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.

 

[poke01]

This time Intel has the node advantage and efficiency should improve massively.

 

[Klingenberg]

True. ARL's LNC is yet to be seen. And I'm not sure, but I think we haven't seen Zen5 final yet either. Both should be revealed soon. Interesting times ahead...

I don't think we should classify Intel as "one step" ahead in technology when they have a lead that kinda marginal at best. In terms of abstracted out (agnostic/modular) cores, tiles, fabric, gpu, process, etc, they've kinda caught up or exceeded a bit. A clear win requires leadership in at least most of it I guess.

Who would you say is the best one then?

 

[SiliconFly]

-

 

[Markfw]

Neither. After years of lagging competition, Intel has finally caught up (in almost all areas). That in itself is a massive feat! They're both almost at par now. A few percent points difference shouldn't be considered a big win.

Things may actually change a lot depending on how both the companies execute in the future. But not anytime now imho.

Based on LNC/Zen5 leaks, it looks like 2024 is gonna be the year of the equals.

I think its early to call that. We have no reviews of new products from either company. Also, server seems to still be squarely in AMDs court, but until reviews come out, its all up in the air. Marketing info from both say NOTHING but try to make themselves look good.

 

[Hulk]

It's hard to make predictions for overall performance when the architectures are so different, meaning all big cores vs. a big/little design.

I think we need to look at specific software. For example, I made this comparison of 9950X vs ARL 8+16 for CB R23 MT using performance from the previous generation and then bumping up for new gen cores based on manufacturer early data. +17% for Zen 5 vs Zen 4 and I think it was +14% for Lion Cove over Raptor Cove and Skymont IPC = Raptor Cove. Assumption was Zen 4 clocks will equal Zen 5 clocks. ARL clocks assumed 5.4 nT for Lion Cove and 4.5GHz for Skymont.

My calcs show Zen 5 around 45,000 and ARL just under 48,000. Maybe a 5 or 6% advantage for this one particular "ridiculously" parallel threaded application. With the estimates I have made for final clocks (they may be high for ARL and low for Zen 5) we are within the margin of error.

So defenders of Intel and AMD be not worried! Zen 5 and ARL will be close enough in performance to sustain fruitful discussions for years to come! I am predicting there will be no clear winner in performance. This makes sense because Intel knew where AMD was going 3 years ago and AMD knew the same about Intel. They will both be hitting each others performance targets perfectly! Yes, I know I am being cynical to the extreme.

As far as efficiency I think Intel will do better on the new node but if I had to bet I think AMD may still have the advantage.

 

[AcrosTinus]

It's hard to make predictions for overall performance when the architectures are so different, meaning all big cores vs. a big/little design.

I think we need to look at specific software. For example, I made this comparison of 9950X vs ARL 8+16 for CB R23 MT using performance from the previous generation and then bumping up for new gen cores based on manufacturer early data. +17% for Zen 5 vs Zen 4 and I think it was +14% for Lion Cove over Raptor Cove and Skymont IPC = Raptor Cove. Assumption was Zen 4 clocks will equal Zen 5 clocks. ARL clocks assumed 5.4 nT for Lion Cove and 4.5GHz for Skymont.

My calcs show Zen 5 around 45,000 and ARL just under 48,000. Maybe a 5 or 6% advantage for this one particular "ridiculously" parallel threaded application. With the estimates I have made for final clocks (they may be high for ARL and low for Zen 5) we are within the margin of error.

So defenders of Intel and AMD be not worried! Zen 5 and ARL will be close enough in performance to sustain fruitful discussions for years to come! I am predicting there will be no clear winner in performance. This makes sense because Intel knew where AMD was going 3 years ago and AMD knew the same about Intel. They will both be hitting each others performance targets perfectly! Yes, I know I am being cynical to the extreme.

As far as efficiency I think Intel will do better on the new node but if I had to bet I think AMD may still have the advantage.

I don't know, you might be right but AMD could only catch up due to architecture and node being tightly linked on the Intel side. With the option to outsource and the cores using industry standard tools for design, the teams can run as fast as they can while having TSMC as a security. The core technology (Hardware + Software) is miles ahead of AMD, the bottleneck in my humble opinion was the node and laziness due to zero competition from AMD in the past.

