Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : AMD, ARMH, INTC, NVDA -- Ignore unavailable to you. Want to Upgrade?

To: neolib who wrote (71901)	10/27/2025 4:49:04 PM
From: Joe NYC	Read Replies (1) \| Respond to of 71960

On client side, looks like both GPU (RDNA4) and CPU (Strix Halo) are on 2 year cadence, and we are now entering the hole of the 2nd year, when nothing is released. Kind of a missed opportunity, we will see how well RDNA5 makes up for it. On server, here is a question: What if Nvidia missed the boat on LPDDR5 with Rubin, and Rubin CPX is an attempt to recover from it? AFAIK, NVidia is using LPDDR5 as memory for their Arm CPU, I am not aware of the GPU using LPDDR5 in a similar fashion as shown on Dylan's diagram. If NVidia had it, you can bet that it would have been first of Dylan's slides. So this could be an ace for AMD, being able to do the full cycle of inference on the same GPU as opposed to shoehorning another whole new system (new GPU, new rack) to do it.