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

[Tigerick]

Wildcat Lake (WCL) Specs

Intel Wildcat Lake (WCL) is upcoming mobile SoC replacing Raptor Lake-U. WCL consists of 2 tiles: compute tile and PCD tile. It is true single die consists of CPU, GPU and NPU that is fabbed by 18-A process. Last time I checked, PCD tile is fabbed by TSMC N6 process. They are connected through UCIe, not D2D; a first from Intel. Expecting launching in Q1 2026.

		Intel Raptor Lake U	Intel Wildcat Lake 15W?	Intel Lunar Lake		Intel Panther Lake 4+0+4
Launch Date		Q1-2024	Q2-2026	Q3-2024		Q1-2026
Model		Intel 150U	Intel Core 7	Core Ultra 7 268V		Core Ultra 7 365
Dies		2	2	2		3
Node		Intel 7 + ?	Intel 18-A + TSMC N6	TSMC N3B + N6		Intel 18-A + Intel 3 + TSMC N6
CPU		2 P-core + 8 E-cores	2 P-core + 4 LP E-cores	4 P-core + 4 LP E-cores		4 P-core + 4 LP E-cores
Threads		12	6	8		8
Max Clock		5.4 GHz	?	5 GHz		4.8 GHz
L3 Cache		12 MB		12 MB		12 MB
TDP		15 - 55 W	15 W ?	17 - 37 W		25 - 55 W
Memory		128-bit LPDDR5-5200	64-bit LPDDR5	128-bit LPDDR5x-8533		128-bit LPDDR5x-7467
Size		96 GB		32 GB		128 GB
Bandwidth				136 GB/s
GPU		Intel Graphics	Intel Graphics	Arc 140V		Intel Graphics
RT		No	No	YES		YES
EU / Xe		96 EU	2 Xe	8 Xe		4 Xe
Max Clock		1.3 GHz	?	2 GHz		2.5 GHz
NPU		GNA 3.0	18 TOPS	48 TOPS		49 TOPS

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.

 

[SiliconFly]

.

 

[FlameTail]

Which Lake will use the 18A-P node?

 

[SiliconFly]

.

 

[igor_kavinski]

Intel Arrow Lake-S to feature Xe-LPG architecture without "Plus", Arrow Lake-H gets the Xe-LPG+ variant - VideoCardz.com

Intel Arrow Lake-S with Xe-LPG graphics without the plus Intel is gearing up to launch its Arrow Lake architecture by the end of this year. Arrow Lake will be the company’s first top-to-bottom client architecture featuring entirely new CPU and GPU architecture in years. The series following...

videocardz.com

Oh no. Desktop ARL iGPU gets shafted. AGAIN!

Oh well. Looks like Intel wants AMD to continue their desktop APU superiority.

 

[DavidC1]

You can't simply compare Xe1 with Xe2 and Xe3 and assume nothing will change. And who says Nova Lake gets 20 Xe cores, this is just a guess from someone. Strix Halo might be irrelevant for mobile, better wait and see. If this thing costs 3k up and comes with dGPU and tiny volume who cares. Strix Point is what really matters for mobile.

Strix Halo is a 256 bit part. Its a completely different beast.

20 Xe core part most likely still will be 128 bit, same as that 12 Xe core part.

Thats the first thing.

Secondly they will be different architecture - Battlemage, instead of Alchemist. The performance/core will change.

Im willing to say that Intel will catch up to AMD with perf/ALU. At least to AMD.

Were you guys paying attention to what Tigerick has been saying? My reply has been to that. He said it'll be 20 Xe cores, and mentioned something like being a big iGPU, when my retort was that 20 Xe in 2027 is not big at all. It's like being impressed with news saying "Meteorlake has 128EUs!" back in 2021, when we'd eventually find out Meteorlake performs like AMD's iGPU but a year later!

AMD will have 16 CUs in Strix point. They'll have something similar for mainstream to equal 20 Xe(~26 CUs) in 2027, if not better. History does not favor Intel iGPUs.

 

[DavidC1]

Xe3 on Panther Lake sounds a bit unlikely if you ask me. It's difficult for them to come out with a new gen igpu in a short span of just 12 months. Doesn't sound like Intel at all.

For example, ARL is coming out with Xe+ or Xe++ this year end. That'd be roughly 3 years since Xe launch. Not very inspiring.

Yes, but Lunarlake is Xe2.

Also, Pantherlake should be a year after Arrowlake, or late 2025/early 2026. That's nearly 24 month away.

 

[DrMrLordX]

Oh no. Desktop ARL iGPU gets shafted. AGAIN!

Probably not the most important part of desktop Arrow Lake. All eyes are going to be on the P cores.

 

[igor_kavinski]

All eyes are going to be on the P cores.

Which are likely to fail so a good iGPU could've provided some solace.

 

[ondma]

Intel Arrow Lake-S to feature Xe-LPG architecture without "Plus", Arrow Lake-H gets the Xe-LPG+ variant - VideoCardz.com

Intel Arrow Lake-S with Xe-LPG graphics without the plus Intel is gearing up to launch its Arrow Lake architecture by the end of this year. Arrow Lake will be the company’s first top-to-bottom client architecture featuring entirely new CPU and GPU architecture in years. The series following...

videocardz.com

Oh no. Desktop ARL iGPU gets shafted. AGAIN!

Oh well. Looks like Intel wants AMD to continue their desktop APU superiority.

Who cares on the desktop?

 

[igor_kavinski]

Who cares on the desktop?

Enemies of heat, noise, power cables sticking out and going into the discrete GPU, melting connectors etc.

