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

Tigerick · Aug 22, 2022

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.

Comparison of upcoming Intel's U-series CPU: Core Ultra 100U, Lunar Lake and Panther Lake

Model	Code-Name	Date	TDP	Node	Tiles	Main Tile	CPU	LP E-Core	LLC	GPU	Xe-cores
Core Ultra 100U	Meteor Lake	Q4 2023	15 - 57 W	Intel 4 + N5 + N6	4	tCPU	2P + 8E	2	12 MB	Intel Graphics	4
?	Lunar Lake	Q4 2024	17 - 30 W	N3B + N6	2	CPU + GPU & IMC	4P + 4E	0	8 MB	Arc	8
?	Panther Lake	Q1 2026 ?	?	Intel 18A + N3E	3	CPU + MC	4P + 8E	4	?	Arc	12

Comparison of die size of Each Tile of Meteor Lake, Arrow Lake, Lunar Lake and Panther Lake

	Meteor Lake	Arrow Lake (20A)	Arrow Lake (N3B)	Arrow Lake Refresh (N3B)	Lunar Lake	Panther Lake
Platform	Mobile H/U Only	Desktop Only	Desktop & Mobile H&HX	Desktop Only	Mobile U Only	Mobile H
Process Node	Intel 4	Intel 20A	TSMC N3B	TSMC N3B	TSMC N3B	Intel 18A
Date	Q4 2023	Q1 2025 ?	Desktop-Q4-2024 H&HX-Q1-2025	Q4 2025 ?	Q4 2024	Q1 2026 ?
Full Die	6P + 8P	6P + 8E ?	8P + 16E	8P + 32E	4P + 4E	4P + 8E
LLC	24 MB	24 MB ?	36 MB ?	?	8 MB	?
tCPU	66.48
tGPU	44.45
SoC	96.77
IOE	44.45
Total	252.15

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.)

ondma · Dec 28, 2023

Khato said:
ARW (Arctic Wolf) is the abbreviation for the next e-core after DKT (Darkmont.) Makes for an amusing typo thanks to that.

It easily could be the case that Zen5 will end up with a ST advantage over ARL. What would it matter if it does? Main point of interest to me is how the two will compare in terms of efficiency as that's where Intel has fallen behind. While such isn't as important in the client space such will provide an indicator of how the corresponding server products might compare.

Well, one may not care about single threaded artificial benchmarks per se, but gaming is still strongly influenced by ST performance, no? It will be interesting to see how long Intel can get by with 8 big cores for gaming. Seems to me that 8 big cores, especially if they dont have HT or rentable units, are going to eventually be insufficient for gaming, and Intel will be in trouble unless they can either add more P cores or more effectively use the E cores for gaming.

H433x0n · Dec 28, 2023

Hulk said:
I think you are correct in expecting up to 20% throughput increase for Arrow Lake but have different opinion on previous generation uplifts in throughput.

I would put Cypress Cove to Golden Cove at about 16.5%
Cypress to Raptor Cove at 19% as you wrote.

Skylake to Golden Cove is about 46% uplift per clock. Of course it depends on the application but I'm considering CB R23 ST.

Now for some speculation.

You are correct in that Arrow Lake needs to not only make up the latency loss in moving to tiles but also the expected clock speed regression. The clock speed regression isn't actually as bad as it may first appear. Most Raptor Refresh parts will only do about 5.4 or 5.5GHz all-core under load before cooling and temps become an issue. Therefore if Intel can only hit 5.4 or 5.5GHz and it has lower power/thermals then this would be an actual clock for MT for these parts. Meaning no clock speed regression outside of anything like CB ST since Raptor parts rarely hit those turbo boost single core frequencies without custom loops or chillers.

Furthermore at the lower part of the stack in the 14600K range they only need hit 5.3Ghz for ARW to achieve parity with RPL-R.

So what does all this mean? I think best case is ARL ends up having 15% better throughput than Raptor and most of that will translate into MT performance, especially considering Crestmont is supposedly improved over Gracemont.

ST benchmarks will suffer for ARL compared to Raptor but they will be meaningless in real world usage cases because most "single threaded"" applications will still utilize 3 or 4 cores thus stopping super high turbo boosting of Raptor anyway. When we talk about ST performance these days it's more about applications using 3 or 4 cores heavily and then then utilizing some other cores for other things not directly related to the foreground application.

Finally, the one ace Intel has up its sleeve is the area efficient E cores. In order to pump up the MT benchmarks all they need to do is add another E cluster.

