AMD CDNA3 Architecture Sees the Inevitable Fusion of Compute Units and x86 CPU at Massive Scale

See the full post here ➡️

Rate this post

AMD in its 2022 Financial Analyst Day presentation unveiled its next-generation CDNA3 compute architecture, which will see something we’ve been expecting for a while—a compute accelerator that has a large number of compute units for scalar processing, and a large number of x86-64 CPU cores based on some future "Zen" microarchitecture, onto a single package. The presence of CPU cores on the package would eliminate the need for the system to have an EPYC or Xeon processor at its head, and clusters of Instinct CDNA3 processors could run themselves without the need for a CPU and its system memory.

The Instinct CDNA3 processor will feature an advanced packaging technology that brings various IP blocks together as chiplets, each based on a node most economical to it, without compromising on its function. The package features stacked HBM memory, and this memory is shared not just by the compute units and x86 cores, but also forms part of large shared memory pools accessible across packages. 4th Generation Infinity Fabric ties it all together.

Why should you share your news?

Contributing is one of the best ways to promote a website. This technique has been used for decades now and is still very effective. But, this strategy can make or break your rankings depending on its application.

A news website is one of the best places to publish your blog. This is because such sites always have massive amounts of targeted traffic. If you write quality content, your post will get many hits, and many people will follow your blog.


The content provided has been modified and is not displayed as intended by the author. Any trademarks, copyrights, and rights remain with the source. Linux Chatter sources content from RSS feeds and personal content submissions. The views and opinions expressed in these articles are those of the authors and do not necessarily reflect Linux Chatter.