[PATCH 5/6] vfprintf: Introduce printf_positional function

[Siddhesh Poyarekar]

On Thu, May 21, 2015 at 12:55:19AM -0400, Carlos O'Donell wrote:
> Oh! You're saying that the performance domain of positional versus
> non-positional is different and should not be lumped together, as
> Florian did not lump them together in his analysis.
> 
> v2
> - Split out positional vs non-positional.
> 
> Test run:
> 
>   "sprintf": {
>    "positional": {
>     "duration": 3.49965e+10,
>     "iterations": 1.7381e+07,
>     "max": 2733.1,
>     "min": 2007.32,
>     "mean": 2013.49
>    },
>    "non-positional": {
>     "duration": 3.49927e+10,
>     "iterations": 2.8668e+07,
>     "max": 1379.96,
>     "min": 1214.8,
>     "mean": 1220.62
>    }
>   }
> 
> 2015-05-21  Carlos O'Donell  <carlos@redhat.com>
> 
> 	* benchtests/Makefile (stdio-common-bench): Define.
> 	(benchset): Add stdio-common-bench.
> 	* sprintf-inputs: New file.
> 	* sprintf-source.c: New file.

Looks good to me.

Thanks,
Siddhesh
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 473 bytes
Desc: not available
URL: <http://sourceware.org/pipermail/libc-alpha/attachments/20150521/2d7c7b77/attachment.sig>