[HN Gopher] AMD's CDNA 4 Architecture Announcement
       ___________________________________________________________________
        
       AMD's CDNA 4 Architecture Announcement
        
       Author : rbanffy
       Score  : 89 points
       Date   : 2025-06-17 17:38 UTC (5 hours ago)
        
 (HTM) web link (chipsandcheese.com)
 (TXT) w3m dump (chipsandcheese.com)
        
       | bee_rider wrote:
       | Machine learning is, of course, a massive market and everybody's
       | focus.
       | 
       | But, does AMD just own the whole HPC stack at this point? (Or
       | would they, if the software was there?).
       | 
       | At least the individual nodes. What's their equivalent to
       | Infiniband?
        
         | phonon wrote:
         | Ultra Ethernet
         | 
         | https://www.tomshardware.com/networking/amd-deploys-its-firs...
         | 
         | https://semianalysis.com/2025/06/11/the-new-ai-networks-ultr...
        
           | OneDeuxTriSeiGo wrote:
           | It's also worth noting Ultra Ethernet isn't just an AMD
           | thing. The steering committee for the UEC is made up of
           | basically every hardware manufacturer in the space except
           | Nvidia. And of course Nvidia is a general contributor as well
           | (presumably so they don't get left behind).
           | 
           | https://ultraethernet.org/
        
           | jauntywundrkind wrote:
           | Also UltraEthernet went 1.0 (6d ago), had a decent sized
           | comments: https://news.ycombinator.com/item?id=44249190
        
         | wmf wrote:
         | Cray Slighshot is even faster than Infiniband.
         | 
         | Now that Nvidia is removing FP64 I assume AMD will have 100% of
         | the HPC market until Fujitsu Monaka comes out.
        
         | latchkey wrote:
         | Within the node (gpu to gpu), it is infinity fabric.
         | 
         | Externally, it is 8x400G NICs, which is the limitation of
         | PCIeV5 anyway.
         | 
         | We had a guy training SOTA models on 9 of our MI300x boxes just
         | fine. Networking wasn't the slow bit.
        
       | robjeiter wrote:
       | When looking at inference is AMD already on par with Nvidia?
        
         | moondistance wrote:
         | Yes, for many applications.
         | 
         | Meta, OpenAI, Crusoe, and xAI recently announced large
         | purchases of MI300 chips for inference.
         | 
         | MI400, which will be available next year, also looks to be at
         | least on par with Nvidia's roadmap.
        
           | moondistance wrote:
           | (this is also why AMD popped 10% at open yesterday - this is
           | a new development and talks from their 2025 "Advancing AI"
           | event were published late last week + over the weekend)
        
           | christkv wrote:
           | Is the software stack still lacking?
        
             | moondistance wrote:
             | Yes, big time, but there continues to be lots of progress.
             | 
             | Most importantly, models are maturing, and this means less
             | custom optimization is required.
        
             | OneDeuxTriSeiGo wrote:
             | Yeah it's still a few years behind but it's getting better.
             | They are hiring software and tooling engineers like crazy.
             | I keep tabs on some of the job slots companies have in our
             | area and every time I check AMD they always have tons of
             | new slots for software, firmware, and tooling (and this has
             | been the case for ~3 years now).
             | 
             | They've been playing catch up after "the bad old days" when
             | they had to let a bunch of people go to avoid going under
             | but it looks like they are catching back up to speed. Now
             | it's just a matter of giving all those new engineers a few
             | years to get their software world in order.
        
               | storus wrote:
               | They pay hardware rates to software engineers (principal
               | engineer at the salary level of a decent fresh graduate)
               | so I won't be too optimistic about them attracting
               | software people that would propel them forward.
        
               | OneDeuxTriSeiGo wrote:
               | At least where I live (very much not west coast), their
               | SW and HW rates are at or above what we normally see in
               | this area.
        
               | latchkey wrote:
               | Stock is undervalued. If you get in now and it pops over
               | the next few years, it'll likely make up for lower
               | compensation.
        
         | latchkey wrote:
         | https://eliovp.com/cranking-out-faster-tokens-for-fewer-doll...
        
       | jauntywundrkind wrote:
       | Faster small matrix, for AI. Yup, that seems like good fit for
       | what folks want.
       | 
       | Supercharging the Local Data Share (LDS) that's shared by threads
       | is really cool to hear about. 64 -> 160KB size. Writes into LDS
       | go from 32B max to 128B, increasing throughout. Transposes, to
       | help get the data in the right shape for its next use.
       | 
       | Really really curious to see what the UDNA unified next gen
       | architectures look like, if they really stick to merging Compute
       | and Radeon CDNA and RDNA, as promised. If consumers end up
       | getting multi-die compute solutions that would be neat & also
       | intimidatingly hard (lots of energy spent keeping bits in sync
       | across cores/coherency). After Navi 4X ended up having its
       | flagship cancelled way back now, been wondering. I sort of expect
       | that this won't scale as nicely as Epyc being a bunch of Ryzen
       | dies. https://wccftech.com/amd-enthusiast-radeon-rx-8000-gpus-
       | alle...
        
       ___________________________________________________________________
       (page generated 2025-06-17 23:00 UTC)