Dojo discussion

[Rarity]

An interesting thread from Pierre Ferragu about why, even though Nvidia's GPUs are perpetually one generation behind on cost/performance, they win in the marketplace. He thinks that the flexibility of the GPUs are needed by most developers and therefore the custom approaches (Google TPU and presumably Dojo) don't and probably won't gain much share.

Not sure that I buy his argument, but it is interesting and seems worth considering.

https://twitter.com/x/status/1663667818913488901

 

[Buckminster]

An interesting thread from Pierre Ferragu about why, even though Nvidia's GPUs are perpetually one generation behind on cost/performance, they win in the marketplace. He thinks that the flexibility of the GPUs are needed by most developers and therefore the custom approaches (Google TPU and presumably Dojo) don't and probably won't gain much share.

Not sure that I buy his argument, but it is interesting and seems worth considering.

https://twitter.com/x/status/1663667818913488901

As Gary keeps reminding us, analysts can't and don't want to see the potential of the future. Dojo will make the cost of the chip irrelevant. What counts is cost and speed per operation as a service.

 

[heltok]

AMD is joining the game:

(anyone else find it funny that AMD's CEO is a feminine version of nVidia's CEO?!)

 

[heltok]

https://twitter.com/x/status/1671660883532038145

 

[Buckminster]

https://twitter.com/x/status/1671655179047895047