Intel Unveils Lunar Lake Architecture: New P and E cores, Xe2-LPG Graphics, New NPU 4 Brings More AI Performance
by Gavin Bonshor on June 3, 2024 11:00 PM ESTClosing Remarks: Piecing Lunar Lake Together, Coming Q4 2024
So, what's Lunar Lake all about? We know that Lunar Lake isn't built using any of Intel's nodes, which may come as a massive surprise to some, but it does leverage TSMC's 3 nm N3B node, and on paper, it looks like a significant upgrade to Meteor Lake. Lunar Lake seems like a big mobile CPU architectural uplift from Intel when compared directly to Meteor Lake in the mobile SoC space, marking a big jump in task-specific processing capabilities. Now, they integrated Lion Cove P-cores with Skymont E-cores, addressing the intensive task together with the background activities to ensure maximum performance.
Also, the inclusion of NPU 4, which pumps 48 TOPS, makes Lunar Lake a strong competitor in the AI and machine learning field, with "world-class" AI performance, highlighting Intel's investment in AI for the AI-driven future. However, AMD's recent Zen 5 and Ryzen AI 300-based disclosure puts it ahead in TOPS at an 8-bit level. Unlike AMD, Intel has focused on giving a holistic figure for combined TOPS for Lunar Lake, although much of this is NPU and GPU.
Intel's system efficiency has been beautifully demonstrated in the provided slides and in the Intel Tech Tour Taipei presentations. However, the proof is what the silicon is like in hand and how it performs in devices. Still, with the latest Xe2-LPG and up to 32 GB of on-package memory brought to the table using their Foveros packaging technology, it remains to be seen how essentially limiting upgradability in terms of memory capacity is seen across the wider industry.
Lunar Lake also brings power management improvements, including the enhanced Intel Thread Director and the quad array Power Management Controllers, which enables Lunar Lake to adjust dynamically to changing workload requirements. The latter is increasingly key for mobile due to battery life concerns and the need for long-lasting performance. Lunar Lake is on track for a launch planned in Q4 2024, and while Meteor Lake was inherently later to market than Intel would have liked, hopefully, Lunar Lake can stay on track.
The choices Intel has made for Lunar Lake make it seem more of an incremental jump instead of a full rethink of what we saw with Meteor Lake. Yes, on paper, Intel has made significant improvements by introducing new P-Cores, E-Cores, a new process node, power improvements, the new NPU 4, and new Xe2-LPG graphics. Still, Intel fails to deliver anything meaningful in the shape of performance figures; not even anything to compare what it can do with other chips currently on the market, nor chips expected to hit the market soon.
It seems as if Lunar Lake is more of a "look at what we can do" than the final and intended result of Intel's disaggregated mobile architecture. It remains to be seen how Lunar Lake will perform compared to Qualcomm and AMD's offerings, but it's clear Intel is the more ambitious of the three, and we look forward to seeing what Lunar Lake has to offer.
91 Comments
View All Comments
thestryker - Monday, June 3, 2024 - link
I'm curious what the overall E-core performance is going to look like since the cluster won't have L3 cache access. Chips and Cheese did some analysis of the LP E-cores on MTL and found this specifically to be a big negative. I'm guessing this design is going to be limited to just LNL and is predominantly for the power savings. ReplyET - Tuesday, June 4, 2024 - link
Interestingly, Intel is comparing Skymont to Raptor Cover. I agree that we have to wonder how the L3 (or lack thereof) affect this, but from the Chips and Cheese figures alongside Intel's performance improvement figures, it looks like Skymont without L3 cache will be faster than Crestmont with L3 cache. Replykwohlt - Tuesday, June 4, 2024 - link
There's 8MB of "SOC cache", separate from both the P and E cores, that should in practice function as the E cores' L3 Replythestryker - Tuesday, June 4, 2024 - link
That's my assumption as well as I think the GPU would be the other part predominantly using it and they shouldn't really both be hitting it at the same time. Replysharath.naik - Monday, June 10, 2024 - link
Side cache is not the same as L3, or I think they would have called it that. shared L3 is where the memory sync can happen across cores. if not, it needs to go all the way back to ram. So, side caches really cannot be considered as L3, more like expanded L2 for E-core and expanded l3 for P-Core? is my guess. Yes, it means things that run on both E-Core and P-Core, at the same time, will take a hit on performance. I think they were targeting the majority use case. where most won't need more than 4 threads or threads won't be working on the same data.Reply
powerarmour - Thursday, June 6, 2024 - link
I can see this being an embarrassing launch if it gets slapped around by Qualcomm's SDx Elite Replymode_13h - Friday, June 7, 2024 - link
Well, they're on a better node that Qualcomm, so there's that. Replysharath.naik - Monday, June 10, 2024 - link
It absolutely will. Because this is going to be slower than meteor lake in CPU. Elite is supposed to be 30% faster. Intel should have released 8 P-core version to compete in performance. But I think they wanted to reserve that to be produced on their own fabs. Replylmcd - Monday, June 17, 2024 - link
Snap Elite is supposed to be 30% faster at essentially-undisclosed power. Lunar Lake will ironically undercut the Snapdragon Elite on power and cost while delivering good performance. ReplyDrumsticks - Tuesday, June 4, 2024 - link
I hate to ask this, but was this article fully written by Gavin and proof'ed by another editor? Was there a deadline push to get it out as soon as Intel released the information on Lunar Lake? It just reads so, so disjointed. It feels like there are so many issues in this paragraph alone on the P-core overview; it feels jarring to read."This Lion Cove architecture **also aligns with performance increases**, boasting a predicted double-digit bump in IPC over the older Redwood Cove generation. This uplift is noticed, especially **in the betterment of its hyper-threading, whereby improved IPC** by 30%, dynamic power efficiency improved by 20%, **and previous technologies, in balancing**, without increasing the core area, **in a commitment of Intel to better performance**, within existing physical constraints."
I've seen so much better work from Gavin, and Anandtech in general, that I almost hope that this page was heavily written by software. I know it's a press release, and there's not a whole lot of information, but the level of first party detail here feels similar to the Architecture Day 2021 presentations Intel did on Alder Lake, which got fantastic coverage from Andrei and Dr. Cuttress, and here it feels like we are getting a poorly worded restating of the slides with hardly any analysis or greater than surface level understanding.
I've been reading Anandtech since I was 15, and the level of detail in the Sandy Bridge era articles honestly had a huge influence on my choice to pursue a career in CPU Design. I've mountains of respect for what Anandtech has published in the past, but this article feels rushed. Reply