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	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.)

 

[igor_kavinski]

According to who?

Qcomm wouldn't have been making plans to buy parts of Intel if they weren't in trouble.

 

[SiliconFly]

According to who?

According to him.

 

[igor_kavinski]

PNL/CWF/DNR are all on track and are very promising! If they deliver as promised, competition is in very serious trouble considering their already minuscule market share both in clients AND servers!

Yeah. At least one whole year for Intel to fend off vultures and hostile takeover groups and investor lawsuits!

 

[DokiDoki]

Qcomm wouldn't have been making plans to buy parts of Intel if they weren't in trouble.

Have they(Qualcomm) announced it yet?

 

[igor_kavinski]

Have they(Qualcomm) announced it yet?

Depends on how desperate Pat gets. He's trying anything and everything at the moment. We'll know more by the end of the year.

 

[cebri1]

AMD wasn't full of absolute morons working against each other.

Intel's teams and management are used to having too much resources at their disposal. AMD has ALWAYS been lean. They don't know what excess is.

Going from having anything available to limited resources doesn't immediately lead to better execution. It will actually cause a lot of teething pains as they discover how to do things with limited budgets and those unable to thrive in such an environment will quit and leave gaping holes in skills and expertise.

Their stupid Meteor Lake hot lots fiasco is a direct result of them thinking they can do anything with their resources, in other words, waste investor money!

AMD, even under Lisa, fired thousands of employees between late 2000s and mid 2010s. You are clearly ignorant about the matter.

“ AMD has ALWAYS been lean. They don't know what excess is.”

AMD to lay off 15 percent of workforce

Chip company Advanced Micro Devices on Thursday said it would lay off 15 percent of its workforce as it tries to inch back to profitability at a time when the PC market is slumping.

www.computerwoche.de

 

[igor_kavinski]

AMD, even under Lisa, fired thousands of employees between late 2000s and mid 2010s. You are clearly ignorant about the matter.

“ AMD has ALWAYS been lean. They don't know what excess is.”

AMD to lay off 15 percent of workforce

Chip company Advanced Micro Devices on Thursday said it would lay off 15 percent of its workforce as it tries to inch back to profitability at a time when the PC market is slumping.

www.computerwoche.de

They have always been a fraction of Intel's workforce. That's why they have been number two for so long. Never made enough to get as big as Intel.

 

[igor_kavinski]

Anyway, carry on, folks with your happy talk about Intel's future. I just wanted ya all to think more clearly. Stepping out for a bit so gonna go silent.

 

[511]

Intel need to cut fat but the right fat that is something only time will tell they need to become lean and flexible and be ready for next bing thing something trinity got right closest comparison would be huang

 

[cebri1]

They have always been a fraction of Intel's workforce. That's why they have been number two for so long. Never made enough to get as big as Intel.

Smaller workforce =\ Lean. Do you know what lean means?

 

[Josh128]

Back on topic here, have y'all seen the Cinebench R24 single core scores of the 288V? 13% faster than Strix @ same clock speed.

If that carries to Arrow Lake, 285K is going to be over 150, and likely ~2500 in R23 if the same uplift applies there. Thats what Im talking about.

Depending on pricing, AMD will have have to lower Zen 5 significantly, their 4nm Zen 5 is going to get trounced by 3nm Lion Cove quite handily. Seems AMD miscalculated in using 4nm for client in Zen 5, but maybe they had no choice / no capacity after Intel bought it all up.

*EDIT - corrected confusion about source of the score, thought it was from a 258V CPU in Yoga laptop, it is not.

 

[DokiDoki]

Back on topic here, have y'all seen the Cinebench R24 single core scores of the Yoga Slim Lunar Lake laptop?? 130 @4.8GHz max boost clock. If true, this destroys Zen5 Strix which averages 115 @5.1GHz max boost.

288V Max Boost is 5.1 though, but yeah ST would be faster on Lion Cove, on desktop and Mobile.

 

[cebri1]

Just to clarify: not polluting the thread, sticking to the topic, not concern trolling, does not equate with saying Intel is fine. Some people do not seem to get the difference. If you are emotionally attached to AMD products I suggest you stick to other threads.

 

[511]

Back on topic here, have y'all seen the Cinebench R24 single core scores of the Yoga Slim Lunar Lake laptop?? 130 @4.8GHz max boost clock. If true, this destroys Zen5 Strix which averages 115 @5.1GHz max boost.

That is very impressive. Its about 13% faster than HX 370 ST average, and with only a 4.8 max boost??. If that carries to Arrow Lake, 285K is going to be over 160, and likely >2500 in R23 if the same uplift applies there. Thats what Im talking about.

