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

[Tigerick]

Wildcat Lake (WCL) Preliminary Specs

Intel Wildcat Lake (WCL) is upcoming mobile SoC replacing ADL-N. 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 Q2/Computex 2026. In case people don't remember AlderLake-N, I have created a table below to compare the detail specs of ADL-N and WCL. Just for fun, I am throwing LNL and upcoming Mediatek D9500 SoC.

		Intel Alder Lake - N	Intel Wildcat Lake	Intel Lunar Lake		Mediatek D9500
Launch Date		Q1-2023	Q2-2026 ?	Q3-2024		Q3-2025
Model		Intel N300	?	Core Ultra 7 268V		Dimensity 9500 5G
Dies		2	2	2		1
Node		Intel 7 + ?	Intel 18-A + TSMC N6	TSMC N3B + N6		TSMC N3P
CPU		8 E-cores	2 P-core + 4 LP E-cores	4 P-core + 4 LP E-cores		C1 1+3+4
Threads		8	6	8		8
Max Clock		3.8 GHz	?	5 GHz
L3 Cache		6 MB	?	12 MB
TDP		7 W	Fanless ?	17 W		Fanless
Memory		64-bit LPDDR5-4800	64-bit LPDDR5-6800 ?	128-bit LPDDR5X-8533		64-bit LPDDR5X-10667
Size		16 GB	?	32 GB		24 GB ?
Bandwidth			~ 55 GB/s	136 GB/s		85.6 GB/s
GPU		UHD Graphics		Arc 140V		G1 Ultra
EU / Xe		32 EU	2 Xe	8 Xe		12
Max Clock		1.25 GHz		2 GHz
NPU		NA	18 TOPS	48 TOPS		100 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.

 

[cannedlake240]

Their designs were being carried by foundry tbh till 14nm debacle now design needs to perform Hope Glenn Hilton gives us a repeat of Nehlam

If he was a part of Royal core, then unfortunately it's not happening. Intels best bet rn is probably to make a P core out of Atom

 

[igor_kavinski]

On the bright side, the iGPU is pretty performant compared to Raptor RIP so now more households can enjoy casual gaming!

 

[Det0x]

I'm not so sure it takes the ST crown and MT is very hit and miss.

I didn't see that. Even in browser benches it's generally behind Zen 5.

ST actually seems like Arrow Lakes weakest point
Best benchmarks for it looks to be 3dmark profiler and Cinebench R24

Also a known overclocker from a other forum have made a youtube video with his results (inhouse overclocker with everything superbinned maxed out)
285K @ static 5800 P-core + 5.300 E-core
9000MT/s Gear 2
And i guess everything else also maxed out, running on a mora radiator

Results are very close to my maxed 9950X, seems to be +- 1 to 3% in everything 🤣
Winning Geekbenches MT while losing in ST

 

[igor_kavinski]

Intels best bet rn is probably to make a P core out of Atom

If I were leading Intel, I would

1) re-hire Jim Keller as chief technology consultant and fire ANYONE on the spot who disagrees with him

2) shut off all fabs other than the extremely necessary ones

3) acquire the Oryon team from Qualcomm for $$ billions (give them an offer they won't refuse) and start making both x86-64 and WARM CPUs

4) create the top three flagship CPUs with dissimilar architecture cores (probably souped up Darkmont for P cores and Oryon cores for E-cores) and bribe Microsoft to include both architecture executables in Windows so that demanding ones always run on P-cores whereas services type of executables run on Oryon cores

2, 3 and 4 subject to change based on Keller's advice.

 

[desrever]

Power efficiency still pretty meh even with 3nm and all these "efficiency" cores. Multi threaded performance also not that amazing, basically ties zen 5 average.

People seem to be severely over estimating e-cores. The only thing they seem good for is optimizing the die area for Cinebench r24.

