\documentclass[11pt]{article}
\usepackage{mhchem}
\usepackage{booktabs}
\usepackage{multirow}
\usepackage{textcomp}
\usepackage{epsfig}
\usepackage{hyperref}
\usepackage{hyphenat}
\usepackage[noabbrev, capitalize]{cleveref} % hyperref must be loaded first
\usepackage[
detect-weight=true,
per=slash,
detect-family=true,
separate-uncertainty=true]{siunitx}

\usepackage[dvipsnames]{xcolor}
\usepackage{upquote}

\usepackage[framemethod=tikz]{mdframed}
\usepackage{adjustbox}
\usepackage{listings}
\usepackage{xparse}
\NewDocumentCommand{\codeword}{v}{%
  \texttt{\textcolor{blue}{#1}}%
}
\lstset{language=C++,keywordstyle={\bfseries \color{blue}}}

\usepackage{forest}

\begin{document}
\title{Moving window decomposition implementation using GPU}
\author{Nam H. Tran \\ Boston University}
\date{\today}
\maketitle

\section{Introduction}%
\label{sec:introduction}
The purpose of this work is assessing the feasibility and performance of using
GPU to process raw waveforms from a HPGe detector. Expected result of the MWD
algorithm is shown in \cref{fig:mwdInputOutput}. The input is a
\num{250000}-sample long waveform taken at the preamplifier output of the HPGe
detector. The MWD algorithm transforms each jump in the input waveform into a
flat-top peak, of which height is proportional to charge deposited in the
detector. 

\begin{figure}[tbp]
  \centering
  \includegraphics[width=0.90\linewidth]{figs/mwdInputOutput}
  \caption{MWD algorithm: input waveform on the left, and expected output on
    the right.}%
  \label{fig:mwdInputOutput}
\end{figure}

\section{Set up}%
\label{sec:set_up}
\subsection{Hardware}%
\label{sub:hardware}
There are two consumer computers used in this study:
\begin{itemize}
  \item PC 1\@:
  \begin{itemize}
    \item CPU\@: AMD Ryzen 5 2400G, running at \SI{3.60}{\giga\hertz},
      maximum frequency \SI{3.90}{\giga\hertz}
    \item GPU\@: GeForce GTX 1060, DDR5 memory \SI{6}{GB},
      maximum frequency \SI{1.70}{\giga\hertz}
  \end{itemize}
  \item PC 2\@:
  \begin{itemize}
    \item CPU\@: Intel Core i5\hyp{}4590 CPU, running at \SI{3.30}{\giga\hertz},
      maximum frequency \SI{3.70}{\giga\hertz}
    \item GPU\@: GeForce GTX 1650, DDR5 memory \SI{4}{GB},
      maximum frequency \SI{1.70}{\giga\hertz}
  \end{itemize}
\end{itemize}

\subsection{Software}%
\label{sub:software}
The computers run two different versions of Linux:
\begin{itemize}
  \item PC 1\@: CentOS 7.2
    \begin{itemize}
      \item gcc
      \item CUDA
    \end{itemize}
  \item PC 2\@: Debian 10.2
    \begin{itemize}
      \item gcc (Debian 8.3.0\hyp{}6) 8.3.0
      \item nvcc V9.2.148, CUDA 10.1, driver version 418.74
    \end{itemize}
\end{itemize}

\section{Implementations}%
\label{sec:implementations}
There are two implementations of the MWD algorithm:
\begin{itemize}
  \item C++ implementation which does all calculations on the CPU. This will be
    used to verify the accuracy of the other code, as well as a benchmark
  \item CUDA implementation: offloads the digital pule processing part on to
    the GPU, CPU only handles input/output related tasks
\end{itemize}

\subsection{C++ code}%
\label{sub:c_code}
This implementation uses raw array wrapped in a \codeword{struct} to represent
waveforms, pointers are managed manually. There are 3 methods
\codeword{Deconvolute}, \codeword{OffsetDifferentiate}, and
\codeword{MovingAverage} corresponds to 3 stages of the MWD algorithm.

The related files are:

\begin{forest}
  for tree={
    font=\ttfamily,
    grow'=0,
    child anchor=west,
    parent anchor=south,
    anchor=west,
    calign=first,
    edge path={
      \noexpand\path [draw, \forestoption{edge}]
      (!u.south west) +(7.5pt,0) |- node[fill,inner sep=1.25pt] {} (.child anchor)\forestoption{edge label};
    },
    before typesetting nodes={
      if n=1
        {insert before={[,phantom]}}
        {}
    },
    fit=band,
    before computing xy={l=15pt},
  }
  [mwd
    [mwd.c]
    [srcs
      [vector.h]
      [vector.c]
      [algo.h]
      [algo.c]
    ]
  ]
\end{forest}

\subsection{CUDA code}%
\label{sub:cuda_code}
The CUDA code implements 3 GPU functions \codeword{gpuDeconvolute},
\codeword{gpuOffsetDifferentiate}, and \codeword{gpuMovingAverage} which
replace 3 C++ methods in the other implementation. There are also helpers for
moving data between main memory and GPU memory, error checking and time
keeping. The I/O part is the same as in the C++ version.

Related files are:

\begin{forest}
  for tree={
    font=\ttfamily,
    grow'=0,
    child anchor=west,
    parent anchor=south,
    anchor=west,
    calign=first,
    edge path={
      \noexpand\path [draw, \forestoption{edge}]
      (!u.south west) +(7.5pt,0) |- node[fill,inner sep=1.25pt] {} (.child anchor)\forestoption{edge label};
    },
    before typesetting nodes={
      if n=1
        {insert before={[,phantom]}}
        {}
    },
    fit=band,
    before computing xy={l=15pt},
  }
  [mwd
  [gmwd.cu]
    [srcs
      [gpuAlgo.cu]
      [gpuAlgo.h]
      [gpuTimer.h]
      [gpuUtils.h]
      [prefixScan.cu]
      [prefixScan.h]
    ]
  ]
\end{forest}

\section{Results}%
\label{sec:results}

\section{Code}%
\label{sec:code}
A tarball of the code is attached as \codeword{mwd.tar.gz}


\end{document}