PING^2 for vectorization and toplevel patches

[Roger Sayle]

On Thu, 21 Apr 2005, Paolo Bonzini wrote:
> Like for UNITS_FOR_SIMD_WORD, there is absolutely no mention of a
> vectorizer in passes.texi except for if-conversion.  I don't think I'm
> most suited to write it so I'm CCing Dorit; I will take care of it if
> she asks me so, anyway.

This is is related to one of the oldest open PRs for gcc, PR951 :-)


> 2004-04-20  Paolo Bonzini  <bonzini@gnu.org>
>
>	* tree-complex.c (gate_expand_vector_operations): New.
>	(pass_lower_vector_ssa): Use it.
>	* tree-optimize.c (init_tree_optimization_passes): Include
>	pass_lower_vector_ssa.
>	* tree-vect-transform.c (vect_min_worthwhile_factor): New.
>	(vectorizable_operation): Use it.
>	* tree-vectorizer.c (get_vectype_for_scalar_type): Accept
>	integer modes for the vector type.
>
>	* doc/tm.texi (UNITS_PER_WORD): Mention 64-bit hosts.
>	(UNITS_PER_SIMD_WORD): New.
>
>	* gcc.dg/gen-vect-11.c, gcc.dg/gen-vect-11a.c,
>       gcc.dg/gen-vect-11b.c, gcc.dg/gen-vect-11c.c,
>       gcc.dg/gen-vect-2.c, gcc.dg/gen-vect-25.c,
>       gcc.dg/gen-vect-26.c, gcc.dg/gen-vect-28.c,
>       gcc.dg/gen-vect-32.c: New.
>       * gcc.dg/vect/vect-82.c, gcc.dg/vect/vect-83.c: Fix dg-final.
>       * gcc.dg/vect/vect-82_64.c, gcc.dg/vect/vect-83_64.c: Remove xfail,
>       don't run on PPC32.

This is Ok for mainline.

Thanks,

Roger
--