[Bug libstdc++/54075] [4.7.1] unordered_map insert still slower than 4.6.2

[Paolo Carlini]

Hi,

On 11/23/2012 10:59 PM, François Dumont wrote:
>   But I think I won't lose my time anymore on this approach and will 
> rather prepare a small patch to change default behavior regarding the 
> hash code. I agree with all your remarks Jonathan so I will use them 
> for the patch.
First thanks a lot for all the time you are spending on this. That said, 
I want to make sure the following is recorded: as far as I can see in 
the current 54075.cc performance testcase (I also ran it myself) there 
isn't much difference between the cached / non-cached cases, right? That 
worries me a lot, because the whole discussion about caching, if I 
remember correctly, started when, basing on some preliminary performance 
numbers:

   http://gcc.gnu.org/ml/libstdc++/2012-11/msg00102.html

we were under the impression that essentially we had the reason of the 
performance problem we were seeing for std vs tr1 nailed. In other 
terms: we thought (or I should say: *I* thought?) that the insert 
performance of the current std code vs the tr1 code was the same for the 
same caching strategy.

Whatever we do for caching we have still to sort out the real reason of 
the performance regression vs tr1 for multiple insertions, or I'm I 
utterly confused?

Thanks,
Paolo.