/*=============================================================================

    This file is part of FLINT.

    FLINT is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2 of the License, or
    (at your option) any later version.

    FLINT is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with FLINT; if not, write to the Free Software
    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA

=============================================================================*/
/******************************************************************************

    Copyright (C) 2009, 2008 William Hart
    Copyright (C) 2011 Sebastian Pancratz
    Copyright (C) 2011 Fredrik Johansson
    Copyright (C) 2013 Mike Hansen

******************************************************************************/

*******************************************************************************

    Memory management

*******************************************************************************

void fmpz_mod_poly_init(fmpz_mod_poly_t poly, const fmpz_t p)

    Initialises \code{poly} for use over $\mathbf{Z} / p \mathbf{Z}$,
    setting its length to zero.

    A corresponding call to \code{fmpz_mod_poly_clear()} must be made after
    finishing with the \code{fmpz_mod_poly_t} to free the memory used by
    the polynomial.  The user is also responsible to clearing the
    integer~$p$.

void fmpz_mod_poly_init2(fmpz_mod_poly_t poly, const fmpz_t p, slong alloc)

    Initialises \code{poly} with space for at least \code{alloc} coefficients
    and sets the length to zero.  The allocated coefficients are all set to
    zero.

void fmpz_mod_poly_clear(fmpz_mod_poly_t poly)

    Clears the given polynomial, releasing any memory used.  It must
    be reinitialised in order to be used again.

void fmpz_mod_poly_realloc(fmpz_mod_poly_t poly, slong alloc)

    Reallocates the given polynomial to have space for \code{alloc}
    coefficients.  If \code{alloc} is zero the polynomial is cleared
    and then reinitialised.  If the current length is greater than
    \code{alloc} the polynomial is first truncated to length \code{alloc}.

void fmpz_mod_poly_fit_length(fmpz_mod_poly_t poly, slong len)

    If \code{len} is greater than the number of coefficients currently
    allocated, then the polynomial is reallocated to have space for at
    least \code{len} coefficients.  No data is lost when calling this
    function.

    The function efficiently deals with the case where it is called
    many times in small increments by at least doubling the number of
    allocated coefficients when length is larger than the number of
    coefficients currently allocated.

void _fmpz_mod_poly_normalise(fmpz_mod_poly_t poly)

    Sets the length of \code{poly} so that the top coefficient is non-zero.
    If all coefficients are zero, the length is set to zero.  This function
    is mainly used internally, as all functions guarantee normalisation.

void _fmpz_mod_poly_set_length(fmpz_mod_poly_t poly, slong len)

    Demotes the coefficients of \code{poly} beyond \code{len} and sets
    the length of \code{poly} to \code{len}.

void fmpz_mod_poly_truncate(fmpz_mod_poly_t poly, slong len)

    If the current length of \code{poly} is greater than \code{len}, it
    is truncated to have the given length.  Discarded coefficients are
    not necessarily set to zero.

*******************************************************************************

    Randomisation

*******************************************************************************

void fmpz_mod_poly_randtest(fmpz_mod_poly_t f, flint_rand_t state, slong len)

    Sets the polynomial~$f$ to a random polynomial of length up~\code{len}.

void fmpz_mod_poly_randtest_irreducible(fmpz_mod_poly_t f,
                                        flint_rand_t state, slong len)

    Sets the polynomial~$f$ to a random irreducible polynomial of length
    up~\code{len}, assuming \code{len} is positive.

void fmpz_mod_poly_randtest_not_zero(fmpz_mod_poly_t f,
                                     flint_rand_t state, slong len)

    Sets the polynomial~$f$ to a random polynomial of length up~\code{len},
    assuming \code{len} is positive.

void fmpz_mod_poly_randtest_monic(fmpz_mod_poly_t poly, flint_rand_t state,
                                  slong len)

    Generates a random monic polynomial with length \code{len}.

void
fmpz_mod_poly_randtest_monic_irreducible(fmpz_mod_poly_t poly,
                                         flint_rand_t state, slong len)

    Generates a random monic irreducible polynomial with length \code{len}.


void
fmpz_mod_poly_randtest_trinomial(fmpz_mod_poly_t poly, flint_rand_t state,
                                 slong len)

    Generates a random monic trinomial of length \code{len}.

int
fmpz_mod_poly_randtest_trinomial_irreducible(fmpz_mod_poly_t poly,
                                            flint_rand_t state,
                                            slong len, slong max_attempts)

    Attempts to set \code{poly} to a monic irreducible trinomial of
    length \code{len}.  It will generate up to \code{max_attempts}
    trinomials in attempt to find an irreducible one.  If
    \code{max_attempts} is \code{0}, then it will keep generating
    trinomials until an irreducible one is found.  Returns $1$ if one
    is found and $0$ otherwise.

void
fmpz_mod_poly_randtest_pentomial(fmpz_mod_poly_t poly, flint_rand_t state,
                                 slong len)

    Generates a random monic pentomial of length \code{len}.

int
fmpz_mod_poly_randtest_pentomial_irreducible(fmpz_mod_poly_t poly,
                                             flint_rand_t state,
                                             slong len, slong max_attempts)

    Attempts to set \code{poly} to a monic irreducible pentomial of
    length \code{len}.  It will generate up to \code{max_attempts}
    pentomials in attempt to find an irreducible one.  If
    \code{max_attempts} is \code{0}, then it will keep generating
    pentomials until an irreducible one is found.  Returns $1$ if one
    is found and $0$ otherwise.

void
fmpz_mod_poly_randtest_sparse_irreducible(fmpz_mod_poly_t poly,
                                          flint_rand_t state, slong len)

    Attempts to set \code{poly} to a sparse, monic irreducible polynomial
    with length \code{len}.  It attempts to find an irreducible
    trinomial.  If that does not succeed, it attempts to find a
    irreducible pentomial.  If that fails, then \code{poly} is just
    set to a random monic irreducible polynomial.


*******************************************************************************

    Attributes

*******************************************************************************

fmpz * fmpz_mod_poly_modulus(const fmpz_mod_poly_t poly)

    Returns the modulus of this polynomial.  This function is
    implemented as a macro.

slong fmpz_mod_poly_degree(const fmpz_mod_poly_t poly)

    Returns the degree of the polynomial.  The degree of the zero
    polynomial is defined to be $-1$.

slong fmpz_mod_poly_length(const fmpz_mod_poly_t poly)

    Returns the length of the polynomial, which is one more than
    its degree.

fmpz * fmpz_mod_poly_lead(const fmpz_mod_poly_t poly)

    Returns a pointer to the first leading coefficient of \code{poly}
    if this is non-zero, otherwise returns \code{NULL}.

*******************************************************************************

    Assignment and basic manipulation

*******************************************************************************

void fmpz_mod_poly_set(fmpz_mod_poly_t poly1, const fmpz_mod_poly_t poly2)

    Sets the polynomial \code{poly1} to the value of \code{poly2}.

void fmpz_mod_poly_swap(fmpz_mod_poly_t poly1, fmpz_mod_poly_t poly2)

    Swaps the two polynomials.  This is done efficiently by swapping
    pointers rather than individual coefficients.

void fmpz_mod_poly_zero(fmpz_mod_poly_t poly)

    Sets \code{poly} to the zero polynomial.

void fmpz_mod_poly_zero_coeffs(fmpz_mod_poly_t poly, slong i, slong j)

    Sets the coefficients of $X^k$ for $k \in [i, j)$ in the polynomial
    to zero.

void fmpz_mod_poly_reverse(fmpz_mod_poly_t res,
                           const fmpz_mod_poly_t poly, slong n)

    This function considers the polynomial \code{poly} to be of length $n$,
    notionally truncating and zero padding if required, and reverses
    the result.  Since the function normalises its result \code{res} may be
    of length less than $n$.

*******************************************************************************

    Conversion

*******************************************************************************

void fmpz_mod_poly_set_ui(fmpz_mod_poly_t f, ulong c)

    Sets the polynomial $f$ to the constant $c$ reduced modulo $p$.

void fmpz_mod_poly_set_fmpz(fmpz_mod_poly_t f, const fmpz_t c)

    Sets the polynomial $f$ to the constant $c$ reduced modulo $p$.

void fmpz_mod_poly_set_fmpz_poly(fmpz_mod_poly_t f, const fmpz_poly_t g)

    Sets $f$ to $g$ reduced modulo $p$, where $p$ is the modulus that
    is part of the data structure of $f$.

void fmpz_mod_poly_get_fmpz_poly(fmpz_poly_t f, const fmpz_mod_poly_t g)

    Sets $f$ to $g$.  This is done simply by lifting the coefficients
    of $g$ taking representatives $[0, p) \subset \mathbf{Z}$.

