Slight variation of Miles Lubin's https://gist.github.com/mlubin/4994c65c7a2fa90a3c7e

newton.c

#include <stdio.h>
#include <math.h>
#include <sys/time.h>

// gcc -O2 -std=c99 -march=native -mno-fma -o newton.gcc newton.c
// clang -O2 -march=native -o newton.clang newton.c

// copied from julia
double clock_now()
{
    struct timeval now;
    gettimeofday(&now, NULL);
    return (double)now.tv_sec + (double)now.tv_usec/1.0e6;
}

double squareroot(double x)
{
    double it = x;
    while (fabs(it*it - x) > 1e-13) {
        it = it - (it*it-x)/(2*it);
    }
    return it;
}
int main()
{
    const int num_iter = 10000000;
    double t = clock_now();
    volatile double sum_real = 0;
    for (int i = 0; i < num_iter; i++) {
        sum_real += squareroot(10000.0);
    }
    double t_double = clock_now() - t;
    printf("%f nsec\n", t_double/num_iter*1E9);
}

newton.jl

function squareroot(x)
    it = x
    while abs(it*it - x) > 1e-13
        it = it - (it*it-x)/(2it)
    end
    return it
end

function time_sqrt(x)
    const num_iter = 10000000
    q = zero(x)
    t = time()
    for i in 1:num_iter
        q += squareroot(x)
    end
    t = time() - t
    @printf("%f nsec\n",t/num_iter*1e9)
    return q
end

q=time_sqrt(10000.0)
@printf("q=%.18f\n",q)
@code_native squareroot(10000.0)

Transcript

$ clang -v
clang version 3.7.0 (trunk 227196)
Target: x86_64-unknown-linux-gnu
Thread model: posix
Found candidate GCC installation: /usr/lib/gcc/i686-redhat-linux/4.8.2
Found candidate GCC installation: /usr/lib/gcc/x86_64-redhat-linux/4.8.2
Selected GCC installation: /usr/lib/gcc/x86_64-redhat-linux/4.8.2
Candidate multilib: .;@m64
Candidate multilib: 32;@m32
Selected multilib: .;@m64
$ clang -O2 -march=native -o newton.clang newton.c
$ newton.clang
46.274900 nsec
$ gcc -v
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/libexec/gcc/x86_64-redhat-linux/4.8.2/lto-wrapper
Target: x86_64-redhat-linux
Configured with: ../configure --prefix=/usr --mandir=/usr/share/man --infodir=/usr/share/info --with-bugurl=http://bugzilla.redhat.com/bugzilla --enable-bootstrap --enable-shared --enable-threads=posix --enable-checking=release --with-system-zlib --enable-__cxa_atexit --disable-libunwind-exceptions --enable-gnu-unique-object --enable-linker-build-id --with-linker-hash-style=gnu --enable-languages=c,c++,objc,obj-c++,java,fortran,ada,go,lto --enable-plugin --enable-initfini-array --disable-libgcj --with-isl=/builddir/build/BUILD/gcc-4.8.2-20140120/obj-x86_64-redhat-linux/isl-install --with-cloog=/builddir/build/BUILD/gcc-4.8.2-20140120/obj-x86_64-redhat-linux/cloog-install --enable-gnu-indirect-function --with-tune=generic --with-arch_32=x86-64 --build=x86_64-redhat-linux
Thread model: posix
gcc version 4.8.2 20140120 (Red Hat 4.8.2-16) (GCC)
$ gcc -O2 -std=c99 -march=native -mno-fma -o newton.gcc newton.c
$ newton
newton.clang      newton.gcc        newton.gcc.nofma  newton.icc        newton.icc.nofma  newton.icc.strict
$ newton.gcc
45.589709 nsec
$ pwd
/localdisk/adrobiso/julia-0.3.5/julia
$ julia newton.jl
70.634222 nsec
q=1000000000.000000000000000000
        .text
Filename: /localdisk/adrobiso/julia-0.3.5/julia/newton.jl
Source line: 3
        push    RBP
        mov     RBP, RSP
Source line: 3
        vmulsd  XMM1, XMM0, XMM0
        vsubsd  XMM1, XMM1, XMM0
        vmovq   RCX, XMM1
        movabs  RAX, 9223372036854775807
        and     RCX, RAX
        vmovq   XMM1, RCX
        movabs  RCX, 139772758918544
        vucomisd        XMM1, QWORD PTR [RCX]
        ja      L64
        vmovaps XMM1, XMM0
        jmpq    L133
L64:    movabs  RDX, 139772758918552
        vmovsd  XMM2, QWORD PTR [RDX]
        vmovaps XMM1, XMM0
Source line: 4
L82:    vmulsd  XMM3, XMM1, XMM2
        vmulsd  XMM4, XMM1, XMM1
        vsubsd  XMM4, XMM4, XMM0
        vdivsd  XMM3, XMM4, XMM3
        vaddsd  XMM1, XMM1, XMM3
        vmulsd  XMM3, XMM1, XMM1
        vsubsd  XMM3, XMM3, XMM0
        vmovq   RDX, XMM3
        and     RDX, RAX
        vmovq   XMM3, RDX
        vucomisd        XMM3, QWORD PTR [RCX]
        ja      L82
Source line: 6
L133:   vmovaps XMM0, XMM1
        pop     RBP
        ret
$