News Intel launches Lunar Lake: claims Arm-beating battery life, world’s fastest mobile CPU cores

[Admin]

Intel finally revealed its performance benchmarks for its Lunar Lake Core Ultra 200V-series processors here in Berlin, Germany, touting ‘historic x86 power efficiency’ coupled with the world’s fastest mobile CPU cores and 30% faster gaming performance than competing processors.

Intel launches Lunar Lake: claims Arm-beating battery life, world’s fastest mobile CPU cores : Read more

 

[Thunder64]

As others have said, I am tired of hearing about salt in every article.

 

[Notton]

Memory-on-package looks like a design win... Intel would be winning more if their graphics drivers were better.

I want AMD to use memory on package for Strix P, the most memory bandwidth starved design in a while.

 

[JamesJones44]

Certainly interesting if these numbers and power draw hold up in independent reviews. I would love to see 3 competitors fighting for position in the CPU and maybe someday GPU space. Competition is always a good thing.

 

[Giroro]

The Core Ultra 9 288V, has a nearly identical looking spec sheet to the Core Ultra 5 268V. That extra GPU core and minor clock boost might make their top tier product perform at best around 20% better than entry level in Integrated-graphics tier games, maybe 10% better elsewhere. It will probably be more significantly better at post-boost multi-core workloads (the kind you really shouldn't want to run on an ultrabook), thanks only to its much higher TDP. But, it might even have worse battery life.
They didn't even bother (or couldn't) to give it an extra boost in memory capacity. 32GB is not enough when you consider they expect this processor to be in $2000+ laptops.

If Intel thinks it will be able to demand "Core i9" premium pricing from customers with their top tier product, I don't think it's going to work out for them this gen.

Plus they need to radically overhaul how they put together these slides and present this kind of marketing information. It comes across as both unexciting, and untrustworthy.

 

[voldemarz]

Why are the slide image of such a poor quality? Can't read any text even when maximized. If so, what's the point to include?

 

[jp7189]

We're finally starting to see what Intel design can do when fabbed at TSMC. All I can think is RIP Intel foundary.

 

[Giroro]

Why are the slide image of such a poor quality? Can't read any text even when maximized. If so, what's the point to include?

I kindof giggled at the irony when I couldn't read the asterisk disclaimer text on their "The Fastest Cores. Period.*" Slide.

It's like I'm trying to make a snide remark about a blatant marketing contradiction over here, and I can't even properly throw Intel's own words back in their face.

 

[graham006]

We're finally starting to see what Intel design can do when fabbed at TSMC. All I can think is RIP Intel foundary.

No.. Intel's fabs just weren't ready for THIS product announcement. The contract to fab Lunar Lake on TSMC was likely completed years ago, before Intel had embarked on it's fabled "four nodes in 5 years" death march. Intel appears to be on track with at least 3 of those four nodes and if they do complete it, you bet that Panther Lake will be manufactured in Intel factories.

 

[vanadiel007]

Intel finally revealed its performance benchmarks for its Lunar Lake Core Ultra 200V-series processors here in Berlin, Germany, touting ‘historic x86 power efficiency’ coupled with the world’s fastest mobile CPU cores and 30% faster gaming performance than competing processors.

Intel launches Lunar Lake: claims Arm-beating battery life, world’s fastest mobile CPU cores : Read more

People who game do not care a lot about power efficiency and typically purchase a gaming laptop with dedicated GPU.
People who occasionally game on their laptop will not care much about a 30% performance increase over competing processors.
That leaves power efficiency as the main attractant. However, I bet $5 OEM's will sacrifice battery size to provide a slimmer, lighter laptop experience and the actual battery will be roughly the same as current generation, leaving nothing noteworthy about this processor release on the table.

 

[ottonis]

"The Empire strikes back!"

Wow, wouldn't have thought that Lunar Lake would single-handedly outclass both the Qualcomm Elite X chip as well as AMD latest and greatest mobile chips.
Now, if independent reviews can confirm these numbers that Intel presented, Lunar Lake will be a game-changer for the x86 market.

 

[JRStern]

Sounds good.
I may be a customer.
So, is there a way to get these chips in a workstation?

