Add Performance in User Manual

Guideline for Hybrid MPI+OMP

doc/UserManual.tex

@@ -9,7 +9,7 @@
 \usepackage{longtable}
 \usepackage{amsmath}
 \usepackage{amsfonts}
-\usepackage{subfigure}
+\usepackage{subcaption}
 \usepackage{afterpage}
 \usepackage[calcwidth]{titlesec}
 \usepackage{verbatim}
@@ -24,6 +24,7 @@
 \usepackage{epstopdf}
 \usepackage{tcolorbox}
 \usepackage{amssymb}
+\usepackage{pgfplots}
 \setmarginsrb{2cm}{2cm}{2cm}{2cm}{0cm}{0cm}{0cm}{0.5cm}%{left}{top}{right}{bottom}{headhgt}{}
 %\numberwithin{equation}{section}
 %Bibliography style:
@@ -1979,6 +1980,52 @@ \section{Generate HORSES3D solution file from OpenFOAM result}
 
 \end{longtable}
 
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+\chapter{Performance}
+\section{Hybrid MPI and OMP}
+Balancing the utilization of MPI and OMP in extensive simulations, particularly for large cases with a degree of freedom (NDOF) exceeding 5,000,000, alongside a substantial number of CPU cores, is advisable. Figure 15.1 illustrates the relative speed-up achieved with varying ratios of shared faces in partitioning and the total number of cores. The hybrid setup demonstrates peak performance at approximately $\left(\frac{nMPIFacesShared}{nMPIFaces}\right)_{max} \approx 0.4-0.6$, particularly when the total number of cores is high. Utilizing this value as a reference point is recommended. In smaller cases, maximizing the number of OMP is recommended. 
+\begin{figure}[h]
+\centering
+        \begin{tikzpicture}
+            \begin{axis}[
+                xlabel={$\left(\frac{nMPIFacesShared}{nMPIFaces}\right)_{max}$},
+                ylabel={Relative Speed-Up},
+                label style={font=\small},
+                xmin=0, xmax=1,
+                ymin=0.6, ymax=1.7,
+                axis lines=left,
+                axis line style={-stealth, line width=2pt}, % Adjust arrow size and line width
+                xtick={0, 0.2, 0.4, 0.6, 0.8, 1.0},
+                ytick={0.5,1.0,1.5},
+                ylabel style={at={(ticklabel cs:0.3)}, anchor=south west, inner sep=0pt, yshift=-10mm}, % Adjust the position of the y-axis label
+                grid=both,
+                ymajorgrids=true,
+                xmajorgrids=true, % Display only vertical grid lines
+                major grid style={line width=0.2pt, grey!50},
+                width=0.48\textwidth,
+                legend pos=south east
+            ]
+                % Plot the curve using the data points
+        		\addplot[blue, thick, mark=*] coordinates {(0.029829545,1.05811138) (0.111114264,1.179805616) (0.216105632,0.957074025) (0.390092879,0.947117469) (0.652849741,1)};
+        		\addlegendentry{nCores = 32}
+
+                \addplot[red, dashed, thick, mark=x] coordinates {(0.111114264,1.31696086) (0.216105632,1.462915601) (0.390092879,1.600746269) (0.652849741,1.383870968) (0.984375,1)};
+                \addlegendentry{nCores = 64}                
+
+                \addplot[black, dashdotted, thick, mark=o] coordinates {(0.216105632,1.237316725) (0.390092879,1.37962963) (0.652849741,1.281892728) (0.984375,1)};
+                \addlegendentry{nCores = 128}  
+
+                % Box Plot
+                \draw[line width=1pt] (current axis.south west) rectangle (current axis.north east); % Box around the axis
+            \end{axis}
+        \end{tikzpicture}
+        \label{fig: OMP_MPI_sharedfaces}
+\caption{Relative speed-up in Hybrid MPI-OMP based on maximum ratio of faces in partitions. NS solver with $64\times64\times32$ elements and polynomial N=3. }
+\end{figure}
+
+
+
 
 
 \clearpage