[Bug target/71720] initialization of a vector of floats generates incorrect code for -mcpu=power9

[acsawdey at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=71720

--- Comment #2 from acsawdey at gcc dot gnu.org ---
I believe this also causes pr57741-2.c to fail, generated code is:

        fmuls 12,1,12
        fadds 0,10,1
        xxpermdi 33,10,11,0
        xscvdpspn 12,12
        xvcvdpsp 33,33
        fadds 1,1,0
.LVL7:
        xxspltw 12,12,3

and again we should be doing xxspltw 12,12,0 here.