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

Page 282 - 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
686
576
106
PPT1.jpg
PPT2.jpg
PPT3.jpg



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

INTEL-CORE-100-ULTRA-METEOR-LAKE-OFFCIAL-SLIDE-2.jpg

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.)

Clockspeed.png
 

Attachments

  • PantherLake.png
    PantherLake.png
    283.5 KB · Views: 23,984
  • LNL.png
    LNL.png
    881.8 KB · Views: 25,456
Last edited:

DavidC1

Senior member
Dec 29, 2023
426
614
96
It's fake. Huge Intel fanboy that doesn't know anything and he's usually all the time around tech twitter trying to get leaks.

Anyway, you can spot on that it's fake due to him claiming CPU tile and SoC tile are separated tiles fabricated on different nodes. While, from what we know, CPU and SoC tile are merged on PTL. The CPU core configuration is also straight out of MLID videos.
@Tigerick You should have also spotted that he claims Pantherlake has the third LPE core, when they are abandoning it with Lunarlake, a predecessor product. So they have LPE with Meteorlake, abandon it with Lunarlake, and comes back with Pantherlake?

You were also posting leaks, which makes this even more questionable. Are your "leaks" even genuine then?
 

mikk

Diamond Member
May 15, 2012
4,176
2,211
136
@Tigerick You should have also spotted that he claims Pantherlake has the third LPE core, when they are abandoning it with Lunarlake, a predecessor product. So they have LPE with Meteorlake, abandon it with Lunarlake, and comes back with Pantherlake?

You were also posting leaks, which makes this even more questionable. Are your "leaks" even genuine then?


I wouldn't say that. Lunar Lake gets 4 LPE cores in a sense they are moved out from the ringbus, means they can shut it down when only the LPE cores are active. They could repeat it for Panther Lake and also add 8 E cores into the ringbus because PTL comes for UPH segment. Of course we won't see another MTL repeat with LPE cores on a different tile and worse node.
 

Tigerick

Senior member
Apr 1, 2022
686
576
106
View attachment 96751

Interesting leaks from unknown user
Hoho, you guys are too fast. I have verified with my source, most of the info are correct: That's mean some of old info are no longer valid:-
  • PTL-H comes with 3 tiles, not 2 as previously leaked: CPU, GPU and PCD tiles.
  • CPU Tile: This round CPU tile is a main tile with 2 D2D connectors: CPU tile is connecting with PCD and GPU tiles. CPU tile consists of 4P+8E+4LPe core with NPU, MC, media/display engine and IPU. 4 LPe can function as MTL; they are being used to shut down main CPU. NPU should have ~48TOPS.
  • GPU Tile: Xe3 iGPU has 120 TOPS with 12Xe cores. 40-50% faster is believable cause Xe3 comes with extra 50% core.
  • PCD is the name Intel used to replace SoC tile. Consists of PCIE, USB, TB, sound, display, imaging, wifi/bt, security complex, sensor hub and some other minor stuff. And indeed, is made by N6.
  • "Up to 40% lower power and 3 hours more battery life." Sadly, Intel don't specify which one. But I believe it is compared to ARL-H, not LNL due to 3 tiles design...
 

Ghostsonplanets

Senior member
Mar 1, 2024
568
962
96

Beautiful thing.

I wouldn't say that. Lunar Lake gets 4 LPE cores in a sense they are moved out from the ringbus, means they can shut it down when only the LPE cores are active. They could repeat it for Panther Lake and also add 8 E cores into the ringbus because PTL comes for UPH segment. Of course we won't see another MTL repeat with LPE cores on a different tile and worse node.
Speaking of LPE, I just learned that the 4C SKT cores in LNL are supposed to be more like cacheless low power usage cores than proper E cores. And the bulk of compute falls into the 4P cores complex.

It certainly will be a disadvantage in certain workloads. On the plus side, efficiency should be great given that the E cores will act more like Apple efficiency cores.
 
  • Like
Reactions: Tlh97 and Elfear

Tigerick

Senior member
Apr 1, 2022
686
576
106
I wouldn't say that. Lunar Lake gets 4 LPE cores in a sense they are moved out from the ringbus, means they can shut it down when only the LPE cores are active. They could repeat it for Panther Lake and also add 8 E cores into the ringbus because PTL comes for UPH segment. Of course we won't see another MTL repeat with LPE cores on a different tile and worse node.
Where have you heard about PCD??? I just heard from my source as explained above
 

Ghostsonplanets

Senior member
Mar 1, 2024
568
962
96
Hoho, you guys are too fast. I have verified with my source, most of the info are correct: That's mean some of old info are no longer valid:-
  • PTL-H comes with 3 tiles, not 2 as previously leaked: CPU, GPU and PCD tiles.
  • CPU Tile: This round CPU tile is a main tile with 2 D2D connectors: CPU tile is connecting with PCD and GPU tiles. CPU tile consists of 4P+8E+4LPe core with NPU, MC, media/display engine and IPU. 4 LPe can function as MTL; they are being used to shut down main CPU. NPU should have ~48TOPS.
  • GPU Tile: Xe3 iGPU has 120 TOPS with 12Xe cores. 40-50% faster is believable cause Xe3 comes with extra 50% core.
  • PCD is the name Intel used to replace SoC tile. Consists of PCIE, USB, TB, sound, display, imaging, wifi/bt, security complex, sensor hub and some other minor stuff. And indeed, is made by N6.
  • "Up to 40% lower power and 3 hours more battery life." Sadly, Intel don't specify which one. But I believe it is compared to ARL-H, not LNL due to 3 tiles design...
This changes a lot of things, huh. At least doesn't sound something as broken down and expensive as MTL

Also, what's IPU? I suppose it's Image Processing Unit but then you claim imaging is on the PCD.
 

