for r := 0; r < nr; r++ {
		t0 = xk[k+0] ^ te0[uint8(s0>>24)] ^ te1[uint8(s1>>16)] ^ te2[uint8(s2>>8)] ^ te3[uint8(s3)]
		t1 = xk[k+1] ^ te0[uint8(s1>>24)] ^ te1[uint8(s2>>16)] ^ te2[uint8(s3>>8)] ^ te3[uint8(s0)]
		t2 = xk[k+2] ^ te0[uint8(s2>>24)] ^ te1[uint8(s3>>16)] ^ te2[uint8(s0>>8)] ^ te3[uint8(s1)]
		t3 = xk[k+3] ^ te0[uint8(s3>>24)] ^ te1[uint8(s0>>16)] ^ te2[uint8(s1>>8)] ^ te3[uint8(s2)]
		k += 4
		s0, s1, s2, s3 = t0, t1, t2, t3
	}