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.

 

[gdansk]

KUBAR LAKLBE

You OK?

 

[SiliconFly]

.

 

[SiliconFly]

.

 

[FlameTail]

You OK?

I thought we agreed to call it that.

/s

 

[FlameTail]

View attachment 93997

Looks stable enough. Might actually launch in 2024 as planned!

Okay! okay! I get it. It's GENUINE.

 

[igor_kavinski]

Those cache sizes look unusual. I think first x86 CPU I've seen that has more L2 than L3. According to the translation, LNL P-cores have 2.5MB per core L2 so with a smaller L3, it has got to be an exclusive cache otherwise 2MB of evicted data from the P/E cores will get discarded even if it is hot data. So is this going to be Intel's first exclusive L3 cache since Google tells me that Intel caches are usually inclusive.

 

[adroc_thurston]

So is this going to be Intel's first exclusive L3 cache since Google tells me that Intel caches are usually inclusive.

They've been exclusive since Willow Cove.
(or SKX-SP if you're into server).

 

[Abwx]

What a dumb idea to use Meteor Lake in a handheld. It's most likely graphics drivers and CPU power consumption as to the culprit.

Particularly the CPU even if in games it does not use as much power as the GPU, but still, there s a review at NBC still untranslated but if anything a 155H score about 1400pts in CB R15 at 24W, at the same power a competing 7840U score 1800pts, that s roughly 25% better perf and this amount to 1.5 -1.6x more power for the 155H to match its AMD counterpart, actually the CPU part of MTL doesnt seem to be much better than RPL.

 

[Saylick]

While I believe that MTL will end up a bit slower, I'd like to point out that ROG Ally is a mature device at this point. It's performance at low power envelopes has gotten a lot better since release, so I think there's quite a bit of headroom for the Claw to grow.

By the time MTL finally has an updated BIOS, updated graphics drivers, updated Windows scheduler, and wide-spread availability, Strix Point would have launched.

 

[mikk]

By the time MTL finally has an updated BIOS, updated graphics drivers, updated Windows scheduler, and wide-spread availability, Strix Point would have launched.

You mean paper launched right?

 

[igor_kavinski]

They've been exclusive since Willow Cove.

So what's your theory on the lower L3 for LNL? Keeping it small for lower latency? Ran out of die space?

 

[igor_kavinski]

You mean paper launched right?

Better paper launch than a botched launch. What is Intel's strategy with MTL? Fine wine SoC?

 

[Philste]

So what's your theory on the lower L3 for LNL? Keeping it small for lower latency? Ran out of die space?

It's 3MB per Core, like every Intel Design of the last years. Don't forget E Cores have no L3 access in LNL. It's just the 4 P-Cores on that 12MB L3.

 

[Tigerick]

It's 3MB per Core, like every Intel Design of the last years. Don't forget E Cores have no L3 access in LNL. It's just the 4 P-Cores on that 12MB L3.

Yeah, now that E cores are not on the same ring bus, 12MB L3 cache make more sense. That's mean E cores can consider as LPe cores in LNL.

 

[igor_kavinski]

Yeah, now that E cores are not on the same ring bus, 12MB L3 cache make more sense than rumored 8MB. That's mean E cores can consider as LPe cores in LNL.

So now the Windows scheduler must be updated again not to switch threads mid-execution across different core types or it will incur a much higher context switch penalty.

 

[mikk]

Better paper launch than a botched launch. What is Intel's strategy with MTL? Fine wine SoC?

A paper launch is worthless if nobody can buy something. But maybe that's why AMDs market share is so low in the notebook market, they keep launching paper products and people like you applaud them for their great strategy.

 

[igor_kavinski]

A paper launch is worthless if nobody can buy something. But maybe that's why AMDs market share is so low in the notebook market, they keep launching paper products and people like you applaud them for their great strategy.

I have a sneaky suspicion that Lenovo and HP buy up their paper launched CPUs in bulk for their enterprise customers so there's barely enough left for consumers. And AMD is content with not producing too much. In other words, they are like the unambitious local fried chicken joint that sells whatever they make and make a comfy living doing it while Intel is KFC.

 

[Abwx]

A paper launch is worthless if nobody can buy something. But maybe that's why AMDs market share is so low in the notebook market, they keep launching paper products and people like you applaud them for their great strategy.

I smell desperation here, MTL has vastly lower perf/watt than PHX, they wouldnt even need to release Strix Point this year, but once it land the gap will be roughly 2x the perf/watt.