 

[Hulk]

I don't know, you might be right but AMD could only catch up due to architecture and node being tightly linked on the Intel side. With the option to outsource and the cores using industry standard tools for design, the teams can run as fast as they can while having TSMC as a security. The core technology (Hardware + Software) is miles ahead of AMD, the bottleneck in my humble opinion was the node and laziness due to zero competition from AMD in the past.

That is a really good point. If it just comes down to putting designs on paper and then sending them to TMSC to make them work then Intel does have the resources to out spend/out design AMD. Lunar Lake may be the first example of that happening. Intel can easily put a huge team on the P cores, another on the E cores, another on the AI cores, another on GPU, etc.. while having a bunch of other teams working on future projects. Someone at Intel realized that and made the move to use TMSC.

 

[Wolverine2349]

I don't know, you might be right but AMD could only catch up due to architecture and node being tightly linked on the Intel side. With the option to outsource and the cores using industry standard tools for design, the teams can run as fast as they can while having TSMC as a security. The core technology (Hardware + Software) is miles ahead of AMD, the bottleneck in my humble opinion was the node and laziness due to zero competition from AMD in the past.

Well if Intel has caught up on node shoulder they be superior to AMD.

Afterall intel on a node behind was equal or a little better than Zen 4 in IPC. Though power usage much higher and stability issues 13th and 14th Gen kind of negated that.

But if Intel is better on node shouldn't they be better and superior given they were equal on inferior node despite power and stability issues om the 10nm inferior node.

 

[AcrosTinus]

That is a really good point. If it just comes down to putting designs on paper and then sending them to TMSC to make them work then Intel does have the resources to out spend/out design AMD. Lunar Lake may be the first example of that happening. Intel can easily put a huge team on the P cores, another on the E cores, another on the AI cores, another on GPU, etc.. while having a bunch of other teams working on future projects. Someone at Intel realized that and made the move to use TMSC.

You get it, I think Pat knows what is he is doing, everything is about de-risking and building resilience while pushing forward so that the past cannot repeat itself. Proof is the "I bet the company on 18A" in reality there is 20A that generates insight and corrections for 18A before it goes into volume. Again, I might be a bit too hopeful due to buying the intel dip but everything is alright as of now.

 

[AcrosTinus]

Well if Intel has caught up on node shoulder they be superior to AMD.

Afterall intel on a node behind was equal or a little better than Zen 4 in IPC. Though power usage much higher and stability issues 13th and 14th Gen kind of negated that.

But if Intel is better on node shouldn't they be better and superior given they were equal on inferior node despite power and stability issues om the 10nm inferior node.

If Intel stays awake it will work out. I cannot estimate the impact of the new transistors and backside power at the moment. These features seem to be a milestone in manufacturing that should unlock a new level in efficiency and clocks/power.

 

[Geddagod]

How do you figure ARL will "wipe out" 9950 in MT? Lets do some speculative math. Assume Lion cove and 9xxx big cores are equal if both have hyperthreading. I think this should be a fairly accurate guess. 9950x has 16 "big cores" all with HT.
ARL has 8 big cores without HT so assuming 25% gain from HT, that is equivalent to 6 AMD cores.
ARL has 16 E cores. They lack hyperthreading and will have a clock speed disadvantage as well. So in "equivalent" AMD cores, that is 16*.75(no HT)*.85(clockspeed disadvantage) = 10.2. So we have 6+10 AMD core equivalents. MT performance should be about equal at best, because I am not even considering the the E cores will have an IPC deficit as well against AMD big cores.

Not how I did it, my method was prob uselessly more complicated lol but whatever, agree with the end conclusion that ARL will be around Zen 5 MT perf.

Also, server seems to still be squarely in AMDs court,

How? Same core counts, Zen 5 will have prob have a ~15% per core IPC advantage and prob a similar margin of perf/watt advantage as well. AVX-512 prob better with Zen 5, running AI workloads is almost certainly going to be better with Intel (if they use their accelerators). That doesn't sound like it's still "squarely in AMDs court". AMD still has a marginal advantage sure, but Intel is in a dramatically more competitive position.

 

[Markfw]

Not how I did it, my method was prob uselessly more complicated lol but whatever, agree with the end conclusion that ARL will be around Zen 5 MT perf.

How? Same core counts, Zen 5 will have prob have a ~15% per core IPC advantage and prob a similar margin of perf/watt advantage as well. AVX-512 prob better with Zen 5, running AI workloads is almost certainly going to be better with Intel (if they use their accelerators). That doesn't sound like it's still "squarely in AMDs court". AMD still has a marginal advantage sure, but Intel is in a dramatically more competitive position.

