[Bug target/91681] Missed optimization for 128 bit arithmetic operations

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91681

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Target|                            |x86_64-*-*, i?86-*-*
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2019-09-06
     Ever confirmed|0                           |1

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
So while we recognize a widening multiply:

  B0_10 = c_9(D) w* b_7(D);

we don't recognize a highpart one:

  _3 = B0_10 >> 64;

maybe because we're not truncating to 64bits.  Not sure if it would help
the testcase though.