*******************************************************************************

    Comparison

*******************************************************************************

int fmpz_mod_poly_equal(const fmpz_mod_poly_t poly1,
                        const fmpz_mod_poly_t poly2)

    Returns non-zero if the two polynomials are equal.

int fmpz_mod_poly_is_zero(const fmpz_mod_poly_t poly)

    Returns non-zero if the polynomial is zero.

*******************************************************************************

    Getting and setting coefficients

*******************************************************************************

void
fmpz_mod_poly_set_coeff_fmpz(fmpz_mod_poly_t poly, slong n, const fmpz_t x)

    Sets the coefficient of $X^n$ in the polynomial to $x$,
    assuming $n \geq 0$.

void fmpz_mod_poly_set_coeff_ui(fmpz_mod_poly_t poly, slong n, ulong x)

    Sets the coefficient of $X^n$ in the polynomial to $x$,
    assuming $n \geq 0$.

void
fmpz_mod_poly_get_coeff_fmpz(fmpz_t x, const fmpz_mod_poly_t poly, slong n)

    Sets $x$ to the coefficient of $X^n$ in the polynomial,
    assumng $n \geq 0$.

void
fmpz_mod_poly_set_coeff_mpz(fmpz_mod_poly_t poly, slong n, const mpz_t x)

    Sets the coefficient of $X^n$ in the polynomial to $x$,
    assuming $n \geq 0$.

void
fmpz_mod_poly_get_coeff_mpz(mpz_t x, const fmpz_mod_poly_t poly, slong n)

    Sets $x$ to the coefficient of $X^n$ in the polynomial,
    assumng $n \geq 0$.

*******************************************************************************

    Shifting

*******************************************************************************

void _fmpz_mod_poly_shift_left(fmpz * res,
                               const fmpz * poly, slong len, slong n)

    Sets \code{(res, len + n)} to \code{(poly, len)} shifted left by
    $n$ coefficients.

    Inserts zero coefficients at the lower end.  Assumes that \code{len}
    and $n$ are positive, and that \code{res} fits \code{len + n} elements.
    Supports aliasing between \code{res} and \code{poly}.

void fmpz_mod_poly_shift_left(fmpz_mod_poly_t f,
                              const fmpz_mod_poly_t g, slong n)

    Sets \code{res} to \code{poly} shifted left by $n$ coeffs.  Zero
    coefficients are inserted.

void _fmpz_mod_poly_shift_right(fmpz * res,
                                const fmpz * poly, slong len, slong n)

    Sets \code{(res, len - n)} to \code{(poly, len)} shifted right by
    $n$ coefficients.

    Assumes that \code{len} and $n$ are positive, that \code{len > n},
    and that \code{res} fits \code{len - n} elements.  Supports aliasing
    between \code{res} and \code{poly}, although in this case the top
    coefficients of \code{poly} are not set to zero.

void fmpz_mod_poly_shift_right(fmpz_mod_poly_t f,
                               const fmpz_mod_poly_t g, slong n)

    Sets \code{res} to \code{poly} shifted right by $n$ coefficients.  If $n$
    is equal to or greater than the current length of \code{poly}, \code{res}
    is set to the zero polynomial.

*******************************************************************************

    Addition and subtraction

*******************************************************************************

void _fmpz_mod_poly_add(fmpz *res, const fmpz *poly1, slong len1,
                                   const fmpz *poly2, slong len2,
                                   const fmpz_t p)

    Sets \code{res} to the sum of \code{(poly1, len1)} and
    \code{(poly2, len2)}.  It is assumed that \code{res} has
    sufficient space for the longer of the two polynomials.

void fmpz_mod_poly_add(fmpz_mod_poly_t res,
                       const fmpz_mod_poly_t poly1,
                       const fmpz_mod_poly_t poly2)

    Sets \code{res} to the sum of \code{poly1} and \code{poly2}.

void _fmpz_mod_poly_sub(fmpz *res, const fmpz *poly1, slong len1,
                                   const fmpz *poly2, slong len2,
                                   const fmpz_t p)

    Sets \code{res} to \code{(poly1, len1)} minus \code{(poly2, len2)}.  It
    is assumed that \code{res} has sufficient space for the longer of the
    two polynomials.

void fmpz_mod_poly_sub(fmpz_mod_poly_t res,
                       const fmpz_mod_poly_t poly1,
                       const fmpz_mod_poly_t poly2)

    Sets \code{res} to \code{poly1} minus \code{poly2}.

void _fmpz_mod_poly_neg(fmpz *res, const fmpz *poly, slong len, const fmpz_t p)

    Sets \code{(res, len)} to the negative of \code{(poly, len)}
    modulo $p$.

void fmpz_mod_poly_neg(fmpz_mod_poly_t res, const fmpz_mod_poly_t poly)

    Sets \code{res} to the negative of \code{poly} modulo $p$.

*******************************************************************************

    Scalar multiplication

*******************************************************************************

void _fmpz_mod_poly_scalar_mul_fmpz(fmpz *res, const fmpz *poly, slong len,
                                    const fmpz_t x, const fmpz_t p)

    Sets \code{(res, len}) to \code{(poly, len)} multiplied by $x$,
    reduced modulo $p$.

void fmpz_mod_poly_scalar_mul_fmpz(fmpz_mod_poly_t res,
    const fmpz_mod_poly_t poly, const fmpz_t x)

    Sets \code{res} to \code{poly} multiplied by $x$.

*******************************************************************************

    Multiplication

*******************************************************************************

void _fmpz_mod_poly_mul(fmpz *res, const fmpz *poly1, slong len1,
                                   const fmpz *poly2, slong len2,
                                   const fmpz_t p)

    Sets \code{(res, len1 + len2 - 1)} to the product of \code{(poly1, len1)}
    and \code{(poly2, len2)}.  Assumes \code{len1 >= len2 > 0}.  Allows
    zero-padding of the two input polynomials.

void fmpz_mod_poly_mul(fmpz_mod_poly_t res,
                       const fmpz_mod_poly_t poly1,
                       const fmpz_mod_poly_t poly2)

    Sets \code{res} to the product of \code{poly1} and \code{poly2}.

void _fmpz_mod_poly_mullow(fmpz *res, const fmpz *poly1, slong len1,
                                      const fmpz *poly2, slong len2,
                                      const fmpz_t p, slong n)

    Sets \code{(res, n)} to the lowest $n$ coefficients of the product of
    \code{(poly1, len1)} and \code{(poly2, len2)}.

    Assumes \code{len1 >= len2 > 0} and \code{0 < n <= len1 + len2 - 1}.
    Allows for zero-padding in the inputs.  Does not support aliasing between
    the inputs and the output.

void fmpz_mod_poly_mullow(fmpz_mod_poly_t res,
    const fmpz_mod_poly_t poly1, const fmpz_mod_poly_t poly2, slong n)

    Sets \code{res} to the lowest $n$ coefficients of the product of
    \code{poly1} and \code{poly2}.

void _fmpz_mod_poly_sqr(fmpz *res, const fmpz *poly, slong len, const fmpz_t p)

    Sets \code{res} to the square of \code{poly}.

void fmpz_mod_poly_sqr(fmpz_mod_poly_t res, const fmpz_mod_poly_t poly)

    Computes \code{res} as the square of \code{poly}.

void _fmpz_mod_poly_mulmod(fmpz * res, const fmpz * poly1, slong len1,
			   const fmpz * poly2, slong len2, const fmpz * f,
			   slong lenf, const fmpz_t p)

    Sets \code{res, len1 + len2 - 1} to the remainder of the product of
    \code{poly1} and \code{poly2} upon polynomial division by \code{f}.

    It is required that \code{len1 + len2 - lenf > 0}, which is equivalent
    to requiring that the result will actually be reduced. Otherwise, simply
    use \code{_fmpz_mod_poly_mul} instead.

