On Sat, 2009-01-10 at 13:57 -0500, Gregory Stark wrote:
> But I gather it's a 6% speedup in the time spent actually in the
> hash function.
That's correct. I was not able to detect any difference at all between
the old and new code using HashAggregate, which is where most of my
testing effort went:
http://archives.postgresql.org/message-id/1231531455.25019.75.camel@jdavis
(see test results attached to that message, if you're interested)
I tested with two data distributions and 6 data types.
The 6-10% speedup I saw was a super-micro benchmark testing the hash
function, and I didn't spend much time with that.
Regards,Jeff Davis