Arrow Lake and future Intel CPUs in my opinion are going to live or die based on the performance of those P cores and how they compare to AMD's equivalent core.

I disagree that the P cores are all that matters. It’s entirely possible that Skymont nearly has a 12-14% IPC increase over Gracemont. This gets Skymont pretty close to Zen 3 IPC. So ARL will basically have 8 pcores with 16 ecores that are basically equivalent to a 5950X without SMT.

Khato · Dec 28, 2023

ondma said:
Well, one may not care about single threaded artificial benchmarks per se, but gaming is still strongly influenced by ST performance, no? It will be interesting to see how long Intel can get by with 8 big cores for gaming. Seems to me that 8 big cores, especially if they dont have HT or rentable units, are going to eventually be insufficient for gaming, and Intel will be in trouble unless they can either add more P cores or more effectively use the E cores for gaming.

My impression is that it really depends upon the implementation of the game. It's been some time since I last looked at VTune traces, but I'd be surprised if there weren't still at least two 'heavy' threads - one for the graphics and another for the game effectively. Each of those obviously can have additional threads performing work on other cores that they're dependent on. The question becomes how small each of those worker threads can be? If the work can be effectively distributed across 64 threads, then E cores are going to be every bit as usual as P cores. If it's just 12 threads though? Then it likely would be the case that the E core approach would result in a bottleneck. Not too likely for such to be an issue any time soon though, at least not until consoles increase their core count.

On a slight tangent, still no idea what 'rentable units' are eh?

Hulk · Dec 28, 2023

H433x0n said:
I disagree that the P cores are all that matters. It’s entirely possible that Skymont nearly has a 12-14% IPC increase over Gracemont. This gets Skymont pretty close to Zen 3 IPC. So ARL will basically have 8 pcores with 16 ecores that are basically equivalent to a 5950X without SMT.

I didn't mean to imply the E cores don't matter. The E cores will not make or break Arrow Lake. If Lion Cove doesn't have at least the throughput of Zen 5 then Intel will lose on the benchmarks that aren't "ridiculously" multithreaded, which is many of them. As I have noted before, when an application scales well to 8 threads it generally keeps scaling well so the 16 E cores can compete with AMD's additional 8 big cores. Intel's hybrid approach can run into trouble with apps that only scale to about 16 cores but not further but those are niche cases.

If the Lion Cove doesn't perform then it doesn't really matter how well the E's perform as they only really matter in highly MT apps like Blender and Cinebench, and of course multitasking, which isn't often benched or benched in a meaningful way.

Intel can always "pump" up the MT scores by adding additional clusters of E and as we know they are quite area "E"fficient so the cost in silicon is not prohibitive. The E's might be so area efficient when it comes to MT that the die area saved by removing HT from the P's might be nearly equal to the space required for the E's or better. What I mean is if you remove 8 logical cores from an 8 core Intel CPU you will reduce CB R23 MT performance by about 25%. In order to make that up you only need to add about 1 E cluster, which is about the size of one P core. Therefore, if removing HT reduces P core size by 12.5% (1/8) and you use that area for another E cluster then you keep your ST performance and MT performance. But if HT is say 15 or 20% of a P core then you can build a faster P core and have better ST performance and equal or better MT performance. Number above are based on the following data. Raptor Cove with HT scores 512 CB R23 MT points per GHz. Raptor Cove no HT scores about 389 CB R23 MT points per GHz. Gracemont scores about 265 CB R23 MT points per GHz.

The fact that we are hearing rumors that Lion Cove may not be hyperthreaded provides further evidence of my belief using the reasoning above. Intel came to the same conclusion I did long ago.

Separating ST and MT performance with the hybrid design allows Intel to develop one architecture optimized for ST performance and one optimized for MT performance. We know this came from Intel falling behind in process technology and it has kept them "in the game" since Alder Lake as Rocket Lake was, let's face it, DOA.

I feel like a political pundit when I say this as they always say, "this election will be the most important one ever!" But honestly Zen 5 and Arrow Lake is going to be the battle of the big cores.

Khato · Dec 28, 2023

Notebookcheck has a review of a retail MSI Prestige 16 up - https://www.notebookcheck.net/MSI-P...-Core-i7-Xe-to-Core-Ultra-7-Arc.785587.0.html

Only one BIOS version dated 2023-11-23 on MSI's website, so unlikely that it has the correct microcode. Stress test implies that its sustained power draw is approximately 44W, and the CB23 MT score of 15013 matches up with the original microcode curve. Still, the battery life matches other review of this laptop with extremely long run times thanks to the 99.9Wh battery. But equally interesting in that metric is that their 18h WiFi test result isn't too far off from the 25h idle/min brightness. I'm more used to seeing WiFi tests at around half the idle number rather than 2/3rds.

