[Bug tree-optimization/97832] AoSoA complex caxpy-like loops: AVX2+FMA -Ofast 7 times slower than -O3

["crazylht at gmail dot com" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=97832

--- Comment #23 from Hongtao.liu <crazylht at gmail dot com> ---

> the blends do not look like no-ops so I wonder if this is really computing
> the same thing ... (it swaps lane 0 from the two loads from x but not the
> stores)

They're computing the same thing since we also do the same "permutation" for
the invariants: f_re and f_imm, can we eliminate that in the vectorizer?

  _232 = {f_im_36, f_im_36, f_im_36, f_im_36};
  _231 = {f_im_36, f_re_35, f_re_35, f_re_35}; ------- here
  _216 = {f_re_35, f_re_35, f_re_35, f_re_35};
  _215 = {f_re_35, f_im_36, f_im_36, f_im_36}; ------ and here.
  ivtmp.36_221 = (unsigned long) y_41(D);
  ivtmp.38_61 = (unsigned long) x_33(D);

  <bb 4> [local count: 214748368]:
  # ivtmp.32_66 = PHI <ivtmp.32_65(4), 0(3)>
  # ivtmp.36_64 = PHI <ivtmp.36_63(4), ivtmp.36_221(3)>
  # ivtmp.38_220 = PHI <ivtmp.38_60(4), ivtmp.38_61(3)>
  # DEBUG c => NULL
  # DEBUG k => 0
  # DEBUG BEGIN_STMT
  # DEBUG BEGIN_STMT
  # DEBUG D#78 => D#79 * 8
  # DEBUG D#77 => x_33(D) + D#78
  _62 = (void *) ivtmp.38_220;
  vect_x_im_61.13_228 = MEM <const vector(4) double> [(const double *)_62];
  vect_x_im_61.14_226 = MEM <const vector(4) double> [(const double *)_62 +
32B];
  vect_x_re_55.15_225 = VEC_PERM_EXPR <vect_x_im_61.14_226,
vect_x_im_61.13_228, { 0, 5, 6, 7 }>;
  vect_x_re_55.23_209 = VEC_PERM_EXPR <vect_x_im_61.13_228,
vect_x_im_61.14_226, { 0, 5, 6, 7 }>;
  # DEBUG D#76 => *D#77
  # DEBUG x_re => D#76
  # DEBUG BEGIN_STMT
  # DEBUG D#74 => (long unsigned int) D#75
  # DEBUG D#73 => D#74 * 8
  # DEBUG D#72 => x_33(D) + D#73
  # DEBUG D#71 => *D#72
  # DEBUG x_im => D#71
  # DEBUG BEGIN_STMT
  # DEBUG D#70 => y_41(D) + D#78
  _59 = (void *) ivtmp.36_64;
  vect_y_re_63.9_235 = MEM <vector(4) double> [(double *)_59];
  vect_y_re_63.10_233 = MEM <vector(4) double> [(double *)_59 + 32B];
  vect__42.18_219 = .FMA (vect_x_im_61.13_228, _232, vect_y_re_63.10_233);
  vect_y_re_69.17_222 = .FNMA (vect_x_re_55.15_225, _231, vect_y_re_63.9_235);
  vect_y_re_69.25_206 = .FNMA (vect_x_re_55.23_209, _215, vect_y_re_69.17_222);
  vect_y_re_69.25_205 = .FNMA (_216, vect_x_im_61.14_226, vect__42.18_219);