[Insight-developers] Empty FixedArray destructor: Performance hit using gcc (times 2) : __attribute__ ((aligned (8))) & derivation

[Luis Ibanez]

Hi Tom,

Derivation combined with __attribute__ ((aligned(8)))  seems to work.


With the following code:

class MyArray
{
public:
   MyArray() {};
   ~MyArray() {};
   double operator[](unsigned int k)
     {
     return foo[k];
     }
   double foo[2];
};

class MyAlignedArray : public MyArray
{
} __attribute__ ((aligned(8)));



An array of MyArray"s is aligned to 4 bytes,
while an array of "MyAlignedArray"s is aligned to 8 bytes.


Therefore, one option for your application is to do

class MyPixelType : public itk::FixedArray<double,2>
{
} __attribute__ ((aligned(8)));


typedef itk::Image< MyPixelType, N >   MyImageType;

and...
move from there.


-----


   We still have not found an explanation of why the
   presence of an empty non-virtual the destructor
   should affect the alignment...   :-/


      Luis


----------------------
Luis Ibanez wrote:
> Hi Tom,
> 
> More on this,  Bradley Lowekamp kindly pointed us to the following
> GCC mechanism for specifying the alignment of structures:
> 
> http://gcc.gnu.org/onlinedocs/gcc-3.2.3/gcc/Type-Attributes.html
> 
> Thank Brad !
> 
> 
> 
> ---
> 
> The Attribute:
> 
> 
>          __attribute__ ((aligned (8)))
> 
> 
> also does the trick.
> 
> 
> When we added it to the end of the minimalistic array:
> 
> class MyArray
> {
> public:
>   MyArray() {};
>   ~MyArray() {};
>   double operator[](unsigned int k)
>     {
>     return foo[k];
>     }
>   double foo[2];
> } __attribute__ ((aligned (8))) ;
> 
> 
> 
> we can compile without -malign-double and the structure
> is still aligned to 8 bytes, despites the fact that the
> destructor is sill present.
> 
> 
> We could create ITK macros for this attribute options,
> and define the macros at configuration time by using
> TRY_COMPILES.
> 
> 
> The remaining question is:
> 
> 
>     Are there any drawbacks to this approach ?
> 
> 
> At first sight, it is much better than the global
> -malign-double option, and we can apply it only
> to structures that we know must be aligned.
> 
> 
> One challenge here is that although we want FixedArray<double,N>
> to be 8-bytes aligned, we don't always want the FixedArray<T,N>
> to be aligned this way.  For example: FixedArray<char,3>  ??
> 
> 
> One option could be to create your pixel type as a class derivied
> from FixedArray<double,2>, and see if we can apply the attribute
> just to the derived class....
> 
> In this way, this will be an application specific issue, as opposed
> to something that has to be done pervasively in ITK.
> 
> 
>   Any suggestions ?
> 
> 
>       Luis
> 
> 
>