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.)

 

[TESKATLIPOKA]

14900KF is 15% faster than 7950X is ST & 20% faster in MT.

And there's no competition in sight for 6 month at least!

As for MTL, just 1 more day to go... 🤞

What?
Are you seriously expecting +15% ST and +20% MT performance from Raptor refresh using the same process?

edit:
@ondma compared to 7950X. I didn't say It was against Raptor.

 

[ondma]

What?
Are you seriously expecting +15% ST and +20% MT performance from Raptor refresh using the same process?

That is not at all what he said.

 

[FangBLade]

What?
Are you seriously expecting +15% ST and +20% MT performance from Raptor refresh using the same process?

edit:
@ondma compared to 7950X. I didn't say It was against Raptor.

Raw power means nothing, Zen 4-3d outperforms Intel in games while consuming significantly less energy. That's a real victory. However, claiming victory with just a 5-10% lead while consuming over 100 watts more isn't a victory at all. On top of that, you get an inferior platform with no upgrade options. You'll pay a hefty price for the 14900 version, and if you want to upgrade, you have to buy everything anew. That's not a victory; the performance-to-power consumption ratio determines the winner.

 

[rtxtwt]

14900KF is 15% faster than 7950X is ST & 20% faster in MT.

And there's no competition in sight for 6 month at least!

As for MTL, just 1 more day to go... 🤞

I won't argue about the % of RPL-R lead. But, considering RPL-R is next month......4-5 months maybe.

 

[TESKATLIPOKA]

Raw power means nothing, Zen 4-3d outperforms Intel in games while consuming significantly less energy. That's a real victory. However, claiming victory with just a 5-10% lead while consuming over 100 watts more isn't a victory at all. On top of that, you get an inferior platform with no upgrade options. You'll pay a hefty price for the 14900 version, and if you want to upgrade, you have to buy everything anew. That's not a victory; the performance-to-power consumption ratio determines the winner.

Shouldn't you have replied to @SiliconFly instead?

 

[FangBLade]

Shouldn't you have replied to @SiliconFly instead?

I put him on ignore, we won't revisit that topic and go off-topic again.

 

[Mopetar]

We're supposedly about a month from launch, so it won't be too long before we know for sure.

 

[TESKATLIPOKA]

I put him on ignore, we won't revisit that topic and go off-topic again.

I don't care about that. My question was why you quoted me, but It was answered.

Raptor refresh is not interesting at all. MTL is what I am interested in.

 

[SiliconFly]

Raptor refresh is not interesting at all. MTL is what I am interested in.

Me too. I'm more interested in MTL. A monolithic RPL-R (on an outdated node) shouldn't even exist in this day & age.

But RPL-R taking the performance crown and beating the competition by a significant margin is worth a mention.

(Source: here. Related articles: here & here).

 

[TESKATLIPOKA]

But RPL-R taking the performance crown and beating the competition by a significant margin is worth a mention.

(Source: here. Related articles: here & here).

Yeah, yeah. I will wait for official tests to see reality, I am really not interested in Geekbench.

BTW, why you posted 3 different links mentioning the same ST and MT score is something I really can't understand.

Ok, at least wccftech also mentioned Geekbench 5 not just 6, but then It was enough to just post that link.

 

[SiliconFly]

BTW, why you posted 3 different links mentioning the same ST and MT score is something I really can't understand.

Just for better clarity.

 

[Kepler_L2]

14900K is just a rebranded 13900KS, it won't change anything in the performance stack.

 

[H433x0n]

14900K is just a rebranded 13900KS, it won't change anything in the performance stack.

It's a rebranded 13900K with process node tweaks to allow +200mhz clocks at iso power. It's a refresh so I don't think people are expecting much.

It will change the performance stack, just not for that long. Across the board 14600K, 14700K and 14900K will get a ~5% ST performance bump. This puts the 14900K ST performance ~15% higher than 7950X. That's not a negligible difference.

 

[gdansk]

If the buyers needs 10% faster opening of bloated Electron applications (which would be nice) and also doesn't mind 200W+ power draw when they do happen to run the wrong games or application they could have already bought a 13900K.
On the high end it's simply a 200MHz boost for people who somehow didn't think the 13900K was good enough at any point in the past year.

 

[ondma]

If the buyers needs 10% faster opening of bloated Electron applications (which would be nice) and also doesn't mind 200W+ power draw when they do happen to run the wrong games or application they could have already bought a 13900K.
On the high end it's simply a 200MHz boost for people who somehow didn't think the 13900K was good enough at any point in the past year.

