Programming Example

Intel® C++ Compiler Classic Developer Guide and Reference

Download PDF

ID 767249

Date 12/16/2022

Version

Public

A newer version of this document is available. Customers should click here to go to the newest version.

Visible to Intel only — GUID: GUID-BF75C173-FE94-4448-9F99-E25FBDF35090

View Details

Programming Example

This sample program uses the F32vec4 class to average the elements of a twenty element floating point array.

//Include Intel® Streaming SIMD Extension (Intel® SSE) Class Definitions
 #include <fvec.h>

//Shuffle any two single precision floating point from a 
//into low two SP FP and shuffle any two SP FP from b 
//into high two SP FP of destination
 
#define SHUFFLE(a,b,i) (F32vec4)_mm_shuffle_ps(a,b,i) 
#include <stdio.h> 
#define SIZE 20

//Global variables
 float result; 
_MM_ALIGN16 float array[SIZE];

//***************************************************** 
// Function: Add20ArrayElements 
// Add all the elements of a twenty element array 
//*****************************************************
void Add20ArrayElements (F32vec4 *array, float *result) {
   F32vec4 vec0, vec1;
   vec0 = _mm_load_ps ((float *) array); // Load array's first four floats

   //*****************************************************
   // Add all elements of the array, four elements at a time
   //******************************************************
   vec0 += array[1]; // Add elements 5-8
   vec0 += array[2]; // Add elements 9-12
   vec0 += array[3]; // Add elements 13-16
   vec0 += array[4]; // Add elements 17-20

   //*****************************************************
   // There are now four partial sums.
   // Add the two lowers to the two raises,
   // then add those two results together
   //*****************************************************
   vec1 = SHUFFLE(vec1, vec0, 0x40);
   vec0 += vec1;
   vec1 = SHUFFLE(vec1, vec0, 0x30);
   vec0 += vec1;
   vec0 = SHUFFLE(vec0, vec0, 2);
   _mm_store_ss (result, vec0); // Store the final sum 
} 

void main(int argc, char *argv[]) {
   int i;
 
//Initialize the array
   for (i=0; i < SIZE; i++) { array[i] = (float) i; }

//Call function to add all array elements
   Add20ArrayElements (array, &result);

//Print average array element value
   printf ("Average of all array values = %f\n", result/20.);
   printf ("The correct answer is %f\n\n\n", 9.5); 
}

Parent topic: Intel® C++ Class Libraries

Select Your Language

Using Intel.com Search

Quick Links

Recent Searches

Advanced Search

Only search in

Intel® C++ Compiler Classic Developer Guide and Reference

Programming Example