On Sat, Oct 17, 2015 at 10:25 PM, Michael Niedermayer
wrote:
> On Sat, Oct 17, 2015 at 09:30:01PM -0400, Ganesh Ajjanagadde wrote:
>> Commit 3a0a2f33a6c955823fa4fb12c0b49cd29a496659 claims large performance
>> advantages for AV_QSORT over libc's qsort. The reason is that I suspect
>> that libc's q
On Sat, Oct 17, 2015 at 09:30:01PM -0400, Ganesh Ajjanagadde wrote:
> Commit 3a0a2f33a6c955823fa4fb12c0b49cd29a496659 claims large performance
> advantages for AV_QSORT over libc's qsort. The reason is that I suspect
> that libc's qsort (at least on non LTO builds, like the typical FFmpeg config)
>
On Sat, Oct 17, 2015 at 9:30 PM, Ganesh Ajjanagadde
wrote:
> Commit 3a0a2f33a6c955823fa4fb12c0b49cd29a496659 claims large performance
> advantages for AV_QSORT over libc's qsort. The reason is that I suspect
> that libc's qsort (at least on non LTO builds, like the typical FFmpeg config)
> can't i
Commit 3a0a2f33a6c955823fa4fb12c0b49cd29a496659 claims large performance
advantages for AV_QSORT over libc's qsort. The reason is that I suspect
that libc's qsort (at least on non LTO builds, like the typical FFmpeg config)
can't inline the comparison callback:
https://stackoverflow.com/questions/5
