[Bug tree-optimization/102391] Failure to optimize adjacent 8-bit loads into a single bigger load

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102391

--- Comment #3 from Richard Biener <rguenth at gcc dot gnu.org> ---
the bswap pass is in principle able to handle these but it sees

  _1 = (sizetype) offset_12(D);
  _2 = RomHeader_13(D) + _1;
  _3 = *_2;
  _4 = (signed short) _3;
  _5 = _1 + 1;
  _6 = RomHeader_13(D) + _5;
  _7 = *_6;

so the constant offset is not forwarded to the MEM_REFs (int vs. size_t issue)
and the bswap pass doesn't perform any fancy dataref analysis to spot
constant offsetted same bases (it could simply use split_constant_offset
on the found base I guess or invoke DR analysis in BB mode).