[Bug c++/78180] Poor optimization of std::array on gcc 4.8/5.4/6.2 as compared to simple raw array

["trippels at gcc dot gnu.org" <gcc-bugzilla at gcc dot gnu dot org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=78180

--- Comment #3 from Markus Trippelsdorf <trippels at gcc dot gnu.org> ---
void BM_Rolling<long [128]>:            |       void
BM_Rolling<std::array<long, 128ul> >:
.LFB1712:                               |       .LFB1713:
        .cfi_startproc                          .cfi_startproc
        pushq   %r13                    <
        .cfi_def_cfa_offset 16          <
        .cfi_offset 13, -16             <
        pushq   %r12                    <
        .cfi_def_cfa_offset 24          <
        .cfi_offset 12, -24             <
        movl    $128, %ecx              <
        pushq   %rbp                            pushq   %rbp
        .cfi_def_cfa_offset 32          |               .cfi_def_cfa_offset 16
        .cfi_offset 6, -32              |               .cfi_offset 6, -16
        pushq   %rbx                            pushq   %rbx
        .cfi_def_cfa_offset 40          |               .cfi_def_cfa_offset 24
        .cfi_offset 3, -40              |               .cfi_offset 3, -24
        movq    %rdi, %rbp              <
        xorl    %eax, %eax                      xorl    %eax, %eax
        xorl    %ebx, %ebx              |               movq    %rdi, %rbx
        xorl    %r12d, %r12d            |               movl    $128, %ecx
                                        >               xorl    %ebp, %ebp
        subq    $1048, %rsp                     subq    $1048, %rsp
        .cfi_def_cfa_offset 1088        |               .cfi_def_cfa_offset
1072
        xorl    %r13d, %r13d            <
        movq    %rsp, %rdi                      movq    %rsp, %rdi
        rep stosq                               rep stosq
                                        >               movabsq $429496729600,
%rax
                                        >               movq    %rax,
1024(%rsp)
        .p2align 4,,10                          .p2align 4,,10
        .p2align 3                              .p2align 3
.L28:                                   |       .L7:
        cmpb    $0, 0(%rbp)             |               cmpb    $0, (%rbx)
        je      .L39                    |               je      .L20
.L23:                                   |       .L2:
        movq    8(%rbp), %rax           |               movq    8(%rbx), %rax
        cmpq    72(%rbp), %rax          |               cmpq    72(%rbx), %rax
        leaq    1(%rax), %rdx                   leaq    1(%rax), %rdx
        movq    %rdx, 8(%rbp)           |               movq    %rdx, 8(%rbx)
        jnb     .L40                    |               jnb     .L21
        movq    24(%rbp), %r8           |               movq    24(%rbx), %r8
        movq    16(%rbp), %rdi          |               movq    16(%rbx), %rsi
        movq    %r8, %rax                       movq    %r8, %rax
        subq    %rdi, %rax              |               subq    %rsi, %rax
        sarq    $2, %rax                        sarq    $2, %rax
        testq   %rax, %rax                      testq   %rax, %rax
        je      .L25                    |               je      .L4
        movl    (%rdi), %edx            |               movl    (%rsi), %eax
        xorl    %eax, %eax              |               xorl    %edx, %edx
        xorl    %ecx, %ecx                      xorl    %ecx, %ecx
        movl    %ebx, %esi              |               testl   %eax, %eax
        testl   %edx, %edx              |               jg      .L5
        jg      .L26                    |               jmp     .L7
        jmp     .L28                    <
        .p2align 4,,10                          .p2align 4,,10
        .p2align 3                              .p2align 3
.L31:                                   |       .L11:
        addq    $1, %rax                |               addq    $1, %rdx
        cmpl    (%rdi), %ecx            |               cmpl    (%rsi), %ecx
        jge     .L28                    |               jge     .L7
.L26:                                   |       .L5:
        addl    $1, %ebx                |               movl    1024(%rsp),
%edi
        movq    %rax, (%rsp,%rsi,8)     |               movq    %rdi, %rax
        movq    %rax, %rdx              |               movq    %rdx,
(%rsp,%rdi,8)
        cmpl    $100, %ebx              |               addl    $1, %eax
        cmove   %r13d, %ebx             |               cmpl    1028(%rsp),
%eax
        movl    %ebx, %esi              |               movl    %eax,
1024(%rsp)
        subq    (%rsp,%rsi,8), %rdx     |               jne     .L9
        cmpq    $999999, %rdx           |               movl    $0, 1024(%rsp)
        jg      .L30                    |               xorl    %eax, %eax
        addq    $1, %r12                |       .L9:
        movq    16(%rbp), %rdi          |               movq    %rdx, %rdi
        movq    24(%rbp), %r8           |               subq    (%rsp,%rax,8),
%rdi
.L30:                                   |               cmpq    $999999, %rdi
        movq    %r8, %rdx               |               jg      .L10
                                        >               addq    $1, %rbp
                                        >               movq    16(%rbx), %rsi
                                        >               movq    24(%rbx), %r8
                                        >       .L10:
                                        >               movq    %r8, %rax
        addl    $1, %ecx                        addl    $1, %ecx
        subq    %rdi, %rdx              |               subq    %rsi, %rax
        sarq    $2, %rdx                |               sarq    $2, %rax
        testq   %rdx, %rdx              |               testq   %rax, %rax
        jne     .L31                    |               jne     .L11