DavidC1

Senior member
Dec 29, 2023
426
614
96
The Lunar Lake MX leak told us all that info. Two tiles. There are some folks in the crowd that exist they cannot believe it until they have seen it with their eyes, like they are run by AI or something.
It certainly will be a disadvantage in certain workloads. On the plus side, efficiency should be great given that the E cores will act more like Apple efficiency cores.
That in itself is no guarantee. Execution of the team in fulfilling their vision is the rest. Lakefield in theory should have been great battery life but it sucked.
 

DavidC1

Senior member
Dec 29, 2023
426
614
96
@Tigerick Sure, sure. If the leakers were real then they wouldn't make such a radical change as going from 2 to 3 tiles. You should ask them that question, or even yourself, saying with authority that they are genuine.

@mikk I'm talking about the mostly-useless LPE core config in Meteorlake where in local video playback, the most optimistic scenario(which maybe 1% of the population uses nowadays) saves a mere 0.15W. My Kabylake-Y Yoga uses about 4W in Youtube video playback. Saving 0.15W is in the margin of error, or some would put it(despite the tiny area usage) "waste of silicon".

Also even if Tigerick's "new leak" is true, 3 hours over crap is still crap, since even Meteorlake is arguably behind AMD's in battery life, nevermind ARM, which probably needs 40% on top of that at the system level!
 
Last edited:
  • Like
Reactions: spursindonesia

Tigerick

Senior member
Apr 1, 2022
686
576
106
@Tigerick Sure, sure. If the leakers were real then they wouldn't make such a radical change as going from 2 to 3 tiles. You should ask them that question, or even yourself, saying with authority that they are genuine.

Don't worry, my source is the one mentioned about 12 XE3 before. Time will tell if above info are correct...


@mikk I'm talking about the mostly-useless LPE core config in Meteorlake where in video playback, the most optimistic scenario saves a mere 0.15W. My Kabylake-Y Yoga uses about 4W in video playback. Saving 0.15W is in the margin of error, or some would put it(despite the tiny area usage) "waste of silicon".
 

DavidC1

Senior member
Dec 29, 2023
426
614
96
They need to move away from local video playback battery life tests. I mean abandon it.

Almost no one does that nowadays. Intel chips had Youtube acceleration since Kabylake.

My Yoga 11 uses 4W in Youtube playback. If it had a giant 75WHr battery such as "ultraportables" nowadays, I'd be able to watch for 12 hours before I plug in to charge at the optimal ~40% mark. The CPU package power is 1-1.2W with it.

IPS display means zero worry of burn-in, despite being a used device. OLED is fancy trash.
 

Ghostsonplanets

Senior member
Mar 1, 2024
568
962
96
The Lunar Lake MX leak told us all that info. Two tiles. There are some folks in the crowd that exist they cannot believe it until they have seen it with their eyes, like they are run by AI or something.
Pretty much. And if we're being charitable, the fact LNL used 2 tiles + dummy die was known for 3 years at least given that Exist had shared this info.
That in itself is no guarantee. Execution of the team in fulfilling their vision is the rest. Lakefield in theory should have been great battery life but it sucked.
True, true. Lakefield one can chalk up to 10nm issues. But if Intel isn't able to execute a low power core on N3B, then their execution is terrible. Let's wait and see.
My Yoga 11 uses 4W in Youtube playback. If it had a giant 75WHr battery such as "ultraportables" nowadays, I'd be able to watch for 12 hours before I plug in to charge at the optimal ~40% mark. The CPU package power is 1-1.2W with it.
To this day I still don't understand how Intel has regressed from the nice battery life and low power improvements they had with Haswell -> Broadwell -> Skylake -> Ice Lake -> Tiger Lake (And I'm being charitable with the later two). The fact Core M/Y series were dropped around ICL is pretty telling.
 

Hulk

Diamond Member
Oct 9, 1999
4,380
2,260
136
This review is quite good. I would love to have known frequencies during some of the benches to figure out IPC but I know that is hard with laptops.

As I was reading through I was getting more and more depressed about MTL thinking, "not gonna buy one of these." Then I saw the battery life and my mind immediately switched to "gonna buy one of these!"
 

tamz_msc

Diamond Member
Jan 5, 2017
3,865
3,729
136
I hope that Gavin can post an updated result with newer drivers as there is a vast difference in performance between 5176 and what is available currently. That said, the Company of Heroes result is quite interesting, as even with DX9 translation using DX12, Arc is pretty competitive with Radeon.
 

