Re: [eigen] (General question) Floating point: why are 'inf' and 'nan' slow?

[ Thread Index | Date Index | More lists.tuxfamily.org/eigen Archives ]


My program is just repeatedly computing inf*inf, so denormalized
numbers can't be the explanation...

Benoit

2009/9/23 Robert Bocquier <robert.bocquier@xxxxxxxxxxx>:
> Benoit Jacob a écrit :
>> Hi,
>>
>> Sorry for adding to the currently already high traffic here.
>>
>> Here, on linux / x86, my programs run 100x slower when the
>> floating-point values are 'inf' or 'nan'.
>>
>> Only scalar code is affected, SSE code is not affected.
>>
>> I haven't enabled floating-point exception signals. I don't have a FP
>> signal handler. Just any basic c++ program.
>>
>> Can this be "fixed"? How?
>>
>> Otherwise, I really need to make sure that solve() methods avoid
>> producing such special values when no solution exists --- otherwise
>> they take much longer to return.
>>
>> Thanks for your help,
>> Benoit
>>
>>
>>
>>
> Hi Benoit,
> may be *before* arriving to those extremes you've encountered
> "denormalized numbers" ?
> There are provisions to get rid of them with SSE, while in regular "387"
> code you must explicitly deal with them. This is consistent with your
> observation (but it's not a proof).
>
> Best,
> --
> Robert Bocquier
>
>
> ARTURIA
> 4 chemin de Malacher
> 38240 Meylan - France
> Tel: +33 438 020 555
> Fax: +33 438 020 525
>
> http://www.arturia.com
>
>
>
>
>



Mail converted by MHonArc 2.6.19+ http://listengine.tuxfamily.org/