Depending on pricing, AMD will have have to lower Zen 5 significantly, their 4nm Zen 5 is going to get trounced by 3nm Lion Cove quite handily. Seems AMD miscalculated in using 4nm for client in Zen 5, but maybe they had no choice / no capacity after Intel bought it all up.

View attachment 107018

I would take this with a grain of salt and also i would make it out as the best case i would expect it to be around 126-127 cause the fact 5.1 requires TB 3.0.It is rare to live up in laptops due to cooling constraints

 

[cebri1]

I would take this with a grain of salt and also i would make it out as the best case i would expect it to be around 126-127 cause the fact 5.1 requires TB 3.0.It is rare to live up in laptops due to cooling constraints

This. I’d wait until independent reviews come out.

 

[jdubs03]

Back on topic here, have y'all seen the Cinebench R24 single core scores of the Yoga Slim Lunar Lake laptop?? 130 @4.8GHz max boost clock. If true, this destroys Zen5 Strix which averages 115 @5.1GHz max boost.

That is very impressive. Its about 13% faster than HX 370 ST average, and with only a 4.8 max boost??. If that carries to Arrow Lake, 285K is going to be over 160, and likely >2500 in R23 if the same uplift applies there. Thats what Im talking about.

Depending on pricing, AMD will have have to lower Zen 5 significantly, their 4nm Zen 5 is going to get trounced by 3nm Lion Cove quite handily. Seems AMD miscalculated in using 4nm for client in Zen 5, but maybe they had no choice / no capacity after Intel bought it all up.

View attachment 107018

(Higher quality image, in case @Tigerick wants to use that in the OP)


Based on the Intel slide^ (slide 20) showing the single thread performance compared to AMD and Qualcomm in CB24/GB6.3/spec2017int, I was thinking it’d be around 133-135 if going by the HX370 percentage difference (scores 115-116); and the statement and claim slide (says X1E84 and not the X1E80 on the slide itself).
Which is odd because the 130 score does lineup more with the X80 difference. But I doubt 130 is unreasonable though.
I think ARL will be around 150 based on the IPC increase of 14% and clock frequency reduction (using the 14900K single thread score of 139).

 

[Josh128]

288V Max Boost is 5.1 though, but yeah ST would be faster on Lion Cove, on desktop and Mobile.

Ah, you are correct-- the Yoga laptop has max 4.8 boost with a 258V, but the R24 slide number is not from the that unit, its from 288V in an unknown unit/power profile. Still, if we assume ISO frequency, it looks like 13% higher R24 IPC vs Strix, still very impressive.

 

[OriAr]

Qcomm wouldn't have been making plans to buy parts of Intel if they weren't in trouble.

I can also make plans to date Amanda Seyfried, doesn't mean I have any chance with her whatsoever.
QComm "making plans" doesn't mean they have any chance to actually carry out said plans, Intel is not gonna sell any of their core design businesses anytime soon.

 

[maddie]

Yeah. Thats Apple. But are you trying to compare Apple with AMD?


After many many years, competition is all set to be hot this year. In clients, Lion Cove + Skymont has already surpassed Zen 5 (by a small margin). In servers, Granite Rapids is all set to catch up with competition. Interesting times ahead.

To refresh the mind , as it seems it sometimes slips. You were the one claiming that because Intel still has the dominant share in servers, everything is fine for them. What did you write? Intel is in trouble, maybe they will recover.


"Oopsie. For a while I was under the impression that AMD server market share would've be around or over 50% when compared to Intel. Seeing these numbers is quite shocking.

AMD is not even at 25%, but just 23% in servers. I think the upcoming Intel server products should be able to stop the market share loss."


You are failing to note that when it comes to the profit share, Intel is trailing far behind AMD, and profits are the values that matter. Delusion and deceit is now a big part of our existence and it seems some relish doing little parts in the overall game. Maybe it's a generational thing.

 

[maddie]

Yeah but engineering being overridden by dumb people who think that the average person buys TWO expensive laptops, one as a backup!

Well if it's Intel laptops, maybe we're getting sly messaging.

 

[SiliconFly]

Just to clarify: not polluting the thread, sticking to the topic, not concern trolling, does not equate with saying Intel is fine. Some people do not seem to get the difference. If you are emotionally attached to AMD products I suggest you stick to other threads.

Imho, I think it's okay for people to say bad stuff about Intel even if they're emotionally attached to AMD or something. It kinda keeps the thread engaged and more importantly, it maintains balance instead of creating wrong illusions that one company is far superior to another. Just my humble opinion.

