custom iterator for custom container - c++

I am designing a container that is a grid, represented as a 1D array (templated). I am posting here an extract of the code, there is actually more to it. It is used as a rolling occupancy grid in a robotic application, where each cell represents a small area of the world.
One operation I do frequently with that grid is to go through all the cells and also retrieve their world coordinates:
for( unsigned r=0; r<mygrid.rows_; ++r ) {
for( unsigned c=0; c<mygrid.cols_; ++c ) {
cell = mygrid.getRC(r,c);
mygrid.rcToXY(r,c,&x,&y);
}
}
I would like to have an iterator than stores all of these: the cell, its rc coordinates and its xy coordinates.
for( Grid<CellType>::const_iterator it=mygrid.begin(); it!=mygrid.end(); ++it ) {
cell = *it;
printf("%d %d %f %f\n", it.r(), it.c(), it.x(), it.y());
}
Following numerous answers and tutorials online I came up with the following implementation, which works. However it seems a bit clumsy to me, and for academic sake I'd like to make it look better. Also STL compatibility would be great.
template <class G, typename C>
class base_iterator
{
private:
G* grid_;
C* cell_;
unsigned r_, c_; // local
double x_, y_;
// this should be private with access for friends (Grid) only
// but I can't make it work
public:
base_iterator(G* grid, unsigned r, unsigned c) : grid_(grid), r_(r), c_(c)
{
cell_ = ( r<grid->rows_ && c<grid->cols_ ) ? &grid_->getRC(r,c) : 0;
grid_->rcToXY(r,c,&x_,&y_);
}
public:
base_iterator() : grid_(0) { }
// used to cast an iterator to a const_iterator
template <class G2, typename C2>
base_iterator(const base_iterator<G2,C2>& other)
{
grid_ = other.grid();
cell_ = & other.cell();
r_ = other.r();
c_ = other.c();
x_ = other.x();
y_ = other.y();
}
// this should be private with access for friends only
G* grid() const { return grid_; }
C& cell() { return *cell_; }
const C& cell() const { return *cell_; }
unsigned r() const { return r_; }
unsigned c() const { return c_; }
double x() const { return x_; }
double y() const { return y_; }
C* operator->() { return cell_; }
const C* operator->() const { return cell_; }
C& operator*() { return *cell_; }
const C& operator*() const { return *cell_; }
//prefix
base_iterator & operator++()
{
// my iteration logic here which needs access to grid
// in order to find the number of rows, etc.
return *this;
}
//postfix
base_iterator operator++(int)
{
base_iterator it(*this); // make a copy for result
++(*this); // Now use the prefix version to do the work
return it; // return the copy (the old) value.
}
template <class G2, typename C2>
bool operator==(const base_iterator<G2,C2> & other) const
{
return cell_ == &other.cell();
}
template <class G2, typename C2>
bool operator!=(const base_iterator<G2,C2>& other) const
{ return cell_!=other.cell(); }
};
And then in my grid class:
typedef base_iterator<Grid<T>,T> iterator;
typedef base_iterator<Grid<T> const, T const> const_iterator;
iterator begin() { return iterator(this,0,0); }
iterator end() { return iterator(this,rows_,cols_); }
const_iterator begin() const { return const_iterator(this,0,0); }
const_iterator end() const { return const_iterator(this,rows_,cols_); }
Again, this works, but I feel that it's a bit clumsy (see the comments in the iterator code), and I'd like to know how I can improve it. I saw numerous posts about using boost iterator facade or adaptor, but I could not figure out how to adapt it to my case.

Well I found one solution, that I am quite satisfied with. Here is the full listing for reference. There are some tricky parts that took me some time, in particular in order to be able to take the implementation outside of the class declarations. I haven't managed to make class base_iterator a non-nested class of Grid, according to what I read here and there, I think it's not possible.
#include <cstdio>
#include <cassert>
#include <stdexcept>
#include <algorithm>
template <class T>
class Grid
{
public:
// these should be private, with public getters...
double resolution_;
unsigned rows_, cols_;
int map_r0_, map_c0_; // grid coordinates of origin of map
private:
T* cell_;
public:
Grid(double resolution, unsigned rows, unsigned cols);
~Grid() { delete[] cell_; }
T & getRC(unsigned r, unsigned c);
const T & getRC(unsigned r, unsigned c) const;
void rcToXY(unsigned r, unsigned c, double* x, double* y) const;
public:
template <class GridType, class CellType>
class base_iterator : std::iterator<std::forward_iterator_tag, CellType>
{
private:
friend class Grid;
GridType* grid_;
CellType* cell_;
unsigned r_, c_; // local
double x_, y_;
base_iterator(GridType* grid, unsigned r, unsigned c);
public:
base_iterator() : grid_(0) { }
template <class G2, class C2>
base_iterator(const base_iterator<G2,C2>& other);
CellType& cell() { return *cell_; }
const CellType& cell() const { return *cell_; }
unsigned r() const { return r_; }
unsigned c() const { return c_; }
double x() const { return x_; }
double y() const { return y_; }
CellType* operator->() { return cell_; }
const CellType* operator->() const { return cell_; }
CellType& operator*() { return *cell_; }
const CellType& operator*() const { return *cell_; }
//prefix
base_iterator & operator++();
//postfix
base_iterator operator++(int);
template <class G2, class C2>
bool operator==(const base_iterator<G2,C2> & other) const
{ return cell_ == other.cell_; }
template <class G2, class C2>
bool operator!=(const base_iterator<G2,C2>& other) const
{ return cell_ != other.cell_; }
};
typedef base_iterator<Grid<T>,T> iterator;
typedef base_iterator<Grid<T> const, T const> const_iterator;
iterator begin() { return iterator(this,0,0); }
iterator end() { return iterator(this,rows_,0); }
const_iterator begin() const { return const_iterator(this,0,0); }
const_iterator end() const { return const_iterator(this,rows_,0); }
};
template <class T>
Grid<T>::Grid(double resolution, unsigned rows, unsigned cols)
: resolution_(resolution), rows_(rows), cols_(cols), map_r0_(0), map_c0_(0)
{
cell_ = new T[rows_*cols_];
}
template <class T>
T & Grid<T>::getRC(unsigned r, unsigned c)
{
if (r >= rows_ || c >= cols_)
throw std::runtime_error("Out of bounds");
return cell_[r * cols_ + c];
}
template <class T>
const T & Grid<T>::getRC(unsigned r, unsigned c) const
{
if (r >= rows_ || c >= cols_)
throw std::runtime_error("Out of bounds");
return cell_[r * cols_ + c];
}
template <class T>
void Grid<T>::rcToXY(unsigned r, unsigned c, double* x, double* y) const
{
*x = (map_c0_ + c + 0.5) * resolution_;
*y = (map_r0_ + r + 0.5) * resolution_;
}
template <class T>
template <class GridType, class CellType>
Grid<T>::base_iterator<GridType,CellType>::base_iterator(GridType* grid, unsigned r, unsigned c)
: grid_(grid), r_(r), c_(c)
{
if( r<grid->rows_ && c<grid->cols_ ) {
cell_ = &grid_->getRC(r,c);
grid_->rcToXY(r,c,&x_,&y_);
}
else
cell_ = &grid_->getRC(grid->rows_-1,grid->cols_-1) + 1;
}
// beautiful triple template declaration !
