Intel Disaggregates Client Chips with Meteor Lake in 2023

Intle Meteor Lake HC34 Cover

We are going to split this one up a bit. The Hot Chips 34 talk by Intel on Meteor Lake is one-half of the equation, but it is going to be a larger article about the disaggregated future. As a result, we are going to split this into two pieces, this one on Meteor Lake, and the next will be on disaggregation.

Note: We are doing this piece live at HC34 during the presentation so please excuse typos.

Intel Enters a New Era of Chiplets and Disaggregation with Meteor Lake

Meteor Lake is the next-generation Intel Core platform for client. Instead of being a monolithic die, Intel is planning to have a disaggregated future.

Intel Meteor Lake Monolithic V Disaggregated
Intel Meteor Lake Monolithic V Disaggregated

Driving this disaggregation is that different types of transistors are best from a cost/performance standpoint for certain types of applications. As a result, disaggregation helps to right-size the process for the application.

HC 34 Intel Transistor Diversity Opportunity
HC 34 Intel Transistor Diversity Opportunity

Disaggregation has been a push for years. This is a relatively lower-end integration than Intel Ponte Vecchio, but is also a higher-volume one.

HC34 Intel Meteor Lake Disaggregation Journey
HC34 Intel Meteor Lake Disaggregation Journey

With Meteor Lake, Intel will have a flexible tiled architecture. There will be a base tile and then four tiles that are connected through the base tile to create the package.

HC34 Intel Meteor Lake Architecture And Design Tradeoffs
HC34 Intel Meteor Lake Architecture And Design Tradeoffs

The basic goal is to create a platform that Intel can build upon in pieces.

HC34 Intel Meteor Lake Scalable Architecture
HC34 Intel Meteor Lake Scalable Architecture

On the compute tile, Intel can scale to different core counts, generations, process nodes, and cache amounts. It can do this without having to touch the rest of the chip. Something worth noting here is that in the above package diagram, the CPU section is nowhere near even half of the package.

HC34 Intel Meteor Lake Compute Tile
HC34 Intel Meteor Lake Compute Tile

The graphics tile can scale similarly. A note here is that the GPU tile blocks in this diagram are just Xe-cores, caches, and fixed functions. The media and display functions are not here because of the process optimization.

HC34 Intel Meteor Lake Graphics Tile
HC34 Intel Meteor Lake Graphics Tile

SoC has media display imaging and display (this is not on the GPU tile!) It also has low-power IP, memory control, and more.

HC34 Intel Meteor Lake SoC Tile
HC34 Intel Meteor Lake SoC Tile

I/O extender tile adds more I/O and that can be varied based on the platform.

HC34 Intel Meteor Lake IO Extender Tile
HC34 Intel Meteor Lake IO Extender Tile

Building Meteor lake uses an older generation process as the base die that has the power delivery, I/O and die-to-die wires.

HC34 Intel Meteor Lake Construction
HC34 Intel Meteor Lake Construction

This is what Intel calls a “high yield” process. Part of the new process is having to test individual tiles to have “known good” before assembling. Having a reliable process is important to ensure that the extra assembly steps do not cause issues.

HC34 Intel Meteor Lake Construction 2
HC34 Intel Meteor Lake Construction 2

This is the die-to-die and base tile that is modular. Power delivery is a big deal on these multi-chip designs.

HC34 Intel Meteor Lake Construction 3 Base Tile
HC34 Intel Meteor Lake Construction 3 Base Tile

Having different capacitors and voltage islands is important for power but also just integrating different tiles from different processes.

HC34 Intel Meteor Lake Colors 3D Capacitors Voltage Islands
HC34 Intel Meteor Lake Colors 3D Capacitors Voltage Islands

Here are the details on the Meteor Lake Foveros.

HC34 Intel Meteor Lake Foveros Die Interconnect FDI
HC34 Intel Meteor Lake Foveros Die Interconnect FDI

An interesting part of the “iCXL” protocol used by the graphics SoC is that this is a CXL protocol without the PHY.

HC34 Intel Meteor Lake Interconnect
HC34 Intel Meteor Lake Interconnect

Creating high-performance products that can scale requires optimizing different processes and packaging for lower thermals.

HC34 Intel Meteor Lake Thermals And Turbo Power Capability
HC34 Intel Meteor Lake Thermals And Turbo Power Capability

This is more on the importance of the power delivery and capacitors on the base tile.

HC34 Intel Meteor Lake Power Delivery
HC34 Intel Meteor Lake Power Delivery

This is a 10-year improvement versus Haswell with an organic package.

HC34 Intel Meteor Lake Haswell To Meteor Lake
HC34 Intel Meteor Lake Haswell To Meteor Lake

Meteor Lake is slated for 2023 and is already booted in the lab. Intel says that it can manufacture these at scale since these are client devices.

HC34 Intel Meteor Lake Booted In Lab
HC34 Intel Meteor Lake Booted In Lab

This shows that the “tax” for disaggregation at a 36um bump pitch is only 2-3%. It is hard to even see the different tiles.

HC34 Intel Monolithic V Disaggregated 1
HC34 Intel Monolithic V Disaggregated 1

With this approach, Intel thinks it can address <10W to 100W+ productsHC34 Intel Meteor Lake Scaling 10W To 100W

HC34 Intel Meteor Lake Scaling 10W To 100Warrow Lake will swap out some of the tiles to create a new generation of chips. These tiles may be on new process nodes as well. Lunar Lake will have the next-generation 25-micron pitch Foveros.

HC34 Intel Meteor Lake Scalable To Arrow And Lunar Lake
HC34 Intel Meteor Lake Scalable To Arrow And Lunar Lake

With this technology, Intel can update portions of the chips without upgrading the entire chip. That means that future mid-cycle refreshes can be more than just 100MHz-200MHz bumps as we had a few years ago. Intel can upgrade cores or the GPU to a new generation without necessarily having to touch the I/O or SoC tiles as an example.

HC34 Intel Meteor Lake Future Of Client
HC34 Intel Meteor Lake Future Of Client

The other implication is that Foveros and Intel 4 will have to be mainstream by 2023.

final words

We will get more information on Meteor Lake CPUs in 2023 as the chips launch. There is still some time between now and then. Still, this is an exciting future capability that we will explore more in a second piece later this week. Disaggregated computing is coming to the lower cost consumer segment.

Leave a Comment

%d bloggers like this: