[Bug c/79938] gcc unnecessarily spills xmm register to stack when inserting vector items

["postmaster at raasu dot org" <gcc-bugzilla at gcc dot gnu dot org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79938

--- Comment #2 from postmaster at raasu dot org ---
(In reply to Richard Biener from comment #1)
> The situation is slightly better with GCC 7, only two spill/loads are
> remaining.
> Possibly BIT_INSERT_EXPR helps here.

With gcc 6.2.0 and
gcc -msse4.1 -mtune=core2 -O3 -S hadd.c -Wall -Wextra -fno-strict-aliasing
-fwrapv -o hadd.s

The resulting assembler output is almost perfect, but adding -mtune=core2 kinda
makes the code optimal only for Intel processors.

---
...
        pxor    %xmm1, %xmm1
        movl    $1, %edi
        movd    %eax, %xmm0
        pshufb  %xmm1, %xmm0
        pextrb  $1, %xmm0, %edx
        pextrb  $0, %xmm0, %eax
        addl    %edx, %eax
        pextrb  $2, %xmm0, %edx
        addl    %edx, %eax
        pextrb  $4, %xmm0, %ecx
        pextrb  $3, %xmm0, %edx
        addl    %eax, %edx
        pextrb  $5, %xmm0, %eax
        addl    %eax, %ecx
        pextrb  $6, %xmm0, %eax
        addl    %eax, %ecx
        pextrb  $9, %xmm0, %esi
        pextrb  $7, %xmm0, %eax
        addl    %eax, %ecx
        pextrb  $8, %xmm0, %eax
        addl    %esi, %eax
        pextrb  $10, %xmm0, %esi
        addl    %esi, %eax
        pextrb  $11, %xmm0, %esi
        addl    %esi, %eax
        pextrb  $13, %xmm0, %esi
        movd    %eax, %xmm1
        pextrb  $12, %xmm0, %eax
        addl    %esi, %eax
        pextrb  $14, %xmm0, %esi
        addl    %eax, %esi
        pextrb  $15, %xmm0, %eax
        movd    %edx, %xmm0
        addl    %esi, %eax
        pinsrd  $1, %ecx, %xmm0
        movl    $.LC0, %esi
        pinsrd  $1, %eax, %xmm1
        xorl    %eax, %eax
        punpcklqdq      %xmm1, %xmm0
...