Intel Unveils Meteor Lake Architecture: Intel 4 Heralds the Disaggregated Future of Mobile CPUs
by Gavin Bonshor on September 19, 2023 11:35 AM ESTIntel Meteor Lake: Changing The Strategy, Laying the Foundation for Intel 3
The strategy for both the Intel 4 process and the first architecture built on it, Meteor Lake, looks to change the dynamic for the mobile market and the foreseeable future of Intel's client processors. With the Foveros 3D packaging, opting for a power-conscious mobile platform seemed the best way to showcase their gains in terms of power efficiency.
One of the main product assembly advantages of Foveros packaging is that Intel can chop and change tiles depending on the processor, which includes current technologies, I/O, graphics, and compute cores. This approach to 3D tiled packaging also means that it is theoretically easier to introduce new tiles with faster cores with higher IPC performance, new graphics processors, and newer I/O, such as Wi-Fi 7. With Foveros not limiting Intel to use a single, monolithic die, it allows Intel to use different manufacturing processes for each of the tiles and integrate them onto the silicon. This is prevalent with the compute tile being built on Intel 4, while the graphics tile in Meteor Lake is made using TSMC's N5 node. This flexibility is key to advancing innovation, customizability, and, of course, wafer yield.
Intel Meteor Lake from Hot Chips Slide Deck
Intel also introduced a dedicated in-silicon AI engine through the NPU within the SoC tile. Similar to AMD with their Ryzen AI technology, Intel is looking to capitalize on the AI rush within its client-focused processors, but with support for OpenVINO and also including MCDM driver-compliance, users can do some pretty cool things with AI inferencing on the chip. Although these implementations aren't akin to the types of AI inferencing done in the cloud via ChatGPT with dedicated AI hardware, it's a step in the right direction in a world that looks to be slowly taken over by AI.
Wrapping things up, while Intel is confirming that Meteor Lake is coming to mobile-first, any details beyond that are slim pickings. At this point in time, Intel hasn't revealed anything in regard to SKUs or possible configurations. Everything disclosed is based on the 'full; Meteor Lake processors, but Intel hasn't spoken about different configurations or what the lower-end segment might look like regarding tiles and implementations. From their Hot Chips disclosures, offering a tiled architecture allows them to scale upwards and down depending on the SKU. The high-end SKU, which hasn't been disclosed yet, will feature the full configuration and implementation of all the features. Otherwise, the scalable nature of Meteor Lake and disaggregation allows for different levels of compute and graphics tiles and the ability to scale the input and output (I/O) depending on the device.
Meteor Lake will also be the first mobile platform from Intel to use their new Core naming scheme for products, which drops the 'i' from the Core branding. This includes the Core 3, 5, and 7, as well as higher spec Ultra 5, 7, and 9 Ultra tiers. Pat Gelsinger, Intel's Chief Executive Officer (CEO), during his opening keynote at Intel Innovation 2023, states that Intel is launching the first Meteor Lake Ultra (high-end) SKU with AI capabilities (NPU) on December 14th.
A tray of Meteor Lake Core Ultra processors (Credit, Intel)
We expect Intel to disclose more about specific SKUs and other specifications, such as clock speeds and core configurations, as we get closer to Meteor Lake's launch. Although we're expecting Ultra-focused Meteor Lake SKUs to launch on December 14th, no details on when we can expect other SKUs are set to hit retail channels. Meteor Lake is likely to launch with the top Ultra SKU or at least one that is close to the top of the stack.
Reading the tea leaves ahead of Innovation 2023, one gets the impression that Intel was hoping to be just a bit closer to launch by now than they actually are. But all things will eventually come in due time...
Facebook
Twitter
RSS
107 Comments
View All Comments
PeachNCream - Thursday, September 21, 2023 - link
Nice trolling lemur! You landed like an entire page of nerd rage this time. You're a credit to your profession and if I could give you an award for whipping dead website readers into a frenzy (including regulars who have seen you do this for years now) I would. Congrats! 10/10 would enjoy again.IUU - Thursday, September 28, 2023 - link
Intel does not need to do anything about its architecture to to match or surpass m3. It just needs to build its cpus on a similar node. Which is not happening anytime soon, thus perpetuating the illusion of efficiency of apple cpus.Two things more. First it is hilarious to compare the prowess of Intel on designing cpus to that of Apple. Apple has long time "building" machines like a glorified Dell borrowing cpus from IBM or Intel and only recently understood the scale and effort needed to design your silicon by improving on ARM designs.
