{"id":55978,"date":"2022-08-25T11:57:03","date_gmt":"2022-08-25T11:57:03","guid":{"rendered":"https:\/\/harchi90.com\/intel-disaggregates-client-chips-with-meteor-lake-in-2023\/"},"modified":"2022-08-25T11:57:03","modified_gmt":"2022-08-25T11:57:03","slug":"intel-disaggregates-client-chips-with-meteor-lake-in-2023","status":"publish","type":"post","link":"https:\/\/harchi90.com\/intel-disaggregates-client-chips-with-meteor-lake-in-2023\/","title":{"rendered":"Intel Disaggregates Client Chips with Meteor Lake in 2023"},"content":{"rendered":"
\n <\/p>\n
\n
Intle Meteor Lake HC34 Cover<\/figcaption><\/figure>\n<\/div>\n

<\/p>\n

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.<\/p>\n

Note: We are doing this piece live at HC34 during the presentation so please excuse typos.<\/p>\n

Intel Enters a New Era of Chiplets and Disaggregation with Meteor Lake<\/h2>\n

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.<\/p>\n

\"Intel
Intel Meteor Lake Monolithic V Disaggregated<\/figcaption><\/figure>\n

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.<\/p>\n

\"HC
HC 34 Intel Transistor Diversity Opportunity<\/figcaption><\/figure>\n

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.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Disaggregation Journey<\/figcaption><\/figure>\n

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.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Architecture And Design Tradeoffs<\/figcaption><\/figure>\n

The basic goal is to create a platform that Intel can build upon in pieces.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Scalable Architecture<\/figcaption><\/figure>\n

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.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Compute Tile<\/figcaption><\/figure>\n

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.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Graphics Tile<\/figcaption><\/figure>\n

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

\"HC34
HC34 Intel Meteor Lake SoC Tile<\/figcaption><\/figure>\n

I\/O extender tile adds more I\/O and that can be varied based on the platform.<\/p>\n

\"HC34
HC34 Intel Meteor Lake IO Extender Tile<\/figcaption><\/figure>\n

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

\"HC34
HC34 Intel Meteor Lake Construction<\/figcaption><\/figure>\n

This is what Intel calls a \u201chigh yield\u201d process. Part of the new process is having to test individual tiles to have \u201cknown good\u201d before assembling. Having a reliable process is important to ensure that the extra assembly steps do not cause issues.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Construction 2<\/figcaption><\/figure>\n

This is the die-to-die and base tile that is modular. Power delivery is a big deal on these multi-chip designs.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Construction 3 Base Tile<\/figcaption><\/figure>\n

Having different capacitors and voltage islands is important for power but also just integrating different tiles from different processes.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Colors 3D Capacitors Voltage Islands<\/figcaption><\/figure>\n

Here are the details on the Meteor Lake Foveros.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Foveros Die Interconnect FDI<\/figcaption><\/figure>\n

An interesting part of the \u201ciCXL\u201d protocol used by the graphics SoC is that this is a CXL protocol without the PHY.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Interconnect<\/figcaption><\/figure>\n

Creating high-performance products that can scale requires optimizing different processes and packaging for lower thermals.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Thermals And Turbo Power Capability<\/figcaption><\/figure>\n

This is more on the importance of the power delivery and capacitors on the base tile.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Power Delivery<\/figcaption><\/figure>\n

This is a 10-year improvement versus Haswell with an organic package.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Haswell To Meteor Lake<\/figcaption><\/figure>\n

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.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Booted In Lab<\/figcaption><\/figure>\n

This shows that the \u201ctax\u201d for disaggregation at a 36um bump pitch is only 2-3%. It is hard to even see the different tiles.<\/p>\n

\"HC34
HC34 Intel Monolithic V Disaggregated 1<\/figcaption><\/figure>\n

With this approach, Intel thinks it can address <10W to 100W+ products\"HC34<\/p>\n

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 a next-generation 25-micron pitch Foveros.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Scalable To Arrow And Lunar Lake<\/figcaption><\/figure>\n

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.<\/p>\n

\"HC34
HC34 Intel Meteor Lake Future Of Client<\/figcaption><\/figure>\n

The other implication is that Foveros and Intel 4 will have to be mainstream by 2023.<\/p>\n

Final Words<\/h2>\n

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.<\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

