Trillium TPU Is GA

Re:Trillium TPU Is GA by teleforce on Thursday December 12, 2024 @10:22PM (#42405682)

It's beyond me why processor with dataflow architecture is not being used for ML and AI workloads, not even in minority [1]. Native dataflow processor will hands down beats Von Neumann based architecture in term of performance and efficiency, and GPU will be left redundant for graphics processing instead of being the default co-processor or accelerator for ML and AI.

[1] Dataflow architecture:

https://en.wikipedia.org/wiki/Dataflow_architecture

[ Parent | on HN ]

Re:Trillium TPU Is GA by almostgotcaught on Friday December 13, 2024 @02:08AM (#42406537)

let me ask you a very serious question and please answer honestly: have you ever tried to program a "dataflow processor"? if the answer is no then I invite you to try and then you will understand intimately why they're not being used for anything.

[ Parent | on HN ]

Re:Trillium TPU Is GA by germanjoey on Friday December 13, 2024 @05:22AM (#42407405)

Sambanova's RDU is a dataflow processor being used for ML/AI workloads! It's amazing and actually works.

[ Parent | on HN ]