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.)

 

[Dayman1225]

Arrow Lake is a Q3 2024 product.

Nope. End of year 24, possibly January 25

 

[Tigerick]

Nope. End of year 24, possibly January 25

What is with 2 downvotes for stating the obvious date??? Seems like somebody don't really follow Intel's timeline and speculate the date...Of course ARL-S will be launching in Q4 2024. Here's the timeline from Raptor Lake-S onwards:-

1. Raptor Lake-S 13th Gen: Q4 2022
2. Raptor Lake-R 14th Gen: Q4 2023
3. Arrow Lake-S 8+16 (N3B): Q4 2024
4. Arrow Lake-R 8+32 (N3B): Q4 2025
5. Nova Lake-S 16+32 (N2): Q4 2026

Unless some showstopper bugs appear, I think Intel will stick to above timetable. As for Arrow Lake 20A, I think Intel will make it for mobile -H only just like Meteor Lake, this one I am not so sure, it all depends on yield and true PPA of 20A, we shall see...

 

[FlameTail]

Nope. End of year 24, possibly January 25

r/UsernameAbsolutelyChecksOut

 

[FlameTail]

Will we see mobile parts with the 8+32 CPU?

Maybe not H, but HX series?

 

[Tigerick]

Will we see mobile parts with the 8+32 CPU?

Maybe not H, but HX series?

Mobile wise, not sure. Depends on power

 

[TESKATLIPOKA]

Here is a review of Acer Swift Go 14 SFG14-72 -> Notebookcheck.net

Didn't show any advantage against HP pavilion with 7840U, which had very similar config(display, RAM, SSd, battery, etc).
Even the other Acer Swift with Raptor U + 16GB + 512GB showed only a bit worse Wifi endurance than this MTL despite having smaller battery.
MTL has a higher sustained power limit of 45W, but that shouldn't matter during a wifi test in my opinion.
So where is that great efficiency during light loads? Is this also because the wrong bios is inside?

 

[Saylick]

Here is a review of Acer Swift Go 14 SFG14-72 -> Notebookcheck.net
View attachment 90728
Didn't show any advantage against HP pavilion with 7840U, which had very similar config(display, RAM, SSd, battery, etc).
Even the other Acer Swift with Raptor U + 16GB + 512GB showed only a bit worse Wifi endurance than this MTL despite having smaller battery.
MTL has a higher sustained power limit of 45W, but that shouldn't matter during a wifi test in my opinion.
So where is that great efficiency during light loads? Is this also because the wrong bios is inside?

The idle power readings in that NBC review weren't too hopeful either but I think we're going to have to wait for software to mature a bit before we come to a final conclusion. The waters are just too muddied at the moment for anyone to come to a rational decision.

 

[eek2121]

I guess ASUS is launching NUCs with MTL-P/H in them. I am hoping Geekom or a similar company releases something as well.

Geekerwan review:

Seems the main issue is the P core, E core looks decent, 10% more performance at 10% lower power, maybe would be roughly 15% higher performance at same power. P core however is garbage, those last 200-300MHz are very expensive on 12th and 13th gen, equalizing performance by power limiting / reducing the clock, power consumption would be similar based on what I've seen.
So yeah, MT efficiency disappointment is due to Redwood Cove being trash.

It isn’t trash, Intel just focused on things besides performance for once.

Intel frequently hides base frequencies on Ark, but then Intel shows base frequencies to the media. I guess not this year. Example with 13th Gen:

View attachment 90596


View attachment 90597


I used to roughly estimate Watts per GHz, but ever since Intel's gone hybrid with E-cores and started hiding easily accessible base frequencies, it's been a crapshoot.

Both Intel and AMD like to hide base frequencies. It is very annoying. A minimum assured frequency should always be specified.

Intel® Core™ i7-1185G7 Processor (12M Cache, up to 4.80 GHz, with IPU) Product Specifications

Intel® Core™ i7-1185G7 Processor (12M Cache, up to 4.80 GHz, with IPU) quick reference guide including specifications, features, pricing, compatibility, design documentation, ordering codes, spec codes and more.

ark.intel.com

Intel® Core™ i7-1195G7 Processor (12M Cache, up to 5.00 GHz) - Product Specifications | Intel

Intel® Core™ i7-1195G7 Processor (12M Cache, up to 5.00 GHz) quick reference with specifications, features, and technologies.

www.intel.com

I think there is a possibility of Intel releasing Core Ultra 9 195H about six months later.