H433x0n · Dec 28, 2023

Hulk said:
I didn't mean to imply the E cores don't matter. The E cores will not make or break Arrow Lake. If Lion Cove doesn't have at least the throughput of Zen 5 then Intel will lose on the benchmarks that aren't "ridiculously" multithreaded, which is many of them. As I have noted before, when an application scales well to 8 threads it generally keeps scaling well so the 16 E cores can compete with AMD's additional 8 big cores. Intel's hybrid approach can run into trouble with apps that only scale to about 16 cores but not further but those are niche cases.

If the Lion Cove doesn't perform then it doesn't really matter how well the E's perform as they only really matter in highly MT apps like Blender and Cinebench, and of course multitasking, which isn't often benched or benched in a meaningful way.

Intel can always "pump" up the MT scores by adding additional clusters of E and as we know they are quite area "E"fficient so the cost in silicon is not prohibitive. The E's might be so area efficient when it comes to MT that the die area saved by removing HT from the P's might be nearly equal to the space required for the E's or better. What I mean is if you remove 8 logical cores from an 8 core Intel CPU you will reduce CB R23 MT performance by about 25%. In order to make that up you only need to add about 1 E cluster, which is about the size of one P core. Therefore, if removing HT reduces P core size by 12.5% (1/8) and you use that area for another E cluster then you keep your ST performance and MT performance. But if HT is say 15 or 20% of a P core then you can build a faster P core and have better ST performance and equal or better MT performance. Number above are based on the following data. Raptor Cove with HT scores 512 CB R23 MT points per GHz. Raptor Cove no HT scores about 389 CB R23 MT points per GHz. Gracemont scores about 265 CB R23 MT points per GHz.

The fact that we are hearing rumors that Lion Cove may not be hyperthreaded provides further evidence of my belief using the reasoning above. Intel came to the same conclusion I did long ago.

Separating ST and MT performance with the hybrid design allows Intel to develop one architecture optimized for ST performance and one optimized for MT performance. We know this came from Intel falling behind in process technology and it has kept them "in the game" since Alder Lake as Rocket Lake was, let's face it, DOA.

I feel like a political pundit when I say this as they always say, "this election will be the most important one ever!" But honestly Zen 5 and Arrow Lake is going to be the battle of the big cores.

We’ll see how it ends up, I feel like ARL will do fine. Even assuming Zen 5 lives up to the hype, I don’t see it having a clear ST performance victory.. I don’t think Zen has ever really had a commanding ST perf advantage. Which is why I don’t see Zen 5 catching ARL in a lot of ST benchmarks such as WebXprt, Speedometer, POVRay, etc.

I’m sure it’ll outperform GNR in datacenter and the X3D chips have a good chance of winning gaming. If it somehow does get a clear ST win over ARL I’ll have to bite the bullet and buy an X670E system again. I’ve got to have the best ST available for my use case (ghidra) so it’s the deciding factor for me. hopefully it’ll be a smoother experience this time if I end up having to go that route.

controlflow · Dec 28, 2023

Khato said:
Notebookcheck has a review of a retail MSI Prestige 16 up - https://www.notebookcheck.net/MSI-P...-Core-i7-Xe-to-Core-Ultra-7-Arc.785587.0.html

Only one BIOS version dated 2023-11-23 on MSI's website, so unlikely that it has the correct microcode. Stress test implies that its sustained power draw is approximately 44W, and the CB23 MT score of 15013 matches up with the original microcode curve. Still, the battery life matches other review of this laptop with extremely long run times thanks to the 99.9Wh battery. But equally interesting in that metric is that their 18h WiFi test result isn't too far off from the 25h idle/min brightness. I'm more used to seeing WiFi tests at around half the idle number rather than 2/3rds.

"Battery capacity has increased from 80 Wh on the Prestige 15 to 99 Wh on our Prestige 16. Combine this with the efficiency of the new 14th gen Intel CPU and you can get extremely long runtimes of almost 18.5 hours of real-world WLAN browsing. This is one of the longest-lasting Windows laptops we've tested with results that rival the MacBook series."

