void FillCacheLines(void *cache_aligned_ptr, void *data16, int count)
{
	dword *t = (dword *)cache_aligned_ptr;
	__m128d val = _mm_loadu_pd((double *)data16);
	dword *e = t + 16 * count;
	while(t < e) {
		_mm_stream_pd((double *)t, val);
		_mm_stream_pd((double *)(t + 4), val);
		_mm_stream_pd((double *)(t + 8), val);
		_mm_stream_pd((double *)(t + 12), val);
		t += 16;
	}
	_mm_sfence();
}

template <class T>
void MemSet(void *dest, T data, int len)
{
	static_assert(sizeof(T) == 1 || sizeof(T) == 2 || sizeof(T) == 4 || sizeof(T) == 8 || sizeof(T) == 16, "invalid sizeof");
	T *t = (T *)dest;
	if(len * sizeof(T) > 550) {
		while((uintptr_t)t & 63) { // align to cache line
			*t++ = data;
			len--;
		}
		const int itemn = 16 / sizeof(T);
		const int per_cache_line = 4 * itemn;
		T m[itemn];
		for(int i = 0; i < itemn; i++)
			m[i] = data;
		int count = len / per_cache_line;
		FillCacheLines(t, m, count);
		len -= per_cache_line * count;
	}
	
	while(len >= 16) {
		t[0] = data; t[1] = data; t[2] = data; t[3] = data;
		t[4] = data; t[5] = data; t[6] = data; t[7] = data;
		t[8] = data; t[9] = data; t[10] = data; t[11] = data;
		t[12] = data; t[13] = data; t[14] = data; t[15] = data;
		t += 16;
		len -= 16;
	}
	switch(len) {
	case 15: t[14] = data;
	case 14: t[13] = data;
	case 13: t[12] = data;
	case 12: t[11] = data;
	case 11: t[10] = data;
	case 10: t[9] = data;
	case 9: t[8] = data;
	case 8: t[7] = data;
	case 7: t[6] = data;
	case 6: t[5] = data;
	case 5: t[4] = data;
	case 4: t[3] = data;
	case 3: t[2] = data;
	case 2: t[1] = data;
	case 1: t[0] = data;
	}
}