template <class T>
template <class GridType, class CellType>
template <class G2, class C2>
Grid<T>::base_iterator<GridType,CellType>::base_iterator(const Grid<T>::base_iterator<G2,C2>& other)
{
grid_ = other.grid_;
cell_ = other.cell_;
r_ = other.r();
c_ = other.c();
x_ = other.x();
y_ = other.y();
}
template <class T>
template <class GridType, class CellType>
Grid<T>::base_iterator<GridType,CellType> & Grid<T>::base_iterator<GridType,CellType>::operator++()
{
assert( grid_!=0 );
if( c_==grid_->cols_-1 )
{
c_ = 0;
x_ = (grid_->map_c0_ + 0.5) * grid_->resolution_;
++r_;
y_ += grid_->resolution_;
}
else
{
++c_;
x_ += grid_->resolution_;
}
++cell_;
return *this;
}
template <class T>
template <class GridType, class CellType>
Grid<T>::base_iterator<GridType,CellType> Grid<T>::base_iterator<GridType,CellType>::operator++(int)
{
base_iterator it(*this); // make a copy for result
++(*this); // Now use the prefix version to do the work
return it; // return the copy (the old) value.
}
void print(unsigned i)
{
printf("%d ", i);
}
int main()
{
Grid<unsigned> mygrid(.1,2,3);
unsigned ctr=0;
for( Grid<unsigned>::iterator it=mygrid.begin(); it!=mygrid.end(); ++it )
*it = ctr++;
ctr = 0;
printf("All elements: r, c, x, y, value\n");
for( Grid<unsigned>::const_iterator it=mygrid.begin(); it!=mygrid.end(); ++it ) {
assert( *it == ctr++ );
printf("%d %d %f %f %d\n", it.r(), it.c(), it.x(), it.y(), *it);
}
printf("All elements values: ");
std::for_each(mygrid.begin(), mygrid.end(), print);
printf("\n");
return 0;
}

Related

Template constructor parameter base type check in C++

Im trying to write some simple math libary in C++ using Expression templates.
template <typename E1, typename E2>
class MatSum : public MatExpression<MatSum<E1, E2>> {
E1 const& _u;
E2 const& _v;
public:
MatSum(E1 const& u, E2 const& v) :_u(u), _v(v) {
assert(u.size() == v.size());
}
GLfloat operator[](size_t i) const { return _u[i] + _v[i]; }
GLfloat operator()(size_t i, size_t j) const { return _u(i,j) + _v(i,j); }
size_t size() const { return _v.size(); }
size_t width() const { return _v.width(); }
size_t height() const { return _v.height(); }
};
How can i make a construtor to check types. I need 3 constructors.
Both are MatExpression
1st is MatExpression, 2nd is Scalar
1st is scalar and 2nd is MatExpression
I understand that i need to use type_traits, but i dont understand how to use them.

Is it possible to get rid of template specialisation to stop recursion?

I'm writing my own container class that also provides iterators. These iterators can be dereferenced and reveal then a sub-range of the original container, for which again an iterator can be obtained.
Currently, I've a template iterator class (using boost::iterator_facade) that dereferences to an Collection ("range") if L!=0 or to a T& (stored elements) if L==0. Is it possible combine both in one class, such that less duplicate code is needed?
template<typename T, int L>
class CollectionIter : public boost::iterator_facade<
CollectionIter<T,L>, // type it selfe
Collection<T,L-1>, // value type
boost::random_access_traversal_tag,
Collection<T,L-1> > // deref. type
{
public:
CollectionIter(T* ptr, const std::vector<int>& collectionSize_)
: pointer(ptr), collectionSize(collectionSize_) { }
T* element() { return pointer; }
private:
friend class boost::iterator_core_access;
bool equal(const CollectionIter<T,L>& other) const { return pointer==other.pointer; }
auto dereference() const { return Collection<T,L-1>(pointer, collectionSize); }
void increment() { pointer = pointer + stepsize(); }
void decrement() { pointer = pointer - stepsize(); }
void advance(size_t i) { pointer = pointer + i*stepsize(); }
auto distance_to(const CollectionIter<T,L>& other) { return (other.pointer - pointer)/stepsize(); }
int stepsize() { return collectionSize.at(L); }
T* pointer;
const std::vector<int>& collectionSize;
};
/* Groundlevel Collection: deref returns T& */
template<typename T>
class CollectionIter<T,0> : public boost::iterator_facade<
CollectionIter<T,0>,
T,
boost::random_access_traversal_tag >
{
public:
CollectionIter(T* ptr, const std::vector<int>& collectionSize_)
: pointer(ptr), collectionSize(collectionSize_) { assert(stepsize()==1); }
T* element() { return pointer; }
private:
friend class boost::iterator_core_access;
bool equal(const CollectionIter<T,0>& other) const { return pointer==other.pointer; }
T& dereference() const { return *pointer; }
void increment() { pointer = pointer + stepsize(); }
void decrement() { pointer = pointer - stepsize(); }
void advance(size_t i) { pointer = pointer + i*stepsize(); }
auto distance_to(const CollectionIter<T,0>& other) { return (other.pointer - pointer)/stepsize(); }
int stepsize() { return collectionSize.at(0); }
T* pointer;
const std::vector<int>& collectionSize;
};
I see only three differences in the two version of CollectionIter:
(1) the boost::iterator_facade() inherited class receive different arguments. You can solve this with std::conditional as suggested by Johannes Schaub; something like
public std::conditional< (L > 0U),
boost::iterator_facade<
CollectionIter<T, L>,
Collection<T, L-1U>,
boost::random_access_traversal_tag,
Collection<T, L-1U> >,
boost::iterator_facade<
CollectionIter<T, 0U>,
T,
boost::random_access_traversal_tag > >
(2) the assert(stepsize()==1); in the constructor is present only in the ground (L == 0U) version. You can modify it as
assert( (L > 0U) || (stepsize() == 1) );
(3) the recursive dereference() method is really different in the ground version. I'm not an expert of SFINAE but, if I'm not wrong, you can insert both as follows
template <int M = L, typename = std::enable_if_t<(M > 0U)>>
auto dereference () const
{ return Collection<T, L-1U>(pointer, collectionSize); }
template <int M = L, typename = std::enable_if_t<(M == 0U)>>
T & dereference () const
{ return *pointer; }
So the full class become (sorry: I've changed L in a std::size_t)
template <typename T, std::size_t L>
class CollectionIter :
public std::conditional< (L > 0U),
boost::iterator_facade<
CollectionIter<T, L>,
Collection<T, L-1U>,
boost::random_access_traversal_tag,
Collection<T, L-1U> >,
boost::iterator_facade<
CollectionIter<T, 0U>,
T,
boost::random_access_traversal_tag > >
{
public:
CollectionIter (T * ptr, const std::vector<int> & collectionSize_)
: pointer(ptr), collectionSize(collectionSize_)
{ assert( (L > 0U) || (stepsize() == 1) ); }
T* element() { return pointer; }
private:
friend class boost::iterator_core_access;
bool equal (const CollectionIter<T, L> & other) const
{ return pointer==other.pointer; }
template <int M = L, typename = std::enable_if_t<(M > 0U)>>
auto dereference () const
{ return Collection<T, L-1U>(pointer, collectionSize); }
template <int M = L, typename = std::enable_if_t<(M == 0U)>>
T & dereference () const
{ return *pointer; }
void increment ()
{ pointer = pointer + stepsize(); }
void decrement()
{ pointer = pointer - stepsize(); }
void advance (size_t i)
{ pointer = pointer + i*stepsize(); }
auto distance_to (const CollectionIter<T, L> & other)
{ return (other.pointer - pointer)/stepsize(); }
int stepsize()
{ return collectionSize.at(L); }
T * pointer;
const std::vector<int> & collectionSize;
};

Assigning to expression templates

I have little c++ experience, but now I need to look at some code that uses expression templates a lot, so I am reading chapter 18 of the book << C++ Templates: The Complete Guide >> and working on the example provided in the book. If you happened to have the book, the example starts from pp 328, with all the contextual information.
My code works fine until I want to add the support for subvector indexing (pp 338), I could not get the assignment to work, g++ gives the following error:
error: binding ‘const value_type {aka const double}’ to reference of type ‘double&’ discards qualifiers
return v[vi[idx]];
I have no idea what's going on, am I assigning to a constant object? How do I make this work? Here is my code:
#include <iostream>
#include <vector>
template<typename T>
class ET_Scalar {
private:
const T& s;
public:
ET_Scalar(const T& v) :
s(v) {}
T operator[](size_t) const
{
return s;
}
size_t size() const
{
return 0; // Zero means it's a scalar
}
};
template<typename T, typename V, typename VI>
class ET_SubVec {
private:
const V& v;
const VI& vi;
public:
ET_SubVec(const V& a, const VI& b) :
v(a), vi(b) {}
const T operator[] (size_t idx) const
{
return v[vi[idx]];
}
T& operator[] (size_t idx)
{
return v[vi[idx]];
}
size_t size() const
{
return vi.size();
}
};
// Using std::vector as storage
template<typename T, typename Rep = std::vector<T>>
class ET_Vector {
private:
Rep expr_rep;
public:
// Create vector with initial size
explicit ET_Vector(size_t s) :
expr_rep(s) {}
ET_Vector(const Rep& v) :
expr_rep(v) {}
ET_Vector& operator=(const ET_Vector& v)
{
for (size_t i = 0; i < v.size(); i++)
expr_rep[i] = v[i];
return *this;
}
template<typename T2, typename Rep2>
ET_Vector& operator=(const ET_Vector<T2, Rep2>& v)
{
for (size_t i = 0; i < v.size(); i++)
expr_rep[i] = v[i];
return *this;
}
size_t size() const
{
return expr_rep.size();
}
const T operator[](size_t idx) const
{
return expr_rep[idx];
}
T& operator[](size_t idx)
{
return expr_rep[idx];
}
template<typename T2, typename Rep2>
ET_Vector<T, ET_SubVec<T, Rep, Rep2>> operator[](const ET_Vector<T2, Rep2>& vi)
{
return ET_Vector<T, ET_SubVec<T, Rep, Rep2>>(ET_SubVec<T, Rep, Rep2>(expr_rep, vi.rep()));
}
template<typename T2, typename Rep2>
const ET_Vector<T, ET_SubVec<T, Rep, Rep2>> operator[](const ET_Vector<T2, Rep2>& vi) const
{
return ET_Vector<T, ET_SubVec<T, Rep, Rep2>>(ET_SubVec<T, Rep, Rep2>(expr_rep, vi.rep()));
}
// Return what the vector currently represents
const Rep& rep() const
{
return expr_rep;
}
Rep& rep()
{
return expr_rep;
}
};
template<typename T>
class ET_Traits {
public:
typedef const T& ExprRef;
};
template<typename T>
class ET_Traits<ET_Scalar<T>> {
public:
typedef ET_Scalar<T> ExprRef;
};
template<typename T, typename LHS, typename RHS>
class ET_Add {
private:
typename ET_Traits<LHS>::ExprRef lhs;
typename ET_Traits<RHS>::ExprRef rhs;
public:
ET_Add(const LHS& l, const RHS& r) :
lhs(l), rhs(r) {}
T operator[](size_t idx) const
{
return lhs[idx] + rhs[idx];
}
size_t size() const
{
return (lhs.size() != 0) ? lhs.size() : rhs.size();
}
};
template<typename T, typename LHS, typename RHS>
class ET_Mul {
private:
typename ET_Traits<LHS>::ExprRef lhs;
typename ET_Traits<RHS>::ExprRef rhs;
public:
ET_Mul(const LHS& l, const RHS& r) :
lhs(l), rhs(r) {}
T operator[](size_t idx) const
{
return lhs[idx] * rhs[idx];
}
size_t size() const
{
return (lhs.size() != 0) ? lhs.size() : rhs.size();
}
};
// Vector + Vector
template<typename T, typename LHS, typename RHS>
ET_Vector<T, ET_Add<T, LHS, RHS>>
operator+(const ET_Vector<T, LHS>& a, const ET_Vector<T, RHS>& b)
{
return ET_Vector<T, ET_Add<T, LHS, RHS>>(ET_Add<T, LHS, RHS>(a.rep(), b.rep()));
}
// Scalar + Vector
template<typename T, typename RHS>
ET_Vector<T, ET_Add<T, ET_Scalar<T>, RHS>>
operator+(const T& s, const ET_Vector<T, RHS>& b)
{
return ET_Vector<T, ET_Add<T, ET_Scalar<T>, RHS>>(ET_Add<T, ET_Scalar<T>, RHS>(ET_Scalar<T>(s), b.rep()));
}
// Vector .* Vector
template<typename T, typename LHS, typename RHS>
ET_Vector<T, ET_Mul<T, LHS, RHS>>
operator*(const ET_Vector<T, LHS>& a, const ET_Vector<T, RHS>& b)
{
return ET_Vector<T, ET_Mul<T, LHS, RHS>>(ET_Mul<T, LHS, RHS>(a.rep(), b.rep()));
}
//Scalar * Vector
template<typename T, typename RHS>
ET_Vector<T, ET_Mul<T, ET_Scalar<T>, RHS>>
operator*(const T& s, const ET_Vector<T, RHS>& b)
{
return ET_Vector<T, ET_Mul<T, ET_Scalar<T>, RHS>>(ET_Mul<T, ET_Scalar<T>, RHS>(ET_Scalar<T>(s), b.rep()));
}
template<typename T>
void print_vec(const T& e)
{
for (size_t i = 0; i < e.size(); i++) {
std::cout << e[i] << ' ';
}
std::cout << '\n';
return;
}
int main()
{
size_t N = 16;
ET_Vector<double> x(N);
ET_Vector<double> y(N);
ET_Vector<double> z(N);
ET_Vector<int> idx(N / 2);
// Do not use auto z = [expr] here! Otherwise the type of z will still be a
// container, and evaluation won't happen until later. But the compiler
// will optimize necessary information away, causing errors.
z = (6.5 + x) + (-2.0 * (1.25 + y));
print_vec(z);
for (int i = 0; i < 8; i++)
idx[i] = 2 * i;
z[idx] = -1.0 * z[idx];
print_vec(z);
return 0;
}
Sorry about its length, I've failed to create a minimal (not) working example.

Expression template with CRTP as lvalue

I'm writing a library that uses expression templates with CRTP. The source files can be found here: https://github.com/mspraggs/pyQCD/tree/master/lib/include/base
The expression templates are based on the example given in the Wikipedia article on the subject. I list the code here in case the Wiki article changes in future:
#include <vector>
#include <cassert>
template <typename E>
// A CRTP base class for Vecs with a size and indexing:
class VecExpression {
public:
typedef std::vector<double> container_type;
typedef container_type::size_type size_type;
typedef container_type::value_type value_type;
typedef container_type::reference reference;
size_type size() const { return static_cast<E const&>(*this).size(); }
value_type operator[](size_type i) const { return static_cast<E const&>(*this)[i]; }
operator E&() { return static_cast< E&>(*this); }
operator E const&() const { return static_cast<const E&>(*this); }
};
// The actual Vec class:
class Vec : public VecExpression<Vec> {
container_type _data;
public:
reference operator[](size_type i) { return _data[i]; }
value_type operator[](size_type i) const { return _data[i]; }
size_type size() const { return _data.size(); }
Vec(size_type n) : _data(n) {} // Construct a given size:
// Construct from any VecExpression:
template <typename E>
Vec(VecExpression<E> const& vec) {
E const& v = vec;
_data.resize(v.size());
for (size_type i = 0; i != v.size(); ++i) {
_data[i] = v[i];
}
}
};
template <typename E1, typename E2>
class VecDifference : public VecExpression<VecDifference<E1, E2> > {
E1 const& _u;
E2 const& _v;
public:
typedef Vec::size_type size_type;
typedef Vec::value_type value_type;
VecDifference(VecExpression<E1> const& u, VecExpression<E2> const& v) : _u(u), _v(v) {
assert(u.size() == v.size());
}
size_type size() const { return _v.size(); }
value_type operator[](Vec::size_type i) const { return _u[i] - _v[i]; }
};
template <typename E>
class VecScaled : public VecExpression<VecScaled<E> > {
double _alpha;
E const& _v;
public:
VecScaled(double alpha, VecExpression<E> const& v) : _alpha(alpha), _v(v) {}
Vec::size_type size() const { return _v.size(); }
Vec::value_type operator[](Vec::size_type i) const { return _alpha * _v[i]; }
};
// Now we can overload operators:
template <typename E1, typename E2>
VecDifference<E1,E2> const
operator-(VecExpression<E1> const& u, VecExpression<E2> const& v) {
return VecDifference<E1,E2>(u,v);
}
template <typename E>
VecScaled<E> const
operator*(double alpha, VecExpression<E> const& v) {
return VecScaled<E>(alpha,v);
}
What I want to do is add another expression template that allows assignment to part of the original template object (the Vec class in the code above, and the LatticeBase class in the code I've linked to). Possible usage:
Vec myvector(10);
Vec another_vector(5);
myvector.head(5) = another_vector; // Assign first 5 elements on myvector
myvector.head(2) = another_vector.head(2); // EDIT
So I'd create a new function Vec::head that would a return an expression template for a portion of the Vec object. I don't know how this would fit into the framework I currently have. In particular I have the following questions/comments:
I've seen examples of what I want to achieve in expression templates that don't use CRTP. What do I gain by using CRTP in this case? Is there any point? Should I ditch it and follow the other examples I've found?
In the current framework, the assignment to the _data member in the Vec class is handled by a copy constructor in the Vec class. This won't work if I want to use the expression template returned by Vec::head, since the assignment happens within the class that holds the data, not the expression template.
I've tried creating an assignment operator within the new expression template, but that won't work with the code above as all the expression template members are const references, and so the assignment operator is deleted at compile time. Can I just switch the members to being values instead of references? Will this impact on performance if additional storage is needed? Will this even work (if I change a stored copy of the expression rather than the expression itself)?
Overall I'm confused about how to go about adding an expression template that can be used as an lvalue in the code above. Any guidance on this would be greatly appreciated.
Try this:
#include <vector>
#include <cassert>
template <typename E>
// A CRTP base class for Vecs with a size and indexing:
class VecExpression {
public:
typedef std::vector<double> container_type;
typedef container_type::size_type size_type;
typedef container_type::value_type value_type;
typedef container_type::reference reference;
size_type size() const { return static_cast<E const&>(*this).size(); }
value_type operator[](size_type i) const { return static_cast<E const&>(*this)[i]; }
operator E&() { return static_cast<E&>(*this); }
operator E const&() const { return static_cast<const E&>(*this); }
};
class VecHead;
// The actual Vec class:
class Vec : public VecExpression<Vec> {
container_type _data;
public:
reference operator[](size_type i) { return _data[i]; }
value_type operator[](size_type i) const { return _data[i]; }
size_type size() const { return _data.size(); }
Vec(size_type n) : _data(n) {} // Construct a given size:
// Construct from any VecExpression:
template <typename E>
Vec(VecExpression<E> const& vec) {
E const& v = vec;
_data.resize(v.size());
for (size_type i = 0; i != v.size(); ++i) {
_data[i] = v[i];
}
}
VecHead head(size_type s);
};
class VecHead : public VecExpression< VecHead >
{
Vec::size_type _s;
Vec& _e;
public:
typedef Vec::size_type size_type;
typedef Vec::value_type value_type;
VecHead(std::size_t s, Vec& e)
: _s(s)
, _e(e)
{
assert(_e.size() >= _s);
}
size_type size() const { return _s; }
value_type operator[](Vec::size_type i) const { assert(i < _s); return _e[i]; }
VecHead& operator = (const VecHead& rhs)
{
return operator=(static_cast<const VecExpression<VecHead>&>(rhs));
}
template <typename E>
VecHead& operator = (const VecExpression<E>& rhs)
{
assert(rhs.size() >= _s);
for (size_type i = 0; i < _s && i < rhs.size(); ++i)
_e[i] = rhs[i];
return *this;
}
};
VecHead Vec::head(size_type s)
{
VecHead aHead(s, *this);
return aHead;
}
template <typename E1, typename E2>
class VecDifference : public VecExpression<VecDifference<E1, E2> > {
E1 const& _u;
E2 const& _v;
public:
typedef Vec::size_type size_type;
typedef Vec::value_type value_type;
VecDifference(VecExpression<E1> const& u, VecExpression<E2> const& v) : _u(u), _v(v) {
assert(u.size() == v.size());
}
size_type size() const { return _v.size(); }
value_type operator[](Vec::size_type i) const { return _u[i] - _v[i]; }
};
template <typename E>
class VecScaled : public VecExpression<VecScaled<E> > {
double _alpha;
E const& _v;
public:
VecScaled(double alpha, VecExpression<E> const& v) : _alpha(alpha), _v(v) {}
Vec::size_type size() const { return _v.size(); }
Vec::value_type operator[](Vec::size_type i) const { return _alpha * _v[i]; }
};
// Now we can overload operators:
template <typename E1, typename E2>
VecDifference<E1, E2> const
operator-(VecExpression<E1> const& u, VecExpression<E2> const& v) {
return VecDifference<E1, E2>(u, v);
}
template <typename E>
VecScaled<E> const
operator*(double alpha, VecExpression<E> const& v) {
return VecScaled<E>(alpha, v);
}
int main()
{
Vec myvector(10);
Vec another_vector(5);
for (int i = 0; i < 5; ++i)
another_vector[i] = i;
myvector.head(5) = another_vector; // Assign first 5 elements on myvector
assert(myvector.head(5).size() == 5);
for (int i = 0; i < 10; ++i)
{
assert(myvector[i] == (i < 5 ? static_cast<double>(i) : 0.));
}
//! Added test due to comment vec1.head(2) = vec2.head(2) doesn't work.
Vec vec1(10), vec2(10);
for (int i = 0; i < 10; ++i)
vec2[i] = 2 * (vec1[i] = i);
vec1.head(2) = vec2.head(2);
for (int i = 0; i < 10; ++i)
{
if (i < 2)
{
assert(vec1[i] == vec2[i]);
}
else
{
assert(vec1[i] != vec2[i]);
}
}
return 0;
}

Fastest way to sort two vectors (key/values) at the same time?

For supercomputing simulation purpose, I have a structure that contains two big (billions of elements) std::vector: one std::vector of "keys" (64 bits integers) and one std::vector of "values". I cannot use a std::map because in the simulations I consider, vectors are far more optimal than std::map. Moreover, I cannot use a vector of pairs because of some optimization and cache efficiency provided by separate vectors. Moreover I cannot use any extra memory.
So, considering these constaints, what is the most optimized way to sort the two vectors by increasing values of the keys ? (template metaprogramming and crazy compile-time tricks are welcome)
Two ideas off the top of my head:
Take a quicksort implementation and apply it to the "key" vector; but modify the code so that every time it does a swap on the key vector, it also performs the same swap on the value vector.
Or, perhaps more in keeping with the spirit of C++, write a custom "wrapper" iterator which iterates over both vectors at once (returning a std::pair when dereferenced). Perhaps Boost has one? You could then combine this with std::sort and a custom comparison function which considers only the "key".
EDIT:
I've used the first suggestion here for a similar problem back in a past life as a C programmer. It's far from ideal for obvious reasons, but it's possibly the quickest way to get something going.
