[Bug middle-end/113813] SVE Reduction of xor/and/ior of 16 bytes can be improved

[pinskia at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113813

Drea Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Keywords|                            |easyhack
          Component|target                      |middle-end

--- Comment #2 from Drea Pinski <pinskia at gcc dot gnu.org> ---
 _47 = MAX_EXPR <16, POLY_INT_CST [48, 48]>;
  _48 = _47 - POLY_INT_CST [48, 48];
  max_mask_49 = .WHILE_ULT (0, _48, { 0, ... });

_47 should be constant folded into POLY_INT_CST [48, 48].
and then _48 into 0.
And then max_mask_49 into {0, ...}

  vect__3.41_27 = .MASK_LOAD (vectp_a.36_26, 8B, max_mask_49, { 0, ... });
...
  vect_b_10.43_35 = VEC_COND_EXPR <max_mask_49, vect__3.41_27, { 255, ... }>;
  _50 = vect_b_10.43_34 & vect_b_10.43_35;

And then _50  into just vect_b_10.43_34

So these seems like all easy first time changes to make too.