Well, if one is building a new platform with Intel, they might as well get RPL-R, for a bit more performance at the same power. I dont think anyone is claiming it is a worthwhile upgrade from RPL.

 

[TESKATLIPOKA]

In CB R23 ST, It really could be 20% faster.
Not bad, but I am really not that keen on such high power draw, that's why I am more interested in MTL.

Well, if one is building a new platform with Intel, they might as well get RPL-R, for a bit more performance at the same power. I dont think anyone is claiming it is a worthwhile upgrade from RPL.

If someone is building a new platform, then this refresh is not a very good choice in my opinion.
1.) It doesn't look like It's upgradable to next gen.
2.) Very high power consumption
3.) Zen5 looks not to be too far away, I would at least wait to see how good It is.

 

[gdansk]

Well, if one is building a new platform with Intel, they might as well get RPL-R, for a bit more performance at the same power. I dont think anyone is claiming it is a worthwhile upgrade from RPL.

My line of thought is simply that if the 13900K wasn't good enough for you then the 14900K isn't cause to run to Microcenter.
For people building in the next few months it depends on what price cuts retailers manage for 13th gen because 200MHz isn't worth much.

There may be more interesting changes lower down in the stack.

 

[Abwx]

In CB R23 ST, It really could be 20% faster.

You know someone who makes renderings in ST...?..

And that s really the most favourable case for intel, that is, CB ST rendering, wich doesnt exist in real life...

 

[TESKATLIPOKA]

You know someone who makes renderings in ST...?..

And that s really the most favourable case for intel, that is, CB ST rendering, wich doesnt exist in real life...

If AMD won by 20% in CB ST you would be the first to shout out how great AMD is.

 

[SiliconFly]

If AMD won by 20% in CB ST you would be the first to shout out how great AMD is.

Thats so true.

AMD has a nice following. Intel not so much.

Intel being in gutter for so long has tarnished its own image. Maybe MTL can change that perspective a bit.

 

[TESKATLIPOKA]

AMD has a nice following. Intel not so much. Maybe MTL can change that perspective.

MTL will show us some improvements, not sure how big.
Maybe the biggest problem I have with Intel CPUs is not the power consumption but big-little approach.
AMD's approach is much more palatable to me.

 

[H433x0n]

If the buyers needs 10% faster opening of bloated Electron applications (which would be nice) and also doesn't mind 200W+ power draw when they do happen to run the wrong games or application they could have already bought a 13900K.
On the high end it's simply a 200MHz boost for people who somehow didn't think the 13900K was good enough at any point in the past year.

It’s not just the 14900K. It’s the entire lineup getting that 200mhz boost.

So you’ve got to factor in:

14600K vs 7600X/7700X
14700K vs 7900X
14900K vs 7950X

It’s a none negligible performance difference in all cases. The i9 will have +15% ST lead and a MT advantage.

Zen 4 efficiency advantage gets reduced since all of these gain +200mhz base clocks at 125W.

 

[SiliconFly]

MTL will show us some improvements, not sure how big.
Maybe the biggest problem I have with Intel CPUs is not the power consumption but big-little approach.
AMD's approach is much more palatable to me.

I'm sure the big.little is just a stop gap measure until their new core architecture is up and running properly.

But then again, if they make huge advancements in the future with the little cores, then it's a different story altogether. Who knows!

 

[TESKATLIPOKA]

It’s a none negligible performance difference in all cases. The i9 will have +15% ST advantage and a MT advantage.

That will be true in some cases, but there won't be +15% ST and MT advantage on average.

Zen 4 efficiency advantage gets reduced since all of these gain +200mhz base clocks at 125W.

That +200mhz at ISO power is not much and won't change anything.

Even in CB R23 MT, which is one of the best cases AMD would win and by a significant margin.
Ok, In the case of 7700X vs 14600K the difference wouldn't be big, but 7700X is not particularly efficient thanks to high clocks and only 8 cores.
13400K is also pretty efficient but at the cost of performance.

Spoiler: CB R23 nT efficiency

If you want it for games, then Raptor is also not doing good. The models with 3D cache are crushing everything.

Spoiler: TPU gaming efficiency average

 

[Abwx]

If AMD won by 20% in CB ST you would be the first to shout out how great AMD is.

Good exemple of bad faith, i said in other words that for CB only the MT score matters, but if you want to forge some falsehood about me that render you happy why not, when arguments are worthless only thing left is bs like your post....