This is not the place for that discussion. I had an opinion, leave it at that. When benchmarks come out, I will find the right thread to discuss them.

 

[Hulk]

You get it, I think Pat knows what is he is doing, everything is about de-risking and building resilience while pushing forward so that the past cannot repeat itself. Proof is the "I bet the company on 18A" in reality there is 20A that generates insight and corrections for 18A before it goes into volume. Again, I might be a bit too hopeful due to buying the intel dip but everything is alright as of now.

When I first heard Intel would be using TSMC my first reaction was, "Intel has surrendered the foundry business." But now I'm understanding "the right node for the right transistors" makes sense. Intel can't do it all and they can maximize their foundry by picking and choosing where to produce the various tiles and on what processes.

Would I be correct in assuming Intel does have an advantage by still having a foundry business or is it a total liability? I'm thinking that at the end of the day the cheaper you can produce your parts the better. Raptor Lake is pretty huge but they could "swallow" that cost because they are the foundry.

 

[Geddagod]

This is not the place for that discussion. I had an opinion, leave it at that. When benchmarks come out, I will find the right thread to discuss them.

The lengths some people go to, to not defend their speculation is wild 💀

 

[poke01]

I’m keeping expectations low about performance but at least one thing is confirmed and that efficiency is confirmed to have improved due to the TSMC node.

We can discussions about who is better when both release, each week the pendulum swings either way.

I don’t people understand what type of node Intel is coming off from. Intel 7 to TSMC N3B is like going from on iPhone 7 to iPhone 15 Pro or an S6 to S23 Ultra.

 

[Doug S]

When I first heard Intel would be using TSMC my first reaction was, "Intel has surrendered the foundry business." But now I'm understanding "the right node for the right transistors" makes sense. Intel can't do it all and they can maximize their foundry by picking and choosing where to produce the various tiles and on what processes.

Would I be correct in assuming Intel does have an advantage by still having a foundry business or is it a total liability? I'm thinking that at the end of the day the cheaper you can produce your parts the better. Raptor Lake is pretty huge but they could "swallow" that cost because they are the foundry.

I think Intel would very much prefer to stop using outside foundries, at least for any process that was current in the past decade. They have no choice today because they don't have enough capacity to serve their own needs, let alone that of outside customers they're trying to take on. That will be true for most of the current decade.

I don't buy the argument that it is more profitable to make chips in house. Sure, they double dip on profit - making money both on producing the chip (what TSMC is making from AMD) and on selling the chip (what AMD is making from the markup they charge on the chips TSMC made for them) but if more total dollars of profit was the goal they should be like Samsung and make smartphones, ships, NAND, TVs, and everything in between. Having the foundry in house was an advantage for Intel in some ways (like designing the process towards the chips they wanted to make) but was a disadvantage in ways too - dysfunction like your example where they could think "well this chip is pretty large and has bad yields as a result but that's fine because we have spare capacity in our fabs that would otherwise be wasted"

Given that AMD and TSMC are both profitable, there are clearly profits to be had in both businesses. But they are so different in terms of capital requirements, business cycles, etc. that I don't believe it makes sense for both to be under one roof. When you add in the fact Intel's chip division competes in some way with many of the biggest potential customers like Apple, Nvidia, Qualcomm and AMD, it is clear they need to spin off the foundry once it is able to stand on its own. I would say they reach that point when they do more business in wafer volume and revenue with outside customers than they do internally. If they are successful and aggressive enough in fab buildout they should be able to reach that position in the early 2030s, though they'd see the runway towards that several years earlier - so 2028/2029 is the earliest I'd expect to see such an announcement.

 

[AcrosTinus]

I think Intel would very much prefer to stop using outside foundries, at least for any process that was current in the past decade. They have no choice today because they don't have enough capacity to serve their own needs, let alone that of outside customers they're trying to take on. That will be true for most of the current decade.