I haven't tried a wrapper iterator like this with std::sort, but TemplateRex in the comments says it won't work, and I'm happy to defer to him on that one.
I think problem may be splitted into 2 independent parts:
How to make effective iterator for virtual map
Which sorting alorithm to use
Iterator
Implementing iterator the main problem how to return pair of key/value not creating
unnecessary copies. We can achieve it by using different types for value_type & reference. My implementation is here.
template <typename _Keys, typename _Values>
class virtual_map
{
public:
typedef typename _Keys::value_type key_type;
typedef typename _Values::value_type mapped_type;
typedef std::pair<key_type, mapped_type> value_type;
typedef std::pair<key_type&, mapped_type&> proxy;
typedef std::pair<const key_type&, const mapped_type&> const_proxy;
class iterator :
public boost::iterator_facade < iterator, value_type, boost::random_access_traversal_tag, proxy >
{
friend class boost::iterator_core_access;
public:
iterator(virtual_map *map_, size_t offset_) :
map(map_),
offset(offset_)
{}
iterator(const iterator &other_)
{
this->map = other_.map;
this->offset = other_.offset;
}
private:
bool equal(const iterator &other) const
{
assert(this->map == other.map);
return this->offset == other.offset;
}
void increment() { ++offset; }
void decrement() { --offset; }
void advance(difference_type n) { offset += n; }
reference dereference() const { return reference(map->keys[offset], map->values[offset]); }
difference_type distance_to(const iterator &other_) const { return other_.offset - this->offset; }
private:
size_t offset;
virtual_map *map;
};
public:
virtual_map(_Keys &keys_, _Values &values_) :
keys(keys_),
values(values_)
{
if(keys_.size() != values_.size())
throw std::runtime_error("different size");
}
public:
iterator begin() { return iterator(this, 0); }
iterator end() { return iterator(this, keys.size()); }
protected:
_Keys &keys;
_Values &values;
};
usage sample:
int main(int argc, char* const argv[])
{
std::vector<int> keys_ = { 17, 2, 13, 4, 51, 78, 49, 37, 1 };
std::vector<std::string> values_ = { "17", "2", "13", "4", "51", "78", "49", "37", "1" };
typedef virtual_map<std::vector<int>, std::vector<std::string>> map;
map map_(keys_, values_);
std::sort(std::begin(map_), std::end(map_), [](map::const_proxy left_, map::const_proxy right_)
{
return left_.first < right_.first;
});
return 0;
}
Sorting algorithm
Its very hard to reason which method better without additional details. What memory restriction do you have? Is it possible to use concurrency?
There are some issues:
Iterating both sequences together requires a pair representing
references to the sequence elements - that pair, itself, is no
reference. Hence, algorithms working on references will not work.
Performance will degenerate (the sequences are loosely coupled) -
An implementation using a pair of references and std::sort:
// Copyright (c) 2014 Dieter Lucking. Distributed under the Boost
// software License, Version 1.0. (See accompanying file
// LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)
#include <algorithm>
#include <chrono>
#include <memory>
#include <iostream>
// None
// ============================================================================
/// A void type
struct None {
None()
{}
/// Explicit conversion to None.
template <typename T>
explicit None(const T&)
{}
template <typename T>
None& operator = (const T&) {
return *this;
}
/// Never null.
None* operator & () const;
};
extern None& none();
inline None* None::operator & () const { return &none(); }
None& none() {
static None result;
return result;
}
// IteratorAdaptorTraits
// ============================================================================
namespace Detail {
// IteratorAdaptorTraits
// =====================
template <typename Iterator, typename ReturnType, bool IsReference>
struct IteratorAdaptorTraits;
// No reference
// ============
template <typename Iterator, typename ReturnType>
struct IteratorAdaptorTraits<Iterator, ReturnType, false>
{
typedef Iterator iterator_type;
typedef ReturnType return_type;
typedef ReturnType value_type;
typedef None reference;
typedef None pointer;
static_assert(
! std::is_base_of<None, return_type>::value,
"None as return type.");
template <typename Accessor>
static return_type iterator_value(const Accessor& accessor, const Iterator& iterator) {
return accessor.value(iterator);
}
template <typename Accessor>
static pointer iterator_pointer(const Accessor& accessor, const Iterator& iterator) {
return &none();
}
};
// Reference
// =========
template <typename Iterator, typename ReturnType>
struct IteratorAdaptorTraits<Iterator, ReturnType, true>
{
typedef Iterator iterator_type;
typedef ReturnType return_type;
typedef typename std::remove_reference<ReturnType>::type value_type;
typedef ReturnType reference;
typedef value_type* pointer;
static_assert(
! std::is_base_of<None, return_type>::value,
"None as return type.");
template <typename Accessor>
static return_type iterator_value(const Accessor& accessor, const Iterator& iterator) {
return accessor.value(iterator);
}
template <typename Accessor>
static pointer iterator_pointer(const Accessor& accessor, const Iterator& iterator) {
return &accessor.value(iterator);
}
};
} // namespace Detail
// RandomAccessIteratorAdaptor
// ============================================================================
/// An adaptor around a random access iterator.
/// \ATTENTION The adaptor will not fulfill the standard iterator requierments,
/// if the accessor does not support references: In that case, the
/// reference and pointer type are None.
template <typename Iterator, typename Accessor>
class RandomAccessIteratorAdaptor
{
// Types
// =====
private:
static_assert(
! std::is_base_of<None, Accessor>::value,
"None as accessor.");
static_assert(
! std::is_base_of<None, typename Accessor::return_type>::value,
"None as return type.");
typedef typename Detail::IteratorAdaptorTraits<
Iterator,
typename Accessor::return_type,
std::is_reference<typename Accessor::return_type>::value
> Traits;
public:
typedef typename Traits::iterator_type iterator_type;
typedef Accessor accessor_type;
typedef typename std::random_access_iterator_tag iterator_category;
typedef typename std::ptrdiff_t difference_type;
typedef typename Traits::return_type return_type;
typedef typename Traits::value_type value_type;
typedef typename Traits::reference reference;
typedef typename Traits::pointer pointer;
typedef typename accessor_type::base_type accessor_base_type;
typedef RandomAccessIteratorAdaptor<iterator_type, accessor_base_type> base_type;
// Tag
// ===
public:
struct RandomAccessIteratorAdaptorTag {};
// Construction
// ============
public:
explicit RandomAccessIteratorAdaptor(
iterator_type iterator, const accessor_type& accessor = accessor_type())
: m_iterator(iterator), m_accessor(accessor)
{}
template <typename IteratorType, typename AccessorType>
explicit RandomAccessIteratorAdaptor(const RandomAccessIteratorAdaptor<
IteratorType, AccessorType>& other)
: m_iterator(other.iterator()), m_accessor(other.accessor())
{}
// Element Access
// ==============
public:
/// The underlaying accessor.
