On 20/02/2015 14:22, Jonathan Wakely wrote:
On 18/02/15 10:35 +0100, François Dumont wrote:
Hello
I am still studying hashtable performances and especially how to
reduce overhead compared to tr1 implementation. Most of the overhead
is coming from the additional modulo operations required w
On 18/02/15 10:35 +0100, François Dumont wrote:
Hello
I am still studying hashtable performances and especially how to
reduce overhead compared to tr1 implementation. Most of the overhead
is coming from the additional modulo operations required with the new
data model. Having a closer look
With patch.
On 18/02/2015 10:35, François Dumont wrote:
Hello
I am still studying hashtable performances and especially how to
reduce overhead compared to tr1 implementation. Most of the overhead
is coming from the additional modulo operations required with the new
data model. Having a c
Hello
I am still studying hashtable performances and especially how to
reduce overhead compared to tr1 implementation. Most of the overhead is
coming from the additional modulo operations required with the new data
model. Having a closer look at PR 57885 bench I realized that we can
quite
