<!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)
{
    unsigned char *src = (unsigned char*)argv[argc-1];
    uint8x16_t v1 = vdupq_n_u8(src[0]), v2 = vdupq_n_u8(src[1]);
    uint32x4_t va = vdupq_n_u32(3);
    int ret = (int)vgetq_lane_u32(vdotq_u32(va, v1, v2), 0);
#ifdef __aarch64__
    ret += (int)vgetq_lane_u32(vdotq_laneq_u32(va, v1, v2, 0), 0);
#endif
    return ret;
}
