https://www.notebookcheck.net/Lenov...Intel-Arc-confronts-Radeon-780M.810926.0.html

This is the fastest Meteor Lake so far on Notebookcheck. Battery life WiFi Websurfing is quite good as well, there is clearly a trend that Meteor Lake has a superior battery life over Phoenix in most of the typical laptop workloads like office, internet, video playback. This is where Raptor Lake suffered.
 

naukkis

Senior member
Jun 5, 2002
708
583
136
Work started on this in 2008. We should also remember that quite a few of the majors were invested in SoftMachines before Intel bought them outright. I would also think that if the tech is feasible, we will see it in some form in other company designs.

If I remember correctly, Intel was not one of the early investors.

I speculated in risc-v threads that cpu designs should go towards split register file designs. VISC is nothing more than split register file core with software abstraction layer - which isn't way I see split register cpu should be made but instead it should rely on ISA that allows using split register files efficiently. CPU front-end have to see which instruction paths share which parts of registers. I really don't see that Intel could make that happening efficiently on x86 without ISA changes.
 

Hitman928

Diamond Member
Apr 15, 2012
5,340
8,111
136
Lenovo Yoga Pro 7 14 with Core Ultra 7 155H tested from Notebookcheck: https://www.notebookcheck.net/Lenov...Intel-Arc-confronts-Radeon-780M.810926.0.html

This is the fastest Meteor Lake so far on Notebookcheck. Battery life WiFi Websurfing is quite good as well, there is clearly a trend that Meteor Lake has a superior battery life over Phoenix in most of the typical laptop workloads like office, internet, video playback. This is where Raptor Lake suffered.

It's performance is literally within +- 1% of the average of all of the 155Hs they've tested, so it's not the fastest. . .

For battery life they only tested Wi-fi and it's good but nothing special. Not sure how you are getting the conclusion you did.
 
Reactions: Tlh97 and Thibsie
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |