[Bug c/55953] New: hand loop faster then builtin memset

[dushistov at mail dot ru]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=55953

             Bug #: 55953
           Summary: hand loop faster then builtin memset
    Classification: Unclassified
           Product: gcc
           Version: unknown
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
        AssignedTo: unassigned@gcc.gnu.org
        ReportedBy: dushistov@mail.ru


variant 1:
char c[100];

void f(void)
{
        for(int i=0; i < 100; ++i)
                c[i] = '0';
}

assembly:
push   %rbp
vmovdqa 0x117(%rip),%ymm0        # 0x400960
mov    %rsp,%rbp
pop    %rbp
movb   $0x30,0x20086c(%rip)# 0x6010c0 <c+96>
vmovdqa %ymm0,0x200804(%rip)# 0x601060 <c>
vmovdqa %ymm0,0x20081c(%rip)# 0x601080 <c+32>
vmovdqa %ymm0,0x200834(%rip)# 0x6010a0 <c+64>
movb   $0x30,0x20084e(%rip)# 0x6010c1 <c+97>
movb   $0x30,0x200848(%rip)# 0x6010c2 <c+98>
movb   $0x30,0x200842(%rip)# 0x6010c3 <c+99>
vzeroupper 
retq   


variant 2:
char c[100];

void f(void)
{
        memset(c, '0', 100);
}

assembly:
movabs $0x3030303030303030,%rax
movl   $0x30303030,0x20086c(%rip)        # 0x6010c0 <c+96>
mov    %rax,0x200805(%rip)        # 0x601060 <c>
mov    %rax,0x200806(%rip)        # 0x601068 <c+8>
mov    %rax,0x200807(%rip)        # 0x601070 <c+16>
mov    %rax,0x200808(%rip)        # 0x601078 <c+24>
mov    %rax,0x200809(%rip)        # 0x601080 <c+32>
mov    %rax,0x20080a(%rip)        # 0x601088 <c+40>
mov    %rax,0x20080b(%rip)        # 0x601090 <c+48>
mov    %rax,0x20080c(%rip)        # 0x601098 <c+56>
mov    %rax,0x20080d(%rip)        # 0x6010a0 <c+64>
mov    %rax,0x20080e(%rip)        # 0x6010a8 <c+72>
mov    %rax,0x20080f(%rip)        # 0x6010b0 <c+80>
mov    %rax,0x200810(%rip)        # 0x6010b8 <c+88>
retq   

The first variants take (for (size_t i = 0; i < 10000000; ++i) f();):
0.150000 secs, abs 0.150255
The second variants take:
0.170000 secs, abs 0.175502

CPU Intel i7, 
gcc --version
gcc (Gentoo 4.7.2 p1.3, pie-0.5.5) 4.7.2
compile options: -Ofast -march=native

Expected behaviour: 
assembly code should be the same, and it should be variant 1, or faster.