 

[TESKATLIPOKA]

* The best server product since Rome arrived
* Desktop is a super tiny niche and Intel's gains are comparable to Zen 5 - both are rather small
* GPU has been a standard "Koduri project" - think of AMD Vega
* Foundry remains to be seen
* Laptop is very good and actually is not a niche like desktop or discrete GPUs

Intel is fine

Intel is fine? I wholeheartedly disagree.
Foundry is a big problem. Just last year foundry had a $7B loss. That's why their operating income was only $93M despite them having $54.2B revenue!
This year and next year will be another loss in foundries, who knows how big, I wouldn't be surprised If It was even bigger with all the money paid to TSMC.
People shouldn't forget that the money they pay to TSMC is the money, which should have gone to their foundries.
Check out my post from a different thread. Link

As for the newly released Arrow Lake. I expected better MT performance than only 1.2% more than 14900K, IGP is pretty good, efficiency is also good, gaming performance is disappointing compared to Raptor Lake.
Didn't particularly impress me.

 

[dttprofessor]

If I were leading Intel, I would

1) re-hire Jim Keller as chief technology consultant and fire ANYONE on the spot who disagrees with him

2) shut off all fabs other than the extremely necessary ones

3) acquire the Oryon team from Qualcomm for $$ billions (give them an offer they won't refuse) and start making both x86-64 and WARM CPUs

4) create the top three flagship CPUs with dissimilar architecture cores (probably souped up Darkmont for P cores and Oryon cores for E-cores) and bribe Microsoft to include both architecture executables in Windows so that demanding ones always run on P-cores whereas services type of executables run on Oryon cores

2, 3 and 4 subject to change based on Keller's advice.

Client is profitable ,and will be good within 2-3 years. Pat pay more attention on fab & DCG.
Pat want PPA & PPW.

 

[cannedlake240]

acquire the Oryon team from Qualcomm for $$ billions

Or why not just let themselves get acquired by Qualcomm and then take over everything in a massive plot twist? Isn't Intel very good at politics

 

[Thunder 57]

If I were leading Intel, I would

1) re-hire Jim Keller as chief technology consultant and fire ANYONE on the spot who disagrees with him

2) shut off all fabs other than the extremely necessary ones

3) acquire the Oryon team from Qualcomm for $$ billions (give them an offer they won't refuse) and start making both x86-64 and WARM CPUs

4) create the top three flagship CPUs with dissimilar architecture cores (probably souped up Darkmont for P cores and Oryon cores for E-cores) and bribe Microsoft to include both architecture executables in Windows so that demanding ones always run on P-cores whereas services type of executables run on Oryon cores

2, 3 and 4 subject to change based on Keller's advice.

You forgot the sarcasam tag.

Why would Jim Keller want to go back to Intel? Also, why do so many think of him as a god and give him credit for things he didn't do? Fire anyone who dare disagree? That'll show 'em! Wait, how did we suddenly become full of groupthink? What happened to diversity of thought? Oh yea, we fired them all.

Create three flagship CPU's. Gee, that's like saying why not call a "touchdown play" every play?

 

[Tup3x]

Meh, I don't know what to say really. Performance is all over the place.

 

[controlflow]

The DLVR topic is pretty interesting on this platform

The DLVR improves efficiency at low and medium mixed core loads but hurts it for all core loads. However if you bypass the DLVR, you get a nice efficiency boost for workstation/all core loads.

You can see in the above video the 285K scored 43k+ in CB R23 with the VRMs feeding ~180 W into the CPU with DLVR bypass.

With OC and tune it manages 47k+ @ 215W

Intel Core Ultra 9 285k 'Arrow Lake' Discussion/News ("15th gen") on LGA-1851

it is free basically. i just use fake dollars conjured up out of nowhere. just add it to the global credit card bill. Global public debt is projected to go above $100 trillion this year. :cry: I think loyalty was buying a bulldozer chip, back in the day. but that time is in the past. it...

forums.overclockers.co.uk

Looks like a decent platform for tuning and tinkering but the gaming performance looks rough no matter how you slice it. Der8auer managed to OC and tune it to get some pretty strong average FPS numbers but the 1% lows still look funky, not to mention that things are just buggy in general.

ARL probably will do better in laptops than in desktops.

