How to generate a sse4.2 popcnt machine instruction

Question

Using the c program:

int main(int argc , char** argv)
{

  return  __builtin_popcountll(0xf0f0f0f0f0f0f0f0);

}

and the compiler line (gcc 4.4

Answer 1

For __builtin_popcountll in GCC, all you need to do is add -mpopcnt

#include 
int main(int argc, char **argv) {
    return __builtin_popcountll(atoi(argv[1]));
}

with -mpopcnt

$ otool -tvV a.out
a.out:
(__TEXT,__text) section
_main:
0000000100000f66    pushq   %rbp
0000000100000f67    movq    %rsp, %rbp
0000000100000f6a    subq    $0x10, %rsp
0000000100000f6e    movq    %rdi, -0x8(%rbp)
0000000100000f72    movq    -0x8(%rbp), %rax
0000000100000f76    addq    $0x8, %rax
0000000100000f7a    movq    (%rax), %rax
0000000100000f7d    movq    %rax, %rdi
0000000100000f80    callq   0x100000f8e ## symbol stub for: _atoi
0000000100000f85    cltq
0000000100000f87    popcntq %rax, %rax
0000000100000f8c    leave
0000000100000f8d    retq

without -mpopcnt

a.out:
(__TEXT,__text) section
_main:
0000000100000f55    pushq   %rbp
0000000100000f56    movq    %rsp, %rbp
0000000100000f59    subq    $0x10, %rsp
0000000100000f5d    movq    %rdi, -0x8(%rbp)
0000000100000f61    movq    -0x8(%rbp), %rax
0000000100000f65    addq    $0x8, %rax
0000000100000f69    movq    (%rax), %rax
0000000100000f6c    movq    %rax, %rdi
0000000100000f6f    callq   0x100000f86 ## symbol stub for: _atoi
0000000100000f74    cltq
0000000100000f76    movq    %rax, %rdi
0000000100000f79    callq   0x100000f80 ## symbol stub for: ___popcountdi2
0000000100000f7e    leave
0000000100000f7f    retq

Notes

Be sure to check the ABM bit (bit 23) of CPUID feature bits before using POPCNTQ