Nobody who controls the purse strings cares about the kernel taint bit if their model doesn’t train, if they’re burning developer time debugging drivers, if they have to burn even more dev time switching off of cuda, etc.
If AMD really cared about making money, they would’ve sent MI300s to all of the top CS research institutions for free and supported rocm on every single product. Investing any less than nvidia, the trillion dollar behemoth, is just letting big green expand their moat even more.
As I said, other than AI. The management made a big bet on crypto when nvidia made a big bet on AI.
That didn’t work out all that well in the medium term (it did in the short term), though it gave them runway to take a big chunk of intel’s server market.
Whether or not that was a good move, it’s not evidence of some engineering shortcoming.
If AMD really cared about making money, they would’ve sent MI300s to all of the top CS research institutions for free and supported rocm on every single product. Investing any less than nvidia, the trillion dollar behemoth, is just letting big green expand their moat even more.