[RFC] Porting string performance tests into benchtests

[Carlos O'Donell]

On 04/05/2013 09:02 PM, Siddhesh Poyarekar wrote:
> On 6 April 2013 01:14, Adhemerval Zanella <azanella@linux.vnet.ibm.com> wrote:
>> I'm not sure if it is worth, but maybe it would be useful to add a configurable
>> timestamp calculation.
> 
> Yes, it would be useful.  I don't think I'll spend time on that now.
> I'll first update this to use HP_TIMING and then there's the laborious
> task of adding all functions imaginable to the benchmark list.  It
> would be nice to have a baseline for as many functions as possible in
> 2.18.

Agreed. A baseline, even if imprecise, and thus a lower-bound on performance,
is useful for tracking regressions. As the precision of the time measurement
increases the performance should get better.

Cheers,
Carlos.