[Bug target/105354] __builtin_shuffle for alignr generates suboptimal code unless SSSE3 is enabled

[crazylht at gmail dot com via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105354

--- Comment #3 from Hongtao.liu <crazylht at gmail dot com> ---
Created attachment 52893
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=52893&action=edit
Patch pending for GCC13

Now, we can also generate

foo3:
.LFB3:
        .cfi_startproc
        movdqa  .LC1(%rip), %xmm2
        pslldq  $9, %xmm1
        psrldq  $5, %xmm0
        pand    %xmm2, %xmm0
        pandn   %xmm1, %xmm2
        por     %xmm2, %xmm0
        ret
.LC1:
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   -1
        .byte   0
        .byte   0
        .byte   0
        .byte   0
        .byte   0
        .byte   0
        .align 16

for

v16qi
foo3 (v16qi a, v16qi b)
{
  return __builtin_shufflevector (a, b, 5, 6, 7, 8, 9, 10, 11, 12,
                                  13, 14, 17, 18, 19, 20, 21, 22);
}