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

Page 671 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Tigerick

Senior member
Apr 1, 2022
702
632
106






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

ModelCode-NameDateTDPNodeTilesMain TileCPULP E-CoreLLCGPUXe-cores
Core Ultra 100UMeteor LakeQ4 202315 - 57 WIntel 4 + N5 + N64tCPU2P + 8E212 MBIntel Graphics4
?Lunar LakeQ4 202417 - 30 WN3B + N62CPU + GPU & IMC4P + 4E012 MBArc8
?Panther LakeQ1 2026 ??Intel 18A + N3E3CPU + MC4P + 8E4?Arc12



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

Meteor LakeArrow Lake (N3B)Lunar LakePanther Lake
PlatformMobile H/U OnlyDesktop & Mobile H&HXMobile U OnlyMobile H
Process NodeIntel 4TSMC N3BTSMC N3BIntel 18A
DateQ4 2023Desktop-Q4-2024
H&HX-Q1-2025
Q4 2024Q1 2026 ?
Full Die6P + 8P8P + 16E4P + 4E4P + 8E
LLC24 MB36 MB ?12 MB?
tCPU66.48
tGPU44.45
SoC96.77
IOE44.45
Total252.15



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.)



 

Attachments

  • PantherLake.png
    283.5 KB · Views: 24,014
  • LNL.png
    881.8 KB · Views: 25,501
Last edited:

Hulk

Diamond Member
Oct 9, 1999
4,701
2,863
136
If we take what he's saying at face value, then the performance of the CPU is below the expectations of the engineers that designed it, despite matching the results seen by the team that ran internal benchmarks shortly before it was released.

He certainly could be doing PR damage control. But if we give the benefit of the doubt for a minute and assume he's telling the truth, there's certainly no contradiction here because the team that would do a 30 game internal benchmark shortly before the product unveiling would be a totally different team than the ones who designed the CPU.
If I am reading your first paragraph correctly then you are implying the engineers were also disappointed by the team that ran the internal benchmarks? If so they Intel should have addressed the issue then.

2nd paragraph would imply that Intel's left hand has no idea of what it's right hand is going. Perfect deniability! I want to no part of a company that operates like that on such a large scale. ARL isn't a minor product, it's bread and butter.
 

SiliconFly

Golden Member
Mar 10, 2023
1,653
997
96
If I am reading your first paragraph correctly then you are implying the engineers were also disappointed by the team that ran the internal benchmarks? If so they Intel should have addressed the issue then.

2nd paragraph would imply that Intel's left hand has no idea of what it's right hand is going. Perfect deniability! I want to no part of a company that operates like that on such a large scale. ARL isn't a minor product, it's bread and butter.
This is getting a bit sour. It's crucial to be objective. Zen 5 wasn't a minor product either. And AMD equally messed it up at launch and had to work with Microsoft to roll out patches to fix the issues that took more than a month. At this point, the only computers that'll suit you is Apple. They're the only ones known for picture perfect product launches.
 

poke01

Platinum Member
Mar 8, 2022
2,583
3,409
106
I suppose you haven't used MacOS in recent years.🤣
It's standard advice now to wait for the .1 or even .2 release before upgrading.
Yeah, Apples software is buggy at launch and it doesn’t mature till xx.4 But their CPU/SoC is top notch and that department at Apple is probably top in the industry equaling Nvidia.

Nvidia doesn’t also seem to have buggy silicon lately.

Edit: okay maybe Nvidia has a slight blunder with Blackwell😅
 

Hulk

Diamond Member
Oct 9, 1999
4,701
2,863
136
This is getting a bit sour. It's crucial to be objective. Zen 5 wasn't a minor product either. And AMD equally messed it up at launch and had to work with Microsoft to roll out patches to fix the issues that took more than a month. At this point, the only computers that'll suit you is Apple. They're the only ones known for picture perfect product launches.
I think it's only getting sour because I'm shedding light on an area many proponents of Intel like to keep in the dark. I myself am a proponent of Intel and have only owned Intel systems for the last 35 years, but this situation has become intolerable
 
Reactions: Tlh97

DrMrLordX

Lifer
Apr 27, 2000
22,184
11,890
136
Zen 5 wasn't a minor product either. And AMD equally messed it up at launch

The hell they did. How many times to people need to get their chops busted for trying to throw shade on some other company to distract from Intel's problems in an Intel thread? Do we really need to go through all the reasons why Zen5's launch has been a massive success? Two hints: Turin and the 9800X3D.
 
