FDTD Acceleration for Cylindrical Resonator Design Based on the Hybrid of Single and Double Precision Floating-Point Computation

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/jcengi/volume-2014/634269/figures/634269.fig.0010a.svgz" name="634269.fig.0010a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Electric field obtained by double precision computation</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/jcengi/volume-2014/634269/figures/634269.fig.0010b.svgz" name="634269.fig.0010b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Electric field obtained by hybrid precision computation</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/jcengi/volume-2014/634269/figures/634269.fig.0010c.svgz" name="634269.fig.0010c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Absolute difference of the double and hybrid computations</td></tr></table>

<div>Comparison of the simulation results using double and hybrid precision computations.</div>

Journal of Computational Engineering

fig10

Figure 10

Figure 10: FDTD Acceleration for Cylindrical Resonator Design Based on the Hybrid of Single and Double Precision Floating-Point Computation 