AMD Patent Points To Complex Chiplet Design For RDNA 5 GPUs

Expert Verified By

RDNA 5 Could Be Very Ambitious!

Story Highlight
  • AMD is exploring advanced multi-chiplet GPU architectures for future RDNA designs to enhance performance and scalability.
  • Their patent outlines three modes of chiplet usage: single GPU mode for integrated processing, independency mode, and hybrid mode.
  • Implementing multi-chiplet designs could increase production costs despite offering scalability and performance advantages.

According to AMD’s patent application, the company is investigating “multi-chiplet” GPU design alternatives, which implies that significant improvements may be included in next-generation RDNA architectures.

Why it matters: AMD already used less complex chiplet designs for its RDNA 3 architecture. However, the company is now trying to develop more intricate multi-chiplet graphics cards for a larger variety of uses.

AMD Patent
Image via AMD

According to the patent, there are three distinct “modes” of chiplet use; the distinction is in how resources are first assigned and subsequently controlled.

The first is the single GPU mode, which operates quite similarly to existing GPUs, where every onboard chiplet will function as a single, integrated processing unit, sharing resources in a cooperative setting.

The “independency mode” is the second mode, in which individual chiplets operate on their own, managing their functions through a separate front-end die that plans out work for the corresponding shader engine dies.

“Hybrid mode” is the third mode, allowing chiplets to coexist and function independently. It offers scalability and effective resource usage by combining the advantages of independent and unified processing.

The current RDNA 3 architecture is different, as AMD employs numerous Memory Cache Die chiplets for the memory interface. Cache and a single Graphics Compute Die chiplet are used for all other important GPU operations.

Details here are more similar to the GPUs found in CDNA data centers.

In general, multi-chiplet arrangements provide scalability and performance advantages, but their production is a far more complex process that needs sophisticated machinery and procedures. This can lead to higher costs.

While AMD has previously stated that it is utilizing GPU chiplets in conjunction with RDNA 3, this goes beyond that degree of dividing functions among separate chips. Though we believe most other GPU players will eventually adopt a similar strategy, AMD might be the first to release it to the market.

Was our article helpful? 👨‍💻

Thank you! Please share your positive feedback. 🔋

How could we improve this post? Please Help us. 😔

Gear Up For Latest News

Get exclusive gaming & tech news before it drops. Sign up today!

Join Our Community

Still having issues? Join the Tech4Gamers Forum for expert help and community support!

Latest News

Join Our Community

104,000FansLike
32,122FollowersFollow

Trending

OpenAI Partners With AMD To Buy Chips Worth Billions of Dollars

OpenAI and AMD have come together to enhance the world's current AI compute capabilities with a massive deal worth billions of dollars.

Assassin’s Creed Mirage Valley of Memory Free DLC Offers 6+ Hours of New Gameplay

Assassin's Creed Mirage is getting a free DLC titled 'Valley of Memory', set to release later this year on November 18th.

Black Ops 7 Beta Struggles on Steam – Player Count Nearly 5x Lower Than Battlefield 6 Beta

According to SteamDB, Black Ops 7 beta player count only topped at about 100K players, compared to Battlefield 6 beta's over 500K.

Activision Claims 97% Of Black Ops 7 Cheaters Are Banned Within 30 Minutes

97% of Call of Duty: Black Ops 7 cheaters were banned within 30 minutes of signing in, while only 1% made it into the game.

Silent Hill 3 Remake Reportedly Coming in 2028 as Bloober Team Works on Resident Evil-Inspired New IP

Bloober Team is rumored to be working on a Silent Hill 3 remake and a new Resident Evil-inspired IP, with releases expected in 2026 and 2028.