Merge sharelatex-2017-05-09-0100 into master

main.tex

@@ -39,6 +39,8 @@ We evaluate an efficient implementation of MLFMM for such two-dimensional volume
 \section{Introduction}
 \label{sec:introduction}
 
+
+
 In order to achieve an efficient implementation on graphics processing units (GPUs), the MLFMM operations are formulated as matrix-matrix multiplications.
 To avoid host-device data transfer, common operators are pre-computed, moved to the GPU, and reused as needed.
 Large matrices are partitioned among message passing interface (MPI) processes and each process employs a single GPU for performing partial multiplications.
@@ -149,6 +151,12 @@ This reflects the current slow pace of single-threaded CPU performance improveme
 The corresponding single-GPU speedup in S822LC over XK is $4.4\times$.
 On a per-node basis (``1 GPU'' in XK, ``4 GPU'' in S822LC), the speedup is $17.9\times$.
 
+\subsection{MPI Communication Overlap}
+
+\tikzstyle{int}=[draw, fill=blue!20, minimum size=2em]
+\tikzstyle{init} = [pin edge={to-,thin,black}]
+
+
 \subsection{Computation Kernel Breakdown}
 
 Fig.~\ref{fig:kernel_breakdown} shows the amount of  of MLFMM execution time spent in computational kernels.