Hacker News Reader

They are expanding into AI space, with Xilinx FPGA accelerators in next ryzens.

https://www.notebookcheck.net/AMD-details-4-nm-Zen-4-Ryzen-7...

cuda is the main advantage nvidia has over amd in this space. amd gpus are close enough to nvidia gpus these days that one should be able to buy either. except for the software support and community. so it makes it 10x harder to get something ML started on an amd GPU. so everyone ahs to buy nvidia

I am not an expert in this space but dabble a bit. This comment is spot on. AMD's software is pretty bad and NVDA has captured all the developer attention with CUDA and is the basis for lot of the frameworks people use. It is not a trivial advantage to break. I do wish good luck to AMD.

I have the same question about Google's TPUs (ie, why is Google not selling them, as opposed to just access to them).