And: "FASTER achieves higher throughput than current systems, by more than two orders of magnitude, and scales better than current pure in-memory data structures, for in-memory working sets."
Looking at 7.2 of the paper, they probably mean "more than 2x", definitely not exponentially faster in most cases. Still nice work though.
From your link: "This was achieved with 32 (out of a maximum 48) data nodes." The project being discussed is benchmarked on a single node, not a cluster. This is why they compare performance to RocksDB.
Looking at 7.2 of the paper, they probably mean "more than 2x", definitely not exponentially faster in most cases. Still nice work though.