intrin.h

#pragma once
#include <stdint.h>

#if defined(__GNUC__)
#   define clz(x) __builtin_clz(x)
#   define ctz(x) __builtin_ctz(x)

#elif defined(_MSC_VER)
#   include <intrin.h>
    uint32_t __inline ctz( uint32_t value ) {
        DWORD trailing_zero = 0;
        _BitScanForward( &trailing_zero, value );
        return trailing_zero;
    }
    uint32_t __inline clz( uint32_t value ) {
        DWORD leading_zero = 0;
        _BitScanReverse( &leading_zero, value );
        return 31 - leading_zero;
    }
#else
    static uint32_t ALWAYS_INLINE popcnt( uint32_t x ) {
        x -= ((x >> 1) & 0x55555555);
        x = (((x >> 2) & 0x33333333) + (x & 0x33333333));
        x = (((x >> 4) + x) & 0x0f0f0f0f);
        x += (x >> 8);
        x += (x >> 16);
        return x & 0x0000003f;
    }
    static uint32_t ALWAYS_INLINE clz( uint32_t x ) {
        x |= (x >> 1);
        x |= (x >> 2);
        x |= (x >> 4);
        x |= (x >> 8);
        x |= (x >> 16);
        return 32 - popcnt(x);
    }
    static uint32_t ALWAYS_INLINE ctz( uint32_t x ) {
        return popcnt((x & -x) - 1);
    }
#endif