 

[FlameTail]

Intel Arrow Lake-S to feature Xe-LPG architecture without "Plus", Arrow Lake-H gets the Xe-LPG+ variant - VideoCardz.com

Intel Arrow Lake-S with Xe-LPG graphics without the plus Intel is gearing up to launch its Arrow Lake architecture by the end of this year. Arrow Lake will be the company’s first top-to-bottom client architecture featuring entirely new CPU and GPU architecture in years. The series following...

videocardz.com

Oh no. Desktop ARL iGPU gets shafted. AGAIN!

Let them keep trying. Eventually, a good iGPU will be born.

 

[Goop_reformed]

ARL compute tile will use 20A on some SKUs, but most of the volume will be on TSMC's N3B according to rumors + leaked document.

N3 for Arrow Lake & N3B for Lunar Lake

Intel CEO Discloses TSMC Production Details: N3 for Arrow Lake & N3B for Lunar Lake

Intel CEO Pat Gelsinger engaged with press/media representatives following the conclusion of his IFS Direct Connect 2024 keynote speech—when asked about Team Blue's ongoing relationship with TSMC, he confirmed that their manufacturing agreement has advanced from "5 nm to 3 nm." According to a...

www.techpowerup.com

 

[ondma]

Enemies of heat, noise, power cables sticking out and going into the discrete GPU, melting connectors etc.

I will give you a serious answer. For non gaming uses, pretty much any recent integrated solution is sufficient. For gaming, they are a limited low end solution. A better igpu may be of some benefit, but they would not be the determining factor if I were purchasing a new cpu. We have been hearing since the days of "Fusion is the future" how APUs are going to be the next great thing. Still waiting.

 

[Hitman928]

N3 for Arrow Lake & N3B for Lunar Lake

Intel CEO Discloses TSMC Production Details: N3 for Arrow Lake & N3B for Lunar Lake

Intel CEO Pat Gelsinger engaged with press/media representatives following the conclusion of his IFS Direct Connect 2024 keynote speech—when asked about Team Blue's ongoing relationship with TSMC, he confirmed that their manufacturing agreement has advanced from "5 nm to 3 nm." According to a...

www.techpowerup.com

There is no N3.

 

[FlameTail]

There is no N3.

There was.

It's dead now.

 

[igor_kavinski]

Still waiting.

Better than a low end card like RX 6400 or Geforce 1650: https://forums.anandtech.com/threads/amd-8700g-igpu-is-pretty-good.2617243/post-41163075

AMD Radeon 780M Specs

AMD Phoenix, 2700 MHz, 768 Cores, 48 TMUs, 32 ROPs

www.techpowerup.com

APUs have come a long way and only thanks to AMD.

 

[mikk]

Better than a low end card like RX 6400 or Geforce 1650: https://forums.anandtech.com/threads/amd-8700g-igpu-is-pretty-good.2617243/post-41163075

It is worse not better, check out real tests.

 

[cebri1]

 

[ondma]

Better than a low end card like RX 6400 or Geforce 1650: https://forums.anandtech.com/threads/amd-8700g-igpu-is-pretty-good.2617243/post-41163075

AMD Radeon 780M Specs

AMD Phoenix, 2700 MHz, 768 Cores, 48 TMUs, 32 ROPs

www.techpowerup.com

View attachment 94406

APUs have come a long way and only thanks to AMD.

But at best, nearly equal to, and in most cases, significantly slower than my ancient 1060 6GB, extrapolating from the 6500XT comparison on Techspot. In any case, I didnt mean to derail this Inte cpul thread with discussion of graphics performance of an AMD cpu, so I will end the conversation.

 

[Glo.]

Were you guys paying attention to what Tigerick has been saying? My reply has been to that. He said it'll be 20 Xe cores, and mentioned something like being a big iGPU, when my retort was that 20 Xe in 2027 is not big at all. It's like being impressed with news saying "Meteorlake has 128EUs!" back in 2021, when we'd eventually find out Meteorlake performs like AMD's iGPU but a year later!

AMD will have 16 CUs in Strix point. They'll have something similar for mainstream to equal 20 Xe(~26 CUs) in 2027, if not better. History does not favor Intel iGPUs.

It is big, 20 Xe cores is 2560 ALUs.

Its the same number of ALUs as RX 6700 XT. For mainstream SOCs - it will still be apropriate.

 

[Hitman928]

View attachment 94408

Seems like there’s really no advantage in going with an 185h over a 155h, outside of a very modest bump in single threaded performance.

 

[SiliconFly]

.

 

[TESKATLIPOKA]

It is big, 20 Xe cores is 2560 ALUs.

Its the same number of ALUs as RX 6700 XT. For mainstream SOCs - it will still be apropriate.

Number of ALUs or Xe doesn't tell you much without knowing the clockspeed.
Then you also need to feed It, that looks like the biggest problem in my opinion.

 

[FlameTail]

Number of ALUs or Xe doesn't tell you much without knowing the clockspeed.
Then you also need to feed It, that looks like the biggest problem in my opinion.

Case in point: Adreno GPU in 8G3, which is a smartphone SoC, has 1792 ALUs (!), which is more than even some dGPUs I believe?

 

[TESKATLIPOKA]

Case in point: Adreno GPU in 8G3, which is a smartphone SoC, has 1792 ALUs (!), which is more than even some dGPUs I believe?

Please stop comparing apples to oranges.

MTL IGP with only 8 XEs is fed by 128-bit 5600-7500mbps (LP)DDR5(x). 20 XEs will need a lot more, unless clockspeed will take a drastic hit.