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

[Tigerick]

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.





Intel Core Ultra 100 - Meteor Lake



As mentioned by Tomshardware, TSMC will manufacture the I/O, SoC, and GPU tiles. That means Intel will manufacture only the CPU and Foveros tiles. (Notably, Intel calls the I/O tile an 'I/O Expander,' hence the IOE moniker.)

 

[FlameTail]

Part of this is because Apple has a 16K page size while Intel's is 4K, and that's not something they're able to change. That has implication on the design of an L1 cache. I wouldn't give all the credit to Apple's design team. They're good, but no one is good enough to halve the latency of the competition without some wind at their back.

I am not sure that is a major factor... because Oryon also exists, and it has 4 KB pages while having similar L1/L2 latencies to Apple

 

[DrMrLordX]

You have a handheld, you are gaming. One has a 22W SoC but 30W system power, for 2 hours of gaming with a 60WHr battery. The other has a 15W SoC but still same 30W system power, for the same 2 hours of gaming with a 60WHr battery.

Did Geekerwan ever establish that the system power for the AMD system was ever actually 30W when the SoC sensor was showing 15W SoC power? Because all I remember is that he set the power limit to 30W. If the board isn't hitting the power limit (for whatever reason) then . . .

If you think that's confusing soon we'll have level negative one cache.

It's the cache that either doesn't exist, or if it does, not for very long. We're writing data to quantum foam!

 

[coercitiv]

If you think that's confusing soon we'll have level negative one cache.

Pre-cache!

 

[coercitiv]

I learned the hard way how much Apple sucks. Got an M1 laptop and $75 in exchange for pawning my 3060 Ti and 3080 10GB. Last time I checked, the laptop wouldn't power on. Misplaced its original charger somewhere. Tried with all other USB-C chargers I had on hand, including one that quick charges my Moto Edge mobile. None of them were able to revive it. That's my first ever laptop purchase where the damn laptop won't even turn on!

Power Delivery, not standard usb-c chargers, not fast charging protocols exclusive to phones.

Wife's MacBook works fine with multiple PD compatible charghers around the house.

 

[igor_kavinski]

Wife's MacBook works fine with multiple PD compatible charghers around the house.

A Mac woman would never marry me. Coz I won't be able to keep my hands off her Mac, doing all sorts of experiments on it

On a serious note, gotta find that stupid charger and the laptop bag it came with, which is the weird thing. How can I lose a WHOLE laptop bag?? It must be stacked down below a lot of crap!

 

[511]

The only thing i like about Mac is the instant wakeup and no charge loss during sleep and the battery life and perf on battery

 

[Nothingness]

I learned the hard way how much Apple sucks. Got an M1 laptop and $75 in exchange for pawning my 3060 Ti and 3080 10GB. Last time I checked, the laptop wouldn't power on. Misplaced its original charger somewhere. Tried with all other USB-C chargers I had on hand, including one that quick charges my Moto Edge mobile. None of them were able to revive it. That's my first ever laptop purchase where the damn laptop won't even turn on!

Pick the higher wattage charger you have, and let it charge the Mac for 24 hours (or more). I didn't use my M1 for almost two years and that's what I had to do (though with the Apple charger).
Same happened with the Mac I got at work (except I think it had been staying in storage for more than 2 years).

 

[igor_kavinski]

Pick the higher wattage charger you have, and let it charge the Mac for 24 hours (or more).

And it will just come to life, just like that? Or do I have to do some other voodoo? Like hold some specific button and then press power on?

 

[Nothingness]

And it will just come to life, just like that? Or do I have to do some other voodoo? Like hold some specific button and then press power on?

All battery powered machines behave like that.

 

[cannedlake240]

Skymont: Intel’s E-Cores reach for the Sky​

Skymont: Intel’s E-Cores reach for the Sky

The 2020s were a fun time for Intel’s Atom line, which went from an afterthought to playing a major role across Intel’s high performance client offerings.

chipsandcheese.com

So the famed E core with so many changes and massive area increase is still at ~Skylake IPC in Specint? What happened? Is it downclocking due to some power savings on the test machine? Lion Cove gets blasted for it's large area, but at least it delivered the 10-15% ipc, but the E core seems like it's not even reaching half of what was promised. Intel said the ring version is only around 5% better, or 5-10% better than a decade old P core...