Ghostsonplanets

Senior member
Mar 1, 2024
568
962
96
As I was reading through I was getting more and more depressed about MTL thinking, "not gonna buy one of these." Then I saw the battery life and my mind immediately switched to "gonna buy one of these!"
You need to take these tests with a grain of salt, though. The VideoPlayback one is basically local playback and can be chalked up to the Compute Tile being deactivated while only the Media Engine, Display Unit and LPE cores being active.

The Office test is way more impressive. But I'm not sure if these numbers translate to real world conditions (But the test is legit and would be a common office day workload).

I do prefer Geekerwan test bench. Where he uses a Python script to do a timed loop through a bunch of applications, from Office work, Web Browsing, etc until the battery is depleted. MTL did really well in his test and was able to get more battery life than a AMD 7840 equivalent.

Either way, MTL is a impressive step up for Intel in battery life department.
 
  • Like
Reactions: Tlh97 and SpudLobby

SiliconFly

Golden Member
Mar 10, 2023
1,234
641
96
...Then I saw the battery life and my mind immediately switched to "gonna buy one of these!"
UL Procyon Battery Test, Video Playback - 50% Brightness


UL Procyon Battery Test, Office - 50% Brightness


These results are stunning! Almost 2X efficient than competition. But still, why is there so much discrepancy when compared to previous test results. What has changed?

And they should've also included 13500H or 13700H in the mix. Would have provided better clarity.

Question is, is it roughly 2X efficient when compared to previous gen? If yes, then it means MTL is terrific. If not, then it's better to wait for next gen.
 

Hitman928

Diamond Member
Apr 15, 2012
5,642
8,894
136
UL Procyon Battery Test, Video Playback - 50% Brightness


UL Procyon Battery Test, Office - 50% Brightness


These results are stunning! Almost 2X efficient than competition. But still, why is there so much discrepancy when compared to previous test results. What has changed?

And they should've also included 13500H or 13700H in the mix. Would have provided better clarity.

Question is, is it roughly 2X efficient when compared to previous gen? If yes, then it means MTL is terrific. If not, then it's better to wait for next gen.

They are not really comparable models. Anandtech is terrible about this in laptop reviews to the point that they use desktop CPUs in their benchmark comparisons (probably because they do so few so their comparison options are limited). The AMD unit has an RTX 4070 in it and is meant as a gaming laptop. The Zenbook with MTL is meant as an ultraportable and geared for battery life. That's why the MTL gets crushed in the performance benchmarks but wins convincingly in the battery life ones.

135042.png


MTL should not lose this bad in performance, but the configurations of the laptops are basically at opposite ends of the spectrum. Using a more comparable model with an AMD chip would see the performance be much closer, but battery life would be roughly equal as well.
 

SiliconFly

Golden Member
Mar 10, 2023
1,234
641
96
Either way, MTL is a impressive step up for Intel in battery life department.
Well, the jury is still out on that one. But it appears the newer models are working well as advertised. Something has changed apparently. Wish someone can shed more light on that.

Then I saw the battery life and my mind immediately switched to "gonna buy one of these!"
Well, battery life is one thing. But performance wise, it's barely on par with previous gen. If its efficiency is as good as advertised, it's definitely a decent buy. But not "top notch" imho.
 

Ghostsonplanets

Senior member
Mar 1, 2024
568
962
96
Well, the jury is still out on that one. But it appears the newer models are working well as advertised. Something has changed apparently. Wish someone can shed more light on that.
I think we had enough testing to conclude that MTL is on par or better in battery life with AMD Phoenix. And, in some scenarios, MTL can shine due to shutting off the Compute Tile. MTL problem is that it's truly a marvelous mess of engineering and costs.

Had Intel released MTL in early 23 like it was planned, it would have been a decently competitive part with AMD.
 

SiliconFly

Golden Member
Mar 10, 2023
1,234
641
96
They are not really comparable models. Anandtech is terrible about this in laptop reviews to the point that they use desktop CPUs in their benchmark comparisons (probably because they do so few so their comparison options are limited). The AMD unit has an RTX 4070 in it and is meant as a gaming laptop. The Zenbook with MTL is meant as an ultraportable and geared for battery life. That's why the MTL gets crushed in the performance benchmarks but wins convincingly in the battery life ones.


MTL should not lose this bad in performance, but the configurations of the laptops are basically at opposite ends of the spectrum. Using a more comparable model with an AMD chip would see the performance be much closer, but battery life would be roughly equal as well.
Thats the problem with these tests. They should have used a similar 13500H or 13700H ultrabook. Would give more clarity. But still, these tests show significantly improved battery life over previous tests. Would be nice if they let us know what has changed since.
 
  • Like
Reactions: igor_kavinski

Hitman928

Diamond Member
Apr 15, 2012
5,642
8,894
136
Thats the problem with these tests. They should have used a similar 13500H or 13700H ultrabook. Would give more clarity. But still, these tests show significantly improved battery life over previous tests. Would be nice if they let us know what has changed since.

Nothing has changed. . .