new

[book_gpu.git] / BookGPU / Chapters / chapter7 / ch7.tex

diff --git a/BookGPU/Chapters/chapter7/ch7.tex b/BookGPU/Chapters/chapter7/ch7.tex
index e4ffb0af4a6f00fa8be14fa330ceb94ad763171f..45fc4537654456483c5e1dc70d7bc7f6d816e1f8 100644 (file)
--- a/BookGPU/Chapters/chapter7/ch7.tex
+++ b/BookGPU/Chapters/chapter7/ch7.tex
@@ -535,7 +535,8 @@ __global__ void laplace_sigma_transformed(
        {                       
                size_type offset_i = i < alpha ? 2*alpha-i : i >= Ns-alpha ? Ns-1-i : alpha;
                size_type row_i    = offset_i*rank;
        {                       
                size_type offset_i = i < alpha ? 2*alpha-i : i >= Ns-alpha ? Ns-1-i : alpha;
                size_type row_i    = offset_i*rank;

-               size_type offset_j = alpha;  // Always centered stencils in x-dir
+    // Always centered stencils in x-dir
+               size_type offset_j = alpha;  

                size_type row_j    = alpha*rank;
                        
                value_type dhdx    = hx[j];
                size_type row_j    = alpha*rank;
                        
                value_type dhdx    = hx[j];


@@ -819,10 +820,12 @@ Ideally, the ratio $\mathcal{C}_\mathcal{G}/\mathcal{C}_\mathcal{F}$ is small an
     \setlength\figureheight{0.35\textwidth}
     \setlength\figurewidth{0.37\textwidth}
     \subfigure[Performance scaling]{
     \setlength\figureheight{0.35\textwidth}
     \setlength\figurewidth{0.37\textwidth}
     \subfigure[Performance scaling]{

-        {\small\input{Chapters/chapter7/figures/PararealScaletestGTX590.tikz}}
+%        {\small\input{Chapters/chapter7/figures/PararealScaletestGTX590.tikz}}
+      \includegraphics[width=0.5\textwidth]{Chapters/chapter7/figures/PararealScaletestGTX590_conv.pdf}

     }
     \subfigure[Speedup]{
     }
     \subfigure[Speedup]{

-        {\small\input{Chapters/chapter7/figures/PararealSpeedupGTX590.tikz}}
+       % {\small\input{Chapters/chapter7/figures/PararealSpeedupGTX590.tikz}}
+ \includegraphics[width=0.5\textwidth]{Chapters/chapter7/figures/PararealSpeedupGTX590_conv.pdf}

     }
     \end{center}
     \caption{(a) Parareal absolute timings for an increasingly number of water waves traveling one wave length, each wave resolution is ($33\times 9$). (b) Parareal speedup for two to sixteen compute nodes compared to the purely sequential single GPU solver. Notice how insensitive the parareal scheme is to the size of the problem solved. Test environment 2.}\label{ch7:fig:DDPA_SPEEDUP}
     }
     \end{center}
     \caption{(a) Parareal absolute timings for an increasingly number of water waves traveling one wave length, each wave resolution is ($33\times 9$). (b) Parareal speedup for two to sixteen compute nodes compared to the purely sequential single GPU solver. Notice how insensitive the parareal scheme is to the size of the problem solved. Test environment 2.}\label{ch7:fig:DDPA_SPEEDUP}