Secondly, it is misguided to say that if a cpu needs 10 times more wattage on the same node to achieve 2 or 3 times the performance is less efficient. This is not how physics works . If Intel built their cpus on N3 of tsmc they would be 2 or 3 times faster best case scenario. Wattage does not scale linearly with performance. This is the same as saying that a car that has 10 times the power would be 10 times faster. Lololol.
Apple designs good cpus recently , but all the hype about its efficiency is just hype. Even if we assume the design is totally coming from Apple , which it doe not, being a very good modification at best, it does not even build its nodes. By large its efficiency is TSMC efficiency. If it were not for TSMC Apple would be non existent on the performance charts.
Silma - Tuesday, September 19, 2023 - link
TLDR:- Intel 4 < TSMC N6
- To not be late, Intel 3 must arrive within 3 months,which is highly doubtful, since Intel 4 isn't even shipping yet
- I assume Intel 3 < TSMC N6, otherwise, why bother enriching the competition?
- Parts of the new tech stack looks promising, but Intel refrains from any real performance claims, or any comparison with offerings from AMD or Apple.
- Did Intel announce another architecture for desktop computers, probably more similar to that of AMD, e.g. perhaps many performance tiles plus one cache tile?
Drumsticks - Tuesday, September 19, 2023 - link
Maybe. Or maybe TSMC6 is cheaper, and Intel doesn't need the power savings or area savings of I4 over TSMC6 for what the non-compute tiles need to accomplish. It's not exactly uncommon to see the SoC / IO tile on a lower node, doesn't AMD do the same thing?Roy2002 - Tuesday, September 19, 2023 - link
Intel 4 and 3 are basically the same with the same device density as 3 is enhanced 4. I assume it has slightly higher density value than TSMC 5nm and performance is slightly better. Let's see.kwohlt - Tuesday, September 19, 2023 - link
Intel 4 is not library complete. It can't be used for the SoC tile.sutamatamasu - Tuesday, September 19, 2023 - link
I wonder if current processor have an dedicated NPU, then what the heck happen with GNA?It still in there or they're remove it?
Exotica - Tuesday, September 19, 2023 - link
Intel should've either implemented TB5 in Meteor Lake or waited until after Meteor Lake shipped to announce TB5. Because as cool and impressive as meteor lake seems, for some of us, it's already obsolete in that it makes no sense to buy a TB4 laptop/PC and instead wait on TB5 silicon to hit the market.FWhitTrampoline - Tuesday, September 19, 2023 - link
Why use TB4 or USB4/40Gbs and have to deal with the extra latency and bandwidth robbing overhead compared to PCI-SIG's OCuLink that's just pure PCIe signalling delivered over an external OCuLink Cable. OCuLink and PCIe requires no extra protocol encapsulation and encoding/decoding steps at the PCIe link stage so that's lower latency there compared to USB4/TB4 and later generations that have to have extra encoding/decoding of any PCIe protocol packets to send that out over TB4/USB4. And for external GPUs 4 lanes of PCIe 4.0 connectivity can provide up to 64Gbs of bandwidth over an OCuLink port/cable and OCuLonk ports can be 8 PCIe lanes and wider there.Once can obtain an M.2/NVMe slot to OCuLink adapter and get an external OCuLink connection of up to 64Gbs as long as the M.2 is 4, PCIe 4.0 lanes wide and no specialized controller chip required on the MB to drive that. And GPD on their Handhelds offers a dedicated OCuLiink port and an external portable eGPU that supports OCuLink or USB4/40Gbs-TB interfacing. TB5 and USB4-V2 will take years to be adopted whereas OCuLink is just PCIe 3.0/4.0 there delivered over an external cable.
Exotica - Tuesday, September 19, 2023 - link
Unlike thunderbolt, Occulink doesn't have hotplugging, meaning your device must be connected at cold boot. Not so good for external storage needs.