[Bug target/123997] Missing patterns for masked vector multiplication with memory operand

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

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=123997

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Last reconfirmed|                            |2026-02-05
             Status|UNCONFIRMED                 |NEW
     Ever confirmed|0                           |1

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
  5c:   62 d1 fd c9 10 14 c1    vmovupd (%r9,%rax,8),%zmm2{%k1}{z}
  63:   62 d1 fd c9 10 0c c0    vmovupd (%r8,%rax,8),%zmm1{%k1}{z}
  6a:   62 f1 ed c9 59 c1       vmulpd %zmm1,%zmm2,%zmm0{%k1}{z}

vs.

  5c:   62 d1 fd c9 10 14 c1    vmovupd (%r9,%rax,8),%zmm2{%k1}{z}
  63:   62 d1 ed c9 59 04 c0    vmulpd (%r8,%rax,8),%zmm2,%zmm0{%k1}{z}

saves 6 bytes (and a register).