#pragma omp declare simd clauses

// routine prototype
#pragma omp declare simd                           // universal but slowest definition matches the use in all three loops
#pragma omp declare simd linear(in1) linear(ref(in2)) uniform(mul) // matches the use in the first loop
#pragma omp declare simd linear(ref(in2))                            // matches the use in the second and the third loops
#pragma omp declare simd linear(ref(in2)) linear(mul)              // matches the use in the second loop
#pragma omp declare simd linear(val(in2:2))                          // matches the use in the third loop
extern int func(int* in1, int& in2, int mul);

int *a, *b, mul, *c;
int *ndx, nn;
...
// loop examples
   for (int i = 0; i < nn; i++) {
       c[i] = func(a + i, *(b + i), mul); // in the loop, the first parameter is changed linearly, 
                                          // the second reference is changed linearly too
                                          // the third parameter is not changed
   }

   for (int i = 0; i < nn; i++) {
       c[i] = func(&a[ndx[i]], b[i], i + 1); // the value of the first parameter is unpredictable,
                                             // the second reference is changed linearly
                                             // the third parameter is changed linearly
   }

   #pragma omp simd
   for (int i = 0; i < nn; i++) {
       int k = i * 2;  // during vectorization, private variables are transformed into arrays: k->k_vec[vector_length]
       c[i] = func(&a[ndx[i]], k, b[i]); // the value of the first parameter is unpredictable,
                                         // the second reference and value can be considered linear
                                         // the third parameter has unpredictable value
                                         // (the #pragma simd linear(val(in2:2))) will be chosen from the two matching variants)
  }

struct Base {
#pragma omp declare simd
#pragma omp declare simd uniform(this)
   virtual int process(int);
};

struct Child1 : Base {
   // int process(int); is inherited
};

struct Child11 : Child1 {
  int process(int); // Overrides implementation, inherits vector declarations
};

struct Child2 : Base {
  int process(int); // Overrides implementation, inherits vector declarations
};

int main() {
    int arr[100];
    Base* c2 = new Child2();
    Base* objs[100];
    int res = 0;

// SIMD-enabled virtual function call for uniform object
#pragma omp simd reduction(+:res)
    for (int i = 0; i < 100; i++) {
      res += c2->process(arr[i]);  // Variant with uniform this is matched 
                                   // call to vector variant of 
                                   // Child2::process() is invoked
   }

// Initialize polymorphic array of objects
    for (int i = 0; i < 100; i++) {
       if (i % 16 < 4) objs[i] = new Base();
       else if (i % 16 < 8) objs[i] = new Child1();
       else if (i % 12 < 12) objs[i] = new Child11();
       else objs[i] = new Child2();
   }

// SIMD-enabled virtual function call for non-uniform objects
#pragma omp simd reduction(+:res) simdlen(8)
    for (int i = 0; i < 100; i++) {
       res += objs[i]->process(arr[i]);  // Variant with non-uniform this is
                                         // matched 
       // Base and Child1 share the same 'process' implementation, so call
       // targets for each even chunk [i*16:i*16+7] are the same even though
       // this pointers are different for all elements of objs[] array.
         
       // Odd chunks [i*16+8:i*16+15] consist of objects of classes Child11
       // and Child2 and so require calls to their respective implementations 
       // of process() virtual functions. Masked vector variant for 
       // Child11::process() is called with mask 0b00001111 (lower lanes of a 
       // chunk) and masked vector variant for Child2::process() is called
       // with mask 0b11110000 (upper lanes of a chunk).
   }

   return res;
}

template <int f(int)>   // Function value template – captures exact function
                        // not a function type
int caller1(int x[100]) {
   int res = 0;
#pragma omp simd reduction(+:res)
   for (int i = 0; i < 100; i++) {
      res += f(x[i]);   // Exact function put here upon instantiation
   }
   return res;
}

template <typename F>  // Generic functional type template – captures 
                       // object type for functors or entire functional type 
                       // for functions. If vector attributes were part of 
                       // a functional type they might be captured and applied
                       // but currently they are not.
int caller2(F f, int x[100]) {
   int res = 0;
#pragma omp simd reduction(+:res)
   for (int i = 0; i < 100; i++) {
      res += f(x[i]);  // Will call matching function 'f' indirectly
                       // Will call matching f.operator() directly
   }
   return res;
}

template <typename RET, typename ARG>  // Type-decomposing template
                                       // captures argument and return types.
                                       // Vector attributes would be lost 
                                       // even if they were part of a 
                                       // functional type.
int caller3(RET (*f)(ARG), int x[100]) {
   int res = 0;
#pragma omp simd reduction(+:res)
   for (int i = 0; i < 100; i++) {
      res += f(x[i]);  // Will call matching function 'f' indirectly
   }
   return res;
}


#pragma omp declare simd 
int function(int x); // SIMD-enabled function
int nv_function(int x);                 // Regular scalar function

struct functor {                        // Functor class with
#pragma omp declare simd                      // SIMD-enabled operator()
   int operator()(int x);
};

int arr[100];

int main() {
   int res;
#pragma noinline
   res = caller1<function>(arr); // This will be instantiated for 
                                 // function() and call short vector variant
#pragma noinline
   res += caller1<nv_function>(arr); // This will be separately instantiated 
                                     // for nv_function()
#pragma noinline
   res += caller2(function, arr); // This will be instantiated for
                                  // int(*)(int) type and will call scalar
                                  // function() indirectly
#pragma noinline
   res += caller2(nv_function, arr); // This will call the same
                                     // instantiation as above on nv_function

#pragma noinline
   res += caller2(functor(), arr); // This will be instantiated for
                                   // functor type and will call short vector
                                   // variant of functor::operator()
#pragma noinline
   res += caller3(function, arr); // This will be instantiated for
                                  // <int, int> types and will call scalar
                                  // function() indirectly
#pragma noinline
   res += caller3(nv_function, arr); // This will call the same
                                     // instantiation as above on nv_function
   return res;
}

a[:] = ef_add(b[:],c[:]);    //operates on the whole extent of the arrays a, b, c

a[0:n:s] = ef_add(b[0:n:s],c[0:n:s]); //use the full array notation construct to also specify n as an extend and s as a stride

void accumulate(float *a, float *b, float *c, d){
  *a+=sin(d);
  *b+=cos(d);
  *c+=log(d);
}

for (i=low; i<high; i++){
    accumulate(&suma, &sumb, &sumc, d[i]);
}

#pragma omp declare simd uniform(a,b,c) aligned(a,b,c)
void accumulate(float *a, float *b, float *c, float d){
// No need to take “loop index”. No need to know VL.
  a[__intel_simd_lane()]+=sin(d);
  b[__intel_simd_lane()]+=cos(d);
  c[__intel_simd_lane()]+=log(d);
}

#define VL 16 // actual SIMD code may use vectorlength of 4 but it's okay.
float a[VL] = {0.0f};
float b[VL] = {0.0f};
float c[VL] = {0.0f};
#pragma omp simd for simdlen(VL)
for (i=low; i<high; i++){
    // If low is known to be zero at compile time, “i & (VL-1)”
    // would accomplish what __intel_simd_lane() is intended for,
    // but only on the caller side.
    accumulate(a, b, c, d[i]);
}
for(i=0;i<VL;i++){
    suma += a[i];
    sumb += b[i];
    sumc += c[i];
}