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+4+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.

 

[DavidC1]

Well it's even greater than that

Ultra X9 388H性能分析：重铸Intel荣光_哔哩哔哩_bilibili

在刚刚过去的CES上，Intel放出豪言壮语：第三代酷睿Ultra处理器（代号Panther Lake）的多核性能比ARL-H更强，续航表现比LNL更好，集显性能直逼4050！这要真能落实下来，那可太厉害了，今天我拿到了这台搭载第三代英特尔酷睿Ultra处理器的联想 小新Pro16 GT AI元启版，不仅散热给力，内存频率拉满，电池还升级到了99.9Wh，可以好好测测看Intel到底是不是吹牛了！, 视频播放量 61041、弹幕量 608、点赞数 4503、投硬币枚数 1232、收藏人数 870、转发人数 860, 视频作者 笔吧评测室, 作者简介...

www.bilibili.com

Lunarlake is lower latency than Arrowlake, that's why I said 10ns.

Look at that, Darkmont is beating Zen 5 per clock, and is near Lion Cove. Within 1%. The LPE cores are faster than Lunarlake too per clock.

 

[regen1]

That was my thought too. Smaller die give you better yields. The trick is to keep performance up when you have so many die to die interfaces to maneuver around. I agree that the highest performant solution is monolithic, it just doesn't seem to be the right answer today if you want your company to remain solvent .

Just checking, since you and few others were mentioning "Zen5 CCD" size, did you by chance miss the part that AMD's mainstream notebook series (Strix Point, Hawk Point, etc.) are monolithic ?
Strix Point's die size is slightly above 230mm^2 (232.5 or something).

 

[DavidC1]

Hardwarecanucks review is showing similar performance to M5 GPU both at 25W in Cyberpunk.

 

[Abwx]

Look at that, Darkmont is beating Zen 5 per clock, and is near Lion Cove. Within 1%. The LPE cores are faster than Lunarlake too per clock.

If that was the case then it should at least match the HX370 given that there s 33% more cores and that CB is quite a better case for Intel, but that doesnt happen.

 

[regen1]

From some of the initial reviews battery life improvements feel pretty decent esp. considering it doesn't have the "memory-on-package" and PMIC of Lunar Lake.

 

[adroc_thurston]

If that was the case then it should at least match the HX370 given that there s 33% more cores and that CB is quite a better case for Intel, but that doesnt happen.

R23 loves ayymd and hates Intel.
2024 is the reverse.

 

[adroc_thurston]

From some of the initial reviews battery life improvements feel pretty decent esp. considering it doesn't have the "memory-on-package" and PMIC of Lunar Lake.

BL@Wh seems the same or worse than LNL.
They just stuffed a 99Wh battery (based) innit.

 

[Abwx]

R23 loves ayymd and hates Intel.
2024 is the reverse.

That s simply not true, you can check at Computerbase, that s about the same difference as CB 2024, beside we can see that it require 55W to match the HX370@45W, methink that s where DavidC1 made the confusion about perf/clock, he thought that power usages were the same.

Edit : The only strong point is the GPU, but at 2600€ that will hardly be a selling point.

 

[regen1]

If that was the case then it should at least match the HX370 given that there s 33% more cores and that CB is quite a better case for Intel, but that doesnt happen.

Adding CB 2024 to the context


In both cases X9 388H gets sizable MT improvements over U9 285H.
Those graphs show compared to HX 370 it is better in CB 2024 and behind in CB 2023.

 

[regen1]

BL@Wh seems the same or worse than LNL.
They just stuffed a 99Wh battery (based) innit.

Battery life compared to LNL it depends on the workload but vs ARL-H it's a good improvement. This is pretty solid esp. in x86 world.

 

[Win2012R2]

Looks like a nice chip, but it's 18A vs N4 (and 18 months old arch), nice improvements tho, wonder at what cost.

 

[adroc_thurston]

but vs ARL-H it's a good improvement

Idk until I see same chassis same battery compare.

This is pretty solid esp. in x86 world.

Solid vs 3yo fabric/mem IP.
that's not forever.

 

[Abwx]

Adding CB 2024 to the context
View attachment 137338

In both cases X9 388H gets sizable MT improvements over U9 285H.
Those graphs show compared to HX 370 it is better in CB 2024 and behind in CB 2023.

