Hi,
Sorry, I thought I'd answered this on Friday, then realized tonight I
hadn't.
Christoph Pospiech <christoph.pospi...@de.ibm.com> wrote on 09/10/2010
06:28:16 AM:
>
> The performance gap to FORTRAN has narrowed to 0.92 orders of magnitude.
This
> decrease in gap width translates to a speed up by a factor of
> 10**(2.10 - 0.92) = 15.14, which is a major jump ahead.
>
> The flat profile has now changed to the following, and I am not surehow
many
> further hints can be deduced from a subroutine profile like that.
>
> Flat profile:
>
> Each sample counts as 0.01 seconds.
> % cumulative self self total
> time seconds seconds calls ms/call ms/call name
> 77.78 0.07 0.07
> matmul__closure__15::apply()
> 22.22 0.09 0.02 1 20.00 20.00
> x10_array_DistArray__closure__0<double>::apply()
>
I think DistArray__closure__0 corresponds to the initialization
closure plsInit in the constructor for DistArray. The code there is
suffering from not knowing that the region over with the DistArray is being
defined has the rect property (so the loop operatons in the "for (pt in
region) { .. } loop at line 261 is quite slow).
--dave
------------------------------------------------------------------------------
Start uncovering the many advantages of virtual appliances
and start using them to simplify application deployment and
accelerate your shift to cloud computing.
http://p.sf.net/sfu/novell-sfdev2dev
_______________________________________________
X10-users mailing list
X10-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/x10-users
