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.

 

[tamz_msc]

People are too stuck up on how LP E-cores work on MTL to think that just because the Skymont cores in Lunar Lake are a different cluster with their own SLC, they are functionally similar to those of MTL.

It is obvious that they are still utilized whenever needed, even if the heavy-lifting is being done by the P-cores.

 

[DavidC1]

People are too stuck up on how LP E-cores work on MTL to think that just because the Skymont cores in Lunar Lake are a different cluster with their own SLC, they are functionally similar to those of MTL.

Perhaps rather than using a harsh tone and making a judgment on people, you might want to take a second look at the official Intel leak that says the E cores are for low priority applications.

 

[tamz_msc]

Perhaps rather than using a harsh tone and making a judgment on people, you might want to take a second look at the official Intel leak that says the E cores are for low priority applications.

That does not mean that when running something like Cinebench MT, those cores are sitting idle.

 

[SiliconFly]

.

 

[Hulk]

I'm so confused about Arrow Lake. Can someone answer the following questions with the best available info/evidence?

Will Arrow Lake be desktop only or desktop and mobile?

What is known about core counts/configurations?

What node(s) will it be using?

Will the P cores have hyperthreading?

I realize we don't have hard information at this point. I'm just curious as to what the best evidence supports regarding these questions.

 

[Ghostsonplanets]

And it also says, ARL will have 2 LPE cores in the I/O die.

IO die? I guess this is a workaround to the fact it's reusing MTL SoC Tile and thus it would have to reuse Crestmont as the LPE core.

I'm so confused about Arrow Lake. Can someone answer the following questions with the best available info/evidence?

Will Arrow Lake be desktop only or desktop and mobile?

What is known about core counts/configurations?

What node(s) will it be using?

Will the P cores have hyperthreading?

I realize we don't have hard information at this point. I'm just curious as to what the best evidence supports regarding these questions.

1 - Both. Mobile Intel next year will be composed on RPL U/H, MTL U, ARL U/H and LNL MX.

2 - Mobile up to 6P/8E. Desktop up to 8P/16E

3 - Intel 20A for some mobile dies. N3B for Desktop and Mobile (Including LNL)

4 - No. HT is done for the foreseeable future. Speculation now says Intel will replace it with Rental Units or whatever it comes from the fabled Royal Core/Exciting new Core project.

 

[SiliconFly]

.

 

[DavidC1]

The latest report from Bionic_Squash and others say Arrowlake 20A is only on 6+8 Desktop, and the rest are N3.

Other reports said Arrowlake does not have the useless LPE core. I think Videocard report is just speculation.

4 - No. HT is done for the foreseeable future. Speculation now says Intel will replace it with Rental Units or whatever it comes from the fabled Royal Core/Exciting new Core project.

Up next is likely the uop cache once they give up fanatical focus on clocks.

 

[tamz_msc]

The +2 in the config refers to the number of GT cores, not LP E cores.

 

[Hulk]

What's up with this? I assume this test was completed running Windows? Will this CPU actually be more performant and efficient than Inte/AMD offerings when we see it in laptops?

Snapdragon X Elite beats AMD and Intel flagship mobile CPUs in Geekbench 6 – Qualcomm's new laptop chip leads in single- and multi-core tests

ARM closes the gap with x86.

www.tomshardware.com

 

[Hitman928]

What's up with this? I assume this test was completed running Windows? Will this CPU actually be more performant and efficient than Inte/AMD offerings when we see it in laptops?

Snapdragon X Elite beats AMD and Intel flagship mobile CPUs in Geekbench 6 – Qualcomm's new laptop chip leads in single- and multi-core tests

ARM closes the gap with x86.

www.tomshardware.com

SPD-X will be mostly competing against Zen 5 and ARL. With that in mind, if we are to believe the rumors and consider this SPD-X score as final, then Zen 5 will have a significant performance lead and ARL a slight performance lead. Efficiency I won't comment on since we don't have actual power numbers yet for any of them.