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, …<\/p>\n

Intel Disaggregates Client Chips with Meteor Lake in 2023<\/span> Read More »<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-global-header-display":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","spay_email":"","jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true},"categories":[4],"tags":[],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":36850,"url":"https:\/\/harchi90.com\/intel-denies-meteor-lake-is-delayed-to-2024-says-consumer-chips-will-launch-in-2023\/","url_meta":{"origin":55978,"position":0},"title":"Intel denies Meteor Lake is delayed to 2024, says consumer chips will launch in 2023","date":"August 6, 2022","format":false,"excerpt":"Intel had an incredibly rough quarter, unexpectedly losing half a billion dollars due to a PC purchasing slump, and yesterday seemed like more bad news \u2014 a report from TrendForce about manufacturing delays sparked rumors that Intel's next big flagship processor Meteor Lake would be delayed until 2024 , which\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":30664,"url":"https:\/\/harchi90.com\/intel-confirms-14th-gen-meteor-lake-has-versatile-processing-unit-for-ai-deep-learning-applications\/","url_meta":{"origin":55978,"position":1},"title":"Intel confirms 14th Gen Meteor Lake has ‘Versatile Processing Unit’ for AI\/Deep Learning applications","date":"July 30, 2022","format":false,"excerpt":"Versatile Processing Unit for deep learning and AI interferenceIntel is adding VPU to Meteor Lake and newer.A new commit to Linux VPU driver today confirms that the company has plans to introduce a new processing unit into consumer 14th Gen Core processors, a Versatile Processing Unit.The VPU driver is included\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/cdn.videocardz.com\/1\/2022\/07\/METOER-LAKE-VPU-HERO2-1200x443.jpg?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":54850,"url":"https:\/\/harchi90.com\/intels-lego-like-chiplet-design-for-next-gen-meteor-lake-arrow-lake-lunar-lake-3d-foveros-cpus-detailed\/","url_meta":{"origin":55978,"position":2},"title":"Intel’s LEGO-Like Chiplet Design For Next-Gen Meteor Lake, Arrow Lake & Lunar Lake “3D Foveros” CPUs Detailed","date":"August 24, 2022","format":false,"excerpt":"Yesterday, we reported a few key details of Intel's next-gen CPUs which feature a very LEGO-Esque design thanks to the 3D Foveros packaging technology. The new CPUs that will be putting the tech to good use include Meteor Lake, Arrow Lake, and Lunar Lake. Today, at Hot Chips 34, Intel\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/cdn.wccftech.com\/wp-content\/uploads\/2022\/08\/Intel-Meteor-Lake-Arrow-Lake-Lunar-Lake_-Hot-Chips-34_16-740x416.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":51525,"url":"https:\/\/harchi90.com\/intel-meteor-lake-cpus-with-tgpu-reportedly-features-ray-tracing-support-sports-fp64-compute-but-lacks-xmx-units\/","url_meta":{"origin":55978,"position":3},"title":"Intel Meteor Lake CPUs With TGPU Reportedly Features Ray Tracing Support, Sports FP64 Compute But Lacks XMX Units","date":"August 21, 2022","format":false,"excerpt":"In a new commit published on GitHub, Intel might have confirmed ray tracing support for their Meteor Lake CPUs with Xe-HPG TGPU. The Intel 14th Gen Meteor Lake CPUs are scheduled for release in 2023 and will come with a range of new features, including brand new hybrid cores, integrated\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/cdn.wccftech.com\/wp-content\/uploads\/2022\/08\/Intel-Meteor-Lake-CPU-Roadmap-tGPU-740x416.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]},{"id":35515,"url":"https:\/\/harchi90.com\/intels-tgpu-for-meteor-lake-cpus-that-utilizes-tsmcs-3nm-node-has-mass-production-delayed-to-late-2023\/","url_meta":{"origin":55978,"position":4},"title":"Intel’s tGPU For Meteor Lake CPUs That Utilizes TSMC’s 3nm Node Has Mass Production Delayed To Late 2023","date":"August 4, 2022","format":false,"excerpt":"In a report published by TrendForce, we get our second confirmation that Intel's tGPU for 14th Gen Meteor Lake CPUs which is expected to utilize TSMC's 3nm process node, has been delayed for volume production till late 2023. Intel's 3nm tGPU Mass Production Delay Hampers TSMC, 14th Gen Meteor Lake\u2026","rel":"","context":"In "Technology"","img":{"alt_text":"Intel's CEO Rumored To Visit TSMC Next Month As 14th Gen Meteor Lake Allegedly Pushed Back to End of 2023","src":"https:\/\/i0.wp.com\/cdn.wccftech.com\/wp-content\/uploads\/2022\/07\/Intel-CEO-740x387.png?resize=350%2C200&ssl=1","width":350,"height":200},"classes":[]}],"fifu_image_url":"https:\/\/www.servethehome.com\/wp-content\/uploads\/2022\/08\/Intle-Meteor-Lake-HC34-Cover.jpg","_links":{"self":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/55978"}],"collection":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/comments?post=55978"}],"version-history":[{"count":0,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/posts\/55978\/revisions"}],"wp:attachment":[{"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/media?parent=55978"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/categories?post=55978"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/harchi90.com\/wp-json\/wp\/v2\/tags?post=55978"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}