 

[bit_user]

Intel claims ‘historic’ x86 power efficiency, saying it delivers 1.2X more performance-per-watt than the Qualcomm X Elite X1E-80-100.

That's not even their lowest-power 12c model. Which Lunar Lake model did they compare it to?

They also beat the AMD Strix Point HX370 by 3% to 33% in single-threaded tasks.

Wow, that's impressive... for AMD!

Seriously, this thing is made on TSMC N3, while Snapdragon X and Strix Point are made on N4 nodes. Is it any surprise it's faster and more efficient? I'd have thought such a node was worth more than that.

Note the position of their M3 datapoint, on this slide:

​

That's the baseline M3. Not even Pro or anything. It also tells us the M4 is going to kick its butt.

I also thought this slide was interesting:

​

Okay, so the only big win it has in productivity is when they use the QuickSync hardware encoder? I'd pay more attention to the two wins AMD got.

Lunar Lake preorders start today, and units start shipping on September 24. If tradition holds, you'll see reviews on that date.

Oh geez. I didn't realize today was a soft launch! I was looking forward to some independent testing!

 

[thestryker]

Why are the slide image of such a poor quality? Can't read any text even when maximized. If so, what's the point to include?

I kindof giggled at the irony when I couldn't read the asterisk disclaimer text on their "The Fastest Cores. Period.*" Slide.

It's like I'm trying to make a snide remark about a blatant marketing contradiction over here, and I can't even properly throw Intel's own words back in their face.

I think something screwed up here when they uploaded them as they're perfectly readable elsewhere: https://wccftech.com/intel-core-ult...p-over-qualcomm-amd-much-better-battery-life/

 

[thestryker]

Intel appears to be on track with at least 3 of those four nodes and if they do complete it

Intel 7, 4 and 3 are already used in shipping parts so that makes 3/5.

 

[thestryker]

That's not even their lowest-power 12c model. Which Lunar Lake model did they compare it to?

Best battery life slide compared 288V, X1E-78-100 and 9 HX 370

Spoiler

Battery life myth slide compared 268V and X1E-80-100

Spoiler

Oh geez. I didn't realize today was a soft launch! I was looking forward to some independent testing!

Yeah this is disappointing.

Very much looking forward to seeing how it performs in power limited scenarios (and also the first look at Battlemage).

 

[bit_user]

I kindof giggled at the irony when I couldn't read the asterisk disclaimer text on their "The Fastest Cores. Period.*" Slide.

It's like I'm trying to make a snide remark about a blatant marketing contradiction over here, and I can't even properly throw Intel's own words back in their face.

Just to echo what @thestryker said, you can find all the testing details here:

Intel® Core™ Ultra Processors (Series 2) - 1 | Performance Index

edc.intel.com

I noticed they listed power mode settings, which might be interesting to note for both the performance and battery life tests. It's enough work to pick out which data points to look at for which claims that I'm not going to bother.

Sometimes, those details are listed in the end notes, but either they stopped doing that or WccfTech didn't post those slides.

 

[Bikki]

The elephant in the room is multi-threaded performance. With only 4p 4e vs 6p 8e on previous core ultra and no SMT, it is sorely lacking. It evident I cant find a single chart for MT benchmark. (Edit: i see 1 chart where it stated +10% at 17w and -6% at 23w.)

The reason for core count regression? Maybe TSMC 3B cost is too high for large die, and Intel itself can't tank losses any longer.

 

[baboma]

>Why are the slide image of such a poor quality? Can't read any text even when maximized. If so, what's the point to include?

THW's slides are low-res. Here's some better ones:

 

[cyrusfox]

Best battery life slide compared 288V, X1E-80-100 and 9 HX 370

Spoiler

Battery life myth slide compared 268V and X1E-80-100

Spoiler

Yeah this is disappointing.

Very much looking forward to seeing how it performs in power limited scenarios (and also the first look at Battlemage).

