[Bug target/90204] [8/9 Regression] C code is optimized worse than C++

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90204

--- Comment #9 from Hongtao.liu <crazylht at gmail dot com> ---
Also what's better between aligned load/store of smaller size  VS unaligned 
load/store of bigger size?

aligned load/store of smaller size:

        movq    %rdx, (%rdi)
        movq    -56(%rsp), %rdx
        movq    %rdx, 8(%rdi)
        movq    -48(%rsp), %rdx
        movq    %rdx, 16(%rdi)
        movq    -40(%rsp), %rdx
        movq    %rdx, 24(%rdi)
        vmovq   %xmm0, 32(%rax)
        movq    -24(%rsp), %rdx
        movq    %rdx, 40(%rdi)
        movq    -16(%rsp), %rdx
        movq    %rdx, 48(%rdi)
        movq    -8(%rsp), %rdx
        movq    %rdx, 56(%rdi)

unaligned load/store of bigger size:

        vmovups %xmm2, (%rdi)
        vmovups %xmm3, 16(%rdi)
        vmovups %xmm4, 32(%rdi)
        vmovups %xmm5, 48(%rdi)