    Aliasing of \code{f} and \code{res} is not permitted.

void fmpz_mod_poly_mulmod(fmpz_mod_poly_t res, const fmpz_mod_poly_t poly1,
		    const fmpz_mod_poly_t poly2, const fmpz_mod_poly_t f)

    Sets \code{res} to the remainder of the product of \code{poly1} and
    \code{poly2} upon polynomial division by \code{f}.

void _fmpz_mod_poly_mulmod_preinv(fmpz * res, const fmpz * poly1, slong len1,
                    const fmpz * poly2, slong len2, const fmpz * f, slong lenf,
                    const fmpz* finv, slong lenfinv, const fmpz_t p)

    Sets \code{res, len1 + len2 - 1} to the remainder of the product of
    \code{poly1} and \code{poly2} upon polynomial division by \code{f}.

    It is required that \code{finv} is the inverse of the reverse of \code{f}
    mod \code{x^lenf}. It is required that \code{len1 + len2 - lenf > 0},
    which is equivalent to requiring that the result will actually be reduced.
    It is required that \code{len1 < lenf} and \code{len2 < lenf}.
    Otherwise, simply use \code{_fmpz_mod_poly_mul} instead.

    Aliasing of \code{f} or \code{finv} and \code{res} is not permitted.

void fmpz_mod_poly_mulmod_preinv(fmpz_mod_poly_t res,
                       const fmpz_mod_poly_t poly1, const fmpz_mod_poly_t poly2,
                       const fmpz_mod_poly_t f, const fmpz_mod_poly_t finv)

    Sets \code{res} to the remainder of the product of \code{poly1} and
    \code{poly2} upon polynomial division by \code{f}. \code{finv} is the
    inverse of the reverse of \code{f}. It is required that \code{poly1} and
    \code{poly2} are reduced modulo \code{f}.

*******************************************************************************

    Powering

*******************************************************************************

void _fmpz_mod_poly_pow(fmpz *rop, const fmpz *op, slong len, ulong e,
                        const fmpz_t p)

    Sets \code{res = poly^e}, assuming that $e > 1$ and \code{elen > 0},
    and that \code{res} has space for \code{e*(len - 1) + 1} coefficients.
    Does not support aliasing.

void fmpz_mod_poly_pow(fmpz_mod_poly_t rop, const fmpz_mod_poly_t op, ulong e)

    Computes \code{res = poly^e}.  If $e$ is zero, returns one,
    so that in particular \code{0^0 = 1}.

void _fmpz_mod_poly_pow_trunc(fmpz * res, const fmpz * poly,
			      ulong e, slong trunc, const fmpz_t p)

    Sets \code{res} to the low \code{trunc} coefficients of \code{poly}
    (assumed to be zero padded if necessary to length \code{trunc}) to
    the power \code{e}. This is equivalent to doing a powering followed
    by a truncation. We require that \code{res} has enough space for
    \code{trunc} coefficients, that \code{trunc > 0} and that
    \code{e > 1}. Aliasing is not permitted.

void fmpz_mod_poly_pow_trunc(fmpz_mod_poly_t res,
		       const fmpz_mod_poly_t poly, ulong e, slong trunc)

    Sets \code{res} to the low \code{trunc} coefficients of \code{poly}
    to the power \code{e}. This is equivalent to doing a powering
    followed by a truncation.

void _fmpz_mod_poly_pow_trunc_binexp(fmpz * res, const fmpz * poly,
				     ulong e, slong trunc, const fmpz_t p)

    Sets \code{res} to the low \code{trunc} coefficients of \code{poly}
    (assumed to be zero padded if necessary to length \code{trunc}) to
    the power \code{e}. This is equivalent to doing a powering followed
    by a truncation. We require that \code{res} has enough space for
    \code{trunc} coefficients, that \code{trunc > 0} and that
    \code{e > 1}. Aliasing is not permitted. Uses the binary
    exponentiation method.

void fmpz_mod_poly_pow_trunc_binexp(fmpz_mod_poly_t res,
			      const fmpz_mod_poly_t poly, ulong e, slong trunc)

    Sets \code{res} to the low \code{trunc} coefficients of \code{poly}
    to the power \code{e}. This is equivalent to doing a powering
    followed by a truncation. Uses the binary exponentiation method.

void _fmpz_mod_poly_powmod_ui_binexp(fmpz * res, const fmpz * poly,
				     ulong e, const fmpz * f,
				     slong lenf, const fmpz_t p)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e > 0}.

    We require \code{lenf > 1}. It is assumed that \code{poly} is already
    reduced modulo \code{f} and zero-padded as necessary to have length
    exactly \code{lenf - 1}. The output \code{res} must have room for
    \code{lenf - 1} coefficients.

void fmpz_mod_poly_powmod_ui_binexp(fmpz_mod_poly_t res,
			      const fmpz_mod_poly_t poly, ulong e,
			      const fmpz_mod_poly_t f)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e >= 0}.

void
_fmpz_mod_poly_powmod_ui_binexp_preinv(fmpz * res, const fmpz * poly,
                              ulong e, const fmpz * f, slong lenf,
                              const fmpz * finv, slong lenfinv, const fmpz_t p)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e > 0}.
    We require \code{finv} to be the inverse of the reverse of \code{f}.

    We require \code{lenf > 1}. It is assumed that \code{poly} is already
    reduced modulo \code{f} and zero-padded as necessary to have length
    exactly \code{lenf - 1}. The output \code{res} must have room for
    \code{lenf - 1} coefficients.

void
fmpz_mod_poly_powmod_ui_binexp_preinv(fmpz_mod_poly_t res,
                         const fmpz_mod_poly_t poly, ulong e,
                         const fmpz_mod_poly_t f, const fmpz_mod_poly_t finv)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e >= 0}.
    We require \code{finv} to be the inverse of the reverse of \code{f}.

void _fmpz_mod_poly_powmod_fmpz_binexp(fmpz * res, const fmpz * poly,
				       const fmpz_t e, const fmpz * f,
				       slong lenf, const fmpz_t p)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e > 0}.

    We require \code{lenf > 1}. It is assumed that \code{poly} is already
    reduced modulo \code{f} and zero-padded as necessary to have length
    exactly \code{lenf - 1}. The output \code{res} must have room for
    \code{lenf - 1} coefficients.

void fmpz_mod_poly_powmod_fmpz_binexp(fmpz_mod_poly_t res,
				const fmpz_mod_poly_t poly, const fmpz_t e,
				const fmpz_mod_poly_t f)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e >= 0}.

void _fmpz_mod_poly_powmod_fmpz_binexp_preinv(fmpz * res, const fmpz * poly,
                                  const fmpz_t e, const fmpz * f, slong lenf,
                                  const fmpz* finv, slong lenfinv,
                                  const fmpz_t p)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e > 0}.
    We require \code{finv} to be the inverse of the reverse of \code{f}.

    We require \code{lenf > 1}. It is assumed that \code{poly} is already
    reduced modulo \code{f} and zero-padded as necessary to have length
    exactly \code{lenf - 1}. The output \code{res} must have room for
    \code{lenf - 1} coefficients.

void fmpz_mod_poly_powmod_fmpz_binexp_preinv(fmpz_mod_poly_t res,
                           const fmpz_mod_poly_t poly, const fmpz_t e,
                           const fmpz_mod_poly_t f, const fmpz_mod_poly_t finv)

    Sets \code{res} to \code{poly} raised to the power \code{e}
    modulo \code{f}, using binary exponentiation. We require \code{e >= 0}.
    We require \code{finv} to be the inverse of the reverse of \code{f}.

void
_fmpz_mod_poly_powmod_x_fmpz_preinv(fmpz * res, const fmpz_t e, const fmpz * f,
                                  slong lenf, const fmpz* finv, slong lenfinv,
                                  const fmpz_t p)

    Sets \code{res} to \code{x} raised to the power \code{e} modulo \code{f},
    using sliding window exponentiation. We require \code{e > 0}.
    We require \code{finv} to be the inverse of the reverse of \code{f}.

    We require \code{lenf > 2}. The output \code{res} must have room for
    \code{lenf - 1} coefficients.

void
fmpz_mod_poly_powmod_x_fmpz_preinv(fmpz_mod_poly_t res, const fmpz_t e,
                           const fmpz_mod_poly_t f, const fmpz_mod_poly_t finv)

    Sets \code{res} to \code{x} raised to the power \code{e}
    modulo \code{f}, using sliding window exponentiation. We require
    \code{e >= 0}. We require \code{finv} to be the inverse of the reverse of
    \code{f}.

*******************************************************************************

    Division

*******************************************************************************

void _fmpz_mod_poly_divrem_basecase(fmpz * Q, fmpz * R,
    const fmpz * A, slong lenA, const fmpz * B, slong lenB,
    const fmpz_t invB, const fmpz_t p)

    Computes \code{(Q, lenA - lenB + 1)}, \code{(R, lenA)} such that
    $A = B Q + R$ with $0 \leq \len(R) < \len(B)$.

