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

Page 380 - 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
696
602
106
PPT1.jpg
PPT2.jpg
PPT3.jpg



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 + 4E08 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 (20A)Arrow Lake (N3B)Lunar LakePanther Lake
PlatformMobile H/U OnlyDesktop OnlyDesktop & Mobile H&HXMobile U OnlyMobile H
Process NodeIntel 4Intel 20ATSMC N3BTSMC N3BIntel 18A
DateQ4 2023Q1 2025 ?Desktop-Q4-2024
H&HX-Q1-2025
Q4 2024Q1 2026 ?
Full Die6P + 8P6P + 8E ?8P + 16E4P + 4E4P + 8E
LLC24 MB24 MB ?36 MB ?12 MB?
tCPU66.48
tGPU44.45
SoC96.77
IOE44.45
Total252.15

LNL-MX.png

Intel Core Ultra 100 - Meteor Lake

INTEL-CORE-100-ULTRA-METEOR-LAKE-OFFCIAL-SLIDE-2.jpg

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.)



Clockspeed.png
 

Attachments

  • PantherLake.png
    PantherLake.png
    283.5 KB · Views: 24,006
  • LNL.png
    LNL.png
    881.8 KB · Views: 25,490
Last edited:

SarahKerrigan

Senior member
Oct 12, 2014
735
2,035
136
Spec dot org has results for the E1050 96 core. Just do a search on google for spec results for ibm power processors and it's one of the first entries.

To give you some perspective:
IBM Power E1050 (2.95 - 3.90 GHz, 96 core, AIX) - [768 instances, 4 chips, SMT8, only 2 threads per core in use) SpecRate2017IntBase=1220 , Peak=1580
IBM Power E1080 (3.55 - 4 GHz, 120 core, AIX) - [120 cores, 8 chips, 960 instances] = SpecRate2017IntBase=1700 , Peak=2170
Kaytus KR1280E2 (AMD EPYC 9754) (256 cores/512 instances) - SpecRate2017IntBase=1930 , Peak=2100
Kaytus KR1280E2 (AMD EPYC 9654) (192 cores/384 instances) - SpecRate2017IntBase=1800 , Peak=1920
Dell PowerEdge R6625 (AMD EPYC 9754 128-Core Processor)- (256 cores/512 instances) = SpecRate2017IntBase=1820 , Peak=1980
Dell PowerEdge R6625 (AMD EPYC 9684X 96-Core Processor) - (192 cores/384 instances) = SpecRate2017IntBase=1790 , Peak=1870
ZTE R8500G5 Server System (1.90 GHz, Intel Xeon Platinum 8490H) - (240 cores/480 instances) = SpecRate2017IntBase=2000 , Peak=2050
HPE Compute Scale-up Server 3200 (1.90 GHz, Intel Xeon Platinum 8490H) - (960 cores/1920 instances) - SpecRate2017IntBase=7310 , Peak=[Not submitted]

IBM Power10 can be configured in a performance competitive manner, but, it doesn't look like they are competitive on a "per-core-throughput" basis.

Sure they are, if you buy IBM's definition of "core", which you shouldn't. (An "SMT8 core" is two cores.)

If one believes in "SMT8 cores" there's a solid advantage over everything else on that list, as best as I can tell. (That being said, the real app for large Power is scale-up HANA, at which it does... fine.)

As already mentioned, Power is not Z. Z single-thread performance is drastically higher.
 
Last edited:

Hitman928

Diamond Member
Apr 15, 2012
6,186
10,693
136
Yeah, my bad you compared absolute perf (as did WFFC)

I chose 165U / 1360P particularily as they clock very close to the Lunar Lake sample (on average) and are lower TDP parts.

I agree your comparison makes more sense, my post was just in response to the comparison WFFCtech did, which of course used the 185H.
 
  • Like
Reactions: Gideon

Magio

Member
May 13, 2024
88
85
51
The single core score is quite good and in line with what I expected, the MT score is not as impressive. That's in line with a good 165U result. Probably at lower power as the 165U's that score in that range probably are those with a higher TDP but still, +/-12k is what I was hoping to see. Early results, but let's see.
 