Last edited:

LightningZ71

Golden Member
Mar 10, 2017
1,910
2,260
136
Zen 5 had two prominent issues at launch: a LONG unaddressed issue with Microsoft applying outdated mitigations to modern Zen cores and an AGESA update needed for cross CCX latency regressions that were proved to negatively affect certain MT use cases. I do hold AMD accountable for not paying attention to the single most common OS on their consumer platform enough to catch and push MS to correct that mitigation bug. The AGESA issue was relatively minor and was most noticeable only in highly synthetic scenarios.
 

SiliconFly

Golden Member
Mar 10, 2023
1,653
997
96
The hell they did. How many times to people need to get their chops busted for trying to throw shade on some other company to distract from Intel's problems in an Intel thread? Do we really need to go through all the reasons why Zen5's launch has been a massive success? Two hints: Turing and the 9800X3D.
Ya. The hell they did. Pls check the posts. When a person tries to paint it as a Intel specific problem, it's important to demystify. And regarding Zen 5 launch, you might find this quote interesting "public memory is short". Meaning, how quickly public opinion can change or how easily past actions and statements can be forgotten or overlooked. See below for details.

Zen 5 had two prominent issues at launch: a LONG unaddressed issue with Microsoft applying outdated mitigations to modern Zen cores and an AGESA update needed for cross CCX latency regressions that were proved to negatively affect certain MT use cases. I do hold AMD accountable for not paying attention to the single most common OS on their consumer platform enough to catch and push MS to correct that mitigation bug. The AGESA issue was relatively minor and was most noticeable only in highly synthetic scenarios.
Thanks for the summary. Some have forgotten all the amd bios updates and OS update frenzy that was going on. Exactly like whats happening now with Intel. Funny thing is, if Intel manages to fix it shortly like amd did, we can see the same users say the same thing like "What Intel problems?" after a short while.

Like one user mentioned a while back, these kinda issues are more frequent now as the cpus get complex with hybrid architecture & chiplets (both companies). Patience is key. Lets see whether Intel manages to provide fixes as promised. If not, then it's open season!
 

OneEng2

Senior member
Sep 19, 2022
259
359
106
This is getting a bit sour. It's crucial to be objective. Zen 5 wasn't a minor product either. And AMD equally messed it up at launch and had to work with Microsoft to roll out patches to fix the issues that took more than a month. At this point, the only computers that'll suit you is Apple. They're the only ones known for picture perfect product launches.
The differences being ....

1) Zen 5 wasn't slower than Zen 4 at anything I am aware of.
2) The issues were identified within days of the first reviews. IDENTIFIED from a technical standpoint, not just ("Oh yea, that's disappointing.... we will sprinkle some magic pixie dust of unknown content on it and it will get better with this "fix").
Yes., but Zen 5 was never slower than Zen 4.
Exactly. Additionally, in the server release of Zen 5, it hit it clear out of the park with the full Turin product besting the latest Intel DC part by 40% on average.... and Turin Dense simply having no competition to speak of. Meanwhile, Intel's new architecture seems to be only a hit in Thin and Light laptops ...... and they are already saying it is too expensive and they will back off using the higher end process for more of the product in the future (ie Lunar Lake design is not moving forward).
Zen 5 had two prominent issues at launch: a LONG unaddressed issue with Microsoft applying outdated mitigations to modern Zen cores and an AGESA update needed for cross CCX latency regressions that were proved to negatively affect certain MT use cases. I do hold AMD accountable for not paying attention to the single most common OS on their consumer platform enough to catch and push MS to correct that mitigation bug. The AGESA issue was relatively minor and was most noticeable only in highly synthetic scenarios.
This. And the fact that Turin was a home run. Strix Point is looking pretty good as well (and is on a less expensive process than Intel's next gen chips to boot) and Strix Halo seems like it will be very potent as well. All-in-all, Zen 5 ends up on top in all but 1 sub market segment. I would say that is the issue with this round of the new Intel architecture.
 

