Mpi init structure

book.bib

@@ -88,6 +88,15 @@ @inproceedings{geimer2007
   year={2007}
 }
 
+% MPI-focused performance - Characterising load and communication imbalance
+@book{bohme2014,
+  title={Characterizing load and communication imbalance in parallel applications},
+  author={B{\"o}hme, David},
+  volume={23},
+  year={2014},
+  publisher={Forschungszentrum J{\"u}lich}
+}
+
 % Peak performance reference - Emily 2026-03-16
 @incollection{sterling_chapter_1_2018,
 	address = {Boston},
@@ -123,3 +132,5 @@ @incollection{sterling_chapter_15_2018
 	pages = {451--481},
 	file = {PDF:C\:\\Users\\MDS_ghvn82_\$\\Zotero\\storage\\ZLITG4MC\\Sterling et al. - 2018 - Chapter 15 - Accelerator Architecture.pdf:application/pdf},
 }
+
+

distributed-memory/collective.tex

@@ -0,0 +1,10 @@
+\section{Collective communication inefficiencies}
+\label{section:distributed-memory:collective}
+
+\subsection{Late broadcaster}
+
+\subsection{Early reduce}
+
+\subsection{Wait at NxN}
+
+\subsection{Early scan}

distributed-memory/communication-imbalance.tex

@@ -0,0 +1,6 @@
+\section{Communication imbalance}
+\label{section:distributed-memory:communication-imbalance}
+
+\subsection{Varying number of MPI calls}
+
+\subsection{Varying size of messages}

distributed-memory/distributed-memory.tex

@@ -0,0 +1,62 @@
+\chapter{Distributed-memory parallelism (inter-node) analysis}
+\label{chapter:node-level}
+
+
+
+%Reaching this section indicates that we are struggling to scale across multiple nodes.
+%This is evidenced by the fact that our intra-node scaling is not good (cmp.~Section~\ref{section:high-level:inter-node}), 
+%i.e.~we measure what we get on one core and then extrapolate what our given number of cores should yield.
+%But they don't:
+%The speedup as introduced from \eqref{equation:hpc-terms:speedup} is poor as we increase the core count.
+%We leave a lot of potential compute capability unused.
+
+
+
+%Our deep dive starts from an analysis if there is enough concurrency in principle to exploit all cores.
+%If there are not enough concurrent operations, further analysis is not required. 
+%The code can be returned immediately to the developers.
+%Otherwise, we take it from there (Figure~\ref{figure:core:decision-graph}).
+
+
+%\subsection*{Preparation}
+
+%Inter-node analysis is all about how efficiently we use multiple threads.
+%Therefore, it focuses predominantly on relative quantities:
+%How well does the code perform if we add another thread?
+%However, we cannot study 128+ measurements in one go---even though modern performance analysis tools have quite powerful capabilities to compare different setups.
+%We need to focus on few setups that yield interesting setup.
+
+
+
+%\begin{assessmentcrime}
+% People study a whole-node run right from the start without a scalability
+% analysis beforehand.
+%\end{assessmentcrime}
+
+
+
+%\noindent
+%It makes sense to run a strong scaling test and plot the efficiency. 
+%Once completed, we can flag those areas where the gradient suddenly changes or   
+%where the efficiency drops below 80\% or 60\% respectively.
+%These are the setups (turning points) on which we should focus most of the time.
+%Do not try to study any other setup, as you'll most likely be swamped with data
+%that is not relevant or difficult to interpret!
+
+
+
+\paragraph*{How it works}
+
+\begin{itemize}[noitemsep]
+  %\item[$\boxplus$] Run a weak scaling test and plot the efficiency. Narrow down the number of setups of interest, i.e.~identify regions where the efficiency apruptly changes or falls under a threshold.
+  \item[$\boxplus$] TBD
+\end{itemize}
+
+
+\paragraph*{How it does not work}
+
+\begin{itemize}[noitemsep]
+  %\item[$\boxminus$] Start with a full-node run right from the start and hope that you spot interesting trends in the data.
+  \item[$\boxminus$] TBD
+\end{itemize}
+

distributed-memory/point-to-point.tex

@@ -0,0 +1,8 @@
+\section{Point-to-point communication inefficiencies}
+\label{section:distributed-memory:point-to-point}
+
+\subsection{Late senders}
+
+\subsection{Late receivers}
+
+\subsection{Wrong order}

distributed-memory/small-messages.tex

@@ -0,0 +1,3 @@
+\section{Small messages}
+\label{section:distributed-memory:small-messages}
+

distributed-memory/workload-imbalance.tex

@@ -0,0 +1,6 @@
+\section{Workload imbalance}
+\label{section:distributed-memory:workload-imbalance}
+
+\subsection{Static workload imbalance}
+
+\subsection{Dynamic workload imbalance}

main.tex

@@ -88,6 +88,11 @@ \part{Deep Dive}
 \input{node-level/hierarchical-decomposition}
 \input{node-level/fine-granular-task-serialisation}
 
+\input{distributed-memory/distributed-memory}
+\input{distributed-memory/small-messages}
+\input{distributed-memory/point-to-point}
+\input{distributed-memory/collective}
+
 \part{Resources}
 \label{part:resources}