    Assumes that the leading coefficient of $B$ is invertible
    modulo $p$, and that \code{invB} is the inverse.

    Assumes that $\len(A), \len(B) > 0$.  Allows zero-padding in
    \code{(A, lenA)}.  $R$ and $A$ may be aliased, but apart from this no
    aliasing of input and output operands is allowed.

void fmpz_mod_poly_divrem_basecase(fmpz_mod_poly_t Q, fmpz_mod_poly_t R,
    const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Computes $Q$, $R$ such that $A = B Q + R$ with
    $0 \leq \len(R) < \len(B)$.

    Assumes that the leading coefficient of $B$ is invertible
    modulo $p$.

void _fmpz_mod_poly_divrem_newton_n_preinv (fmpz* Q, fmpz* R, const fmpz* A,
                            slong lenA, const fmpz* B, slong lenB,
                            const fmpz* Binv, slong lenBinv, const fmpz_t mod)

    Computes $Q$ and $R$ such that $A = BQ + R$ with $\len(R)$ less than
    \code{lenB}, where $A$ is of length \code{lenA} and $B$ is of length
    \code{lenB}. We require that $Q$ have space for \code{lenA - lenB + 1}
    coefficients. Furthermore, we assume that $Binv$ is the inverse of the
    reverse of $B$ mod $x^{\len(B)}$. The algorithm used is to call
    \code{div_newton_n_preinv()} and then multiply out and compute
    the remainder.

void fmpz_mod_poly_divrem_newton_n_preinv(fmpz_mod_poly_t Q, fmpz_mod_poly_t R,
                               const fmpz_mod_poly_t A, const fmpz_mod_poly_t B,
                               const fmpz_mod_poly_t Binv)

    Computes $Q$ and $R$ such that $A = BQ + R$ with $\len(R) < \len(B)$.
    We assume $Binv$ is the inverse of the reverse of $B$ mod $x^{\len(B)}$.

    It is required that the length of $A$ is less than or equal to
    2*the length of $B$ - 2.

    The algorithm used is to call \code{div_newton_n()} and then multiply out
    and compute the remainder.

void _fmpz_mod_poly_div_basecase(fmpz * Q, fmpz * R,
    const fmpz * A, slong lenA, const fmpz * B, slong lenB,
    const fmpz_t invB, const fmpz_t p)

    Notationally, computes $Q$, $R$ such that $A = B Q + R$ with
    $0 \leq \len(R) < \len(B)$ but only sets \code{(Q, lenA - lenB + 1)}.

    Requires temporary space \code{(R, lenA)}.  Allows aliasing
    only between $A$ and $R$.  Allows zero-padding in $A$ but
    not in $B$.  Assumes that the leading coefficient of $B$
    is a unit modulo $p$.

void fmpz_mod_poly_div_basecase(fmpz_mod_poly_t Q,
    const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Notationally, computes $Q$, $R$ such that $A = B Q + R$ with
    $0 \leq \len(R) < \len(B)$ assuming that the leading term
    of $B$ is a unit.

void _fmpz_mod_poly_div_newton_n_preinv (fmpz* Q, const fmpz* A, slong lenA,
                                    const fmpz* B, slong lenB, const fmpz* Binv,
                                    slong lenBinv, const fmpz_t mod)

    Notionally computes polynomials $Q$ and $R$ such that $A = BQ + R$ with
    $\len(R)$ less than \code{lenB}, where \code{A} is of length \code{lenA}
    and \code{B} is of length \code{lenB}, but return only $Q$.

    We require that $Q$ have space for \code{lenA - lenB + 1} coefficients
    and assume that the leading coefficient of $B$ is a unit. Furthermore, we
    assume that $Binv$ is the inverse of the reverse of $B$ mod $x^{\len(B)}$.

    The algorithm used is to reverse the polynomials and divide the
    resulting power series, then reverse the result.

void fmpz_mod_poly_div_newton_n_preinv(fmpz_mod_poly_t Q,
                               const fmpz_mod_poly_t A, const fmpz_mod_poly_t B,
                               const fmpz_mod_poly_t Binv)

    Notionally computes $Q$ and $R$ such that $A = BQ + R$ with
    $\len(R) < \len(B)$, but returns only $Q$.

    We assume that the leading coefficient of $B$ is a unit and that $Binv$ is
    the inverse of the reverse of $B$ mod $x^{\len(B)}$.

    It is required that the length of $A$ is less than or equal to
    2*the length of $B$ - 2.

    The algorithm used is to reverse the polynomials and divide the
    resulting power series, then reverse the result.

ulong fmpz_mod_poly_remove(fmpz_mod_poly_t f, const fmpz_mod_poly_t g)

    Removes the highest possible power of \code{g} from \code{f} and
    returns the exponent.

void _fmpz_mod_poly_rem_basecase(fmpz * R,
    const fmpz * A, slong lenA, const fmpz * B, slong lenB,
    const fmpz_t invB, const fmpz_t p)

    Notationally, computes $Q$, $R$ such that $A = B Q + R$ with
    $0 \leq \len(R) < \len(B)$ but only sets \code{(R, lenA)}.

    Allows aliasing only between $A$ and $R$.  Allows zero-padding
    in $A$ but not in $B$.  Assumes that the leading coefficient
    of $B$ is a unit modulo $p$.

void fmpz_mod_poly_rem_basecase(fmpz_mod_poly_t R,
    const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Notationally, computes $Q$, $R$ such that $A = B Q + R$ with
    $0 \leq \len(R) < \len(B)$ assuming that the leading term
    of $B$ is a unit.

void _fmpz_mod_poly_divrem_divconquer_recursive(fmpz * Q, fmpz * BQ, fmpz * W,
    const fmpz * A, const fmpz * B, slong lenB,
    const fmpz_t invB, const fmpz_t p)

    Computes \code{(Q, lenB)}, \code{(BQ, 2 lenB - 1)} such that
    $BQ = B \times Q$ and $A = B Q + R$ where $0 \leq \len(R) < \len(B)$.

    Assumes that the leading coefficient of $B$ is invertible
    modulo $p$, and that \code{invB} is the inverse.

    Assumes $\len(B) > 0$.  Allows zero-padding in \code{(A, lenA)}.  Requires
    a temporary array \code{(W, 2 lenB - 1)}.  No aliasing of input and output
    operands is allowed.

    This function does not read the bottom $\len(B) - 1$ coefficients from
    $A$, which means that they might not even need to exist in allocated
    memory.

void _fmpz_mod_poly_divrem_divconquer(fmpz * Q, fmpz * R,
    const fmpz * A, slong lenA, const fmpz * B, slong lenB,
    const fmpz_t invB, const fmpz_t p)

    Computes \code{(Q, lenA - lenB + 1)}, \code{(R, lenA)} such that
    $A = B Q + R$ and $0 \leq \len(R) < \len(B)$.

    Assumes that the leading coefficient of $B$ is invertible
    modulo $p$, and that \code{invB} is the inverse.

    Assumes $\len(A) \geq \len(B) > 0$.  Allows zero-padding in
    \code{(A, lenA)}.  No aliasing of input and output operands is
    allowed.

void fmpz_mod_poly_divrem_divconquer(fmpz_mod_poly_t Q, fmpz_mod_poly_t R,
    const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Computes $Q$, $R$ such that $A = B Q + R$ and $0 \leq \len(R) < \len(B)$.

    Assumes that $B$ is non-zero and that the leading coefficient
    of $B$ is invertible modulo $p$.

void _fmpz_mod_poly_divrem(fmpz * Q, fmpz * R, const fmpz * A, slong lenA,
    const fmpz * B, slong lenB, const fmpz_t invB, const fmpz_t p)

    Computes \code{(Q, lenA - lenB + 1)}, \code{(R, lenA)} such that
    $A = B Q + R$ and $0 \leq \len(R) < \len(B)$.

    Assumes that $B$ is non-zero, that the leading coefficient
    of $B$ is invertible modulo $p$ and that \code{invB} is
    the inverse.

    Assumes $\len(A) \geq \len(B) > 0$.  Allows zero-padding in
    \code{(A, lenA)}.  No aliasing of input and output operands is
    allowed.

void fmpz_mod_poly_divrem(fmpz_mod_poly_t Q, fmpz_mod_poly_t R,
                          const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Computes $Q$, $R$ such that $A = B Q + R$ and
    $0 \leq \len(R) < \len(B)$.