Impressive battery life here. Would be curious to see how a PHX laptop with a similar size battery performs.
Not a fan of how MSI decided to set the PL2 to 115W in this laptop. Hopefully there is at least an easy option to cap power much lower. Asus in the Zenbook seems to allow you to cap the power to 28W, which is much more appropriate for a thin and light laptop.

As you noted, this is running a pretty old bios. Would be interesting to see if things can improve with newer FW.

Khato · Dec 28, 2023

controlflow said:
Not a fan of how MSI decided to set the PL2 to 115W in this laptop. Hopefully there is at least an easy option to cap power much lower. Asus in the Zenbook seems to allow you to cap the power to 28W, which is much more appropriate for a thin and light laptop.

Agree 100% with this. It's quite annoying that manufacturers don't more easily expose these controls. Means that users either suffer with the preconfigured levels or have adequate technical ability to set it themselves. (Throttlestop is the utility I've been using on Windows for such, and then there's a setPL.sh script on github that I've used in Linux.) Limiting the PL1/PL2 does a great job at making a laptop silent without notably impacting performance.

Hitman928 · Dec 28, 2023

Khato said:
Notebookcheck has a review of a retail MSI Prestige 16 up - https://www.notebookcheck.net/MSI-P...-Core-i7-Xe-to-Core-Ultra-7-Arc.785587.0.html

Only one BIOS version dated 2023-11-23 on MSI's website, so unlikely that it has the correct microcode. Stress test implies that its sustained power draw is approximately 44W, and the CB23 MT score of 15013 matches up with the original microcode curve. Still, the battery life matches other review of this laptop with extremely long run times thanks to the 99.9Wh battery. But equally interesting in that metric is that their 18h WiFi test result isn't too far off from the 25h idle/min brightness. I'm more used to seeing WiFi tests at around half the idle number rather than 2/3rds.

Hopefully they can get their hands on an Asus Zenbook as that one has an updated bios they could use.

Hulk · Dec 28, 2023

H433x0n said:
We’ll see how it ends up, I feel like ARL will do fine. Even assuming Zen 5 lives up to the hype, I don’t see it having a clear ST performance victory.. I don’t think Zen has ever really had a commanding ST perf advantage. Which is why I don’t see Zen 5 catching ARL in a lot of ST benchmarks such as WebXprt, Speedometer, POVRay, etc.

I’m sure it’ll outperform GNR in datacenter and the X3D chips have a good chance of winning gaming. If it somehow does get a clear ST win over ARL I’ll have to bite the bullet and buy an X670E system again. I’ve got to have the best ST available for my use case (ghidra) so it’s the deciding factor for me. hopefully it’ll be a smoother experience this time if I end up having to go that route.

The last few Intel/AMD generations have been very even in terms of overall performance (not efficiency) and I have a feeling it's going to stay that way in terms of performance. It remains to be seen if Intel can close the gap in efficiency. Despite what we have heard and read Meteor Lake has narrowed the efficiency gap. How much remains up for debate.

Abwx · Dec 28, 2023

controlflow said:
"Battery capacity has increased from 80 Wh on the Prestige 15 to 99 Wh on our Prestige 16. Combine this with the efficiency of the new 14th gen Intel CPU and you can get extremely long runtimes of almost 18.5 hours of real-world WLAN browsing. This is one of the longest-lasting Windows laptops we've tested with results that rival the MacBook series."
View attachment 91120

Impressive battery life here. Would be curious to see how a PHX laptop with a similar size battery performs.
Not a fan of how MSI decided to set the PL2 to 115W in this laptop. Hopefully there is at least an easy option to cap power much lower. Asus in the Zenbook seems to allow you to cap the power to 28W, which is much more appropriate for a thin and light laptop.

As you noted, this is running a pretty old bios. Would be interesting to see if things can improve with newer FW.

There s a 7530U in their comparison, in the second wifi test it last 605 mn with a 45Wh battery, to compare with MTL s 1100 mn with a 99.9 Wh one,
actually the 7530U has better perf in this test than MTL, so a 7840U shouldnt be that different overall.

Also it is odd that the first CB R15 run is no different from the next ones, yet the laptop boost up to 105W, wich amount to about 75W at the CPU level, there should be a big difference from first run to the following ones.

Edit ; Actually the CPU boost up to 110W, the power measured at the main is limited by the 100W AC adaptator, so the difference is extracted from the battery.

Edit 2 : Sustained CPU power is roughly 50W since the laptop sustained power is 72W.