There were rumors of an internal part hitting ~5.4ghz so I wouldn’t be surprised if they did.

 

[Khato]

Here is a review of Acer Swift Go 14 SFG14-72 -> Notebookcheck.net

Didn't show any advantage against HP pavilion with 7840U, which had very similar config(display, RAM, SSd, battery, etc).
Even the other Acer Swift with Raptor U + 16GB + 512GB showed only a bit worse Wifi endurance than this MTL despite having smaller battery.
MTL has a higher sustained power limit of 45W, but that shouldn't matter during a wifi test in my opinion.
So where is that great efficiency during light loads? Is this also because the wrong bios is inside?

That great MTL efficiency is entirely masked by the abysmal efficiency of the OLED display. The review even says as much, "According to our energy measurements, it's the OLED panel that uses the most power when surfing."

And comparing to the RPL variant of the same model seems like it should be a fair comparison since it's even the same reported part number on the display, right? But it's clearly not the same display given the 391 cd/m^2 brightness on the MTL device compared to 279 cd/m^2 on the RPL variant.

Now in terms of judging a laptop their methodology is perfectly sound. It just can't be directly used to judge an individual component within that laptop. (Would be fun if they provided average CPU package power reported over the entire battery life test, but obviously they don't.)

 

[TESKATLIPOKA]

That great MTL efficiency is entirely masked by the abysmal efficiency of the OLED display. The review even says as much, "According to our energy measurements, it's the OLED panel that uses the most power when surfing."

And comparing to the RPL variant of the same model seems like it should be a fair comparison since it's even the same reported part number on the display, right? But it's clearly not the same display given the 391 cd/m^2 brightness on the MTL device compared to 279 cd/m^2 on the RPL variant.

They didn't mention at what brightness it was tested, but It wasn't at max brightness. They mentioned that only under full load.
There is still that HP Pavilion with OLED. It has comparable brightness and actually higher refresh rate of 120Hz. I think there shouldn't be that much difference.

Notebookcheck doesn't do bad reviews, but some things should really be more detailed.

 

[Khato]

They didn't mention at what brightness it was tested, but It wasn't at max brightness. They mentioned that only under full load.
There is still that HP Pavilion with OLED. It has comparable brightness and actually higher refresh rate of 120Hz. I think there shouldn't be that much difference.

Notebookcheck doesn't do bad reviews, but some things should really be more detailed.

In general I'd say their reviews are excellent, they're just focused on the device as a whole. Which is generally of greater interest to readers. It'd just be nice if they went into greater depth on the initial review of a new processor/graphics card release.

Anyway, their standard for battery life testing is 150 cd/m^2 unless it's noted as min/max brightness. But even then comparisons can't be made. The difference in maximum brightness is indicative of different panel/driving circuitry. The display in the MTL variant could easily be a constant 1W higher power draw than the RPL variant, we have no way to know. Similarly, despite the higher 120Hz refresh rate of that HP Pavillion the display may be using less power. Makes no sense right? That's the current problem with OLED screens on laptops. Some are abysmal, others are on par with IPS. The easiest comparison points for abysmal examples are on Lenovo Thinkpads, eg 5 hours for an X1 Carbon gen10 with a 2880x1800 OLED compared to 7.5 hours on the X1 Carbon gen9 with 3840x2400 IPS.

Assuming the OLED display is consuming something along the lines of the curve represented here - https://arstechnica.com/gadgets/2023/04/oled-is-great-but-where-are-all-the-mini-led-laptops/4/ - then at 150 cd/m^2 it might be in the range of 5-6W. Out of the average 8.14W the device would be consuming to arrive at 479 minutes of run time with a 65Wh battery. And the CPU is only part of that remaining 2-3W.

 

[DrMrLordX]

I guess ASUS is launching NUCs with MTL-P/H in them. I am hoping Geekom or a similar company releases something as well.

Hopefully someone will do a NUC review so we can get better performance and power numbers off the SoC in isolation from other factors (screens, etc.) and with proper cooling.

 

[majord]

It isn’t trash, Intel just focused on things besides performance for once.

Such as?

 

[Hulk]

Such as?

Moving their mainstream chips from monolithic to tiled and using outside foundries. The biggest change in direction for them since their inception.