poke01

Platinum Member
Mar 8, 2022
2,583
3,409
106
I don’t get using a product from company just cause you used them before. Intel is failed to up your expectations then move on. Stop giving them your hard earned money.

Go to AMD and experience their CPU. You will have more stable experience with them. Intel isn’t stable right now and won’t be till 2026.
 
Reactions: Tlh97

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
26,389
15,513
136
Zen 5 had two prominent issues at launch: a LONG unaddressed issue with Microsoft applying outdated mitigations to modern Zen cores and an AGESA update needed for cross CCX latency regressions that were proved to negatively affect certain MT use cases. I do hold AMD accountable for not paying attention to the single most common OS on their consumer platform enough to catch and push MS to correct that mitigation bug. The AGESA issue was relatively minor and was most noticeable only in highly synthetic scenarios.
I would not comment about AMD in an Intel thread, but I am just replying on a comment about them.

So I have Zen 5, it has not been updated since day one, and I had it like day one. I don't care what issues may have been found, but mine has not been updated bios or otherwise, or rebooted. Its stable and fast, and has run at 100% load since day one. So I don't care about these so called "issues". Not like all the ones Intel has had with raptor lake and now the current CPU line.
 
Reactions: Tlh97 and Hulk

Meteor Late

Member
Dec 15, 2023
116
98
61
PTL more likely 35% less efficient than LNL than 35% more efficient.

PTL is going to be more like RPL and will use way more power to win 5% vs AMD.

Because they are probably talking about MT efficiency, that's what this is all about. Of course it's going to be much more efficient with more cores, but only in workloads that use all the cores.
 

MoistOintment

Member
Jul 31, 2024
59
107
66
If I am reading your first paragraph correctly then you are implying the engineers were also disappointed by the team that ran the internal benchmarks? If so they Intel should have addressed the issue then.

2nd paragraph would imply that Intel's left hand has no idea of what it's right hand is going. Perfect deniability! I want to no part of a company that operates like that on such a large scale. ARL isn't a minor product, it's bread and butter.
Or the CPU was launched before it was fully ready and needs a microcode update? Or Hallock is doing PR damage control? Or he's mainly talking about all of the weird issues (like instability in 24'H2 and APO not on be default)?

Im not making any claims to the accuracy of Hallock's statements regarding a performance uplift incoming with an update. I'm just simply pointing out that:

1) "performance is not where we would like to see it and are working on a patch" and

2) "the performance 3rd party reviewers see and what we see align"

Are **not** mutually exclusive statements. Both *can* be true.
 

Hulk

Diamond Member
Oct 9, 1999
4,701
2,863
136
Or the CPU was launched before it was fully ready and needs a microcode update? Or Hallock is doing PR damage control? Or he's mainly talking about all of the weird issues (like instability in 24'H2 and APO not on be default)?

Im not making any claims to the accuracy of Hallock's statements regarding a performance uplift incoming with an update. I'm just simply pointing out that:

1) "performance is not where we would like to see it and are working on a patch" and

2) "the performance 3rd party reviewers see and what we see align"

Are **not** mutually exclusive statements. Both *can* be true.
This is the crux of what disappoints me regarding Intel's handling of this problem. All we know, all they will divulge is benchmark results were "unexpected" and we're going to fix it?

Fix what? Why? Maybe the benchmarks were higher than they expected? Who knows. People are happy because Intel actually popped their head up and said something. OMG they listened to us, the little people. They are only responding because this is not good for sales in what could be a big way. But still, it's Intel and they generally aren't forthcoming (read honest).

