[Bug tree-optimization/46008] Floating point condexpr not vectorized

[pinskia at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46008

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|---                         |FIXED
   Target Milestone|---                         |5.0

--- Comment #4 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Fixed:
.L2:
        ldr     q0, [x1, x4]
        ldr     q3, [x5, x4]
        ldr     q1, [x2, x4]
        ldr     q2, [x3, x4]
        fadd    v0.2d, v0.2d, v3.2d
        fmla    v0.2d, v2.2d, v1.2d
        fcmlt   v1.2d, v0.2d, 0
        bit     v0.16b, v4.16b, v1.16b
        str     q0, [x0, x4]
        add     x4, x4, 16
        cmp     x4, 8192
        bne     .L2

5.4.0 produces something slightly worse but still vectorizered:
.L2:
        ldr     q0, [x1, x4]
        ldr     q3, [x5, x4]
        ldr     q1, [x2, x4]
        ldr     q2, [x3, x4]
        fadd    v0.2d, v0.2d, v3.2d
        fmla    v0.2d, v2.2d, v1.2d
        fcmlt   v1.2d, v0.2d, 0
        bit     v0.16b, v4.16b, v1.16b
        str     q0, [x4, x0]
        add     x4, x4, 16
        cmp     x4, 8192
        bne     .L2