Snappy Team 0c7ed08a25 The result on protobuf benchmark is around 19%. Results vary by their propensity for compression. As the frequency of finding matches influences the amount of branch misspredicts and the amount of hashing. ...

Two ideas
1) The code uses "heuristic match skipping" has a quadratic interpolation. However for the first 32 bytes it's just every byte. Special case 16 bytes. This removes a lot of code.
2) Load 64 bit integers and shift instead of reload. The hashing loop has a very long chain data = Load32(ip) -> hash = Hash(data) -> offset = table[hash] -> copy_data = Load32(base_ip + offset) followed by a compare between data and copy_data. This chain is around 20 cycles. It's unreasonable for the branch predictor to be able to predict when it's a match (that is completely driven by the content of the data). So when it's a miss this chain is on the critical path. By loading 64 bits and shifting we can effectively remove the first load.

PiperOrigin-RevId: 302893821

2020-04-11 04:40:39 +00:00

18 KiB

Raw Blame History

View Raw