|
|
|
|
|
by nimbius
636 days ago
|
|
Tesla seeks to work to standardize a new high-speed/low-latency fabric (be that TTPoE or otherwise) for AI/ML/Datacenters however theres nothing inherently abject about TCP as it exists today. RDMA over Converged Ethernet suffices perfectly well for whatever an "AI/ML/Datacenter" is and if we're being fair, the lackadaisical approach to the documentation suggests that they may not be taking it as seriously as they could anyway. If Tesla were really seeking to shake things up they wouldnt have picked IPv4 to do it when the newest release has been around for nearly 30 years and has latency reduction baked in. this smacks of a pandersome attempt from a company that sees the quite mandarin writing on the walls and has decided (in true Muskovite fashion) they too are just a misunderstood font of futurism. |
|
TCP has the wrong abstraction for truly high performance.
I wouldn't necessarily standardize what Tesla does here, but most of the big companies have their own layer 3 transport protocol for things that need truly high speed and are operating within a datacenter.
Cray/HPE has their own Ethernet-based protocol (Slingshot was an earlier version of it - not sure what its name is now) which seems to be better than whatever Tesla has, but is not necessarily published.