    Assumes that $B$ is non-zero and that the leading coefficient
    of $B$ is invertible modulo $p$.

void fmpz_mod_poly_divrem_f(fmpz_t f, fmpz_mod_poly_t Q, fmpz_mod_poly_t R,
                            const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Either finds a non-trivial factor~$f$ of the modulus~$p$, or computes
    $Q$, $R$ such that $A = B Q + R$ and $0 \leq \len(R) < \len(B)$.

    If the leading coefficient of $B$ is invertible in $\mathbf{Z}/(p)$,
    the division with remainder operation is carried out, $Q$ and $R$ are
    computed correctly, and $f$ is set to $1$.  Otherwise, $f$ is set to
    a non-trivial factor of $p$ and $Q$ and $R$ are not touched.

    Assumes that $B$ is non-zero.

void _fmpz_mod_poly_rem(fmpz *R,
                        const fmpz *A, slong lenA, const fmpz *B, slong lenB,
                        const fmpz_t invB, const fmpz_t p)

    Notationally, computes \code{(Q, lenA - lenB + 1)}, \code{(R, lenA)}
    such that $A = B Q + R$ and $0 \leq \len(R) < \len(B)$, returning
    only the remainder part.

    Assumes that $B$ is non-zero, that the leading coefficient
    of $B$ is invertible modulo $p$ and that \code{invB} is
    the inverse.

    Assumes $\len(A) \geq \len(B) > 0$.  Allows zero-padding in
    \code{(A, lenA)}.  No aliasing of input and output operands is
    allowed.

void fmpz_mod_poly_rem(fmpz_mod_poly_t R,
                       const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Notationally, computes $Q$, $R$ such that $A = B Q + R$
    and $0 \leq \len(R) < \len(B)$, returning only the remainder
    part.

    Assumes that $B$ is non-zero and that the leading coefficient
    of $B$ is invertible modulo $p$.

*******************************************************************************

    Power series inversion

*******************************************************************************

void _fmpz_mod_poly_inv_series_newton(fmpz * Qinv, const fmpz * Q, slong n,
                                      const fmpz_t cinv, const fmpz_t p)

    Sets \code{(Qinv, n)} to the inverse of \code{(Q, n)} modulo $x^n$,
    where $n \geq 1$, assuming that the bottom coefficient of $Q$ is
    invertible modulo $p$ and that its inverse is \code{cinv}.

void fmpz_mod_poly_inv_series_newton(fmpz_mod_poly_t Qinv,
    const fmpz_mod_poly_t Q, slong n)

    Sets \code{Qinv} to the inverse of \code{Q} modulo $x^n$,
    where $n \geq 1$, assuming that the bottom coefficient of
    $Q$ is a unit.

*******************************************************************************

    Greatest common divisor

*******************************************************************************

void fmpz_mod_poly_make_monic(fmpz_mod_poly_t res, const fmpz_mod_poly_t poly)

    If \code{poly} is non-zero, sets \code{res} to \code{poly} divided
    by its leading coefficient.  This assumes that the leading coefficient
    of \code{poly} is invertible modulo $p$.

    Otherwise, if \code{poly} is zero, sets \code{res} to zero.

slong _fmpz_mod_poly_gcd_euclidean(fmpz *G, const fmpz *A, slong lenA,
                                           const fmpz *B, slong lenB,
                                           const fmpz_t invB, const fmpz_t p)

    Sets $G$ to the greatest common divisor of $(A, \len(A))$
    and $(B, \len(B))$ and returns its length.

    Assumes that $\len(A) \geq \len(B) > 0$ and that the vector $G$ has
    space for sufficiently many coefficients.

    Assumes that \code{invB} is the inverse of the leading coefficients
    of $B$ modulo the prime number $p$.

void fmpz_mod_poly_gcd_euclidean(fmpz_mod_poly_t G,
                                 const fmpz_mod_poly_t A,
                                 const fmpz_mod_poly_t B)

    Sets $G$ to the greatest common divisor of $A$ and $B$.

    The algorithm used to compute $G$ is the classical Euclidean
    algorithm.

    In general, the greatest common divisor is defined in the polynomial
    ring $(\mathbf{Z}/(p \mathbf{Z}))[X]$ if and only if $p$ is a prime
    number.  Thus, this function assumes that $p$ is prime.

slong _fmpz_mod_poly_gcd(fmpz *G, const fmpz *A, slong lenA,
                                 const fmpz *B, slong lenB,
                                 const fmpz_t invB, const fmpz_t p)

    Sets $G$ to the greatest common divisor of $(A, \len(A))$
    and $(B, \len(B))$ and returns its length.

    Assumes that $\len(A) \geq \len(B) > 0$ and that the vector $G$ has
    space for sufficiently many coefficients.

    Assumes that \code{invB} is the inverse of the leading coefficients
    of $B$ modulo the prime number $p$.

void fmpz_mod_poly_gcd(fmpz_mod_poly_t G,
                       const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Sets $G$ to the greatest common divisor of $A$ and $B$.

    In general, the greatest common divisor is defined in the polynomial
    ring $(\mathbf{Z}/(p \mathbf{Z}))[X]$ if and only if $p$ is a prime
    number.  Thus, this function assumes that $p$ is prime.

slong _fmpz_mod_poly_gcd_euclidean_f(fmpz_t f, fmpz *G,
    const fmpz *A, slong lenA, const fmpz *B, slong lenB, const fmpz_t p)

    Either sets $f = 1$ and $G$ to the greatest common divisor
    of $(A, \len(A))$ and $(B, \len(B))$ and returns its length,
    or sets $f \in (1,p)$ to a non-trivial factor of $p$ and
    leaves the contents of the vector $(G, lenB)$ undefined.

    Assumes that $\len(A) \geq \len(B) > 0$ and that the vector $G$ has
    space for sufficiently many coefficients.

    Does not support aliasing of any of the input arguments
    with any of the output argument.

void fmpz_mod_poly_gcd_euclidean_f(fmpz_t f, fmpz_mod_poly_t G,
    const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Either sets $f = 1$ and $G$ to the greatest common divisor
    of $A$ and $B$, or $ \in (1,p)$ to a non-trivial factor of $p$.

    In general, the greatest common divisor is defined in the polynomial
    ring $(\mathbf{Z}/(p \mathbf{Z}))[X]$ if and only if $p$ is a prime
    number.

slong _fmpz_mod_poly_gcd_f(fmpz_t f, fmpz *G, const fmpz *A, slong lenA,
                          const fmpz *B, slong lenB, const fmpz_t p)

    Either sets $f = 1$ and $G$ to the greatest common divisor
    of $(A, \len(A))$ and $(B, \len(B))$ and returns its length,
    or sets $f \in (1,p)$ to a non-trivial factor of $p$ and
    leaves the contents of the vector $(G, lenB)$ undefined.

    Assumes that $\len(A) \geq \len(B) > 0$ and that the vector $G$ has
    space for sufficiently many coefficients.

    Does not support aliasing of any of the input arguments
    with any of the output argument.

void fmpz_mod_poly_gcd_f(fmpz_t f, fmpz_mod_poly_t G,
                         const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Either sets $f = 1$ and $G$ to the greatest common divisor
    of $A$ and $B$, or $ \in (1,p)$ to a non-trivial factor of $p$.

    In general, the greatest common divisor is defined in the polynomial
    ring $(\mathbf{Z}/(p \mathbf{Z}))[X]$ if and only if $p$ is a prime
    number.

slong _fmpz_mod_poly_xgcd_euclidean(fmpz *G, fmpz *S, fmpz *T,
                                   const fmpz *A, slong lenA,
                                   const fmpz *B, slong lenB,
                                   const fmpz_t invB, const fmpz_t p)

    Computes the GCD of $A$ and $B$ together with cofactors $S$ and $T$
    such that $S A + T B = G$.  Returns the length of $G$.

    Assumes that $\len(A) \geq \len(B) \geq 1$ and
    $(\len(A),\len(B)) \neq (1,1)$.

    No attempt is made to make the GCD monic.

    Requires that $G$ have space for $\len(B)$ coefficients.  Writes
    $\len(B)-1$ and $\len(A)-1$ coefficients to $S$ and $T$, respectively.
    Note that, in fact, $\len(S) \leq \max(\len(B) - \len(G), 1)$ and
    $\len(T) \leq \max(\len(A) - \len(G), 1)$.

