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="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/sp/volume-2015/739107/figures/739107.fig.0011a.svgz" name="739107.fig.0011a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Computing time obtained with HT disabled (12 threads)</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/sp/volume-2015/739107/figures/739107.fig.0011b.svgz" name="739107.fig.0011b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Computing time obtained with HT enabled (24 threads)</td></tr></table>

<div>Computing times obtained on the Dual Xeon CPU.</div>

Scientific Programming

fig11

Figure 11

Figure 11: Performance of a Code Migration for the Simulation of Supersonic Ejector Flow to SMP, MIC, and GPU Using OpenMP, OpenMP+LEO, and OpenACC Directives 

Figure 11 | Performance of a Code Migration for the Simulation of Supersonic Ejector Flow to SMP, MIC, and GPU Using OpenMP, OpenMP+LEO, and OpenACC Directives 