Every new version of CB came at the rescue of Intel, ARL has better perf/watt than the 9950X in CB2024 but is far behind in X264, i wouldnt be surprised if CB 2026 follow the same trend.
You can follow the evolution since R15 in this review :

https://www.notebookcheck.net/Asus-ZenBook-Duo-UX8407-convertible-review-Intel-Panther-Lake-is-a-game-changer.1212285.0.html

 

[MoistOintment]

Well it's even greater than that

Ultra X9 388H性能分析：重铸Intel荣光_哔哩哔哩_bilibili

在刚刚过去的CES上，Intel放出豪言壮语：第三代酷睿Ultra处理器（代号Panther Lake）的多核性能比ARL-H更强，续航表现比LNL更好，集显性能直逼4050！这要真能落实下来，那可太厉害了，今天我拿到了这台搭载第三代英特尔酷睿Ultra处理器的联想 小新Pro16 GT AI元启版，不仅散热给力，内存频率拉满，电池还升级到了99.9Wh，可以好好测测看Intel到底是不是吹牛了！, 视频播放量 61041、弹幕量 608、点赞数 4503、投硬币枚数 1232、收藏人数 870、转发人数 860, 视频作者 笔吧评测室, 作者简介...

www.bilibili.com

View attachment 137334
View attachment 137333

Those are pretty substantial latency improvements vs ARL-H. Wonder what this means for NVL-S vs ARL-S latency improvements

 

[OneEng2]

From some of the initial reviews battery life improvements feel pretty decent esp. considering it doesn't have the "memory-on-package" and PMIC of Lunar Lake.

I think that battery life may well be more important than gaming in this segment.

Looks like a nice chip, but it's 18A vs N4 (and 18 months old arch), nice improvements tho, wonder at what cost.

Indeed. Doesn't do much good if the company goes bankrupt making the chips.

 

[coercitiv]

the Single Core performance is my only issue with these rn no improvement

There's no way they can fix everything at once, and fixing the uncore while having a solid foundation with the Mont cores is a much needed move. Would have been nice to see this with ARL, but we never get what we want when we want. From now on, execution is king. AMD is slowing down on the consumer side because there's more juice on the other side of the road, let's see if Intel is agile enough to make a comeback.

Also, it's so refreshing to see Intel capitalize on their iGPU progress to gain momentum in the mass media. I just hope they keep pushing with their dGPU effort as well, even if scaled back. Like a few others on this forum, I am convinced that part of what we're seeing today in mobile is a bi-product of their "wasted" dGPU R&D.

 

[adroc_thurston]

AMD is slowing down on the consumer side because there's more juice on the other side of the road

They ain't, you're going to Zen6 on N2p and then to Zen7 on A14 straight up.

There's no way they can fix everything at once, and fixing the uncore while having a solid foundation with the Mont cores is a much needed move.

LNL already was allat.

 

[511]

They ain't, you're going to Zen6 on N2p and then to Zen7 on A14 straight up.

2.5-3 years gap

 

[adroc_thurston]

2.5-3 years gap

they're exactly 8Q spaced.
They also deliver Actual Real Perf (god forbid anyone does that!).

 

[regen1]

Solid vs 3yo fabric/mem IP.
that's not forever.

ARL-H is just a year old not 3 years old and ARL-H too improved battery life compared to MTL-H (Yeah, ARL-H fabric is largely from MTL-H which is slightly over 2 years old).
Comparison at this point is with what we have at the time, not some comparisons some did here of PTL vs some future AMD product ignoring Gorgon Point(timeline reality).

 

[coercitiv]

Cinememe power numbers analysis on Notebookcheck, don't know if they were posted before.

Intel Panther Lake Core Ultra X9 388H performance analysis - Outpaces Arrow Lake and exceeds Zen 5 in efficiency

Notebookcheck test/review/analysis of the Intel Panther Lake Core Ultra X9 388H mobile processor.

www.notebookcheck.net

CPU	20 watts	28 watts	35 watts	45 watts
Intel Core Ultra X9 338H	794 points	959 points	1,043 points	1,136 points
Intel Core Ultra 9 285H	597 points	778 points	892 points	977 points
Intel Core Ultra 7 255H	492 points	696 points	834 points	962 points
Intel Core Ultra 7 258V	512 points	587 points
Intel Core Ultra 7 155H	438 points	637 points	752 points	887 points
AMD Ryzen AI 9 465	768 points	842 points	930 points
AMD Ryzen AI 9 HX370	760 points	927 points	1022 points	1107 points
AMD Ryzen 7 PRO 350	604 points	739 points	813 points

 

[adroc_thurston]

ARL-H is just a year old not 3 years old and ARL-H too improved battery life compared to MTL-H (Yeah, ARL-H fabric is largely from MTL-H which is slightly over 2 years old).

I mean AMD.
It's still Phoenix fabric/memory IP there.

Comparison at this point is with what we have at the time, not some comparisons some did here of PTL vs some future AMD product ignoring Gorgon Point(timeline reality).

PTL volumes do not exist until Q2'26 so yes I can and yes I will.
In any case, gimme a 4+0+4 benches vs LNL, I wanna see the difference.

 

[mvprod123]

 

[Geddagod]

they're exactly 8Q spaced.
They also deliver Actual Real Perf (god forbid anyone does that!).

i have very little confidence in A14 products to be shipping in 28'.
TSMC couldn't ship the year they claimed HVM for N2 or N3 either.

 

[adroc_thurston]

i have very little confidence in A14 products to be shipping in 28'.

It's Q3'28 A14 parts for whole 3 vendors.
Your opinion has no relation to product roadmaps.

TSMC couldn't ship the year they claimed HVM for N2 or N3 either.

N2 is right on schedule.