Globally distributed GPU clusters mean massive cost reduction from reused hardware
Akash Weekly - October 12th 2022 (Akash Network)
“The potential outcome of a globally distributed GPU cluster is just cost reduction to a massive level, and repurposing existing hardware instead of trying to go build new hardware. With the supply chain shortages… if we don’t look inwards, we don’t try to reuse what we have… I think it’s going to be a failing endeavor.” — 00:06:32
Context: Explaining why a common GPU interface across heterogeneous data centers is pioneering work nobody has built; supply-chain shortages make reuse the only viable path.