gf2m_SQR1
u[11] = gf2m_SQR1(v[5]);
u[9] = gf2m_SQR1(v[4]);
u[7] = gf2m_SQR1(v[3]);
u[5] = gf2m_SQR1(v[2]);
u[3] = gf2m_SQR1(v[1]);
u[1] = gf2m_SQR1(v[0]);
u[11] = gf2m_SQR1(v[5]);
u[9] = gf2m_SQR1(v[4]);
u[7] = gf2m_SQR1(v[3]);
u[5] = gf2m_SQR1(v[2]);
u[3] = gf2m_SQR1(v[1]);
u[1] = gf2m_SQR1(v[0]);
u[13] = gf2m_SQR1(v[6]);
u[11] = gf2m_SQR1(v[5]);
u[9] = gf2m_SQR1(v[4]);
u[7] = gf2m_SQR1(v[3]);
u[5] = gf2m_SQR1(v[2]);
u[3] = gf2m_SQR1(v[1]);
u[1] = gf2m_SQR1(v[0]);
*pr++ = gf2m_SQR1(a_i);