Khato · Dec 28, 2023

Abwx said:
There s a 7530U in their comparison, in the second wifi test it last 605 mn with a 45Wh battery, to compare with MTL s 1100 mn with a 99.9 Wh one,
actually the 7530U has better perf in this test than MTL, so a 7840U shouldnt be that different overall.

Also it is odd that the first CB R15 run is no different from the next ones, yet the laptop boost up to 105W, wich amount to about 75W at the CPU level, there should be a big difference from first run to the following ones.

Edit ; Actually the CPU boost up to 110W, the power measured at the main is limited by the 100W AC adaptator, so the difference is extracted from the battery.

The ~10 seconds of operation at the 110W PL2 level isn't long enough to meaningfully affect the scores. It very quickly saturates the heatsink and drops down to the steady state 44W level. It's clearly constrained by the cooling solution rather than PL1 value.

As for the battery life, all reviews thus far put MTL on par with Phoenix when normalized for battery capacity and display. I see eight laptop reviews on notebookcheck using the 780M integrated graphics. The three OLED models span 6.2, 7.5, and 8.2 minutes/Wh compared to 7.4 minutes/Wh for the Acer MTL. Meanwhile with 14" IPS displays (save for the 13.5" framework), the three 1920x1200 7840U models span 13.9, 13.9, and 15.3 minutes/Wh, while the higher resolution 2560x1600 and 2256x1504 are 9.2 and 11.9 minutes/Wh, respectively. This compared to 11 minutes/Wh for the MSI MTL with its 2560x1600 16" display.

TESKATLIPOKA · Dec 29, 2023

Timorous said:
Only?

Yeah, with HT It would be 48 threads.

Saylick said:
Ehhh, those extra 8 E cores is going to cater to such a small portion of the market in my opinion. If you're the type of user who really needs 8 more E cores, I think you're better suited for another product lineup, i.e. Xeon or EPYC.

Does It even matter how many would really use It? We are talking about absolute performance here.
If someone can't use that many threads, then just buy something with less cores.

TESKATLIPOKA · Dec 29, 2023

Khato said:
As for the battery life, all reviews thus far put MTL on par with Phoenix when normalized for battery capacity and display. I see eight laptop reviews on notebookcheck using the 780M integrated graphics. The three OLED models span 6.2, 7.5, and 8.2 minutes/Wh compared to 7.4 minutes/Wh for the Acer MTL. Meanwhile with 14" IPS displays (save for the 13.5" framework), the three 1920x1200 7840U models span 13.9, 13.9, and 15.3 minutes/Wh, while the higher resolution 2560x1600 and 2256x1504 are 9.2 and 11.9 minutes/Wh, respectively. This compared to 11 minutes/Wh for the MSI MTL with its 2560x1600 16" display.

My opinion is that If someone wants a very long battery life, then It doesn't really matter If he buys MTL or PHX. What he needs to buy is a laptop with IPS panel and the largest battery. End of story.

FlameTail · Dec 29, 2023

TESKATLIPOKA said:
My opinion is that If someone wants a very long battery life, then It doesn't really matter If he buys MTL or PHX. What he needs to buy is a laptop with IPS panel and the largest battery. End of story.

Or maybe X Elite?

DrMrLordX · Dec 29, 2023

FlameTail said:
Or maybe X Elite?

That isn't on the market yet.

TESKATLIPOKA · Dec 29, 2023

FlameTail said:
Or maybe X Elite?

What do you always have with this X Elite? You are mentioning It quite often.
The results provided by Qualcomm looks very good, but that's all.
We don't know how good It will be for x86(x86-64) apps, respectively windows users.
Then there is still the price, this won't be cheap at all.

SiliconFly · Dec 29, 2023

TESKATLIPOKA said:
There is no such a thing as "will win in efficiency for sure", that's just what you want to happen.

And that efficiency is during light load, right? I care more about efficiency during full load, than light load where difference is 1-2W at best.

Overall efficiency.

TESKATLIPOKA said:
What leaks suggest 30% 1T uplift?

MLID. Not exactly very reliable. But the only one who's made that claim afaik.

SiliconFly · Dec 29, 2023

H433x0n said:
I can already tell you where LNC will end up… it’s going to be 18-20% IPC increase. That’s the typical generational target by Intel.

Cypress Cove -> Golden Cove +19%

There’s a small chance (imo a very small chance) that the uplift will be similar to Skylake -> Golden Cove but I wouldn’t count on it.

Skylake -> Cypress Cove -> Golden Cove +28%.

