AMD's Strix Halo under the hood

I don&#x27;t understand the name &quot;Strix&quot;. It&#x27;s a name a GPU and motherboard partner of theirs, Asus, uses (used?) for their products. It&#x27;s impossible for me to read &quot;AMD Strix&quot; and not think of it as some ASU&#x27;s GPU with an AMD chip in it, or some motherboard for AMD sockets.<p>Aren&#x27;t there enough syllables out there to invent a combination which doesn&#x27;t collide with your own board partners?

For me the question is: what does this mean for future of desktop CPUs? High bandwidth unified memory seems very compelling for many applications, but the GPU doesn&#x27;t have as much juice as a separate unit. Are we going to see more these supposedly laptop APUs finding their way into desktops, and essentially a bifurcation of desktops into APUs and discrete CPU&#x2F;GPUs? Or will desktop CPUs also migrate to becoming APUs?

I don&#x27;t really like these &quot;lightly edited&quot; machine transcripts. There are transcription errors in many paragraphs, just adds that little bit of extra friction when reading.

Interesting read, and interesting product. If I understand it right, this seems like it could be at home in a spiritual successor to the Hades Canyon NUCs. I always thought those were neat.<p>I wish Chips and Cheese would clean up transcripts instead of publishing verbatim. Maybe I&#x27;ll use the GPU on my Strix Halo to generate readable transcripts of Chips and Cheese interviews.

I really want LPDDR5X (and future better versions) to become standard on desktops, alongside faster and more-numerous memory controllers to increase overall bandwidth. Why hasn&#x27;t CAMM gotten anywhere?<p>I <i>also</i> really want an update to typical form factors and interconnects of desktop computers. They&#x27;ve been roughly frozen for decades. Off the top of my head:<p>- Move to single-voltage power supplies at 36-57 volts.<p>- Move to bladed power connectors with fewer pins.<p>- Get rid of the &quot;expansion card&quot; and switch to twinax ribbon interconnects.<p>- Standardize on a couple sizes of &quot;expansion socket&quot; instead, putting the high heat-flux components on the bottom side of the board.<p>- Redesign cases to be effectively a single ginormous heatsink with mounting sockets to accept things which produce heat.<p>- Kill SATA. It&#x27;s over.<p>- Use USB-C connectors for both power and data for internal peripherals like disks. Now there&#x27;s no difference between internal and external peripherals.

When, if ever, will this be released as a bare processor&#x2F;memory&#x2F;motherboard combination that I can buy and throw in my own case?<p>Does anyone know?

Fascinating how Strix Halo feels like AMD&#x27;s spiritual successor to their ATI merger dreams - finally delivering desktop-class graphics and CPU power in a genuinely portable form factor. Can&#x27;t wait to see where it pushes laptop capabilities.

I think having a (small desktop) system with Strix Halo plus a GPU to accelerate prompt processing could be a good combo, avoiding the weakness of the Mac Ultra. The Strix Halo has 16 PCIe lanes.

Cool I guess for a mini PC but Im one of those desktop PC tower nerds :)

But why did they choose to build this as a mobile cpu though? I don’t need 128GB of unified RAM on my laptop. It’s the desktop where things happen.

As long as they cant even provide something similiar to a simple CUDA C API on consumer hardware i dont buy their stuff.

Seems like Apple&#x27;s M2 is a sweet spot for AI performance at 800 GB&#x2F;s of memory bandwidth which can be added under $1,500 refurbished for 65 gigs of RAM.