We heard more about Intel’s Arrow Lake processors – and Lunar Lake – from Moore’s Law is Dead, and while there are plenty of positives to take from all this, don’t get carried away with the idea that Team Blue I’m going romp home with an easy victory over AMD in the battle for next-generation CPUs.
According to one of the top Intel YouTuber sources, Arrow Lake will deliver a 25% to 35% performance boost over Meteor Lake, as MLID has been saying for a while – and that’s a minimum (so it could work out better – we remember one leak suggesting 40%, although that was now a good way back).
This is comparing chips with the same number of cores, plus Arrow Lake won’t have hyper-threading (as has been widely rumored for a while), so this is even more impressive in that regard.
In short, Arrow Lake will be a huge generational leap, and one that will surpass the Zen 5 in terms of pure CPU performance. (AMD’s next-gen Ryzen processors are believed to be more on the order of 20% gen-on-gen increase, maybe a little less even – be careful with all these rumors, as always).
Where Arrow Lake may disappoint is on the AI front, with the NPU (Neural Processing Unit) not really a step beyond what we already have with Meteor Lake.
Where Intel will advance AI acceleration much more meaningfully is with Lunar Lake, its chips aimed at premium thin and light laptops, with the NPU expected to achieve 40+ TOPS (a benchmark for AI performance). In contrast, Arrow Lake is expected to score more around 13 TOPS.
MLID believes that the Arrow Lake desktop CPUs (succeeding Raptor Lake Refresh) are still on track for a late 2024 launch, again as long rumored – but the catch is that the YouTuber is suggesting that this could be a paper launch.
In other words, real production volume and high inventory on shelves may not happen until early 2025 – when Arrow Lake laptop CPUs will be launched to take over from Meteor Lake.
Meanwhile, Lunar Lake, as mentioned for notebooks only, will be released in Q4 2024, and that’s now a firmer prospect, we’re told.
MLID also provides some details on the integrated graphics for both processor families, and they will use (up to) 8 Xe Cores in both cases. The crucial difference, however, is that Arrow Lake will be Alchemist+ and Lunar Lake will be Battlemage.
Arrow Lake will still offer much more performance than Meteor Lake with integrated graphics, but Lunar Lake obviously has the advantage here, in theory using that 2nd generation architecture from Intel. Lunar Lake will also be faster than Meteor Lake’s integrated graphics, but crucially it will also try to halve power consumption, with an emphasis on efficiency rather than going all out for performance.
Keep in mind, however, that there are Lunar Lake designs that allow higher power consumption for big performance gains for integrated graphics, but MLID seems skeptical that these will see the light of day. The emphasis here is very much on energy efficiency, and more powerful mobile chips will come elsewhere (like Arrow Lake, previous speculation suggested – although it will also have low-power chips, or at least that’s the theory).
Analysis: Intel takes the performance crown out of the gate, but that’s not the full story
There’s a good chance we’ll see both the Arrow Lake desktop and Lunar Lake before this year is out, at about the same time, late 2024, in the fourth quarter. The main question for those eyeing a next-generation CPU is: will the Zen 5 come out first, and how do these rival ranges obviously stack up?
More recent news from the rumor mill has suggested that AMD’s Zen 5 desktop chips could arrive in the fourth quarter (Team Red itself has also confirmed a launch for this year). So we could see all these processor families landing around the same time, in the fourth quarter. However, MLID also addresses the possible release date for Zen 5 here, showing a Q3 timeframe (across multiple arenas, not just desktop CPUs).
What does this all mean? While Arrow Lake could see a much bigger jump in performance (35% vs. 15-20%, so perhaps double the gains offered by AMD), the Zen 5 could be the first to market in a few months. Zen 5 can also be a lot cheaper (with seasoning), because Arrow Lake is built on a more advanced (and expensive) process (3nm, versus 4nm for AMD). And if Intel can’t rein in the power and efficiency side much better than it can with Raptor Lake Refresh, the Zen 5 could be a winner there too.
MLID also points out that while Arrow Lake is expected to be in pole position in terms of overall raw performance at launch, AMD will soon have X3D spins for Zen 5 desktop processors on the docket – and these will take away any advantage that Team Blue has, leveling.
All of this is in theory, of course, but the upshot is that Intel may have something special with Arrow Lake, as has been rumored all the time – but AMD may not have to worry too much thanks to what it has as a next-gen answer on Team Blue’s incoming CPUs.
As a final note on Lunar Lake, with Battlemage graphics offering faster frame rates than Meteor Lake, at much less power, this could be a fantastic chip for the increasingly popular gaming handhelds (the just-launched MSI Claw uses a Meteor Lake processor, remember). Assuming Intel can get the drivers for Battlemage right, and therein lies the problem: if finalizing the 2nd generation Arc GPUs takes longer than expected (another recent suggestion), this could delay Lunar Lake until 2025.