void FillX(void *p, dword data, int len)
{
	dword *t = (dword *)p;
	if(len < 4) {
		if(len & 2) {
			t[0] = t[1] = t[len - 1] = data;
			return;
		}
		if(len & 1)
			t[0] = data;
		return;
	}

	__m128i val4 = _mm_set1_epi32(data);
	auto Set4 = [&](int at) { _mm_storeu_si128((__m128i *)(t + at), val4); };

	Set4(len - 4); // fill tail
	if(len >= 16) {
		Set4(0); // align up on 16 bytes boundary
		const dword *e = t + len;
		t = (dword *)(((uintptr_t)t | 15) + 1);
		len = e - t;
		e -= 16;
		if(len >= 1024*1024) { // for really huge data, bypass the cache
			huge_memsetd(t, data, len);
			return;
		}
		while(t <= e) {
			Set4(0); Set4(4); Set4(8); Set4(12);
			t += 16;
		}
	}
	if(len & 8) {
		Set4(0); Set4(4);
		t += 8;
	}
	if(len & 4)
		Set4(0);
}