Gideon

Golden Member
Nov 27, 2007
1,774
4,145
136
The single core score is quite good and in line with what I expected, the MT score is not as impressive. That's in line with a good 165U result. Probably at lower power as the 165U's that score in that range probably are those with a higher TDP but still, +/-12k is what I was hoping to see. Early results, but let's see.
IMO considering Lunar Lake TDP and 8c/8t corecount, it's very impressive, it's probably TDP limited. 165U has 12 cores and 14 threads and a 57W power limit for all core loads.
 

Magio

Member
May 13, 2024
88
85
51
IMO considering Lunar Lake TDP and 8c/8t corecount, it's very impressive, it's probably TDP limited. 165U has 12 cores and 14 threads and a 57W power limit for all core loads.
For me I'd say it depends, if it does 10K MT while truly sticking to its 17W PL1, then that's OK if not super impressive, but if it needs to gets close to its 30W PL2 to achieve that then that's a disappointment. A fanless M3 or even M2 can get that score with the same core count.
 
  • Like
Reactions: Gideon

dttprofessor

Member
Jun 16, 2022
61
16
51
For me I'd say it depends, if it does 10K MT while truly sticking to its 17W PL1, then that's OK if not super impressive, but if it needs to gets close to its 30W PL2 to achieve that then that's a disappointment. A fanless M3 or even M2 can get that score with the same core count.
M1 7700 15W
M2 8700 20W
M3 10395 17W

4 skymont cores is enough for 90% apps, except game.
 
Last edited:
  • Wow
Reactions: Henry swagger

Magio

Member
May 13, 2024
88
85
51
The Geekbench 6 MT test is garbage.
I'm not the biggest fan of Geekbench, don't get me wrong. Usually I put a lot more weight on Cinebench, but really no benchmark is perfect.

However right now all we have is this Geekbench score and it's basically a "worst" case scenario in MT, only matching 165U. Hopefully we'll see better scores later and it'll do better in Cinebench.
 

coercitiv

Diamond Member
Jan 24, 2014
6,677
14,272
136
+/-12k is what I was hoping to see.
Here's Alder Lake @ 5Ghz in 8P/8T config getting 12K.

For me I'd say it depends, if it does 10K MT while truly sticking to its 17W PL1, then that's OK if not super impressive, but if it needs to gets close to its 30W PL2 to achieve that then that's a disappointment.
Out of curiosity, I ran the test a second time with HWInfo running, watching CPU package power. One MT test went to ~116W (PL2 is 120W), another to ~90W and most others hovered around 60W and few even lower than that. I think I saw one with 45W. From a power perspective Geekbench is not pushing the chips at all.

In fact, it just dawned on me as I typed this, I can test at lower power ceilings. 30W might mess up boosting algo on my 12700K, but 45W is definitely doable and will not affect ST score either.

And the MT score for 8P/8T Golden Cove @ PL1=PL2=45W is.... drumroll... lights moving... 10K!

I think it's safe to say LNL does not need 30W for a 10K score. Now excuse me while I go get my desktop config back...
 

mikk

Diamond Member
May 15, 2012
4,247
2,311
136
I'm not the biggest fan of Geekbench, don't get me wrong. Usually I put a lot more weight on Cinebench, but really no benchmark is perfect.

However right now all we have is this Geekbench score and it's basically a "worst" case scenario in MT, only matching 165U. Hopefully we'll see better scores later and it'll do better in Cinebench.


If 165U matches this core it needs more power. LNL 17W will be 20-35% faster than 165U 15W depending on the MT benchmark. Having only 8 threads won't give exciting MT results but that's not the main thing of LNL. Main thing for most consumers will be battery life/energy consumption in idle and small loads which will help everyone running in battery mode. Also iGPU performance is a big improvement in this TPD range.
 
  • Like
Reactions: controlflow

DavidC1

Senior member
Dec 29, 2023
939
1,471
96
Estimating clocks for the Skymont cluster in Lunar Lake.

SpecInt scales at about 90% relative to clocks. With 38% gain in uarch, at the same power we're at about 3.1GHz and at max performance it's at 3.7GHz for single thread, compared to max 2.5GHz for Crestmont LPE.

For the MT version, Intel claims 2.9x with 2x the cores. Core count scaling is similar for the most part at about 90%, so it leaves 53% for uarch+clocks. That leaves us at 10% higher clocks for Skymont cluster with 2x the core count at the same power as MTL LPE, while having 38%/68% per clock gain. Quite impressive!
Hah, looks like I got the peak clocks for Lunarlake E core correct!

So Lunarlake is where the E core not only covers MT performance but works very efficient at lower load workloads.