RWBuffer<int> In : register(u0); RWBuffer<int> Out : register(u1); [numthreads(1,1,1)] void main() { int4x4 A = int4x4(In[0], In[1], In[2], In[3], In[4], In[5], In[6], In[7], In[8], In[9], In[10], In[11], In[12], In[13], In[14], In[15]); int4x4 B; B[0] = A[3]; B[1].rbag = A[1]; B[2] = A[2].bagr; B[3] = A[0]; const uint COLS = 4; for(int i = 0; i < 16; i++) { uint row = i / COLS; uint col = i % COLS; Out[i] = B[row][col]; } }