#include #include #include #include int main(int argc, char **argv) { float *block; int blockSize=8388608*8, numBlocks=200, i, j, iblock; block = (float *)memalign(32, blockSize*sizeof(float)); memset(block, 0, blockSize*sizeof(float)); for(iblock = 0; iblock < numBlocks; iblock++) { //#pragma omp simd for(j = 0; j < blockSize; j++) { block[j] += sqrtf((float)(j)); } } printf("Last blocksize element is %f\n", block[blockSize-1]); return 0; }