[Bug tree-optimization/60172] ARM performance regression from trunk@207239

[joey.ye at arm dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=60172

--- Comment #8 from Joey Ye <joey.ye at arm dot com> ---
Here is tree dump and diff of 133t.forwprop4
  <bb 2>:
  Int_Index_4 = Int_1_Par_Val_3(D) + 5;
  Int_Loc.0_5 = (unsigned int) Int_Index_4;
  _6 = Int_Loc.0_5 * 4;
  _8 = Arr_1_Par_Ref_7(D) + _6;
  *_8 = Int_2_Par_Val_10(D);
  _13 = _6 + 4;
  _14 = Arr_1_Par_Ref_7(D) + _13;
  *_14 = Int_2_Par_Val_10(D);
  _17 = _6 + 60;
  _18 = Arr_1_Par_Ref_7(D) + _17;
  *_18 = Int_Index_4;
  pretmp_20 = Int_Loc.0_5 * 100;
  pretmp_2 = Arr_2_Par_Ref_22(D) + pretmp_20;
  _42 = (sizetype) Int_1_Par_Val_3(D);
  _41 = _42 * 4;
-  _40 = pretmp_2 + _41; // good
+  _12 = _41 + pretmp_20; // bad
+  _40 = Arr_2_Par_Ref_22(D) + _12;  // bad
  MEM[(int[25] *)_40 + 20B] = Int_Index_4;
  MEM[(int[25] *)_40 + 24B] = Int_Index_4;
  _29 = MEM[(int[25] *)_40 + 16B];
  _30 = _29 + 1;
  MEM[(int[25] *)_40 + 16B] = _30;
  _32 = pretmp_20 + 1000;
  _33 = Arr_2_Par_Ref_22(D) + _32;
  _34 = *_8;
-  _51 = _33 + _41;  // good
+  _16 = _41 + _32;  // bad
+  _51 = Arr_2_Par_Ref_22(D) + _16;  // bad

  MEM[(int[25] *)_51 + 20B] = _34;
  Int_Glob = 5;
  return;