So instead of a working HPC, what we saw in #Dojo is a single node that’s is running a rudimentary NN on a single test bench. Designing a chip is easy. What’s hard is building the compiler, runtime scheduler in a HPC environment at scale. none of which @Tesla is anywhere close to 
When asked, its brushed off as “No but we will”. This exapod doesn’t exist it’s a photoshopped image and won’t exist for many years. That’s why there’s no MLPerf benchmarks. There is only one exapod in existence & that’s @Google TPU version 4. In use today by @Waymo #Dojo
By the time this is working and ready in the presented form and specs there will already be a TPU V5. @Tesla will always be 3-4 years behind on this front. But this won’t stop the fanboys because ignorance is bliss.
https://mobile.twitter.com/Model3Owners/status/1428538088951799964
*Tile not node
• • •
Missing some Tweet in this thread? You can try to
force a refresh