const accessor_type& accessor() const { return m_accessor; }
/// The underlaying iterator.
const iterator_type& iterator() const { return m_iterator; }
/// The underlaying iterator.
iterator_type& iterator() { return m_iterator; }
/// The underlaying iterator.
operator iterator_type () const { return m_iterator; }
/// The base adaptor.
base_type base() const {
return base_type(m_iterator, m_accessor.base());
}
// Iterator
// ========
public:
return_type operator * () const {
return Traits::iterator_value(m_accessor, m_iterator);
}
pointer operator -> () const {
return Traits::iterator_pointer(m_accessor, m_iterator);
}
RandomAccessIteratorAdaptor increment() const {
return ++RandomAccessIteratorAdaptor(*this);
}
RandomAccessIteratorAdaptor increment_n(difference_type n) const {
RandomAccessIteratorAdaptor tmp(*this);
tmp.m_iterator += n;
return tmp;
}
RandomAccessIteratorAdaptor decrement() const {
return --RandomAccessIteratorAdaptor(*this);
}
RandomAccessIteratorAdaptor decrement_n(difference_type n) const {
RandomAccessIteratorAdaptor tmp(*this);
tmp.m_iterator -= n;
return tmp;
}
RandomAccessIteratorAdaptor& operator ++ () {
++m_iterator;
return *this;
}
RandomAccessIteratorAdaptor operator ++ (int) {
RandomAccessIteratorAdaptor tmp(*this);
++m_iterator;
return tmp;
}
RandomAccessIteratorAdaptor& operator += (difference_type n) {
m_iterator += n;
return *this;
}
RandomAccessIteratorAdaptor& operator -- () {
--m_iterator;
return *this;
}
RandomAccessIteratorAdaptor operator -- (int) {
RandomAccessIteratorAdaptor tmp(*this);
--m_iterator;
return tmp;
}
RandomAccessIteratorAdaptor& operator -= (difference_type n) {
m_iterator -= n;
return *this;
}
bool equal(const RandomAccessIteratorAdaptor& other) const {
return this->m_iterator == other.m_iterator;
}
bool less(const RandomAccessIteratorAdaptor& other) const {
return this->m_iterator < other.m_iterator;
}
bool less_equal(const RandomAccessIteratorAdaptor& other) const {
return this->m_iterator <= other.m_iterator;
}
bool greater(const RandomAccessIteratorAdaptor& other) const {
return this->m_iterator > other.m_iterator;
}
bool greater_equal(const RandomAccessIteratorAdaptor& other) const {
return this->m_iterator >= other.m_iterator;
}
private:
iterator_type m_iterator;
accessor_type m_accessor;
};
template <typename Iterator, typename Accessor>
inline RandomAccessIteratorAdaptor<Iterator, Accessor> operator + (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& i,
typename RandomAccessIteratorAdaptor<Iterator, Accessor>::difference_type n) {
return i.increment_n(n);
}
template <typename Iterator, typename Accessor>
inline RandomAccessIteratorAdaptor<Iterator, Accessor> operator - (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& i,
typename RandomAccessIteratorAdaptor<Iterator, Accessor>::difference_type n) {
return i.decrement_n(n);
}
template <typename Iterator, typename Accessor>
inline typename RandomAccessIteratorAdaptor<Iterator, Accessor>::difference_type
operator - (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& a,
const RandomAccessIteratorAdaptor<Iterator, Accessor>& b) {
return a.iterator() - b.iterator();
}
template <typename Iterator, typename Accessor>
inline bool operator == (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& a,
const RandomAccessIteratorAdaptor<Iterator, Accessor>& b) {
return a.equal(b);
}
template <typename Iterator, typename Accessor>
inline bool operator != (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& a,
const RandomAccessIteratorAdaptor<Iterator, Accessor>& b) {
return ! a.equal(b);
}
template <typename Iterator, typename Accessor>
inline bool operator < (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& a,
const RandomAccessIteratorAdaptor<Iterator, Accessor>& b) {
return a.less(b);
}
template <typename Iterator, typename Accessor>
inline bool operator <= (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& a,
const RandomAccessIteratorAdaptor<Iterator, Accessor>& b) {
return a.less_equal(b);
}
template <typename Iterator, typename Accessor>
inline bool operator > (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& a,
const RandomAccessIteratorAdaptor<Iterator, Accessor>& b) {
return a.greater(b);
}
template <typename Iterator, typename Accessor>
inline bool operator >= (
const RandomAccessIteratorAdaptor<Iterator, Accessor>& a,
const RandomAccessIteratorAdaptor<Iterator, Accessor>& b) {
return a.greater_equal(b);
}
// ElementPair
// ============================================================================
/// A pair of references which can mutate to a pair of values.
/// \NOTE If the key is one or two the pair is less comparable
/// regarding the first or second element.
template <typename First, typename Second, unsigned Key = 0>
class ElementPair
{
// Types
// =====
public:
typedef First first_type;
typedef Second second_type;
// Construction
// ============
public:
/// Reference
/// \POSTCONDITION reference() returns true
ElementPair(first_type& first, second_type& second)
: m_first(&first), m_second(&second)
{}
/// Copy construction
/// \POSTCONDITION reference() returns false
ElementPair(const ElementPair& other)
: m_first(new(m_first_storage) first_type(*other.m_first)),
m_second(new(&m_second_storage) second_type(*other.m_second))
{}
/// Move construction
/// \POSTCONDITION reference() returns false
ElementPair(ElementPair&& other)
: m_first(new(m_first_storage) first_type(std::move(*other.m_first))),
m_second(new(m_second_storage) second_type(std::move(*other.m_second)))
{}
~ElementPair() {
if( ! reference()) {
reinterpret_cast<first_type*>(m_first_storage)->~first_type();
reinterpret_cast<second_type*>(m_second_storage)->~second_type();
}
}
// Assignment
// ==========
public:
/// Swap content.
void swap(ElementPair& other) {
std::swap(*m_first, *other.m_first);
std::swap(*m_second, *other.m_second);
}
/// Assign content.
