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

Page 413 - 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
695
601
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 + 4E012 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)Lunar LakePanther Lake
PlatformMobile H/U OnlyDesktop OnlyDesktop & Mobile H&HXMobile U OnlyMobile H
Process NodeIntel 4Intel 20ATSMC N3BTSMC N3BIntel 18A
DateQ4 2023Q1 2025 ?Desktop-Q4-2024
H&HX-Q1-2025
Q4 2024Q1 2026 ?
Full Die6P + 8P6P + 8E ?8P + 16E4P + 4E4P + 8E
LLC24 MB24 MB ?36 MB ?12 MB?
tCPU66.48
tGPU44.45
SoC96.77
IOE44.45
Total252.15

LNL-MX.png

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: 24,004
  • LNL.png
    LNL.png
    881.8 KB · Views: 25,487
Last edited:

Magio

Member
May 13, 2024
77
78
51
The 30 W Ultra 9 288V exists solely for giving the iGPU more oomph, and will therefore be used mainly in gaming-centric designs.

Also, the Prestige 13 Meteor Lake had pretty meh cooling.

I wouldn't hold my breath for any magical MT improvements. 12-13K in GB6 MT is the upper limit of what it may achieve.

Also, there is no '30 W sustained' or, for that matter any fixed power limit in Intel Mobile CPU land unless you disable DTT using Throttlestop. So comparisons of MT score, especially on different laptop models, is meaningless.
Of course I'm not expecting a 2x (or even 1.5x) from the 17W parts in CPU benchmarks, but a measurable improvement would be welcome. It's highly unlikely to compete with a 28W Strix part in MT CPU tasks, though.

And it's not a hard coded guarantee, but you'd expect a good design around a 30W PL1 part to at least be able to sustain close to 30W, just like you'd expect those that will ship the 17W SKUs to sustain roughly 17W with short bursts at 30W.
 

511

Senior member
Jul 12, 2024
401
259
96
PTL-U is just a cheaper LNL variant from Intel i am more excited about PTL-H with 4+8+4 + 12 Xe3 cores if it can give LNL battery with 3050-3060 mobile Gpu performance it will be solid but it will be bandwidth starved if it's still at 128bit i wish they make the mc support 192bit as an option
 
  • Like
Reactions: Ghostsonplanets

Magio

Member
May 13, 2024
77
78
51
The thing with PTL-U is it's hard to imagine it be that compelling an option at the top end when that Dell leaked roadmap says the early 2026 XPS 13 redesign will still ship with LNL (and Oryon V2), only getting a refresh when NVL-U drops in early 2027.
 

511

Senior member
Jul 12, 2024
401
259
96
Those are leaked roadmap and are bound to change they are 2-3+ year in future crazy things can happen if PTL-U is pin compatible with LNL. which it should be maybe?
 

SteinFG

Senior member
Dec 29, 2021
635
767
106
Zen 5 competition will be arrow lake hx and h not lunar lake.. lunar lake competition is m2 m3
AMD's Zen 5 line is their most efficient, they will definitely compete with lunar lake. Especially Kraken. Kraken and Lunar wil have comparable ST numbers, and Kraken will win by some% in MT. They'll probably be close in efficiency. Gaming perf should be similar too, I hope.
 
Last edited:

FlameTail

Diamond Member
Dec 15, 2021
3,855
2,297
106
AMD's Zen 5 line is their most efficient, they will definitely compete with lunar lake. Especially Kraken. Kraken and Lunar wil have comparable ST numbers, and Kraken will win by some% in MT. They'll probably be close in efficiency. Gaming perf should be similar too, I hope.
Lunar Lake will crush Kraken in gaming, becuase LNL has a fatter GPU.
 
  • Like
Reactions: Henry swagger

exquisitechar

Senior member
Apr 18, 2017
683
940
136
View attachment 104153

Using basic napkin math, it appears Lunar Lake could have an IPC advantage against Zen 5.

Zen 5 has +7% int and +12% fp advantage over Redwood Cove and Lion Cove is advertised as having a +14% IPC increase over Redwood Cove.
Looks like it. That int performance is pretty bad considering the breadth of the changes in Zen5. People were right about AMD's IPC claims/questionable benchmark choices, it's the first time that they aren't representative of overall performance at all and it shows in SPEC.
 