 

[majord]

Moving their mainstream chips from monolithic to tiled and using outside foundries. The biggest change in direction for them since their inception.

sure, but the person he was replying to was referring specifically to the P core's 'garbage'

 

[Abwx]

Assuming the OLED display is consuming something along the lines of the curve represented here - https://arstechnica.com/gadgets/2023/04/oled-is-great-but-where-are-all-the-mini-led-laptops/4/ - then at 150 cd/m^2 it might be in the range of 5-6W. Out of the average 8.14W the device would be consuming to arrive at 479 minutes of run time with a 65Wh battery. And the CPU is only part of that remaining 2-3W.

Power comsumption with the OLED screen off is 8W, for the 7840U Pavillion it s about 6.5W on average, numbers are here, it s just a matter of spoting them...

So it appear that when idling MTL is not that efficient, its idle power is 1.5-2W higher than the Pavillion and the OLED screen has nothing to do with it.

 

[controlflow]

Power comsumption with the OLED screen off is 8W, for the 7840U Pavillion it s about 6.5W on average, numbers are here, it s just a matter of spoting them...

So it appear that when idling MTL is not that efficient, its idle power is 1.5-2W higher than the Pavillion and the OLED screen has nothing to do with it.

Idle and light load power is probably the strongest feature of MTL.

There are some issues currently with FW and OS scheduling which result in sub-optimal use of the LP E cores but this test does show the potential in idle and low use situations. This system here has a 120hz OLED BTW.

 

[Abwx]

Idle and light load power is probably the strongest feature of MTL.

There are some issues currently with FW and OS scheduling which result in sub-optimal use of the LP E cores but this test does show the potential in idle and low use situations. This system here has a 120hz OLED BTW.

View attachment 90737

If MTL was as efficient than in this graph NBC would have measured better autonomy, even if only 30-40% that what they got.

Guess that to get those times they did set a convenenient corner case where only the LPE cores were active with a purely HTML page displayed if not a blank screen...

Anyway the idle values measured by NBC do not match those surprisingly favourable numbers, most likely that they are more or less made up..

Edit : Here the most favourable case i was talking about, and even in this exemple improvement in respect of RPL is 33%, not 90%, when that really happen because just a tiny more activity will wake up the biggest cores :

Intel Core Ultra alias Meteor Lake: Details und Specs

Heute startet endlich Intels neue CPU-Generation Meteor Lake in Form von elf U- und H-Modellen bei allen namhaften Partnern.

www.computerbase.de

 

[nicalandia]

So MTL is doing really bad on Linux.

Intel Core Ultra 7 155H CPU Fails Miserably Against The AMD Ryzen 7 7840U In Linux Benchmarks

Intel's Core Ultra 7 155H "Meteor Lake" CPU gets crushed by AMD's Ryzen 7 7840U in Linux tests, falling behind in performance & efficiency.

wccftech.com

 

[gdansk]

Why would you link to WCCFTech instead of directly to Phoronix?
For others who wish to avoid that pain:

Intel Core Ultra 7 155H Meteor Lake vs. AMD Ryzen 7 7840U On Linux In 300+ CPU Benchmarks Review - Phoronix

www.phoronix.com

 

[desrever]

View attachment 90737

How is refreshing every 15 secs even realistic as a light load?

 

[gdansk]

How is refreshing every 15 secs even realistic as a light load?

Pretty much what I do while using my laptop (although it's different tabs). It's not the worst benchmark.

 

[desrever]

Pretty much what I do while using my laptop (although it's different tabs). It's not the worst benchmark.

You don't load new pages and just refresh the ones that are open and cached?

 

[gdansk]

You don't load new pages and just refresh the ones that are open and cached?

It's a mix of both in real life. Does the page being cached help Intel more than AMD? One wonders.

 

[Khato]

Power comsumption with the OLED screen off is 8W, for the 7840U Pavillion it s about 6.5W on average, numbers are here, it s just a matter of spoting them...

So it appear that when idling MTL is not that efficient, its idle power is 1.5-2W higher than the Pavillion and the OLED screen has nothing to do with it.

Power consumption as measured at the AC socket, yes. So including AC to DC power adapter, battery charge maintenance, etc. Simple fact is that without a power trace of CPU package power no definitive conclusion can be drawn regarding MTL efficiency versus entire laptop efficiency.