Based on leaked Intel slides I’m expecting an 18-20% IPC increase with a 500-800mhz frequency regression and that gets us to a +5% ST performance uplift. If it manages to reach 5.4ghz boost clocks it will be an okay generation. If you look at IgorsLab leak you’ll see the real world ST performance increase is ~10-12% with WebXprt & Geekbench projections.

Totally agree. That pretty much sums it up!

Considering the IPC uplift & clock freq regression, I too expect only a single digit performance uplift for the desktop parts. But since the freq regression doesn't affect the laptop parts, I expect a decent double digit performance uplift for the mobile parts.

FlameTail · Dec 29, 2023

TESKATLIPOKA said:
What do you always have with this X Elite? You are mentioning It quite often.
The results provided by Qualcomm looks very good, but that's all.

I cannot deny that I am excited about the Snapdragon X Elite. There's very good reason for that. The X Elite- the Oryon CPU in particular is product of Nuvia, which Qualcomm acquired. The Nuvia team was jam packed with talent from some of the best engineers in the industry. So many remarkable and distinguished people.

Back in the day there was so much hype around Nuvia. A lot of people were thirsting to have a product with the Nuvia Phoenix core. Ostensibly, all that hype has died down. But the Nuvia people have not. They are at Qualcomm, and have now announced the product of their efforts.

TESKATLIPOKA said:
We don't know how good It will be for x86(x86-64) apps, respectively windows users.

Indeed. Qualcomm now has put forward the powerful hardware that Windows on ARM lacked for so long. The hardware is good. Now the ball is in Microsoft's court to do the software.

SiliconFly · Dec 29, 2023

TESKATLIPOKA said:
But Intel got rid of HT, so even If they release 8P+32E that's still 40 threads vs 32 threads for Zen5.
What is worse is that AMD stagnates with core count and from Zen2 to Zen5 we are still limited to only 16 cores for desktop.

Apple Silicon has only one thread per core. Hyper threading isn't a necessity for IPC uplift in LNC I guess. New architecture, new paradigm.

SiliconFly · Dec 29, 2023

TESKATLIPOKA said:
We don't know how good It will be for x86(x86-64) apps, respectively windows users.

x86-64 apps on ARM require virtualization. Not exactly an ideal situation as the user experience suffers. But we can get most of the apps to working to a certain level but requires patience. Not just MS, but top software companies should start coming out with native ARM apps. Native is still the best.

FlameTail · Dec 29, 2023

SiliconFly said:
Apple Silicon has only one thread per core. Hyper threading isn't a necessity for IPC uplift in LNC I guess. New architecture, new paradigm.

I think by removing HT, they can dedicate more resources in the core to uplift ST performance.

FlameTail · Dec 29, 2023

SiliconFly said:
x86-64 apps on ARM require virtualization. Not exactly an ideal situation as the user experience suffers. But we can get most of the apps to working to a certain level but requires patience. Not just MS, but top software companies should start coming out with native ARM apps. Native is still the best.

The problem with WoA before was that there was no performant hardware. Hence these top software companies felt no need at all to create ARM native versions of their apps. This is why X Elite is a gamechanger, as we now have competent hardware for WoA. Hopefully this will incentivize the software companies to do their part.

Hulk · Dec 29, 2023

SiliconFly said:
Overall efficiency.

MLID. Not exactly very reliable. But the only one who's made that claim afaik.

I have to admit I do listen to MLID, it's a guilty pleasure. Every now and then while I'm working I put him on in the background. You know what I noticed? He's not really a tech guy. Seems like his interest/knowledge in the tech is superficial. Where is his encyclopedic is in his marketing knowledge. He seems to know when every product CPU and GPU was released, how much it cost, and general performance.

He was explaining to the other guy in the latest video how the E cores are for efficiency but they're really not all that efficient. So many people still don't understand that Intel told us they were for area efficiency, not power efficiency. MLID was saying the P cores are actually more efficient than the E cores! Yeah, that's right, that's because they should be given the die space they consume for the compute they produce. Argh!

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

Senior member

Attachments

Platinum Member

Senior member

Golden Member

Diamond Member

Golden Member

Senior member

Member

Golden Member

Diamond Member

Diamond Member

Lifer

Golden Member

Platinum Member

Platinum Member

Platinum Member

Lifer

Platinum Member

Golden Member

Golden Member

Platinum Member

Golden Member

Golden Member

Platinum Member

Platinum Member

Diamond Member