Bit disingenuous or confusing I would say on that second slide, no longer have the same display or same battery but showing better life for office but worse for Teams... I am glad they included it but the first slide is much better although it would be better if they compared like for like (They have the top bin and I think highest consuming part 288V compared to the lowest end X1E-78). While the second slide seems like more comparable parts (268V vs X1E-80).
Guess I will go check out the disclaimers at the end of the slide deck.

 

[thestryker]

I'm not really confident in comparisons with this type of product given that it's built to fit a specific market. The AMD AI parts are 15-54W and Qualcomm doesn't specifically list TDP whereas LNL are 8-37W. The other thing with comparing the X1E-78 that I found out while looking for TDP is that it doesn't have the dual core boost of the higher SKUs which probably impacts some of the performance. Of course at the end of the day most consumers don't care about this as they're looking for features and price, but it makes marketing comparisons nebulous and independent reviews even more important.

Though after the debacle that has been AMD's marketing slides recently and Intel's public perception problems they'd be well served to maximize accuracy. Of course they're still a corporation so I certainly won't be assuming they've done so.

 

[baboma]

>Bit disingenuous or confusing I would say on that second slide, no longer have the same display or same battery but showing better life for office but worse for Teams

Announcements are always heavy on the PR, so don't pay attention to the details. Just take it from the bird's-eye view.

My take (from Intel's blurbs, which may be subject to change):

. Battlemage is comparable to Strix Point (accounting for some pro-Intel bias from its benchmarks).

. Power efficiency is nearly equal to Qualcomm's, close enough that other factors will matter more, such as apps and games compatibility.

. There's very little difference between the 9/7/5 SKUs, with 9 being virtually identical to 7, aside from the 30W-vs-17W base power bump. For thin&light laptop, 7 is actually better. The main difference is 8 Xe2 cores in 7 & 9, and 7 cores in 5. Not sure how much that impacts iGPU perf. So that's my cut-off: 5 has best value, but for best gfx perf, 7 is the sweet spot.

Of course, we'd need to see like-for-like compares against Ryzen 370/365, especially for iGPU, for more grounded eval. But I think the above "gut-feel" eval will stand, that graphics-wise, Battlemage & Strix Point are comparable, and LNL wins on efficiency, while Ryzen 300 wins in (MT) perf, especially at higher power.

. Assuming LNL's efficiency claim stands up, Qualcomm will need to expand its sales pitch to better pricing. That may not be Qualcomm's forte, as it has positioned its brand as "premium," but others like MediaTek may take up that banner.

. Another point that hasn't been mentioned is Intel's GPU effort likely has handhelds as a consideration, as that seems to be a segment gaining in popularity. Acer's reported jump into handhelds (using LNL) would be a significant event.

 

[Giroro]

Note the position of their M3 datapoint, on this slide:

Is that chart saying that Ultra 9 288V is less efficient than Ultra 7 165H? Because to me it looks like they've had a significant regression in Perf/W at high(er) package power, yet the words they chose are "Astonishing perf/W improvements across the entire operating range".

 

[MacZ24]

At that point I fear that Intel has become Topper from Dilbert :

AMD : My CPU has 16 cores
Intel : That's nothing! My CPU has 8+16=24 cores (even though you'll use only 8 in games)

Apple : My battery life is 20 hours
Intel: That's nothing! My battery life is 20,1 hours ! (and it could be even greater if I just had only 2 cores without SMT)

I think they just have a narcisstic image problem that can't allow them to admit they are behind.

Also at that point, if microchips are a US national security issue, I'm confident that the health of Intel is also a US national security issue, with all that entails (ahem).

 

[cyrusfox]

Is that chart saying that Ultra 9 288V is less efficient than Ultra 7 165H? Because to me it looks like they've had a significant regression in Perf/W at high(er) package power, yet the words they chose are "Astonishing perf/W improvements across the entire operating range".

This is a multi-thread compute chart comparing power efficiency: The 165H, with its 14 cores (6 Performance and 8 Efficiency), outperforms Lunar Lake 8 cores (4P/4E) at power levels above 25W, not too surprising with the 6 missing cores.

Lunar Lake's advantage lies in its superior efficiency at lower power levels (sub-25W), rivaling the efficiency of the M3, which is commendable. It's unfortunate, however, that it's still dependent on running Windows.