[Bug libstdc++/57885] unordered_map find slower in 4.8.1 than 4.7.3 with integer key

["jhand at austin dot rr.com" <gcc-bugzilla at gcc dot gnu dot org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=57885

--- Comment #3 from Jim Hand <jhand at austin dot rr.com> ---
As a simplification, I tried compiling the following code with gcc-4.6.3 into
assembly with gcc-4.6.3 and 4.8.1:

#include <unordered_map>

bool contains(std::unordered_map<int, int> a) {
   return a.find(5) != a.end();
}

gcc-4.6.3 generates the following assembly:

.LFB574:
    .cfi_startproc
    movq    8(%rdi), %rcx
    movq    16(%rdi), %rdi
    xorl    %edx, %edx
    movl    $5, %eax
    divq    %rdi
    xorl    %eax, %eax
    movq    (%rcx,%rdi,8), %rsi
    movq    (%rcx,%rdx,8), %rdx
    testq    %rdx, %rdx
    jne    .L6
    jmp    .L2
    .p2align 4,,10
    .p2align 3
.L11:
    movq    8(%rdx), %rdx
    testq    %rdx, %rdx
    je    .L10
.L6:
    cmpl    $5, (%rdx)
    jne    .L11
    cmpq    %rdx, %rsi
    setne    %al
.L2:
    rep
    ret
    .p2align 4,,10
    .p2align 3
.L10:
    xorl    %eax, %eax
    ret
    .cfi_endproc

gcc-4.8.1 generates the following assembly:

.LFB1323:
    .cfi_startproc
    movq    8(%rdi), %r8
    xorl    %edx, %edx
    movl    $5, %eax
    divq    %r8
    movq    (%rdi), %rax
    movq    (%rax,%rdx,8), %rax
    movq    %rdx, %r9
    testq    %rax, %rax
    je    .L7
    movq    (%rax), %rcx
    movl    8(%rcx), %esi
    .p2align 4,,10
    .p2align 3
.L3:
    cmpl    $5, %esi
    je    .L5
    movq    (%rcx), %rcx
    testq    %rcx, %rcx
    je    .L7
    movl    8(%rcx), %esi
    xorl    %edx, %edx
    movslq    %esi, %rax
    divq    %r8
    cmpq    %rdx, %r9
    je    .L3
.L7:
    xorl    %eax, %eax
    ret
    .p2align 4,,10
    .p2align 3
.L5:
    movl    $1, %eax
    ret
    .cfi_endproc

In the gcc-4.8.1 code, I see two divq instructions that I think are coming from
line 345 of _Mod_range_hashing in bits/hashtable_policy.h:

 343     result_type
 344     operator()(first_argument_type __num, second_argument_type __den)
const
 345     { return __num % __den; }

I would think that the hash function only needs to be called once for this
function, but I could be misinterpreting the assembly output. It does look to
me like the 4.8 output is doing a lot more than the 4.6.3 output, but I'll
leave it for you to explore.