[Libav-user] gcc auto-vectorisation

[Claudio Freire]

On Wed, Feb 27, 2013 at 1:46 PM, "René J.V. Bertin" <rjvbertin at gmail.com> wrote:
> On Feb 27, 2013, at 17:37, Claudio Freire wrote:
>
>>> Detailed benchmark results: (32 bit, MMX/SSE code, -fno-tree-vectorize)
>>>                   samples          user t        kernel t          real t           CPU %
>>> Video decode  :      85166         27.0846s        2.48361s        13.5333s        218.484%
>>
>>
>> Wait... 200%... what's your hardware like?
>>
>> If by any chance you have Hyper Threading enabled (which is quite
>> likely), then I bet that's what the penalty is coming from (there's
>
> Ah, ok. I have a dual core, hyper-threaded i7 . Do you think there's an interest other than academic to deactivate hyper threading?

I think it's just academic. It would be one mystery less.

Perhaps it would be easier trying to disable threading in ffmpeg and
re-running the benchmark.