On 30 December 2015 at 15:44, Bill Fischofer
wrote:
> I think Petri makes a good point. First is that here should be some hint
> at odp_init_global() time that the application will be using processes vs.
> threads.
>
Processes/threads are OS dependent so doesn't this approach break the
portabili
Using time API makes the performance test OS independent but it makes the
actual results dependent also on the time API implementation. This could be
an issue especially when comparing crypto performances of different
platforms.
Alex
On 30 December 2015 at 16:59, Maxim Uvarov wrote:
> Alex, I t
ping
On 18 December 2015 at 22:35, Bill Fischofer
wrote:
>
>
> On Fri, Dec 18, 2015 at 3:10 PM, Mike Holmes
> wrote:
>
>> Describe how changes to the public api are handled from release to
>> release.
>>
>> Signed-off-by: Mike Holmes
>>
>
> Reviewed-and-Tested-by: Bill Fischofer
>
>
>> ---
>
You need to create a .gitignore file in example/time and add the output
binary (odp_global_time_test) to it for this patch to be complete. Other
than that:
On Thu, Dec 31, 2015 at 5:46 AM, Ivan Khoronzhuk wrote:
> This test example uses linux helper functions to schedule worker
> threads in ord