 

[mikk]

I smell desperation here, MTL has vastly lower perf/watt than PHX, they wouldnt even need to release Strix Point this year, but once it land the gap will be roughly 2x the perf/watt.

He is moaning about a non widerspread available Meteor Lake and at the same time cheer for a paper launch of Strix Point. The so much better perf/watt doesn't seem to transfer into a better battery life by the way. AMD should release something new (with real volume of course) if they want to increase their notebook market share.

 

[Abwx]

He is moaning about a non widerspread available Meteor Lake and at the same time cheer for a paper launch of Strix Point. The so much better perf/watt doesn't seem to transfer into a better battery life by the way. AMD should release something new (with real volume of course) if they want to increase their notebook market share.

Granted a 14" Lenovos FI use an IPS for a 7840U FI but with a 51Wh battery it hold as much time as the 14" HP 360 with a OLED but 67Wh battery, so essentially Intel today is barely selling last year s battery life and boast it as a great acheievment, and i wont talk of real usage.

Now if you were to use the laptop such that it drain about 10-15W CPU power the PHX would last 50% more time at equivalent configuration, both laptops are throttled at 24W, compare the CB R15 scores once throthling occur and you ll understand that Intel is several years late with their 2024 product.

If Intel manage to keep a big marketshare that s surely not due to competitivness
but rather to their usual dirty tricks.

https://www.notebookcheck.com/HP-Spectre-x360-14-im-Test-High-End-Convertible-jetzt-mit-groesserem-120-Hz-OLED.801566.0.html

https://www.notebookcheck.com/Lenovo-ThinkPad-T14s-G4-im-Test-Business-Laptop-ist-besser-mit-AMD-Zen4.762542.0.html

 

[controlflow]

If Intel manage to keep a big marketshare that s surely not due to competitivness
but rather to their usual dirty tricks.

The AMD platforms are nonexistent for months after "launch" and then when they do arrive they are still scarce and rarely ever in the most desirable designs. I'm not sure how you can blame AMD's paper launching tendencies on Intel's dirty tricks.

 

[jpiniero]

If Intel manage to keep a big marketshare that s surely not due to competitivness
but rather to their usual dirty tricks.

IMO, it's a cost issue. TSMC's prices plus AMD spends too much silicon on the IGP. That and Corpo apathy.

Corpos who care buy Apple.

 

[Khato]

Granted a 14" Lenovos FI use an IPS for a 7840U FI but with a 51Wh battery it hold as much time as the 14" HP 360 with a OLED but 67Wh battery, so essentially Intel today is barely selling last year s battery life and boast it as a great acheievment, and i wont talk of real usage.

Now if you were to use the laptop such that it drain about 10-15W CPU power the PHX would last 50% more time at equivalent configuration, both laptops are throttled at 24W, compare the CB R15 scores once throthling occur and you ll understand that Intel is several years late with their 2024 product.

If Intel manage to keep a big marketshare that s surely not due to competitivness
but rather to their usual dirty tricks.

I'm sure we're all stunned to see yet another comparison of a 7840U laptop with an IPS screen that's 45% the resolution and half the refresh rate of the OLED screen on the Meteor Lake laptop.

Guess what happens when that Meteor Lake HP Spectre is compared against a 7840U laptop with the same battery size and display? Surprise, Meteor Lake comes out on top with 555 minutes on the WiFi test versus 510 minutes for the 7840U. https://www.notebookcheck.net/HP-Pa...Changes-in-all-the-right-places.765524.0.html

No question that AMD has a marginal lead on compute and graphics efficiency over Meteor Lake. Unfortunately for AMD, that doesn't count for much. There being a laptop available in the right size, form factor, and screen for the right price is what matters to the overwhelming majority of consumers, not whether the sticker says Intel or AMD. I point that out because while it's fun to discuss the merits of one chip versus another there shouldn't be any expectation of such being reflected in the market.

 

[DAPUNISHER]

Better paper launch than a botched launch. What is Intel's strategy with MTL? Fine wine SoC?

Fine Blueberry 🫐 wine, get it right.

All we have seen is ARC get better week by week. Why would this be any different? Performance per watt, particularly at lower power isn't going to dazzle, but that's okay. It's the first attempt and we need the competition in the handheld space.

 

[branch_suggestion]

https://twitter.com/x/status/1758875038130794977

What on earth is IDC doing?