benwtrent commented on PR #15564:
URL: https://github.com/apache/lucene/pull/15564#issuecomment-3744665791
Here is 1M vectors dibit with byte query:
```
recall latency(ms) netCPU avgCpuCount fanout visited
0.600 0.258 0.244 0.946 0 1086
0.655 0.305 0.297 0.974 5 1360
0.682 0.341 0.334 0.979 10 1603
0.717 0.473 0.465 0.983 25 2305
0.740 0.654 0.646 0.988 50 3417
0.753 1.049 1.041 0.992 100 5463
```
Here is the same data set, but dibit with nibble query:
```
0.594 0.190 0.183 0.963 0 2 bits 1056
262.08 3815.67 227.70 3221.32 3126.144 196.457
0.642 0.229 0.223 0.974 5 2 bits 1328
262.08 3815.67 227.70 3221.32 3126.144 196.457
0.669 0.265 0.259 0.977 10 2 bits 1582
262.08 3815.67 227.70 3221.32 3126.144 196.457
0.709 0.367 0.361 0.984 25 2 bits 2306
262.08 3815.67 227.70 3221.32 3126.144 196.457
0.730 0.519 0.512 0.987 50 2 bits 3424
262.08 3815.67 227.70 3221.32 3126.144 196.457
0.744 0.801 0.794 0.991 100 2 bits 5481
262.08 3815.67 227.70 3221.32 3126.144 196.457
```
Hmmm, not much improvement on recall. Let me see if increasing `k` or
changing the dataset adjusts these results.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