 

[Abwx]

ST actually seems like Arrow Lakes weakest point
Best benchmarks for it seems to be 3dmark profiler and Cinebench R24

Also a known overclocker from a other forum have made a youtube video with his results (inhouse overclocker with everything superbinned maxed out)
285K @ static 5800 P-core + 5.300 E-core
9000MT/s Gear 2
And i guess everything else maxed out, running on a mora radiator

Results are very close to my maxed 9950X, seems to be +- 1 to 3 in everything 🤣
Winning Geekbenches MT while losing in ST
View attachment 110228

So far CB seems an exception, as for ST the 9950X is ahead in GB4.4, GB5.0, GB5.5, GB6, XPRT3 and 4, Kraken, 7 Zip ST and even in the Intel MT friendly Affinity Photo when the test is done on ST.

That s really a lot even if the gap is often quite small, although for XPRT3/4 it s 8/17% and 8% for 7 Zip ST where the 7950X is better at +15%.

Btw NBC made a separate review for the 245K :

https://www.notebookcheck.net/Intel-Core-Ultra-5-245K-review-The-perfect-balance-between-power-and-efficiency.906819.0.html

 

[511]

If I were leading Intel, I would

1) re-hire Jim Keller as chief technology consultant and fire ANYONE on the spot who disagrees with him

2) shut off all fabs other than the extremely necessary ones

3) acquire the Oryon team from Qualcomm for $$ billions (give them an offer they won't refuse) and start making both x86-64 and WARM CPUs

4) create the top three flagship CPUs with dissimilar architecture cores (probably souped up Darkmont for P cores and Oryon cores for E-cores) and bribe Microsoft to include both architecture executables in Windows so that demanding ones always run on P-cores whereas services type of executables run on Oryon cores

2, 3 and 4 subject to change based on Keller's advice.

No one can do anything with 2 due to Joint agreement with equity and Governments conditions so might as well remove it

 

[Hans Gruber]

So far CB seems an exception, as for ST the 9950X is ahead in GB4.4, GB5.0, GB5.5, GB6, XPRT3 and 4, Kraken, 7 Zip ST and even in the Intel MT friendly Affinity Photo when the test is done on ST.

That s really a lot even if the gap is often quite small, although for XPRT3/4 it s 8/17% and 8% for 7 Zip ST where the 7950X is better at +15%.

Btw NBC made a separate review for the 245K :

https://www.notebookcheck.net/Intel-Core-Ultra-5-245K-review-The-perfect-balance-between-power-and-efficiency.906819.0.html

Intel really needed to keep hyperthreading. It's easy to see why Intel is behind without it.

 

[desrever]

So far CB seems an exception, as for ST the 9950X is ahead in GB4.4, GB5.0, GB5.5, GB6, XPRT3 and 4, Kraken, 7 Zip ST and even in the Intel MT friendly Affinity Photo when the test is done on ST.

That s really a lot even if the gap is often quite small, although for XPRT3/4 it s 8/17% and 8% for 7 Zip ST where the 7950X is better at +15%.

Btw NBC made a separate review for the 245K :

https://www.notebookcheck.net/Intel-Core-Ultra-5-245K-review-The-perfect-balance-between-power-and-efficiency.906819.0.html

Should rename these as Intel Cinebench Ultra 285k

 

[DavidC1]

The DLVR topic is pretty interesting on this platform

DeBauer's test shows overclocking the ring from 3.8GHz to 4.2GHz results in 5% gains in one game and 7% in another.

That's quite a bit of an increase for just 10% increase in ring clocks.

@adroc_thurston Told ya the larger L2 cache won't be enough to make up for slow ring.

