I'm a little confused as to what constitutes a single AES round. Most sources say it's this:
t0=Te0[s0>>24]^Te1[(s1>>16)&0xff]^Te2[(s2>>8)&0xff]^Te3[s3&0xff]^rk[4];
t1=Te0[s1>>24]^Te1[(s2>>16)&0xff]^Te2[(s3>>8)&0xff]^Te3[s0&0xff]^rk[5];
t2=Te0[s2>>24]^Te1[(s3>>16)&0xff]^Te2[(s0>>8)&0xff]^Te3[s1&0xff]^rk[6];
t3=Te0[s3>>24]^Te1[(s0>>16)&0xff]^Te2[(s1>>8)&0xff]^Te3[s2&0xff]^rk[7];
If so, then (by my testing) it requires 3, not 2, rounds for diffusion. It's also hard to implement an even number of rounds because it seems to require I begin and end on a t0=... round (vs. the alternating s0=... round).