Subject: Re: [boost] [chrono] steady_clock efficiency
From: Kenneth Porter (shiva.blacklist_at_[hidden])
Date: 2011-12-01 23:23:41
Marsh Ray <marsh_at_[hidden]> wrote in
news:4ED7BF7F.8050404_at_[hidden]:
> On 11/29/2011 08:31 PM, Kenneth Porter wrote:
>
>> 10.0\release\asynch-exceptions-on\threading-multi
>> \store_now_in_vector_static.output: steady_clock 636746989
>> nanoseconds
>>
>> So about 650 nanoseconds using a 32-bit build on Vista 64 Ultimate.
>
> Some of that may reflect quantization error.
>
> E.g., the clock output might be truncated to microsecond precision
> which introduces a 500 ns error on average and the actual read
> overhead is something like 150 ns.
The profiling program reads the clock a million times, storing the results
in a pre-allocated array, and times the whole operation. (An initial run
that constructs a million time_points is used to factor out the loop and
array member constructor time.) How would microsecond jitter affect the
overall operation to that degree?