For many months, Intel has spared no opportunity to remind us that its Meteor Lake chips would be the ones to watch — its first CPU with different chiplets for each component; its first on its Intel 4 process node; its first with a dedicated AI coprocessor inside. Today, Intel is revealing a whole lot more.
Meteor Lake will “launch” on December 14th, the company now says, as the most power-efficient client processor the company’s ever made — and with up to twice the graphics performance, a “low power island” that can run tasks independently, and hooks into Microsoft Windows to intelligently control the new chips.
In no particular order, here are the highlights of Intel’s Core Ultra — because yeah, this one’s not called a Core i7.
It’s made of tiles
With Meteor Lake, Intel will join its peers in crafting computer chips out of Lego-like building blocks — where the “CPU” and “GPU” aren’t just separate components on the same chip, for example, but actually separate pieces of silicon printed at different sizes and grafted together. The likes of AMD and Qualcomm have been doing this for a while, but heterogeneous computing is relatively new to Intel.
The downside for you is that only part of Intel’s chip is actually on the company’s bleeding-edge Intel 4 process. The graphics are on TSMC’s 5nm process, and the I/O and new “SoC Tile” are on TSMC N6. But the upside is that companies can choose the best building blocks — and selectively cut off power to the rest.
Right out of the gate, no pun intended, Intel is attempting to use chiplets to radically reduce how much power its processors draw. And it’s doing so by taking some of the “Central” out of CPU.
Instead of a single CPU or display region of the chip, each Meteor Lake has two — one on a “low power island” that can theoretically run all by itself, with its own efficiency CPU core, NPU AI coprocessor, media engine, and memory.
The other processor cores are distributed among a “Compute Tile” on Intel 4 that houses the P (Performance) and E (Efficiency) cores, dubbed Redwood Cove and Crestmont, respectively, plus a separate Graphics Tile on TSMC N5.
Realistically, most people using a computer will invoke the Compute Tile, but Intel wants to heat up the chip as little as it can, with an enhanced “Thread Director” that only pushes work to higher-power cores after it’s tried the lowest-power ones first:
That goes for the AI coprocessor, too — which Windows can natively see and monitor in the Task Manager, by the way.
Since “Media” is separated from “Graphics,” integrated encoding and decoding of video could theoretically happen without hitting the graphics tile at all. “An example of this is the addition of hardware support for the AV1 film grain feature, which was previously executed with GPU shaders,” writes Intel.
In addition to AV1 video, native HDMI 2.1 and DisplayPort 2.1 support, and either 8K HDR video or up to four 4K monitors at once, that SoC tile offers Bluetooth 5.4 and Wi-Fi 7. The latter theoretically offers up to 5.76Gbps transfer speeds, assuming you manage to set up a 320MHz channel in your workplace or neighborhood.
Can it game?
But all those “graphics”-like tasks separate from GPU doesn’t mean the GPU is just for show. Intel says Meteor Lake can add its Intel Arc graphics — now with dedicated ray-tracing units and up to 8 Xe cores on the chip itself.
Intel says the “Xe LPG” GPU offers up to twice the performance per watt of Xe LP, which themselves were twice the performance per watt of its 11th Gen Intel UHD that came integrated in processors before.
They also support Intel’s XeSS — its intelligent upscaler akin to Nvidia’s DLSS and AMD’s FSR — for the first time on integrated graphics, which could help boost frame rates even more.
While it didn’t provide any performance numbers, Intel says the GPU can “run at a much lower minimum voltage and reach a much higher maximum clock speed” than previous iGPUs, at well over 2GHz.
And Intel has developed its own “patented low-cost vapor chamber” cooling solution, the company claims, to help get gamer and creator laptops with Meteor Lake out in the world.
Just know that not every Meteor Lake / Core Ultra processor will get the fancy GPU. The fine print reads: “Intel Arc graphics only available on select MTL processor-powered systems with dual-channel memory.”
But the NPU — that AI coprocessor — should theoretically be in every chip. “The NPU will be available across the full product stack of Meteor Lake,” says Intel’s Tim Wilson, VP of architecture.
(That would line up with what Intel CEO Pat Gelsinger said on a July earnings call: “We’re going to build AI into every platform we build.” But I haven’t confirmed if Meteor Lake will appear outside Core Ultra, so buying a non-Ultra chip may mean no NPU for now.)
Intel isn’t suggesting the tiny NPU will suddenly mean generative AI can stop running on giant cloud servers filled with Nvidia H100 chips, nor is the company saying this one NPU can do it all while you sleep. Instead, it’s suggesting that you now have options — it’s much more efficient to let the NPU run image generator Stable Diffusion, and it’s faster and still decently more efficient to have your GPU and NPU run it together:
The company didn’t seem to have a lot of specific examples for how “AI is going to reinvent how you do everything on Windows,” to borrow a phrase from Microsoft’s out-the-door Windows boss Panos Panay — at least beyond the same things Qualcomm’s NPUs can already do with Windows Studio Effects in Microsoft Teams.
But it does have an OpenVINO Inference Engine to help talk to those applications and pipe them directly to the NPU, and a lot of general ideas, including:
Intel is using Meteor Lake as proof that it’s executing again, as part of Gelsinger’s grand turnaround plan for the company. The company says yields of the Intel 4 parts of Meteor Lake (read: the Compute Tile) outstrip not only its introductions of 14nm with Broadwell and 10nm with Ice Lake but also its “tock” refinements to the “tick tock” formula with Skylake and Tiger Lake, respectively.
None of this matters if the components don’t actually perform, and Intel’s said nothing about raw performance or battery life in response to our questions. Reps repeatedly apologized on a conference call, saying they’d answer those sorts of questions closer to launch. On the CPU side, the only hints I saw were that the new Crestmont E-cores have unspecified “IPC gains over previous E-cores” — though results may vary, the fine print warns — and that the new Redwood Cove P-cores have “improved performance efficiency.”
But Intel says it’s investing big in this model of the future. It’s putting $3.5 billion into New Mexico through next year and $7 billion into Penang, Malaysia, over the next 10 years to invest in a “sharp ramp in capacity” for Meteor Lake and other Foveros-style chips — the ones that three-dimensionally stack and assemble different building block chips onto a single package. Next, it’s moving to direct copper-to-copper bonding, something it’s calling Foveros Direct, and it intends to sit these chips on glass by the end of the decade.