When HN users recommended it
1 HN user recommended this in 2016, in one comment.
20072026
Each tall tick is one HN user's first recommendation. A short tick is the same user again. Click a tick to jump to the comment.
1 HN user recommended this in 2016, in one comment.
Each tall tick is one HN user's first recommendation. A short tick is the same user again. Click a tick to jump to the comment.
It seems entirely reasonable to me, and there's good historical precedent for it. Let's look at SHA256 hashing as an example. The maximum number of hashes that the best GPU around can do is around 1 GHash/s. However, for the same cost, of around $600, specialized hardware can do around 5 THash/s. That's about five thousand times the performance/price. There's no reason that hardware that is super-specific to neural network computation can't similarly have large gains.
Link to the specialized hardware for SHA256 hashing: http://www.amazon.com/Antminer-~4-73TH-25W-Bitcoin-Miner/dp/...