    No aliasing of input and output operands is permitted.

void fmpz_mod_poly_xgcd_euclidean(fmpz_mod_poly_t G,
                             fmpz_mod_poly_t S, fmpz_mod_poly_t T,
                             const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Computes the GCD of $A$ and $B$. The GCD of zero polynomials is
    defined to be zero, whereas the GCD of the zero polynomial and some other
    polynomial $P$ is defined to be $P$. Except in the case where
    the GCD is zero, the GCD $G$ is made monic.

    Polynomials \code{S} and \code{T} are computed such that
    \code{S*A + T*B = G}. The length of \code{S} will be at most
    \code{lenB} and the length of \code{T} will be at most \code{lenA}.

slong _fmpz_mod_poly_xgcd(fmpz *G, fmpz *S, fmpz *T,
                         const fmpz *A, slong lenA,
                         const fmpz *B, slong lenB,
                         const fmpz_t invB, const fmpz_t p)

    Computes the GCD of $A$ and $B$ together with cofactors $S$ and $T$
    such that $S A + T B = G$.  Returns the length of $G$.

    Assumes that $\len(A) \geq \len(B) \geq 1$ and
    $(\len(A),\len(B)) \neq (1,1)$.

    No attempt is made to make the GCD monic.

    Requires that $G$ have space for $\len(B)$ coefficients.  Writes
    $\len(B)-1$ and $\len(A)-1$ coefficients to $S$ and $T$, respectively.
    Note that, in fact, $\len(S) \leq \max(\len(B) - \len(G), 1)$ and
    $\len(T) \leq \max(\len(A) - \len(G), 1)$.

    No aliasing of input and output operands is permitted.

void fmpz_mod_poly_xgcd(fmpz_mod_poly_t G,
                        fmpz_mod_poly_t S, fmpz_mod_poly_t T,
                        const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Computes the GCD of $A$ and $B$. The GCD of zero polynomials is
    defined to be zero, whereas the GCD of the zero polynomial and some other
    polynomial $P$ is defined to be $P$. Except in the case where
    the GCD is zero, the GCD $G$ is made monic.

    Polynomials \code{S} and \code{T} are computed such that
    \code{S*A + T*B = G}. The length of \code{S} will be at most
    \code{lenB} and the length of \code{T} will be at most \code{lenA}.

slong _fmpz_mod_poly_gcdinv(fmpz *G, fmpz *S,
                         const fmpz *A, slong lenA, const fmpz *B, slong lenB,
                         const fmpz_t p)

    Computes \code{(G, lenA)}, \code{(S, lenB-1)} such that
    $G \cong S A \pmod{B}$, returning the actual length of $G$.

    Assumes that $0 < \len(A) < \len(B)$.

void fmpz_mod_poly_gcdinv(fmpz_mod_poly_t G, fmpz_mod_poly_t S,
                          const fmpz_mod_poly_t A, const fmpz_mod_poly_t B)

    Computes polynomials $G$ and $S$, both reduced modulo~$B$,
    such that $G \cong S A \pmod{B}$, where $B$ is assumed to
    have $\len(B) \geq 2$.

    In the case that $A = 0 \pmod{B}$, returns $G = S = 0$.

int _fmpz_mod_poly_invmod(fmpz *A,
                          const fmpz *B, slong lenB,
                          const fmpz *P, slong lenP, const fmpz_t p)

    Attempts to set \code{(A, lenP-1)} to the inverse of \code{(B, lenB)}
    modulo the polynomial \code{(P, lenP)}.  Returns $1$ if \code{(B, lenB)}
    is invertible and $0$ otherwise.

    Assumes that $0 < \len(B) < \len(P)$, and hence also $\len(P) \geq 2$,
    but supports zero-padding in \code{(B, lenB)}.

    Does not support aliasing.

    Assumes that $p$ is a prime number.

int fmpz_mod_poly_invmod(fmpz_mod_poly_t A,
                         const fmpz_mod_poly_t B, const fmpz_mod_poly_t P)

    Attempts to set $A$ to the inverse of $B$ modulo $P$ in the polynomial
    ring $(\mathbf{Z}/p\mathbf{Z})[X]$, where we assume that $p$ is a prime
    number.

    If $\deg(P) < 2$, raises an exception.

    If the greatest common divisor of $B$ and $P$ is~$1$, returns~$1$ and
    sets $A$ to the inverse of $B$.  Otherwise, returns~$0$ and the value
    of $A$ on exit is undefined.

*******************************************************************************

    Derivative

*******************************************************************************

void _fmpz_mod_poly_derivative(fmpz *res, const fmpz *poly, slong len,
                               const fmpz_t p)

    Sets \code{(res, len - 1)} to the derivative of \code{(poly, len)}.
    Also handles the cases where \code{len} is $0$ or $1$ correctly.
    Supports aliasing of \code{res} and \code{poly}.

void fmpz_mod_poly_derivative(fmpz_mod_poly_t res, const fmpz_mod_poly_t poly)

    Sets \code{res} to the derivative of \code{poly}.

*******************************************************************************

    Evaluation

*******************************************************************************

void _fmpz_mod_poly_evaluate_fmpz(fmpz_t res, const fmpz *poly, slong len,
                                  const fmpz_t a, const fmpz_t p)

    Evaluates the polynomial \code{(poly, len)} at the integer $a$ and sets
    \code{res} to the result.  Aliasing between \code{res} and $a$ or any
    of the coefficients of \code{poly} is not supported.

void fmpz_mod_poly_evaluate_fmpz(fmpz_t res,
                                 const fmpz_mod_poly_t poly, const fmpz_t a)

    Evaluates the polynomial \code{poly} at the integer $a$ and sets
    \code{res} to the result.

    As expected, aliasing between \code{res} and $a$ is supported.  However,
    \code{res} may not be aliased with a coefficient of \code{poly}.

*******************************************************************************

    Multipoint evaluation

*******************************************************************************

void _fmpz_mod_poly_evaluate_fmpz_vec_iter(fmpz * ys, const fmpz * coeffs,
                        slong len, const fmpz * xs, slong n, const fmpz_t mod)

    Evaluates (\code{coeffs}, \code{len}) at the \code{n} values
    given in the vector \code{xs}, writing the output values
    to \code{ys}. The values in \code{xs} should be reduced
    modulo the modulus.

    Uses Horner's method iteratively.

void fmpz_mod_poly_evaluate_fmpz_vec_iter(fmpz * ys,
                        const fmpz_mod_poly_t poly, const fmpz * xs, slong n)

    Evaluates \code{poly} at the \code{n} values given in the vector
    \code{xs}, writing the output values to \code{ys}. The values in
    \code{xs} should be reduced modulo the modulus.

    Uses Horner's method iteratively.

void _fmpz_mod_poly_evaluate_fmpz_vec_fast_precomp(fmpz * vs,
              const fmpz * poly, slong plen, fmpz_poly_struct * const * tree,
                                                 slong len, const fmpz_t mod)
    Evaluates (\code{poly}, \code{plen}) at the \code{len} values given
    by the precomputed subproduct tree \code{tree}.

void _fmpz_mod_poly_evaluate_fmpz_vec_fast(fmpz * ys,
    const fmpz * poly, slong plen, const fmpz * xs, slong n, const fmpz_t mod)

    Evaluates (\code{coeffs}, \code{len}) at the \code{n} values
    given in the vector \code{xs}, writing the output values
    to \code{ys}. The values in \code{xs} should be reduced
    modulo the modulus.

    Uses fast multipoint evaluation, building a temporary subproduct tree.

void fmpz_mod_poly_evaluate_fmpz_vec_fast(fmpz * ys,
                        const fmpz_mod_poly_t poly, const fmpz * xs, slong n)

    Evaluates \code{poly} at the \code{n} values given in the vector
    \code{xs}, writing the output values to \code{ys}. The values in
    \code{xs} should be reduced modulo the modulus.

    Uses fast multipoint evaluation, building a temporary subproduct tree.

void _fmpz_mod_poly_evaluate_fmpz_vec(fmpz * ys, const fmpz * coeffs,
                        slong len, const fmpz * xs, slong n, const fmpz_t mod)

    Evaluates (\code{coeffs}, \code{len}) at the \code{n} values
    given in the vector \code{xs}, writing the output values
    to \code{ys}. The values in \code{xs} should be reduced
    modulo the modulus.

void fmpz_mod_poly_evaluate_fmpz_vec(fmpz * ys,
                        const fmpz_mod_poly_t poly, const fmpz * xs, slong n)

    Evaluates \code{poly} at the \code{n} values given in the vector
    \code{xs}, writing the output values to \code{ys}. The values in
    \code{xs} should be reduced modulo the modulus.