One of the only times I remember some honesty was the interview with Raja Kodure regarding Arc. He said they didn't expect the driver issues they were having because they had so many years creating iGPU's, what could go wrong? They'd be doing drivers forever.

Then he admitted when you throw more hardware into the GPU all sorts of bottlenecks in the software begin to pop up and this is something that pretty much hit them from out of the blue and it was a big problem that required and still requires a lot of hours to work through. He also admitted that some of the design hardware-wise was stronger than it needed to be in areas and not as strong in others and this also came back to the difficulty of creating a balanced design that is 10x or 100x more powerful than what you had been building.

Now to me this all made perfect sense and Intel was and still is cranking out driver updates that have done wonders to make Arc more performant and more stable. 8 months ago Arc and Topaz AI apps was dicey, today it actually works quite well. It does not hurt to try and obviscate issues. Most people, probably 90% only need to hear a fix is coming and they move on with their lives. But others, like me, get frustrated with the lack of transparency when it comes to a product I may have already spent my money on or are considering for purchase.

I like Intel. I want them to succeed. I also like AMD and want them to succeed. They both have done amazing things and I'm sure they will continue to do so. I'm only saying more honestly, not less, will lead to greater brand alligience and trust from the public, not less, which has been and continues to be their business practice. This is my opinion so it is worth exactly nothing.


Now back to our regularly scheduled program. I will wait with baited breath for the resolution of ARL.

Specifically, I have three questions I'd like to eventually have the answer.
1. Was the press release performance data what was expected of the final product and is that what or not what we saw in reviewers benchmark data?

2. If that is what we saw then why is Intel talking about Windows and BIOS updates to fix the "unexpected" results?

3. If that is not what happened, meaning Intel press release benchmarks and reviewer benches were in alignment, then why is there any talk of a fix? Where did that come from because it couldn't have been from reviewers benchmark data if that data supported the press release data and vice-versa?

3. Please provide insights into the BIOS and Windows changes. I mean you have divluged so many details regarding the architecure how could it be harmful to your IP to tell us about the software bottlenecks you are fixing?

Something is not striking me as logical thus far.

AMD was different. Some benches were low, AMD agreed, told us why, and fixed it. End of story.
 

OneEng2

Senior member
Sep 19, 2022
259
359
106
Of all the companies in the universe, Apple is the last one I'd expect to acquire Intel.
Seems like a stretch to me as well. I don't think anyone is buying Intel until at least 2026.

To the original topic:

Really, for desktop and laptop, the new generation of Intel processors aren't bad from a performance standpoint ...... IF you don't game on your machine. For most consumers, they look pretty good to me.

Now, the big issues I see are:

1) Intel isn't making nearly enough margin on these processors to make a profit. They are too expensive for Intel to make at this time.

2) The core design will get killed in DC without SMT which would drastically change the design IMO.

If Intel can't stop the bleeding of market share in the high margin DC with CWF, they are in trouble. My question is, will 288 cores of Skymont be enough to combat 192 cores on Turin Dense?
 

Hulk

Diamond Member
Oct 9, 1999
4,701
2,863
136
Seems like a stretch to me as well. I don't think anyone is buying Intel until at least 2026.

To the original topic:

Really, for desktop and laptop, the new generation of Intel processors aren't bad from a performance standpoint ...... IF you don't game on your machine. For most consumers, they look pretty good to me.

Now, the big issues I see are:

1) Intel isn't making nearly enough margin on these processors to make a profit. They are too expensive for Intel to make at this time.

2) The core design will get killed in DC without SMT which would drastically change the design IMO.

If Intel can't stop the bleeding of market share in the high margin DC with CWF, they are in trouble. My question is, will 288 cores of Skymont be enough to combat 192 cores on Turin Dense?
What is #1 based on? Not denying, just curious about the numbers.

As for #2 I'm not sure DC make or breaks the desktop?
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |