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 (20A)	Arrow Lake (N3B)	Lunar Lake	Panther Lake
Platform	Mobile H/U Only	Desktop Only	Desktop & Mobile H&HX	Mobile U Only	Mobile H
Process Node	Intel 4	Intel 20A	TSMC N3B	TSMC N3B	Intel 18A
Date	Q4 2023	Q1 2025 ?	Desktop-Q4-2024 H&HX-Q1-2025	Q4 2024	Q1 2026 ?
Full Die	6P + 8P	6P + 8E ?	8P + 16E	4P + 4E	4P + 8E
LLC	24 MB	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.)

poke01 · Tuesday at 10:10 AM

Josh128 · Tuesday at 10:15 AM

Indeed, 14" vs 16" display.

Hitman928 · Tuesday at 10:22 AM

9949asd said:
how about max out 288v st will be 130？

I’ve only seen 1 288v sample tested so far and it scored 125.

cebri1 · Tuesday at 10:25 AM

Josh128 said:
Indeed, 14" vs 16" display.

Has also a larger battery.

288V CB24 ST

poke01 · Tuesday at 10:26 AM

This a well rounded review

poke01 · Tuesday at 10:27 AM

Lunar lake will be awesome for x86 handhelds

9949asd · Tuesday at 10:29 AM

Hitman928 said:
I’ve only seen 1 288v sample tested so far and it scored 125.

258v only run at 4.6ghz

Abwx · Tuesday at 10:31 AM

Hitman928 said:
I’ve only seen 1 288v sample tested so far and it scored 125.

There s a 288V tested at Computerbase, it score 127, what would Intel do without Maxon s "updated" benchs, because in CB R15/20/23 it s not as good, and is slightly slower per clock vs the 370 in 7 Zip ST, wich is in line with Spec_int scores.

Intel Core Ultra 9 288V „Lunar Lake“ im Test

Es ist so weit: Nach einem Jahr Salamischeibenmarketing ist Intel Lunar Lake ab sofort verfügbar. Core Ultra 200V überzeugt im Test.

www.computerbase.de

poke01 · Tuesday at 10:32 AM

I was right. 15 watts @ 5.1 GHz

gdansk · Tuesday at 10:33 AM

It looks decent. Perhaps the first x86 chip to fix the high 1T power problem. Which *should* mean browsing websites won't turn on the fan randomly.

But Pat, where is my fanless x86 laptop?

cebri1 · Tuesday at 10:36 AM

poke01 said:
I was right. 15 watts @ 5.1 GHz
View attachment 108147

That’s N100 levels of power consumption.

MoogleW · Tuesday at 10:37 AM

月光下的新探索：Lunar Lake CPU (Lion Cove / Skymont) 微架构测试 | David Huang's Blog

That Skymont has better scores than Lion Cove in some microbenchmarks is rather impressive

Det0x · Tuesday at 10:40 AM

Are you guys seeing it ?

Hitman928 · Tuesday at 10:41 AM

9949asd said:
View attachment 108146
258v only run at 4.6ghz

No, it boosts to 4.8 GHz. Maybe his laptop has a cooling issue or he’s mistaken on the clock speed.

cebri1 · Tuesday at 10:41 AM

MoogleW said:
月光下的新探索：Lunar Lake CPU (Lion Cove / Skymont) 微架构测试 | David Huang's Blog

That Skymont has better scores than Lion Cove in some microbenchmarks is rather impressive

It went from Skylake to Raptor levels of performance. It’s a massive improvement. Skymont based N-cpus would be great for home servers and mini pc

poke01 · Tuesday at 10:41 AM

gdansk said:
But Pat, where is my fanless x86 laptop?

It’s good but not anywhere near fanless good.

This is likely why, an all core load consumes about 30 watts with peaks of 36 watts. Of course Lunar Lake can be configured with 9 watts but then it would be slower than M2.

Hitman928 · Tuesday at 10:43 AM

Det0x said:
Are you guys seeing it ?
View attachment 108148

No. But we need more gaming tests.

Hitman928 · Tuesday at 10:46 AM

poke01 said:
It’s good but not anywhere near fanless good.

