antirez ca8f491e9c Speedup hllRawSum() processing 8 bytes per iteration.
The internal HLL raw encoding used by PFCOUNT when merging multiple keys
is aligned to 8 bits (1 byte per register) so we can exploit this to
improve performances by processing multiple bytes per iteration.

In benchmarks the new code was several times faster with HLLs with many
registers set to zero, while no slowdown was observed with populated
HLLs.
2014-04-17 18:05:27 +02:00
..
2012-04-13 17:52:33 -07:00
2013-01-19 10:59:44 +01:00
2013-01-19 10:59:44 +01:00
2014-04-07 08:58:06 +02:00
2013-01-19 10:59:44 +01:00
2013-05-14 11:23:16 +02:00
2013-01-19 10:59:44 +01:00
2014-03-28 12:11:55 +01:00
2014-04-04 17:25:35 +02:00
2014-03-20 16:20:37 +01:00
2013-01-19 10:59:44 +01:00
2014-04-17 17:32:59 +02:00
2014-04-17 14:49:25 +02:00
2013-01-19 10:59:44 +01:00
2014-01-22 09:54:55 +01:00
2013-07-16 15:43:36 +02:00
2013-08-12 11:38:21 +02:00
2013-01-19 10:59:44 +01:00
2014-04-17 14:49:25 +02:00
2013-07-24 18:59:54 +02:00
2013-07-02 12:08:07 +02:00
2011-07-06 15:22:00 +02:00
2013-05-27 11:44:04 +02:00
2013-09-03 15:15:51 +02:00