How to get best AVX2 performance from gfortran?

[Thomas Koenig]

Hi Matt,
[timings]

> Intel AVX2:
> 
>  Â Â  C_SWÂ Â Â Â Â Â  1.4931
>  Â Â  D_SWÂ Â Â Â Â Â  5.4254
>  Â Â  PG_DÂ Â Â Â Â Â  1.0878
>  Â Â  TRACER_2D 24.7418
>  Â Â  REMAPPING 27.2644

> Now I looked at GNU Fortran (7.3.0). Here my "stock" flags are quite 
> boring (and all flags, not just the optimization ones):

[Various options elided, the best was]:

> GNU Haswell NoFMA Repack:
>  Â Â  C_SWÂ Â Â Â Â Â Â  2.4350
>  Â Â  D_SWÂ Â Â Â Â Â Â  9.7109
>  Â Â  PG_DÂ Â Â Â Â Â Â  0.7869
>  Â Â  TRACER_2D 163.6474
>  Â Â  REMAPPING 100.6820
> 
> So, my questions to you gurus are: Is there something I could try adding 
> to my gfortran options that might help with this discrepancy between 
> Intel AVX2 and GCC? Or perhaps I need to *remove* something (some flag 
> kills the vectorizer)?
The gcc 8 release is just around the corner, and a lot of improvements
have been made to code generation, also for AVX2. You might want to give
the current trunk (or the soon-to-be-released) release candidate, or the
then newly released gcc8 a spin.

Second, this performance gap with respect to Intel (a factor of 6.6 for
your TRACER_2D routine) is dramatic. If anything like this persists in 
gcc8, the only way to get this fixed is to submit a bug report.
Profile the code, try to reduce the code to something that shows
the the problem (and that you can put in a bug report).

Regards

	Thomas