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

[Tigerick]

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	8 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)	Arrow Lake Refresh (N3B)	Lunar Lake	Panther Lake
Platform	Mobile H/U Only	Desktop Only	Desktop & Mobile H&HX	Desktop Only	Mobile U Only	Mobile H
Process Node	Intel 4	Intel 20A	TSMC N3B	TSMC N3B	TSMC N3B	Intel 18A
Date	Q4 2023	Q1 2025 ?	Desktop-Q4-2024 H&HX-Q1-2025	Q4 2025 ?	Q4 2024	Q1 2026 ?
Full Die	6P + 8P	6P + 8E ?	8P + 16E	8P + 32E	4P + 4E	4P + 8E
LLC	24 MB	24 MB ?	36 MB ?	?	8 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.)

 

[Hitman928]

Gaming is 23% above their current MTL iGPU average, beating most of the tested 780Ms. CPU is normal tho.

Gaming with the iGPU is indeed higher. Wouldn't surprise me as Intel has been improving their drivers quite a bit. Still have some ways to go but reports are that it's much better than it was.

 

[SiliconFly]

Gaming with the iGPU is indeed higher. Wouldn't surprise me as Intel has been improving their drivers quite a bit. Still have some ways to go but reports are that it's much better than it was.

True. They've been releasing constant updates with huge improvements in each release. Their graphics drivers are already very mature and by the time ARL arrives, it should be on par with nvidia and amd drivers.

 

[Saylick]

LOL @igor_kavinski

 

[mikk]

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

It's 8% faster than the second fastest 155H in the CPU performance ranking and 16% faster than the second fastest in the gaming ranking.

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.

This is a conclusion from all Meteor Lake battery life tests. There is a clear pattern that Meteor Lake has a superior battery life over Phoenix.

 

[SiliconFly]

It's 8% faster than the second fastest 155H...
...16% faster than the second...
...Meteor Lake has a superior battery life over Phoenix.

Sounds interesting. But if you ask me, Meteor Lake is too little too late to join the party. It has lost the initial momentum which is very important for any product launch. It's been 3 months already even after the super late launch, and I still haven't come across *enough* good reviews to say MTL is awesome. MTL is already a dud. And with a heavy heart, I'd like to say MTL is a failed launch.

MTL is Microsoft's Windows Vista.

(Or Windows 8 if you like Steve Ballmer)

 

[Hitman928]

It's 8% faster than the second fastest 155H in the CPU performance ranking and 16% faster than the second fastest in the gaming ranking.

Eh?



This isn't all of the 155Hs they've tested though. It's just a small sample included in the list which is why they show the average of all their tests, which like I said, shows this MTL sample being right in line with the average 155H performance. You can easily add additional samples to the list to see that there are multiple laptops with the 155H that have higher performance than this sample. It's really just about how much power the chips are allowed to consume when plugged in that determines which model will have higher performance. The Lenovo has average power consumption for 155H laptops and so it gets an average performance rating.

This is a conclusion from all Meteor Lake battery life tests. There is a clear pattern that Meteor Lake has a superior battery life over Phoenix.

You're going to have to show receipts on this one because I haven't seen such evidence. I'd say they're roughly in line with each other. It's hard to give a more firm conclusion given that battery life is a system level test and a ton of variables come into play.

 

[Geddagod]

 

[tamz_msc]

View attachment 95130

That's 10K points in CB R23 (MTL-U - assuming Core Ultra 7 165U) -> 15K points in LNL.

If that is indeed true, then it'll be just 1K points shy of the Ryzen 9 7940HS and similar to the Core Ultra 7 165H.

 

[tamz_msc]

Actually, it is not completely unrealistic to extrapolate that if Skymont is 20% higher ST perf than Crestmont - which to me is a reasonable assumption - then Lion Cove will have to be roughly 25% higher ST perf than Redwood Cove. If Lunar Lake is indeed 1.5 times faster at CB R23 MT than MTL-U that is.

 

[mikk]

That's 10K points in CB R23 (MTL-U - assuming Core Ultra 7 165U) -> 15K points in LNL.

If that is indeed true, then it'll be just 1K points shy of the Ryzen 9 7940HS and similar to the Core Ultra 7 165H.

This score is way too high if it runs strictly at 15W without boost. How do you get a 15W score from MTL-U without PL2 boost? Do we have a 15W score from RPL-U? A 50% speedup is quite good however given that LNL won't have SMT which hurts in Cinebench and 2+8 compared to 4+4 isn't much different in multithreaded apps.