  • Like
Reactions: Henry swagger

Ghostsonplanets

Senior member
Mar 1, 2024
685
1,111
96
PTL-U is just a cheaper LNL variant from Intel i am more excited about PTL-H with 4+8+4 + 12 Xe3 cores if it can give LNL battery with 3050-3060 mobile Gpu performance it will be solid but it will be bandwidth starved if it's still at 128bit i wish they make the mc support 192bit as an option
PTL should adopt LNL 8533 LP5X memory controller (Or even be improved to support 9600/10700T). Besides, Intel has a lot of cache (8MB) for the iGPU. So their designs aren't as memory bandwidth starved as the competitors.


Intel problem really was that their GPU IP nor their software stack were ready for the prime time. Which is something I suppose will be fixed by the time Panther Lake comes to market. Because, otherwise, they seem to be much more serious and giving more area consideration towards iGPU performance than AMD for example.
 

Abwx

Lifer
Apr 2, 2011
11,536
4,323
136
View attachment 104153

Using basic napkin math, it appears Lunar Lake could have an IPC advantage against Zen 5.

Zen 5 has +7% int and +12% fp advantage over Redwood Cove and Lion Cove is advertised as having a +14% IPC increase over Redwood Cove.

Intel s 14% is comparable to AMD s 16%, that is, an average of various softwares, not only Spec, you are implying here that LNL will also have 14% uplift in Spec.
 
  • Like
Reactions: Nothingness

511

Senior member
Jul 12, 2024
401
259
96
Btw an interesting thing with the LNC slide in LNL it shows that Intel 4 is superior to N3B at high power assuming +14% IPC it means intel was not lying about their Intel 4/3 providing same P/W as N3 derivative
 

Attachments

  • Screenshot_20240730-204915.png
    Screenshot_20240730-204915.png
    372.8 KB · Views: 26
  • Like
Reactions: Henry swagger

511

Senior member
Jul 12, 2024
401
259
96
PTL should adopt LNL 8533 LP5X memory controller (Or even be improved to support 9600/10700T). Besides, Intel has a lot of cache (8MB) for the iGPU. So their designs aren't as memory bandwidth starved as the competitors.


Intel problem really was that their GPU IP nor their software stack were ready for the prime time. Which is something I suppose will be fixed by the time Panther Lake comes to market. Because, otherwise, they seem to be much more serious and giving more area consideration towards iGPU performance than AMD for example.
Yeah as Xe2 will give us a glimpse of their effort too bad BK ran the company to ground no innovation nothing It took gelsinger to correct predecessors mistake he is just dumping money in fabs and their core buisness
 

Abwx

Lifer
Apr 2, 2011
11,536
4,323
136
Btw an interesting thing with the LNC slide in LNL it shows that Intel 4 is superior to N3B at high power assuming +14% IPC it means intel was not lying about their Intel 4/3 providing same P/W as N3 derivative
LNL CPU use TSMC s N3 while MTL CPU use Intel 4.
 

DavidC1

Senior member
Dec 29, 2023
830
1,306
96
Using basic napkin math, it appears Lunar Lake could have an IPC advantage against Zen 5.

Zen 5 has +7% int and +12% fp advantage over Redwood Cove and Lion Cove is advertised as having a +14% IPC increase over Redwood Cove.
Where's the Wave that claims that Arrowlake is awesome now? It comparatively sucks much less than 2 days ago isn't it?

:p

I do speculate though Lion Cove may be similar in that FP gains are going to be greater than Int. No, it's practically guaranteed with the 4 FP units.
They'll probably be close in efficiency.
Efficiency at this level is pretty much battery life, which Lunarlake should be significantly better at.
 
  • Like
Reactions: exquisitechar

DavidC1

Senior member
Dec 29, 2023
830
1,306
96
I know but if we take 14% IPC as avg uplift at higher curver Intel 4 is better than N3B this method has its flaws
Intel sucks on mobile for this very reason. The whole company has been in the mindset of highest performance transistors for 30 years.

Therefore it is natural that at the peak clocks, Intel processes are better. But in Lunarlake and Server products, TSMC is better.
 
  • Like
Reactions: 511