<!DOCTYPE html>
<html lang="en">

<head>
    <meta charset="UTF-8">
    <meta http-equiv="X-UA-Compatible" content="IE=edge">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.0-alpha1/dist/css/bootstrap.min.css" rel="stylesheet"
        integrity="sha384-GLhlTQ8iRABdZLl6O3oVMWSktQOp6b7In1Zl3/Jr59b6EGGoI1aFkw7cmDA6j6gD" crossorigin="anonymous">
    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.3.0/css/all.min.css"
        integrity="sha512-SzlrxWUlpfuzQ+pcUCosxcglQRNAq/DZjVsC0lE40xsADsfeQoEypE+enwcOiGjk/bSuGGKHEyjSoQ1zVisanQ=="
        crossorigin="anonymous" referrerpolicy="no-referrer" />
</head>
</html>
#ifdef _MSC_VER
    #include <Intrin.h>
#endif
#include <arm_neon.h>

int main(int argc, char **argv)
{
    float16_t *src = (float16_t*)argv[argc-1];
    float *src2 = (float*)argv[argc-2];
    float16x8_t vhp  = vdupq_n_f16(src[0]);
    float16x4_t vlhp = vdup_n_f16(src[1]);
    float32x4_t vf   = vdupq_n_f32(src2[0]);
    float32x2_t vlf  = vdup_n_f32(src2[1]);

    int ret  = (int)vget_lane_f32(vfmlal_low_f16(vlf, vlhp, vlhp), 0);
        ret += (int)vgetq_lane_f32(vfmlslq_high_f16(vf, vhp, vhp), 0);

    return ret;
}