View attachment 107019
(Higher quality image, in case @Tigerick wants to use that in the OP)

View attachment 107021
Based on the Intel slide^ (slide 20) showing the single thread performance compared to AMD and Qualcomm in CB24/GB6.3/spec2017int, I was thinking it’d be around 133-135 if going by the HX370 percentage difference (scores 115-116); and the statement and claim slide (says X1E84 and not the X1E80 on the slide itself).
Which is odd because the 130 score does lineup more with the X80 difference. But I doubt 130 is unreasonable though.
I think ARL will be around 150 based on the IPC increase of 14% and clock frequency reduction (using the 14900K single thread score of 139).

Thats what I too have been saying all along. ARL-S LNC is going to wipe the floor with Zen 5. But too many people here believe that the overall ST performance uplift compared to 14900K is gonna be in the 5% ballpark! Not happening people.

I can also make plans to date Amanda Seyfried, doesn't mean I have any chance with her whatsoever.
QComm "making plans" doesn't mean they have any chance to actually carry out said plans, Intel is not gonna sell any of their core design businesses anytime soon.

True.

To refresh the mind , as it seems it sometimes slips. You were the one claiming that because Intel still has the dominant share in servers, everything is fine for them. What did you write? Intel is in trouble, maybe they will recover.


"Oopsie. For a while I was under the impression that AMD server market share would've be around or over 50% when compared to Intel. Seeing these numbers is quite shocking.

AMD is not even at 25%, but just 23% in servers. I think the upcoming Intel server products should be able to stop the market share loss."


You are failing to note that when it comes to the profit share, Intel is trailing far behind AMD, and profits are the values that matter. Delusion and deceit is now a big part of our existence and it seems some relish doing little parts in the overall game. Maybe it's a generational thing.

Short term profits & losses aren't that important as market share. Intel has slipped a bit. But GNR should arrest the server market share erosion. And more importantly, Diamond Rapids should improve the market share.

 

[majord]

Ah, you are correct-- the Yoga laptop has max 4.8 boost with a 258V, but the R24 slide number is not from the that unit, its from 288V in an unknown unit/power profile. Still, if we assume ISO frequency, it looks like 13% higher R24 IPC vs Strix, still very impressive.

I don't think its too wise to make such nuanced IPC comparisons with R24.. the scores are obviously influenced by other factors. A 9950X for e.g does ~140cb @ 5.7Ghz

Not downplaying the performance advantage here , it's a strong win SoC vs SoC and should of course count towards its performance along with every other workload , but it's just not something i'd use as an indication of comparative IPC on average.

 

[SiliconFly]

I don't think its too wise to make such nuanced IPC comparisons with R24.. the scores are obviously influenced by other factors. A 9950X for e.g does ~140cb @ 5.7Ghz

Not downplaying the performance advantage here , it's a strong win SoC vs SoC and should of course count towards its performance along with every other workload , but it's just not something i'd use as an indication of comparative IPC on average.

There are too many leaks (both trusted and unverified) out there that signal that ARL's LNC is stronger than expected. A lot stronger.

 

[Josh128]

I don't think its too wise to make such nuanced IPC comparisons with R24.. the scores are obviously influenced by other factors. A 9950X for e.g does ~140cb @ 5.7Ghz

Not downplaying the performance advantage here , it's a strong win SoC vs SoC and should of course count towards its performance along with every other workload , but it's just not something i'd use as an indication of comparative IPC on average.

R24 is much easier to gauge than something like Geekbench-- 9950X does around 132-138 in R24 ST depending on the review you look at. Anandtech put 9950X and 9900X at 132 and 131 respectively in their review. That is right in line with the 11.8% clock increase over HX 370 ST average of 115.

Im not using it for average IPC, but specifically R24. If the number cited is real, Lion Cove is looking like ~10-13% faster per clock than Zen 5 Nirvana core in R24.

 

[MS_AT]

R24 is much easier to gauge than something like Geekbench-- 9950X does around 132-138 in R24 ST depending on the review you look at. Anandtech put 9950X and 9900X at 132 and 131 respectively in their review. That is right in line with the 11.8% clock increase over HX 370 ST average of 115.

Im not using it for average IPC, but specifically R24. If the number cited is real, Lion Cove is looking like ~10-13% faster per clock than Zen 5 Nirvana core in R24.

R24 is memory subsystem dependant what makes it different to R23. I suggest checking out Chips&Cheese review of the benchmark. AT is using stock memory, while other outlets are using 6000MHz+ RAM. In case of Lunar Lake vs Strix, Lunar is enjoying both bandwidth and latency advantage. Since there exists memory subsystem dependency L3 size might also be of importance.