Effective SIMD Vectorization for Intel Xeon Phi Coprocessors

Algorithm 5

An example of OpenMP parallel for and SIMD combined usage.

#pragma omp declare SIMD uniform(max_iter) SIMDlen(32)

uint32_t mandel (fcomplex c, uint32_t max_iter)

  // Computes number of iterations(count variable)

  // that it takes for parameter c to be known to

  // be outside mandelbrot set

  uint32_t count = 1; fcomplex z = c;

  for (int32_t i = 0; i < max_iter; i += 1) {

   z = z   z + c;

   int t = (cabsf(z) < 2.0f);

   count += t;

   if (t == 0) {  break;}

  }

  return count;

Caller site code:

int main() {

  …  …  …

  #pragma omp parallel for schedule(guided)

  for (int32_t y = 0; y < ImageHeight; ++y) {

   float c_im = max_imag - y   imag_factor;

   #pragma omp SIMD safelen(32)

   for (int32_t x = 0; x < ImageWidth; ++x) {

    fcomplex in_val;

    in_val = (min_real + xreal_factor) + (c_im1.0iF);

    countyx  = mandel (in_val, max_iter);

   }

  }

  …  …  …