I don't buy the argument that it is more profitable to make chips in house. Sure, they double dip on profit - making money both on producing the chip (what TSMC is making from AMD) and on selling the chip (what AMD is making from the markup they charge on the chips TSMC made for them) but if more total dollars of profit was the goal they should be like Samsung and make smartphones, ships, NAND, TVs, and everything in between. Having the foundry in house was an advantage for Intel in some ways (like designing the process towards the chips they wanted to make) but was a disadvantage in ways too - dysfunction like your example where they could think "well this chip is pretty large and has bad yields as a result but that's fine because we have spare capacity in our fabs that would otherwise be wasted"

Given that AMD and TSMC are both profitable, there are clearly profits to be had in both businesses. But they are so different in terms of capital requirements, business cycles, etc. that I don't believe it makes sense for both to be under one roof. When you add in the fact Intel's chip division competes in some way with many of the biggest potential customers like Apple, Nvidia, Qualcomm and AMD, it is clear they need to spin off the foundry once it is able to stand on its own. I would say they reach that point when they do more business in wafer volume and revenue with outside customers than they do internally. If they are successful and aggressive enough in fab buildout they should be able to reach that position in the early 2030s, though they'd see the runway towards that several years earlier - so 2028/2029 is the earliest I'd expect to see such an announcement.

I don't want to get political but for the west the foundry is a burden worth carrying. That is the main reason I invested into Intel.

 

[Doug S]

I don't want to get political but for the west the foundry is a burden worth carrying. That is the main reason I invested into Intel.

Intel doesn't need to own the foundry under the same roof as their chip business for that though. If they spun it off under a separate stock symbol and management what you say is still true.

 

[inquiss]

Neither. After years of lagging competition, Intel has finally caught up (in almost all areas). That in itself is a massive feat! They're both almost at par now. A few percent points difference shouldn't be considered a big win.

Things may actually change a lot depending on how both the companies execute in the future. But not anytime now imho.

Based on LNC/Zen5 leaks, it looks like 2024 is gonna be the year of the equals.

Doubt it. Lunar is good, sure, but its not competing in the same race. Lunar lake will dominate the small core count stuff, and tablets, strix anything higher. So like, not equals?

 

[dttprofessor]

Intel doesn't need to own the foundry under the same roof as their chip business for that though. If they spun it off under a separate stock symbol and management what you say is still true.

IT 's not.

 

[SiliconFly]

-

 

[SiliconFly]

-

 

[AcrosTinus]

Totally agree. The massive node jump is gonna contribute a lot to increased efficiency mostly. But this increase is only sufficient enough to catch up to competition as of now (or maybe exceed a bit at best). For all practical purposes, we can safely assume they're mostly at par this year.


Not really. For example, Intel is still stuck with their power hungry P core in servers (it's still using RWC). Nothing much to expect there. In clients, the LNC leaks didn't indicate much (but an official ARL's LNC reveal might say something entirely different; who knows).

At this point, Intel needs to go the extra mile with its P core architecture to be "superior to AMD". No sure whether ARL's LNC can pull it off. I'll be interesting if it happens. But it's a definite possibility with future P core architectures.

Maybe Intel 3 can tame the beast. From the benchmarks I saw and the ones I ran myself, Zen 4 is an inferior core but more balanced than GLC, RWC, RPC. The SPEC results show a slight advantage for Intel and a huge one if you artificially manage to load up the backend to the max.
I don't know for sure but Intel's mesh and old node resulted in higher power draw and lower clocks. AMD could use the bleeding edge on a less wide core, using less power on a better communication protocol(infinity fabric?) that scales better, meaning higher clocks on server.

After Intel fixes their nodes, Intel 3 is promising, their mesh interconnect might need a second look. (not a hardware designer, the mesh might be just the right thing)

 

[lightisgood]

There is no delay.

Intel Lunar Lake "Core Ultra 200V" Laptops Hit Retail In September, Arrow Lake "Core Ultra 200" CPUs Launch In October

Intel's next-gen Lunar Lake & Arrow Lake "Core Ultra 200" CPUs are expected to hit retail shelves in September & October, respectively.

wccftech.com

 

[dttprofessor]

Maybe Intel 3 can tame the beast. From the benchmarks I saw and the ones I ran myself, Zen 4 is an inferior core but more balanced than GLC, RWC, RPC. The SPEC results show a slight advantage for Intel and a huge one if you artificially manage to load up the backend to the max.
I don't know for sure but Intel's mesh and old node resulted in higher power draw and lower clocks. AMD could use the bleeding edge on a less wide core, using less power on a better communication protocol(infinity fabric?) that scales better, meaning higher clocks on server.

After Intel fixes their nodes, Intel 3 is promising, their mesh interconnect might need a second look. (not a hardware designer, the mesh might be just the right thing)

It's balance,CLF is 24 cores per tile *12.
Of course CLF is E core.