Performance of a Code Migration for the Simulation of Supersonic Ejector Flow to SMP, MIC, and GPU Using OpenMP, OpenMP+LEO, and OpenACC Directives

<table class="algorithm-group"><tr><td><table class="algorithm" id="alg4"><tr><td colspan="2">!$OMP PARALLEL</td></tr><tr><td colspan="2"> !$OMP DO</td></tr><tr><td colspan="2"> !$OMP END DO</td></tr><tr><td colspan="2"> </td></tr><tr><td colspan="2"> !$OMP DO</td></tr><tr><td colspan="2"> !$OMP END DO</td></tr><tr><td colspan="2">!$OMP END PARALLEL</td></tr></table></td></tr></table>

<div>Parallel region persistent between loops.</div>

Scientific Programming

alg4

Listing 4

Listing 4: Performance of a Code Migration for the Simulation of Supersonic Ejector Flow to SMP, MIC, and GPU Using OpenMP, OpenMP+LEO, and OpenACC Directives 

Listing 4 | Performance of a Code Migration for the Simulation of Supersonic Ejector Flow to SMP, MIC, and GPU Using OpenMP, OpenMP+LEO, and OpenACC Directives 