felem_square_reduce
felem_square_reduce,
felem_square_reduce(delta, z_in); /* delta[i] < 2^56 */
felem_square_reduce(gamma, y_in); /* gamma[i] < 2^56 */
felem_square_reduce(ftmp, z1); /* ftmp[i] < 2^56 */
felem_square_reduce(ftmp2, z2); /* ftmp2[i] < 2^56 */
felem_square_reduce(ftmp, ftmp); /* ftmp[i] < 2^56 */
felem_square_reduce,
felem_square_reduce(ftmp, in); /* 2^1 */
felem_square_reduce(ftmp, ftmp); /* 2^2 + 2^1 */
felem_square_reduce(ftmp, ftmp); /* 2^5 + 2^4 + 2^3 */
felem_square_reduce(ftmp, ftmp); /* 2^11 + ... + 2^6 */
felem_square_reduce(ftmp, ftmp); /* 2^14 + ... + 2^3 */
felem_square_reduce(ftmp, ftmp); /* 2^29 + ... + 2^15 */
felem_square_reduce(ftmp, ftmp); /* 2^59 + ... + 2^30 */
felem_square_reduce(ftmp, ftmp); /* 2^119 + ... + 2^60 */
felem_square_reduce(ftmp, ftmp); /* 2^239 + ... + 2^120 */
felem_square_reduce(ftmp, ftmp); /* 2^254 + ... + 2^15 */
felem_square_reduce(ftmp, ftmp); /* 2^285 + ... + 2^31 */
felem_square_reduce(ftmp, ftmp); /* 2^287 + ... + 2^33 + 2^31 + ... + 2^2 */
felem_square_reduce(ftmp, ftmp); /* 2^381 + ... + 2^127 + 2^125 + ... + 2^94 */
felem_square_reduce(ftmp, ftmp); /* 2^383 + ... + 2^129 + 2^127 + ... + 2^96 + 2^31 + ... + 2^2 */
felem_square_reduce,