 

[Hitman928]

* Intel *still* rides all the OEMs after all those years when AMD offered far more competitive products than now.
* Desktops aka the big boxes sitting at a desk are a niche - even detachable x-in-ones are larger
* dGPUs other than nVidia are on life support in general - AMD's been delaying their next-gen which even got the highend segment canned completely...
* I got no clue about their margins

• Server spend has shifted a huge chunk to cloud where AMD has more than 50% share. AMD has been slower to gain share in Enterprise, largely thanks to Intel offering huge discounts to try and hold onto share, but that has cratered their own revenue and margins and AMD has finally started picking up momentum in Enterprise anyway.
• Desktops aren't niche. They are significantly smaller than laptops but still have a very significant portion of the market. Super high end desktops are niche.
• Intel has 0% of the market share and only lost money. AMD still makes money on their GPU efforts.
• Intel's gross margins suck and are at historic lows, that is all.

 

[adroc_thurston]

Told ya the larger L2 cache won't be enough to make up for slow ring.

Yeah looks rough. TGL was roughly on par, this is a bit worse.

 

[BigDH01]

Or why not just let themselves get acquired by Qualcomm and then take over everything in a massive plot twist? Isn't Intel very good at politics

Worked for Boeing's "acquisition" of McDonnell Douglas.

 

[Hitman928]

The DLVR topic is pretty interesting on this platform

The DLVR improves efficiency at low and medium mixed core loads but hurts it for all core loads. However if you bypass the DLVR, you get a nice efficiency boost for workstation/all core loads.

You can see in the above video the 285K scored 43k+ in CB R23 with the VRMs feeding ~180 W into the CPU with DLVR bypass.

With OC and tune it manages 47k+ @ 215W

Intel Core Ultra 9 285k 'Arrow Lake' Discussion/News ("15th gen") on LGA-1851

it is free basically. i just use fake dollars conjured up out of nowhere. just add it to the global credit card bill. Global public debt is projected to go above $100 trillion this year. :cry: I think loyalty was buying a bulldozer chip, back in the day. but that time is in the past. it...

forums.overclockers.co.uk

Looks like a decent platform for tuning and tinkering but the gaming performance looks rough no matter how you slice it. Der8auer managed to OC and tune it to get some pretty strong average FPS numbers but the 1% lows still look funky, not to mention that things are just buggy in general.

ARL probably will do better in laptops than in desktops.

Integrated voltage regulators do OK in efficiency when the voltage difference is small but when they voltage difference increases, their efficiency drops off a cliff. With DLVR bypass, the VRM's are probably less efficient, so at the system level you're not gaining as much as you think in all core loads, but the VRMs probably handle it better than the integrated regulators.

 

[DavidC1]

The DLVR improves efficiency at low and medium mixed core loads but hurts it for all core loads. However if you bypass the DLVR, you get a nice efficiency boost for workstation/all core loads.

This is EXACTLY what Intel patent said years ago.

DLVR is a linear regulator. It is by itself an overall efficiency loss. But because of the way it behaves on a CPU, it can be a gain. DLVR parallels regulators so it can result in less voltage droop when "burst" increase in power is required. That's why it's better on low/med loads.

 

[jpiniero]

• Server spend has shifted a huge chunk to cloud where AMD has more than 50% share. AMD has been slower to gain share in Enterprise, largely thanks to Intel offering huge discounts to try and hold onto share but that has cratered their own revenue and margins and AMD has finally started picking up momentum in Enterprise anyway.

Which is why Intel can't afford the foundries.

• Desktops aren't niche. They are significantly smaller than laptops but still have a very significant portion of the market. Super high end desktops are niche.

Intel makes way more money just on desktops compared to AMD's entire client business.

 

[Josh128]

You forgot the sarcasam tag.

Why would Jim Keller want to go back to Intel? Also, why do so many think of him as a god and give him credit for things he didn't do? Fire anyone who dare disagree? That'll show 'em! Wait, how did we suddenly become full of groupthink? What happened to diversity of thought? Oh yea, we fired them all.

Create three flagship CPU's. Gee, that's like saying why not call a "touchdown play" every play?

Forget Keller, what Intel need is to get Raja back in the fold.

 

[igor_kavinski]

Meh, I don't know what to say really. Performance is all over the place.

*Plays Michael Jackson's Speechless song*

 

[igor_kavinski]

what Intel need is to get Raja back in the fold.

Intel goes stealth for five years.

Comes out with Bulldozer 2.0 !!!