 

[Joe NYC]

Intel still control ~80% of the market in clients. With that kinda volume, EOS (economies of scale) comes into play. Significantly reduces the cost per unit. They aren't paying as much as some youtubers say.

That 80% market share in client means nothing for the orders from TSMC, and the entire Arrow Lake is now made of TSMC dies.

Intel is not getting pricing that is any better than AMD or Qualcomm. If anything, Intel's pricing is worse. Intel already announced it wants to shift production away from TSMC, so TSMC has zero incentive to offer Intel favorable pricing.

Given the fact that Arrow Lake is on N3B, for the CPU die while Zen 5 is N4P, Arrow Lake is on more expensive node and is also using more expensive packaging.

In short, no economies of scale, and cost disadvantage vs. Zen 5.

 

[poke01]

https://videocardz.com/newz/intel-core-ultra-200v-lunar-lake-wont-have-more-cores-and-does-not-have-a-direct-successor

So LNL prupose was being able to compete with Apple, okay but Apple will release more than M3. So for Intel LNL was a just showcase that displays "we can do this too". That Dell leak is starting to make sense and why Lunar Lake is still being sold in 2026. Apple will be on M5 then and not sure how LNL can compete without a direct successor.

One could argue that LNL is enough for battery life and this is true but it will lack in ST and MT come 2026.

 

[Henry swagger]

View attachment 108663

https://videocardz.com/newz/intel-core-ultra-200v-lunar-lake-wont-have-more-cores-and-does-not-have-a-direct-successor

So LNL prupose was being able to compete with Apple, okay but Apple will release more than M3. So for Intel LNL was a just showcase that displays "we can do this too". That Dell leak is starting to make sense and why Lunar Lake is still being sold in 2026. Apple will be on M5 then and not sure how LNL can compete without a direct successor.

One could argue that LNL is enough for battery life and this is true but it will lack in ST and MT come 2026.

Makes no difference apple is struggling with sales

 

[poke01]

Makes no difference apple is struggling with sales

Yes because M3 is very poor value.

 

[jdubs03]

Makes no difference apple is struggling with sales

I think you’re significantly underestimating the M4 series. There is quite a jump in the capabilities of the machine, even outside CPU and GPU performance. And even though it was long overdue, now having a base of 16GB should be beneficial.
The M5 MBPs are also rumored to have a design change as well to freshen up their lineup. To me the M4 and M5 lineups would be far more compelling than anything Lunar lake has to offer.

This is why PTL-U has to be a meaningful improvement and performance, and at least retained the battery life of what lunar lake is showing itself to have. If they can’t do that, the gap is only going to widen.

The M4 is going to run circles around Lunar Lake. Its single thread performance is far and away top class and beats the highest end Intel and AMD chips with much less power draw. And then in multithread it’s right near where the X Elite and the HX 370 are. That’s just for the base chip.

 

[511]

So the famed E core with so many changes and massive area increase is still at ~Skylake IPC in Specint? What happened? Is it downclocking due to some power savings on the test machine? Lion Cove gets blasted for it's large area, but at least it delivered the 10-15% ipc, but the E core seems like it's not even reaching half of what was promised. Intel said the ring version is only around 5% better, or 5-10% better than a decade old P core...

Look at the subtest and explanation it's held back by the weaker SLC cache we will know with ARL 🙂 we all know how different was Crestmont LPE vs Crestmont in Ring

 

[cannedlake240]

I think you’re significantly underestimating the M4 series. There is quite a jump in the capabilities of the machine, even outside CPU and GPU performance. And even though it was long overdue, now having a base of 16GB should be beneficial.
The M5 MBPs are also rumored to have a design change as well to freshen up their lineup. To me the M4 and M5 lineups would be far more compelling than anything Lunar lake has to offer.

This is why PTL-U has to be a meaningful improvement and performance, and at least retained the battery life of what lunar lake is showing itself to have. If they can’t do that, the gap is only going to widen.

The M4 is going to run circles around Lunar Lake. Its single thread performance is far and away top class and beats the highest end Intel and AMD chips with much less power draw. And then in multithread it’s right near where the X Elite and the HX 370 are. That’s just for the base chip.

