From www.techradar.com

CPU concept art of a chip with blue electricity coursing through it

(Image credit: 3dartists / Shutterstock)

Intel has been fanning the flames of hype around its Lunar Lake CPUs, as well as dropping some info about another next-gen range, Arrow Lake.

Arrow Lake will be desktop and higher-end laptop processors, whereas Lunar Lake is for laptops only and designed to be supremely power-efficient.

As Tom’s Hardware reports, by way of running interference with Qualcomm’s new Snapdragon X silicon – revealed in a whole bunch of AI PCs, including new Microsoft Surface devices – Intel boasted about how Lunar Lake will drive this kind of machine forward.

Intel reckons that Lunar Lake will deliver 1.4x faster AI performance than the Snapdragon X Elite, as per Team Blue’s estimation of comparative performance in Stable Diffusion (so add some seasoning here, and bear in mind the kind of cherry-picking that always goes on with marketing claims).

With Lunar Lake’s dedicated NPU – Neural Processing Unit for AI acceleration – hitting 45 TOPS (trillions of operations per second), and the GPU providing 60 TOPS, Lunar Lake offers well over 100 TOPS in total (the CPU itself will add a touch more grunt, too).

That’s extremely nippy for AI workloads when you consider that Meteor Lake has about 30 TOPS in total (NPU + GPU + CPU), putting the generational leap here into perspective.

Intel also underlined the frugal nature of Lunar Lake in terms of power usage, noting that this next-gen laptop silicon will sip 20% less power than Qualcomm’s new Snapdragon SoCs, or 30% less than AMD’s Ryzen 7 7840U.

Sign up for breaking news, reviews, opinion, top tech deals, and more.

Lunar Lake is on track for a Q3 launch, Intel informed us, ready to power up premium thin-and-light laptops. It will also have Xe2 and Intel Battlemage graphics on board – another sizeable stride forward.

Arrow Lake was also mentioned – the big desktop rival for AMD’s incoming Ryzen 9000 processors, as well as high-end mobile CPUs – and Intel assured us these chips are arriving in Q4 of 2024.


The Intel Core Ultra 7 badge on a laptop

(Image credit: Intel)

Analysis: Lunar gap

Arrow Lake is happening as intended, which is good to hear – as there have been whispers of suggestions that this next-gen CPU range could just slip to 2025. Apparently not, and while we can’t rule out any possibility of a delay yet, Intel will certainly be doing all it can to make sure that doesn’t occur. Mainly because Arrow Lake is very much needed on the desktop, given that AMD’s Zen 5-powered Ryzen 9000 CPUs are expected to debut in Q3 of this year.

Speaking of Q3, that’s when Lunar Lake is arriving as detailed by Intel, and that isn’t far off now.

However, when Intel talks about Lunar Lake debuting, and the reality of a large volume of these mobile processors actually being in laptops on shelves – there’s always going to be a sizeable gap in between those points of progression.

In short, as we’ve heard via the rumor mill, Lunar Lake may not be around as a major presence until early 2025, whereas Qualcomm’s new Snapdragon X SoCs are bursting onto the scene right now. Which is likely the reason Intel felt the need to remind us of exactly what’s coming with Lunar Lake…

Via Wccftech

You might also like

Darren is a freelancer writing news and features for TechRadar (and occasionally T3) across a broad range of computing topics including CPUs, GPUs, various other hardware, VPNs, antivirus and more. He has written about tech for the best part of three decades, and writes books in his spare time (his debut novel – ‘I Know What You Did Last Supper’ – was published by Hachette UK in 2013).

[ For more curated Computing news, check out the main news page here]

The post Excited about Snapdragon X Elite laptops? Forget them, says Intel, the true AI PC powerhouse CPU will be Lunar Lake first appeared on www.techradar.com

New reasons to get excited everyday.



Get the latest tech news delivered right in your mailbox

You may also like

Subscribe
Notify of
0 Comments
Inline Feedbacks
View all comments

More in computing