ElementPair& operator = (const ElementPair& other) {
if(&other != this) {
*m_first = *other.m_first;
*m_second = *other.m_second;
}
return *this;
}
/// Assign content.
ElementPair& operator = (ElementPair&& other) {
if(&other != this) {
*m_first = std::move(*other.m_first);
*m_second = std::move(*other.m_second);
}
return *this;
}
// Element Access
// ==============
public:
/// True if the pair holds references to external elements.
bool reference() {
return (m_first != reinterpret_cast<first_type*>(m_first_storage));
}
const first_type& first() const { return *m_first; }
first_type& first() { return *m_first; }
const second_type& second() const { return *m_second; }
second_type& second() { return *m_second; }
private:
first_type* m_first;
typename std::aligned_storage<
sizeof(first_type),
std::alignment_of<first_type>::value>::type
m_first_storage[1];
second_type* m_second;
typename std::aligned_storage<
sizeof(second_type),
std::alignment_of<second_type>::value>::type
m_second_storage[1];
};
// Compare
// =======
template <typename First, typename Second>
inline bool operator < (
const ElementPair<First, Second, 1>& a,
const ElementPair<First, Second, 1>& b)
{
return (a.first() < b.first());
}
template <typename First, typename Second>
inline bool operator < (
const ElementPair<First, Second, 2>& a,
const ElementPair<First, Second, 2>& b)
{
return (a.second() < b.second());
}
// Swap
// ====
namespace std {
template <typename First, typename Second, unsigned Key>
inline void swap(
ElementPair<First, Second, Key>& a,
ElementPair<First, Second, Key>& b)
{
a.swap(b);
}
}
// SequencePairAccessor
// ============================================================================
template <typename FirstSequence, typename SecondSequence, unsigned Keys = 0>
class SequencePairAccessor
{
// Types
// =====
public:
typedef FirstSequence first_sequence_type;
typedef SecondSequence second_sequence_type;
typedef typename first_sequence_type::size_type size_type;
typedef typename first_sequence_type::value_type first_type;
typedef typename second_sequence_type::value_type second_type;
typedef typename first_sequence_type::iterator iterator;
typedef None base_type;
typedef ElementPair<first_type, second_type, Keys> return_type;
// Construction
// ============
public:
SequencePairAccessor(first_sequence_type& first, second_sequence_type& second)
: m_first_sequence(&first), m_second_sequence(&second)
{}
// Element Access
// ==============
public:
base_type base() const { return base_type(); }
return_type value(iterator pos) const {
return return_type(*pos, (*m_second_sequence)[pos - m_first_sequence->begin()]);
}
// Data
// ====
private:
first_sequence_type* m_first_sequence;
second_sequence_type* m_second_sequence;
};
This test shows a degenaration of performance (on my system) by a factor of 1.5 for const char* and a factor of 3.4 for a std::string (compared to a single vector holding std::pair(s)).
// Test
// ============================================================================
#define SAMPLE_SIZE 1e1
#define VALUE_TYPE const char*
int main() {
const unsigned samples = SAMPLE_SIZE;
typedef int key_type;
typedef VALUE_TYPE value_type;
typedef std::vector<key_type> key_sequence_type;
typedef std::vector<value_type> value_sequence_type;
typedef SequencePairAccessor<key_sequence_type, value_sequence_type, 1> accessor_type;
typedef RandomAccessIteratorAdaptor<
key_sequence_type::iterator,
accessor_type>
iterator_adaptor_type;
key_sequence_type keys;
value_sequence_type values;
keys.reserve(samples);
values.reserve(samples);
const char* words[] = { "Zero", "One", "Two", "Three", "Four", "Five", "Six", "Seven", "Eight", "Nine" };
for(unsigned i = 0; i < samples; ++i) {
key_type k = i % 10;
keys.push_back(k);
values.push_back(words[k]);
}
accessor_type accessor(keys, values);
std::random_shuffle(
iterator_adaptor_type(keys.begin(), accessor),
iterator_adaptor_type(keys.end(), accessor)
);
if(samples <= 10) {
std::cout << "\nRandom:\n"
<< "======\n";
for(unsigned i = 0; i < keys.size(); ++i)
std::cout << keys[i] << ": " << values[i] << '\n';
}
typedef std::pair<key_type, value_type> pair_type;
std::vector<pair_type> ref;
for(const auto& k: keys) {
ref.push_back(pair_type(k, words[k]));
}
struct Less {
bool operator () (const pair_type& a, const pair_type& b) const {
return a.first < b.first;
}
};
auto ref_start = std::chrono::system_clock::now();
std::sort(ref.begin(), ref.end(), Less());
auto ref_end = std::chrono::system_clock::now();
auto ref_elapsed = double((ref_end - ref_start).count())
/ std::chrono::system_clock::period::den;
auto start = std::chrono::system_clock::now();
std::sort(
iterator_adaptor_type(keys.begin(), accessor),
iterator_adaptor_type(keys.end(), accessor)
);
auto end = std::chrono::system_clock::now();
auto elapsed = double((end - start).count())
/ std::chrono::system_clock::period::den;;
if(samples <= 10) {
std::cout << "\nSorted:\n"
<< "======\n";
for(unsigned i = 0; i < keys.size(); ++i)
std::cout << keys[i] << ": " << values[i] << '\n';
}
std::cout << "\nDuration sorting " << double(samples) << " samples:\n"
<< "========\n"
<< " One Vector: " << ref_elapsed << '\n'
<< "Two Vectors: " << elapsed << '\n'
<< " Factor: " << elapsed/ref_elapsed << '\n'
<< '\n';
}
(Please adjust SAMPLE_SIZE and VALUE_TYPE)
My conclusion is a sorted view into a sequence of unsorted data might be more aprropiate (but that violates the requirement of the question).