'

AMD brings multi-chip Radeon GPUs one step closer with their ACTIVE-BRIDGE patent

AMD's bringing the multi-die benefits of Zen to the GPU market

AMD brings multi-chip Radeon GPUs one step closer with their ACTIVE-BRIDGE patent

AMD brings multi-chip Radeon GPUs one step closer with their ACTIVE-BRIDGE patent

The semiconductor market is on the cusp of a chiplet revolution, bringing multi-die architectures to the masses across all areas of the computing market. AMD has already highlighted the benefits of multi-die architectures with their Ryzen and EPYC CPU lineups, and it looks like those benefits will soon be seen within the GPU market. 

Thanks to @KOMACHI_ENSAKA, we have gotten a look at AMD's patent for "ACTIVE-BRIDGE-COUPLED GPU CHIPLETS", a design structure that will facilitate the creation of large chiplet-based graphics cards that can act as a singular entity in software. In short, AMD is building a multi-die graphics chip that should act as a large monolithic GPU in the eyes of software and programmers. 

With the death of SLI and Crossfire within the PC gaming markets, it is clear that a chiplet-based graphics card cannot act like a multi-GPU solution. Chiplet-based GPUs will need to act as a single, unified entity, and achieving that is a difficult task for graphics card manufacturers. 

Intel, AMD and Nvidia are all working on chiplet-based graphics card designs, seeing the benefits of multi-die architectures over creating larger monolithic products. AMD has already proven with EPYC that chiplet-based designs can be cheaper to produce and enable higher silicon yields. Through the power of chiplets, GPU manufacturers hope to create graphics cards that are larger and more performant than any monolithic design. 

AMD's patent for an active bridge appears to be an evolution of AMD's Infinity Cache structure. AMD's Infinity Cache is a new last-level cache structure that arrived with its RDNA 2 graphics architecture. Thanks to the information within AMD's net patent, this cache's "Infinity" branding makes a lot more sense. 

AMD's active bridge patent describes an interconnect that connects GPU chiplets using an active bridge that contains a large last-level cache. This provides a large coherent cache that sits above all GPU chiplets and an inter-chiplet interconnect for chiplet-based graphics products. Yes, this structure could be seen as a merger between AMD's Infinity Cache and RDNA 2's last level cache. With this in mind, AMD's "Infinity Cache" name makes a lot of sense.

With this new Infinity Cache interconnect structure, a chiplet-based graphics card can interface with other devices like a single monolithic graphics card. In theory, this will allow AMD's chiplet-based graphics card to run today's software like a single graphics card and allow developers to continue using traditional GPU programming models. To make chiplet-based GPUs viable, AMD needs them to act like monolithic GPUs, and AMD's new patent describes how that may be made possible.   

AMD brings multi-chip Radeon GPUs one step closer with their ACTIVE-BRIDGE patent
Multi-die/chiplet-based graphics cards are an inevitability, facilitating the creation of stronger products that can provide customers with next-level performance while freeing manufacturers from the downsides of large monolithic GPU dies while lessening their reliance on leading-edge semiconductor nodes for increases in GPU transistor counts. 

AMD, Nvidia and Intel are working on chiplet-based GPUs because of their potential to change the industry. Only time will tell who will be the first to create a chiplet-based GPU for gamers and whether or not these new GPU designs will be able to work around the potential downsides of multi-chip architectures. 

You can join the discussion on AMD's multi-chip GPU plans and their "ACTIVE-BRIDGE" patent on the OC3D Forums.   

AMD brings multi-chip Radeon GPUs one step closer with their ACTIVE-BRIDGE patent  

«Prev 1 Next»

Most Recent Comments

05-04-2021, 18:56:36

AngryGoldfish
Exciting. 2022 should hopefully be a better year for graphics.Quote

05-04-2021, 19:35:49

KingNosser
Note to self: Going to need a bigger wallet, especially as i got the 6800XT free this time around

I'd feel sure Nvidia have similar in the works, but if they don't well they are going too suffer.Quote

05-04-2021, 20:42:28

AngryGoldfish
Quote:
Originally Posted by KingNosser View Post
Note to self: Going to need a bigger wallet, especially as i got the 6800XT free this time around

I'd feel sure Nvidia have similar in the works, but if they don't well they are going too suffer.
I've heard Nvidia are still going for a monolithic die to compete against RDNA3. After that is when we could see their 'glued together' GPUs.Quote

05-04-2021, 21:00:00

Dicehunter
Chiplet style GPU's are going to have to be the way forward, While yes the 3000 series from Nvidia and the 6000 series from AMD are nice upgrades from their previous gen parts, You can clearly see areas that are starting to slow down in terms of progress due to monolithic dies, And then there's the cost of monolithic dies which is only going to get ever more expensive.Quote

06-04-2021, 15:45:35

WYP
Quote:
Originally Posted by Dicehunter View Post
Chiplet style GPU's are going to have to be the way forward, While yes the 3000 series from Nvidia and the 6000 series from AMD are nice upgrades from their previous gen parts, You can clearly see areas that are starting to slow down in terms of progress due to monolithic dies, And then there's the cost of monolithic dies which is only going to get ever more expensive.
While I do agree that progress has slowed down for Nvidia, I wouldn't say that AMD has slowed down in terms of progress. If anything they are hitting their stride. RDNA 2 is a big change from RDNA, and RDNA was a huge improvement over Vega.

If AMD can continue this rate of progress with RDNA 3, they will have some great cards at launch.

As far as Nvidia is concerned, they are kinda taking the old AMD Vega approach and have made GPUs for basically all markets. Workstations, gaming, and enterprise. Nvidia had to invent DLSS to justify the die space for AI, and it took a while for Nvidia to make DLSS a worthwhile feature.

One of the strange things about Ampere is that its compute benefits are not really seen in gaming, it is best seen in workstations. Nvidia's new architectural enhancements are not targeted at gaming workloads.

There is a reason why AMD made the best mining GPUs in 2017 and why Nvidia makes the best mining GPUs in 2021. I'll leave it at that for now.Quote
Reply
x

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.