Cover image for C++ type casting with example for C developers

C++ type casting with example for C developers

visheshpatel profile image Vishal Chovatiya Updated on ・15 min read

The typecasting is the feature which makes C++ more type-safe, robust & may convince you to use it over C. But this is also a more underrated topic when you are a newbie or moving from C background. Hence, I come up with an article on it . Here, we will not only see the C++ typecasting but we will also cover why we need it & cheat codes for C developers to remember & employ it easily. Although I am not an expert but this is what I have learned so far from various sources & 5+ yrs of industry experience.

/!\: This article has been originally published on my blog. If you are interested in receiving my latest articles, please sign up to my newsletter.

In C++, there are 5 different types of casts: C-style casts, static_cast, const_cast, dynamic_cast, and reinterpret_cast.

I usually start with "Why we need it?", but this time first we quickly go through some jargons & I will end this article with some of CPP core guidelines.

Jargons you need to face

  1. Implicit conversion: where the compiler automatically typecast. Like float f = 3;, here compiler will not complain but directly transform 3 which is of type integer into float & assign to f.
  2. Explicit conversions: where the developer uses a casting operator to direct the conversion. All types of manual casting fall under the explicit type conversions category. Like int * p = (int*)std::malloc(10);, here we explicitly casting void* to int*.
  3. l-value: an identifier which represents memory location. For example, variable name, *ptr where ptr points to a memory location, etc.
  4. r-value: a value which is not l-value, r-value appear on the right-hand side of assignment(=) operator. Like
int a = 5; // 5 = r-value, 
q = p + 5; // p + 5 is r-value

Note: Although there are some exceptions & more to learn on l-value & r-value which I have discussed here.

Why we need typecasting?

  • Data is a representation of the bits(0s & 1s) in memory.
  • Data-type is compiler directive which tells the compiler how to store & process particular data.
  • uint32_t a = 5; by this statement you can presume that 4 bytes will be reserved in your memory & upon execution, it will store 0000 0000 0000 0000 0000 0000 0000 0101 data bits in that memory location. This was plain & simple.
  • Let's go a bit further, float f = 3.0; this statement will also reserve 4 bytes in memory & store data bits in form of 1). the sign bit, 2). exponent & 3). mantissa. Recall how floating-point numbers are stored in memory.
  • But when you write like float f = 3;, the compiler will be confused that how to store an integer value in float type of memory.
  • So it will automatically presume(Implicit conversion here) that you want to store 3.0 rather than 3 which is technically same from the human point of view but it's different when you think from computer memory perspective cause they stored differently.
  • There are many such scenarios where you provide data to store in memory which used to represent different data type.
  • For example, in the following example, you are trying to assign an object of type B into an object of type A
class A{};
class B{};

int main ()
  B b;
  A a = b; 
  return 0;
  • In such scenario compiler can not presume anything & simply throws a compilation error:
exit status 1
error: no viable conversion from 'B' to 'A'
  A a = b;
    ^   ~
note: candidate constructor (the implicit copy constructor) not viable: no known conversion from 'B' to 'const A &' for 1st argument
class A{};
note: candidate constructor (the implicit move constructor) not viable: no known conversion from 'B' to 'A &&' for 1st argument
class A{};
1 error generated.
  • But when you define a conversion operator as follows:
class B {
  operator A(){
    return A();
  • The compiler will simply call this member function & won't throw any error because programmer explicitly mentioning that this is how he/she wants to convert.

5️⃣ C++ type casting with example for C developers

C-style casts

int main() { 
    float res = 10 / 4;
    return 0; 
  • When you will try to run the above code, you will get 2 as output which we didn't expect. To initialize res variable correctly we need to typecast using float as follows:
float res = (float)10 / 4;
  • Now your answer will be 2.5. This type of casting is very simple & straight forward as it appears.
  • You can also write above casting in C++ as:
float res = float(10) / 4;
  • C-style casts can change a data type without changing the underlying memory representation which may lead to garbage results.


  • If you are C developer like me, then this will be your best goto C++ cast which fits in most of the example like:
int * p = std::malloc(10);
  • When you try to compile above code using C compiler it works fine. But C++ compiler is not kind enough. It will throw an error as follows :
exit status 1
error: cannot initialize a variable of type 'int *' with an rvalue of type 'void *'
  int * p = std::malloc(10);
        ^   ~~~~~~~~~~
1 error generated.
  • The first thing that comes to your mind is the C-style cast:
int * p = (int*)std::malloc(10);
  • This will work, but this style of the cast is not recommended in C++. static_cast handles implicit conversions like this. We will primarily use it for converting in places where implicit conversions fail, such as std::malloc.
int * p = static_cast<int*>(std::malloc(10));
  • The main advantage of static_cast is that it provides compile-time type checking, making it harder to make an inadvertent error. Let's understand this with C++ example:
class B {};
class D : public B {};
class X {};

int main()
  D* d = new D;
  B* b = static_cast<B*>(d); // this works
  X* x = static_cast<X*>(d); // ERROR - Won't compile
  return 0;
  • As you can see, there is no easy way to distinguish between the two situations without knowing a lot about all the classes involved.
  • Another problem with the C-style casts is that it is too hard to locate. In complex expressions, it can be very hard to see C-style casts e.g. T(something) syntax is equivalent to (T)something.