*******************************************************************************

    Composition

*******************************************************************************

void _fmpz_mod_poly_compose_horner(fmpz *res, const fmpz *poly1, slong len1,
                                              const fmpz *poly2, slong len2,
                                              const fmpz_t p)

    Sets \code{res} to the composition of \code{(poly1, len1)} and
    \code{(poly2, len2)} using Horner's algorithm.

    Assumes that \code{res} has space for \code{(len1-1)*(len2-1) + 1}
    coefficients, although in $\mathbf{Z}_p[X]$ this might not actually
    be the length of the resulting polynomial when $p$ is not a prime.

    Assumes that \code{poly1} and \code{poly2} are non-zero polynomials.
    Does not support aliasing between any of the inputs and the output.

void fmpz_mod_poly_compose_horner(fmpz_mod_poly_t res,
                                  const fmpz_mod_poly_t poly1,
                                  const fmpz_mod_poly_t poly2)

    Sets \code{res} to the composition of \code{poly1} and \code{poly2}
    using Horner's algorithm.

    To be precise about the order of composition, denoting \code{res},
    \code{poly1}, and \code{poly2} by $f$, $g$, and $h$, respectively,
    sets $f(t) = g(h(t))$.

void _fmpz_mod_poly_compose_divconquer(fmpz *res,
	const fmpz *poly1, slong len1, const fmpz *poly2, slong len2, const fmpz_t p)

    Sets \code{res} to the composition of \code{(poly1, len1)} and
    \code{(poly2, len2)} using a divide and conquer algorithm which
    takes out factors of \code{poly2} raised to $2^i$ where possible.

    Assumes that \code{res} has space for \code{(len1-1)*(len2-1) + 1}
    coefficients, although in $\mathbf{Z}_p[X]$ this might not actually
    be the length of the resulting polynomial when $p$ is not a prime.

    Assumes that \code{poly1} and \code{poly2} are non-zero polynomials.
    Does not support aliasing between any of the inputs and the output.

void fmpz_mod_poly_compose_divconquer(fmpz_mod_poly_t res,
                                      const fmpz_mod_poly_t poly1,
                                      const fmpz_mod_poly_t poly2)

    Sets \code{res} to the composition of \code{poly1} and \code{poly2}
    using a divide and conquer algorithm which takes out factors of
    \code{poly2} raised to $2^i$ where possible.

    To be precise about the order of composition, denoting \code{res},
    \code{poly1}, and \code{poly2} by $f$, $g$, and $h$, respectively,
    sets $f(t) = g(h(t))$.

void _fmpz_mod_poly_compose(fmpz *res, const fmpz *poly1, slong len1,
                                       const fmpz *poly2, slong len2,
                                       const fmpz_t p)

    Sets \code{res} to the composition of \code{(poly1, len1)} and
    \code{(poly2, len2)}.

    Assumes that \code{res} has space for \code{(len1-1)*(len2-1) + 1}
    coefficients, although in $\mathbf{Z}_p[X]$ this might not actually
    be the length of the resulting polynomial when $p$ is not a prime.

    Assumes that \code{poly1} and \code{poly2} are non-zero polynomials.
    Does not support aliasing between any of the inputs and the output.

void fmpz_mod_poly_compose(fmpz_mod_poly_t res, const fmpz_mod_poly_t poly1,
                                                const fmpz_mod_poly_t poly2)

    Sets \code{res} to the composition of \code{poly1} and \code{poly2}.

    To be precise about the order of composition, denoting \code{res},
    \code{poly1}, and \code{poly2} by $f$, $g$, and $h$, respectively,
    sets $f(t) = g(h(t))$.

*******************************************************************************

    Modular composition

*******************************************************************************

void _fmpz_mod_poly_compose_mod(fmpz * res,
	                           const fmpz * f, slong lenf, const fmpz * g,
				   const fmpz * h, slong lenh, const fmpz_t p)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero and that the length of $g$ is one less than the
    length of $h$ (possibly with zero padding). The output is not allowed
    to be aliased with any of the inputs.

void
fmpz_mod_poly_compose_mod(fmpz_mod_poly_t res, const fmpz_mod_poly_t f,
		    const fmpz_mod_poly_t g, const fmpz_mod_poly_t h)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero.

void _fmpz_mod_poly_compose_mod_horner(fmpz * res,
	                      const fmpz * f, slong lenf, const fmpz * g,
					  const fmpz * h, slong lenh, const fmpz_t p)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero and that the length of $g$ is one less than the
    length of $h$ (possibly with zero padding). The output is not allowed
    to be aliased with any of the inputs.

    The algorithm used is Horner's rule.

void
fmpz_mod_poly_compose_mod_horner(fmpz_mod_poly_t res, const fmpz_mod_poly_t f,
			   const fmpz_mod_poly_t g, const fmpz_mod_poly_t h)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero. The algorithm used is Horner's rule.

void
_fmpz_mod_poly_compose_mod_brent_kung(fmpz * res, const fmpz * f, slong len1,
                    const fmpz * g, const fmpz * h, slong len3, const fmpz_t p)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero and that the length of $g$ is one less than the
    length of $h$ (possibly with zero padding). We also require that
    the length of $f$ is less than the length of $h$. The output is not
    allowed to be aliased with any of the inputs.

    The algorithm used is the Brent-Kung matrix algorithm.

void fmpz_mod_poly_compose_mod_brent_kung(
	                       fmpz_mod_poly_t res, const fmpz_mod_poly_t f,
			       const fmpz_mod_poly_t g, const fmpz_mod_poly_t h)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero and that $f$ has smaller degree than $h$.
    The algorithm used is the Brent-Kung matrix algorithm.

void
_fmpz_mod_poly_reduce_matrix_mod_poly (fmpz_mat_t A, const fmpz_mat_t B,
                                   const fmpz_mod_poly_t f)

    Sets the ith row of \code{A} to the reduction of the ith row of $B$ modulo
    $f$ for $i=1,\ldots,\sqrt{\deg(f)}$. We require $B$ to be at least
    a $\sqrt{\deg(f)}\times \deg(f)$ matrix and $f$ to be nonzero.

void
_fmpz_mod_poly_precompute_matrix (fmpz_mat_t A, const fmpz * f,
                          const fmpz * g, slong leng, const fmpz * ginv,
                          slong lenginv, const fmpz_t p)

    Sets the ith row of \code{A} to $f^i$ modulo $g$ for
    $i=1,\ldots,\sqrt{\deg(g)}$. We require $A$ to be
    a $\sqrt{\deg(g)}\times \deg(g)$ matrix. We require
    \code{ginv} to be the inverse of the reverse of \code{g} and $g$ to be
    nonzero.

void
fmpz_mod_poly_precompute_matrix(fmpz_mat_t A, const fmpz_mod_poly_t f,
                   const fmpz_mod_poly_t g, const fmpz_mod_poly_t ginv)

    Sets the ith row of \code{A} to $f^i$ modulo $g$ for
    $i=1,\ldots,\sqrt{\deg(g)}$. We require $A$ to be
    a $\sqrt{\deg(g)}\times \deg(g)$ matrix. We require
    \code{ginv} to be the inverse of the reverse of \code{g}.

void
_fmpz_mod_poly_compose_mod_brent_kung_precomp_preinv(fmpz * res,
         const fmpz * f, slong lenf, const fmpz_mat_t A, const fmpz * h,
         slong lenh, const fmpz * hinv, slong lenhinv, const fmpz_t p)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero. We require that the ith row of $A$ contains $g^i$ for
    $i=1,\ldots,\sqrt{\deg(h)}$, i.e. $A$ is a
    $\sqrt{\deg(h)}\times \deg(h)$ matrix. We also require that
    the length of $f$ is less than the length of $h$. Furthermore, we require
    \code{hinv} to be the inverse of the reverse of \code{h}.
    The output is not allowed to be aliased with any of the inputs.