 

[Philste]

That LNL result sounds really good. It's 8 vs 12 (or even 14 if LPE-Cores work for Benching in MTL) Threads afterall. My personal guess is that SKT is the bigger IPC jump of the 2.

 

[SiliconFly]

Actually, it is not completely unrealistic to extrapolate that if Skymont is 20% higher ST perf than Crestmont - which to me is a reasonable assumption - then Lion Cove will have to be roughly 25% higher ST perf than Redwood Cove. If Lunar Lake is indeed 1.5 times faster at CB R23 MT than MTL-U that is.

LNC sounds very promising. Might deliver after all. Intel is on the right path ditching GLC/RPC/RWC.

 

[poke01]

Apple MacBook Air 13 M3 review - A lot faster and with Wi-Fi 6E

We tested the new MacBook Air M3 with a faster 10-core graphics card, Wi-Fi 6E and 16 GB RAM.

www.notebookcheck.net

M3 performs extremely well in the battery test against MTL. Lunar Lake HAS to match or exceed M3. Since both are N3B, if Intel fails then the architecture is 100% at fault this time but I have high hopes they will succeed.

 

[coercitiv]

Since both are N3B, if Intel fails then the architecture is 100% at fault this time but I have high hopes they will succeed.

We would still have to account for the OS.

 

[FlameTail]

Apple MacBook Air 13 M3 review - A lot faster and with Wi-Fi 6E

We tested the new MacBook Air M3 with a faster 10-core graphics card, Wi-Fi 6E and 16 GB RAM.

www.notebookcheck.net

M3 performs extremely well in the battery test against MTL. Lunar Lake HAS to match or exceed M3. Since both are N3B, if Intel fails then the architecture is 100% at fault this time but I have high hopes they will succeed.

There is no way LNL is going to be more efficient than M3.

 

[tamz_msc]

This score is way too high if it runs strictly at 15W without boost. How do you get a 15W score from MTL-U without PL2 boost? Do we have a 15W score from RPL-U? A 50% speedup is quite good however given that LNL won't have SMT which hurts in Cinebench and 2+8 compared to 4+4 isn't much different in multithreaded apps.

I think Bionic_squash is comparing the SKU TDP, not the actual power levels at which the benchmark is being run.

 

[SiliconFly]

There is no way LNL is going to be more efficient than M3.

LNL can easily be as efficient as M3 (but just not equally performant).

 

[SiliconFly]

There is no way LNL is going to be more efficient than M3.

Also, now we can use M3 MacBook Air to heat water or coffee, and keep our room warm in winter, and can also use it for some cooking purposes as it runs hotter at 114°C (237°F) compared to raptor lake cpus!

Here' the link.

Looks like LNL may actually easily beat M3 in efficiency after all!

 

[CouncilorIrissa]

Also, now we can use M3 MacBook Air to heat water or coffee, and keep our room warm in winter, and can also use it for some cooking purposes as it runs hotter at 114°C (237°F) compared to raptor lake cpus!

Here' the link.

Looks like LNL may actually easily beat M3 in efficiency after all!

Breaking news: passively-cooled CPU on a much more dense process runs much hotter than an actively-cooled CPU!

 

[maddie]

LNL can easily be as efficient as M3 (but just not equally performant).

What is this crazy statement?

 

[FlameTail]

Also, now we can use M3 MacBook Air to heat water or coffee, and keep our room warm in winter, and can also use it for some cooking purposes as it runs hotter at 114°C (237°F) compared to raptor lake cpus!

Here' the link.

Looks like LNL may actually easily beat M3 in efficiency after all!

What does temperature have to do with efficiency...

 

[FlameTail]

What is this crazy statement?

Ig he is talking about comparing certain points in the performance/power curve instead of taking into consideration the whole curve.

 

[igor_kavinski]

What does temperature have to do with efficiency...

More temperature would reduce the efficiency and waste more power. People were not too happy with Zen 4 bumping up against 95C. Apple engineers must be smoking something to let their CPU go above 100C. Either make a better, heftier thermal solution to sustain such temperatures or clamp down on them before they go out of hand.

 

[Hitman928]

We would still have to account for the OS.

Plus screen, WiFi implementation, memory, etc. It’s a comparison of the whole system.

 

[FlameTail]

More temperature would reduce the efficiency and waste more power.

Which law of electronics is this?