Edit: The reference laptop they used as a demo machine had much better scores. Not sure what makes the "in the wild" scores so much lower but probably comes down to immature firmware.

 

[moinmoin]

Will this CPU actually be more performant and efficient than Inte/AMD offerings when we see it in laptops?

Performant in GB6's "MT" (which is really a limited cores test, rather than a reflection of multi core capability) anyway. No info about efficiency in that one.

 

[dullard]

What's up with this? I assume this test was completed running Windows? Will this CPU actually be more performant and efficient than Inte/AMD offerings when we see it in laptops?

Snapdragon X Elite beats AMD and Intel flagship mobile CPUs in Geekbench 6 – Qualcomm's new laptop chip leads in single- and multi-core tests

ARM closes the gap with x86.

www.tomshardware.com

That type of CPU is exactly why I've been saying that we shouldn't have AMD vs Intel fights. The real battle is ARM vs x86. AMD and Intel are on the same x86 team. Any infighting between them deflects attention from the real upcoming war against ARM.

 

[moinmoin]

That type of CPU is exactly why I've been saying that we shouldn't have AMD vs Intel fights. The real battle is ARM vs x86. AMD and Intel are on the same x86 team. Any infighting between them deflects attention from the real upcoming war against ARM.

Right, Intel and the x86 ecosystem as a whole are lucky to have AMD. Otherwise ARM would be seen as a clear winner for quite some time already. AMD's comeback took the wind out of a lot of ARM sails over the years (be it ARM servers, be it Apple Silicon, etc.). It's actually quite telling that plenty comparisons over the years were about ARM chips compared with Intel chips.

 

[Henry swagger]

Right, Intel and the x86 ecosystem as a whole are lucky to have AMD. Otherwise ARM would be seen as a clear winner for quite some time already. AMD's comeback took the wind out of a lot of ARM sails over the years (be it ARM servers, be it Apple Silicon, etc.). It's actually quite telling that plenty comparisons over the years were about ARM chips compared with Intel chips.

Lol

 

[Hulk]

How is this ARM cpu able to compete with native x86 designs? It must be using some type of emulation, which is normally a performance killer?

 

[tamz_msc]

How is this ARM cpu able to compete with native x86 designs? It must be using some type of emulation, which is normally a performance killer?

?
Geekbench has arm binaries with native support on Windows.

 

[gdansk]

How is this ARM cpu able to compete with native x86 designs? It must be using some type of emulation, which is normally a performance killer?

Microsoft has included an x86 and x64 emulator in ARM builds of Windows for sometime now.
Ex-microsoft employee Darek Mihochka, who lead development of this feature, goes over a history here of their emulation here: http://www.emulators.com/docs/abc_history_of_woa.htm
(he's now at Nvidia which @FlameTail may find interesting)

 

[igor_kavinski]

How is this ARM cpu able to compete with native x86 designs?

Woefully behind in some areas: https://forums.anandtech.com/threads/qualcomm-snapdragon-thread.2616013/post-41184685

 

[trivik12]

https://twitter.com/x/status/1776005067117592756

1st Lunar Lake mode ntel(R) Core(TM) Ultra 5 234V 2.10GHz

 

[igor_kavinski]

Oh, the "V" series. The jokes will never end...

 

[Schmide]

How is this ARM cpu able to compete with native x86 designs? It must be using some type of emulation, which is normally a performance killer?

Comes to mind. Arm has some cool instructions, ironically kind of complex, like VLD that permute RGB elements better than x86.

 

[S'renne]

Is there no more leaks on Arrow Lake?

 

[uzzi38]

Is there no more leaks on Arrow Lake?

Not a whole lot left to leak, is there?

 

[Hulk]

Not a whole lot left to leak, is there?

How about a nice solid, reliable, CB R23 score with the clock speed and power draw during the run? Those three numbers would tell us about 95% of what we need to know.