void inline Fill3T2(dword *b, dword data, int len){
	if(len<4){
		if(len&1) *b++ = data;
		if(len&2){ *b++ = data; *b++ = data; }
		return;
	}

	__m128i q = _mm_set1_epi32(*(int*)&data);
	__m128i *w = (__m128i*)b;
	
	if(len >= 32) {
		__m128i *e = (__m128i*)b + (len>>2) - 8;
		if(len > 4*1024*1024 / 4 && ((uintptr_t)w & 3) == 0) { // for really huge data, bypass the cache
			_mm_storeu_si128(w, q); // Head align
			int s=(-((int)((uintptr_t)b)>>2))&0x3;
			w = (__m128i*) (b + s);
			do {
				_mm_stream_si128(w++, q);
				_mm_stream_si128(w++, q);
				_mm_stream_si128(w++, q);
				_mm_stream_si128(w++, q);
				_mm_stream_si128(w++, q);
				_mm_stream_si128(w++, q);
				_mm_stream_si128(w++, q);
				_mm_stream_si128(w++, q);
			}while(w<=e);
			_mm_sfence();
		}
		else
			do {
				_mm_storeu_si128(w++, q);
				_mm_storeu_si128(w++, q);
				_mm_storeu_si128(w++, q);
				_mm_storeu_si128(w++, q);
				_mm_storeu_si128(w++, q);
				_mm_storeu_si128(w++, q);
				_mm_storeu_si128(w++, q);
				_mm_storeu_si128(w++, q);
			}while(w<=e);
	}
	
	if(len & 16) {
		_mm_storeu_si128(w++, q);
		_mm_storeu_si128(w++, q);
		_mm_storeu_si128(w++, q);
		_mm_storeu_si128(w++, q);
	}
	if(len & 8) {
		_mm_storeu_si128(w++, q);
		_mm_storeu_si128(w++, q);
	}
	if(len & 4) {
		_mm_storeu_si128(w, q);
	}
	_mm_storeu_si128((__m128i*) (b + len - 4), q); // Tail align
}