    The algorithm used is the Brent-Kung matrix algorithm.

void
fmpz_mod_poly_compose_mod_brent_kung_precomp_preinv(fmpz_mod_poly_t res,
                   const fmpz_mod_poly_t f, const fmpz_mat_t A,
                   const fmpz_mod_poly_t h, const fmpz_mod_poly_t hinv)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that the
    ith row of $A$ contains $g^i$ for $i=1,\ldots,\sqrt{\deg(h)}$, i.e. $A$ is
    a $\sqrt{\deg(h)}\times \deg(h)$ matrix. We require that $h$ is nonzero and
    that $f$ has smaller degree than $h$. Furthermore, we require \code{hinv}
    to be the inverse of the reverse of \code{h}. This version of Brent-Kung
    modular composition is particularly useful if one has to perform several
    modular composition of the form $f(g)$ modulo $h$ for fixed $g$ and $h$.

void
_fmpz_mod_poly_compose_mod_brent_kung_preinv(fmpz * res, const fmpz * f,
                 slong lenf, const fmpz * g, const fmpz * h, slong lenh,
                 const fmpz * hinv, slong lenhinv, const fmpz_t p)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero and that the length of $g$ is one less than the
    length of $h$ (possibly with zero padding). We also require that
    the length of $f$ is less than the length of $h$. Furthermore, we require
    \code{hinv} to be the inverse of the reverse of \code{h}.
    The output is not allowed to be aliased with any of the inputs.

    The algorithm used is the Brent-Kung matrix algorithm.

void
fmpz_mod_poly_compose_mod_brent_kung_preinv(fmpz_mod_poly_t res,
                   const fmpz_mod_poly_t f, const fmpz_mod_poly_t g,
                   const fmpz_mod_poly_t h, const fmpz_mod_poly_t hinv)

    Sets \code{res} to the composition $f(g)$ modulo $h$. We require that
    $h$ is nonzero and that $f$ has smaller degree than $h$. Furthermore,
    we require \code{hinv} to be the inverse of the reverse of \code{h}.
    The algorithm used is the Brent-Kung matrix algorithm.

*******************************************************************************

    Subproduct trees

*******************************************************************************

fmpz_poly_struct ** _fmpz_mod_poly_tree_alloc(slong len)

    Allocates space for a subproduct tree of the given length, having
    linear factors at the lowest level.

void _fmpz_mod_poly_tree_free(fmpz_poly_struct ** tree, slong len)

    Free the allocated space for the subproduct.

void _fmpz_mod_poly_tree_build(fmpz_poly_struct ** tree,
                             const fmpz * roots, slong len, const fmpz_t mod)

    Builds a subproduct tree in the preallocated space from
    the \code{len} monic linear factors $(x-r_i)$ where $r_i$ are given by
    \code{roots}. The top level product is not computed.

*******************************************************************************

    Radix conversion

    The following functions provide the functionality to solve the
    radix conversion problems for polynomials, which is to express
    a polynomial $f(X)$ with respect to a given radix $r(X)$ as
    \begin{equation*}
    f(X) = \sum_{i = 0}^{N} b_i(X) r(X)^i
    \end{equation*}
    where $N = \floor{\deg(f) / \deg(r)}$.

    The algorithm implemented here is a recursive one, which performs
    Euclidean divisions by powers of $r$ of the form $r^{2^i}$, and it
    has time complexity $\Theta(\deg(f) \log \deg(f))$.

    It facilitates the repeated use of precomputed data, namely the
    powers of $r$ and their power series inverses.  This data is stored
    in objects of type \code{fmpz_mod_poly_radix_t} and it is computed
    using the function \code{fmpz_mod_poly_radix_init()}, which only
    depends on~$r$ and an upper bound on the degree of~$f$.

*******************************************************************************

void _fmpz_mod_poly_radix_init(fmpz **Rpow, fmpz **Rinv,
                    const fmpz *R, slong lenR, slong k,
                    const fmpz_t invL, const fmpz_t p)

    Computes powers of $R$ of the form $R^{2^i}$ and their Newton inverses
    modulo $x^{2^{i} \deg(R)}$ for $i = 0, \dotsc, k-1$.

    Assumes that the vectors \code{Rpow[i]} and \code{Rinv[i]} have space
    for $2^i \deg(R) + 1$ and $2^i \deg(R)$ coefficients, respectively.

    Assumes that the polynomial $R$ is non-constant, i.e.\ $\deg(R) \geq 1$.

    Assumes that the leading coefficient of $R$ is a unit and that the
    argument \code{invL} is the inverse of the coefficient modulo~$p$.

    The argument~$p$ is the modulus, which in $p$-adic applications is
    typically a prime power, although this is not necessary.  Here, we
    only assume that $p \geq 2$.

    Note that this precomputed data can be used for any $F$ such that
    $\len(F) \leq 2^k \deg(R)$.

void fmpz_mod_poly_radix_init(fmpz_mod_poly_radix_t D,
                              const fmpz_mod_poly_t R, slong degF)

    Carries out the precomputation necessary to perform radix conversion
    to radix~$R$ for polynomials~$F$ of degree at most \code{degF}.

    Assumes that $R$ is non-constant, i.e.\ $\deg(R) \geq 1$,
    and that the leading coefficient is a unit.

void _fmpz_mod_poly_radix(fmpz **B, const fmpz *F, fmpz **Rpow, fmpz **Rinv,
                        slong degR, slong k, slong i, fmpz *W, const fmpz_t p)

    This is the main recursive function used by the
    function \code{fmpz_mod_poly_radix()}.

    Assumes that, for all $i = 0, \dotsc, N$, the vector
    \code{B[i]} has space for $\deg(R)$ coefficients.

    The variable $k$ denotes the factors of $r$ that have
    previously been counted for the polynomial $F$, which
    is assumed to have length $2^{i+1} \deg(R)$, possibly
    including zero-padding.

    Assumes that $W$ is a vector providing temporary space
    of length $\len(F) = 2^{i+1} \deg(R)$.

    The entire computation takes place over $\mathbf{Z} / p \mathbf{Z}$,
    where $p \geq 2$ is a natural number.

    Thus, the top level call will have $F$ as in the original
    problem, and $k = 0$.

void fmpz_mod_poly_radix(fmpz_mod_poly_struct **B, const fmpz_mod_poly_t F,
                         const fmpz_mod_poly_radix_t D)

    Given a polynomial $F$ and the precomputed data $D$ for the radix $R$,
    computes polynomials $B_0, \dotsc, B_N$ of degree less than $\deg(R)$
    such that
    \begin{equation*}
    F = B_0 + B_1 R + \dotsb + B_N R^N,
    \end{equation*}
    where necessarily $N = \floor{\deg(F) / \deg(R)}$.

    Assumes that $R$ is non-constant, i.e.\ $\deg(R) \geq 1$,
    and that the leading coefficient is a unit.

*******************************************************************************

    Input and output

    The printing options supported by this module are very similar to
    what can be found in the two related modules \code{fmpz_poly} and
    \code{nmod_poly}.

    Consider, for example, the polynomial $f(x) = 5x^3 + 2x + 1$ in
    $(\mathbf{Z}/6\mathbf{Z})[x]$.  Its simple string representation
    is \code{"4 6  1 2 0 5"}, where the first two numbers denote the
    length of the polynomial and the modulus.  The pretty string
    representation is \code{"5*x^3+2*x+1"}.

*******************************************************************************

int _fmpz_mod_poly_fprint(FILE * file, const fmpz *poly, slong len,
                          const fmpz_t p)

    Prints the polynomial \code{(poly, len)} to the stream \code{file}.

    In case of success, returns a positive value.  In case of failure,
    returns a non-positive value.

int fmpz_mod_poly_fprint(FILE * file, const fmpz_mod_poly_t poly)

    Prints the polynomial to the stream \code{file}.

    In case of success, returns a positive value.  In case of failure,
    returns a non-positive value.

int fmpz_mod_poly_fprint_pretty(FILE * file,
                                const fmpz_mod_poly_t poly, const char * x)

    Prints the pretty representation of \code{(poly, len)} to the stream
    \code{file}, using the string \code{x} to represent the indeterminate.

    In case of success, returns a positive value.  In case of failure,
    returns a non-positive value.

int fmpz_mod_poly_print(const fmpz_mod_poly_t poly)

    Prints the polynomial to \code{stdout}.

    In case of success, returns a positive value.  In case of failure,
    returns a non-positive value.

int fmpz_mod_poly_print_pretty(const fmpz_mod_poly_t poly, const char * x)

    Prints the pretty representation of \code{poly} to \code{stdout},
    using the string \code{x} to represent the indeterminate.

    In case of success, returns a positive value.  In case of failure,
    returns a non-positive value.