  • Now we will directly jump to example. No theory> can explain this better than example.

1. Ignore constness

int i = 0;
const int& ref = i;
const int* ptr = &i;

*ptr = 3; // Not OK
const_cast<int&>(ref) = 3;  //OK
*const_cast<int*>(ptr) = 3; //OK
  • You are allowed to modify i, because of the object(i here) being assigned to, is not const. If you add const qualifier to i, code will compile, but its behaviour will be undefined (which can mean anything from "it works just fine" to "the program will crash>".)

2. Modifying data member using const this pointer

  • const_cast can be used to change non-const class members by a method in which this pointer declared as const. - This can also be useful when overloading member functions based on const, for instance:
class X
    int var;
    void changeAndPrint(int temp) const
        this->var = temp;                    // Throw compilation error
        (const_cast<X *>(this))->var = temp; // Works fine
    void changeAndPrint(int *temp)
        // Do some stuff
int main()
    int a = 4;
    X x;
    cout << x.var << endl;
    return 0;

3. Pass const argument to a function which accepts only non-const argument

  • const_cast can also be used to pass const data to a function that doesn’t receive const argument. See the following code:
int fun(int* ptr) 
    return (*ptr + 10); 

int main(void) 
    const int val = 10; 
    cout << fun(const_cast <int *>(&val)); 
    return 0; 

4. Castaway volatile attribute

  • const_cast can also be used to cast away volatile attribute. Whatever we discussed above in const_cast is also valid for volatile keyword.


  • dynamic_cast uses the type checking at runtime in contrary to static_cast which does it at compile time. dynamic_cast is more useful when you don't know the type of input which it represents. Let assume:
Base* CreateRandom()
    if( (rand()%2) == 0 )
        return new Derived1;
        return new Derived2;

Base* base = CreateRandom();
  • As you can see, we don't know which object will be returned by CreateRandom() at run time but you want to execute Method1() of Derived1 if it returns Derived1. So in this scenario, you can use dynamic_cast as follows
Derived1 *pD1 = dynamic_cast<Derived1 *>(base);
if (pD1){
  • In case, if input of dynamic_cast does not point to valid data, it will return nullptr for pointers or throw a std::bad_cast exception for references. In order to work with dynamic_cast, your classes must be polymorphic type i.e. must include at least one virtual methods.
  • dynamic_cast take advantage of RTTI(Run Time Type Identification) mechanism.


  • reinterpret_cast is a compiler directive which tells the compiler to treat the current type as a new type.
  • You can use reinterpret_cast to cast any pointer or integral type to any other pointer or integral type.
  • This can lead to dangerous situations: nothing will stop you from converting an int to an std::string*.
  • You will use reinterpret_cast in your embedded systems. A common scenario where reinterpret_cast applies is converting between uintptr_t and an actual pointer or between:
error: static_cast from 'int *' to 'uintptr_t'
      (aka 'unsigned long') is not allowed
        uintptr_t ptr = static_cast<uintptr_t>(p);
1 error generated.
  • Instead, use this:
uintptr_t ptr = reinterpret_cast<uintptr_t>(p);

I have tried to cover most of the intricacies to clear the main concept behind different typecasting, but still, there might be a chance that I may miss some. So, this is it for C++ type casting with an example for C developers. Let's quickly recap:

Cheat code for C developers moving to C++ on type casting

After reading all this you may confuse on what to use & when! That's why I have created this cheat code

  • Avoid C-style casts. Be sure about what you want while casting.
  • Use static_cast wherever you were using C-style cast.
  • Use dynamic_cast with polymorphic classes. Keep in mind that only use dynamic_cast on classes with at least one virtual member in the inheritance hierarchy.
  • Use const_cast when you need to remove const or volatile qualifiers.
  • Use reinterpret_cast when you have no options.

Note: const_cast and reinterpret_cast should generally be avoided because they can be harmful if used incorrectly. Don't use it unless you have a very good reason to use them.

Some of C++ core guidelines

Other related articles

Have any suggestions, query or wants to say Hi? Take the Pressure Off, you are just a click away.🖱️

Posted on by:

visheshpatel profile

Vishal Chovatiya


Software Developer⌨, Fitness Freak🏋, Geek🤓, Hipster🕴, Blogger👨‍💻, Productivity Hacker⌚, Technical Writer✍️, Always a Student👨‍🎓 & Learning Junkie📚.


Editor guide

Most of explanations sound not very clear to me. For instance, regarding constness. It would be great to see more comments about given examples touching some basics for the people who, for instance, are trying to master C++ after C#, etc. I think it would be more efficient than addressing such people to other references, books...


isn't it subjective matter?


Every matter is subjective ;) We all express our thoughts and wishes.


Erm, (float)10/2 is not 2.5 coliru.stacked-crooked.com/a/77b57...

Also, "you can also write (float)10 like float(10) isn't correct and makes it seem as if they're interchangable. I know some later text mentions the danger (eg (float) "danger"s) but by then the damage might be done


Yes...! You are correct. But that is what my point is.
You shouldn't use C-style cast.


Use new instead of malloc and delete instead of free.

There is malloc and free in C++ i.e. std::malloc and std::free respectively.


Hey man!
Thanks for pointing it out.


You should update the following as well.


Finally! This is exactly the article I have been looking for in the past year. Thank you for this!


Thanks, Dood...