PTL U will be a regression in most of those. It'd be quite surprising if it somehow retains the battery life gains from LNL. Right now Intel has bigger fish to fry than M5

 

[poke01]

I think you’re significantly underestimating the M4 series. There is quite a jump in the capabilities of the machine, even outside CPU and GPU performance. And even though it was long overdue, now having a base of 16GB should be beneficial.
The M5 MBPs are also rumored to have a design change as well to freshen up their lineup. To me the M4 and M5 lineups would be far more compelling than anything Lunar lake has to offer.

This is why PTL-U has to be a meaningful improvement and performance, and at least retained the battery life of what lunar lake is showing itself to have. If they can’t do that, the gap is only going to widen.

The M4 is going to run circles around Lunar Lake. Its single thread performance is far and away top class and beats the highest end Intel and AMD chips with much less power draw. And then in multithread it’s right near where the X Elite and the HX 370 are. That’s just for the base chip.

I don''t think Intel has to worry about Apple that much. Next year it seems only Intel on the PC side will release an update, which is PTL New AMD and Qualcomm SoCs aren't expected till early 2026.



Zen6 and X Elite 2 isn't out 1H26

 

[511]

PTL U will be a regression in most of those. It'd be quite surprising if it somehow retains the battery life gains from LNL. Right now Intel has bigger fish to fry than M5

It will be definitely better in CPU perf/watt battery life yes it will be slightly worse Graphics would be worse dark silicon NPU will take less area

 

[AcrosTinus]

View attachment 108663

https://videocardz.com/newz/intel-core-ultra-200v-lunar-lake-wont-have-more-cores-and-does-not-have-a-direct-successor

So LNL prupose was being able to compete with Apple, okay but Apple will release more than M3. So for Intel LNL was a just showcase that displays "we can do this too". That Dell leak is starting to make sense and why Lunar Lake is still being sold in 2026. Apple will be on M5 then and not sure how LNL can compete without a direct successor.

One could argue that LNL is enough for battery life and this is true but it will lack in ST and MT come 2026.

Enjoy the now and let later be later. Time moves in one direction, hence what is currently on the market is the only thing that matters.

Currently LNL is good product in the market and for people with higher performance needs on x86, Intel and AMD will offer more powerful SKUs, you have to just accept that this kind of performance on windows will not come with 15+ hours of battery life.

Or just choose Apple and deal with their restricted computing platform.

 

[GTracing]

One thing to keep in mind with the L1 latency discussion, x86 cores clock higher, so the real latency is closer than the latency in cycles.

L1d size and latency

	M3 - performance core	X Elite - Oryon	Lunar Lake - Lion Cove	Strix Point - Zen5
size	192 KB	128 KB	48 KB 192KB	48 KB
latency (cycles)	3 cycles	3 cycles	4 cycles 9 cycles	4 cycles
core max clock speed	4.05 GHz	3.8 - 4.2 GHz	4.5 - 5.1GHz	5.0 - 5.1 GHz
latency (nanoseconds)	0.74 ns	0.79 - 0.71 ns	0.88 - 0.78 ns 2 - 1.76 ns	0.8 - 0.78 ns

 

[AcrosTinus]

Look at the subtest and explanation it's held back by the weaker SLC cache we will know with ARL 🙂 we all know how different was Crestmont LPE vs Crestmont in Ring

True, I read the whole article. Using LNL to evaluate the true performance of Skymont is not valid due to it being essentially a LP-Ecore on steroids. I'm wondering what the Ringbus can get out of it.

 

[Hitman928]

True, I read the whole article. Using LNL to evaluate the true performance of Skymont is not valid due to it being essentially a LP-Ecore on steroids. I'm wondering what the Ringbus can get out of it.

Getting access to the L3 will certainly give it an IPC boost. Wild guess is about 10%. Hopefully C&C tests ARL as well, they do really great work.

 

[Nothingness]

C&C about Skymont: https://chipsandcheese.com/2024/10/03/skymont-intels-e-cores-reach-for-the-sky/

 

[Magio]

Considering this is the first time in god knows how long there's actual excitement for an Intel mobile platform I think Intel would be fools not to have a successor to it eventually. It makes sense that PTL won't have one as the plans for that were set in stone long before they knew how LNL would turn out, but going onto NVL they really ought to bring back the V series.

A 4P + 6/8 Arctic Wolf + Celestial (or newer) GPU and the general LNL design choices on 18A or even 18A-P (which they've already said would be optimized for mobile) sounds feasible and would b a dream chip for thin and lights.