This is likely why, an all core load consumes about 30 watts with peaks of 36 watts. Of course Lunar Lake can be configured with 9 watts but then it would be slower than M2.
View attachment 108149

I think this might be where LNL is actually a hard sell for Intel. It seems that OEMs are wanting to push it into ‘U’ class territory power consumption to get higher performance and put a nice OLED screen on it, but then they kinda defeats the purpose of the chip. Hope I’m wrong though.

Magio · Tuesday at 10:46 AM

From these early reviews, Lunar Lake seems like the best x86 platforms for thin and lights by a good distance. But looking at performance across different power modes it's a bit infuriating these early designs even made their "full speed" modes 28/30W because it really doesn't seem to have a major impact on performance going from there to the low/mid 20s while it makes a big thermal and noise difference in designs that thin.

Of course there's the option of using only the lower power modes but it makes me wonder why Intel or AMD would even bother continuing to optimize low power performance when OEMs are going to stubbornly redline those chips outside their efficiency window anyway... If Asus/Lenovo are going to make them run at 30W anyway, they might as well have 16 threads and not 8.

cebri1 · Tuesday at 10:46 AM

Hitman928 said:
No. But we need more gaming tests.

In some test is 30% slower than the MTL GPU. I hope we get proper gaming test soon.

jdubs03 · Tuesday at 10:58 AM

Hitman928 said:
I think this might be where LNL is actually a hard sell for Intel. It seems that OEMs are wanting to push it into ‘U’ class territory power consumption to get higher performance and put a nice OLED screen on it, but then they kinda defeats the purpose of the chip. Hope I’m wrong though.

This is why I’m a bit annoyed and perplexed as to why they chose ARL-U to just be a MTL refresh. If they had chosen Lion Cove and Skymont, they wouldn’t have a gap in their product line with a different architecture between the V and H classes. Pretty much looks like the 288V is the only thing that could try to compete in the higher power “U” segment.

Ideally, they would have something to compete like for like against the HX 370/375.

jur · Tuesday at 11:00 AM

MoogleW said:
月光下的新探索：Lunar Lake CPU (Lion Cove / Skymont) 微架构测试 | David Huang's Blog

That Skymont has better scores than Lion Cove in some microbenchmarks is rather impressive

Lion Cove's branch prediction is very disappointing. Already previous P cores were rather medicore compared to Zen. Now looks like P core is even falling behind the E core.

StinkyPinky · Tuesday at 11:20 AM

These battery life tests with different displays and different display sizes etc just seem pointless. A 16" laptop with a brighter display drains quicker than a 14"? Who is surprised by that?

That said, I do like the GPU gains. Although once again, how many people are really gaming on thin and light laptops? Seems a very niche type of demand.

controlflow · Tuesday at 11:22 AM

Magio said:
From these early reviews, Lunar Lake seems like the best x86 platforms for thin and lights by a good distance. But looking at performance across different power modes it's a bit infuriating these early designs even made their "full speed" modes 28/30W because it really doesn't seem to have a major impact on performance going from there to the low/mid 20s while it makes a big thermal and noise difference in designs that thin.

Of course there's the option of using only the lower power modes but it makes me wonder why Intel or AMD would even bother continuing to optimize low power performance when OEMs are going to stubbornly redline those chips outside their efficiency window anyway... If Asus/Lenovo are going to make them run at 30W anyway, they might as well have 16 threads and not 8.

Hitman928 said:
I think this might be where LNL is actually a hard sell for Intel. It seems that OEMs are wanting to push it into ‘U’ class territory power consumption to get higher performance and put a nice OLED screen on it, but then they kinda defeats the purpose of the chip. Hope I’m wrong though.

At least in the case of Asus, with the Zenbook 14 they actually set the default out of box power mode to just 19 watts at steady state. You only get the 28W+ behavior in performance mode.

Lenovo seems to want to push power a little more but I think it makes no sense given there is already not much performance gain above 20W.

511 · Tuesday at 11:29 AM

Granite rappids review out destroying amd genoa we are so back

Intel Xeon 6980P "Granite Rapids" Linux Benchmarks Review - Phoronix

www.phoronix.com

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

Senior member

Attachments

Platinum Member

Attachments

Senior member

Diamond Member

Senior member

Platinum Member

Platinum Member

Member

Lifer

Platinum Member

Platinum Member

Senior member

Member

Golden Member

Diamond Member

Senior member

Platinum Member

Diamond Member

Diamond Member

Member

Senior member

Senior member

Member

Diamond Member

Member

Senior member