\documentclass[10pt,a4paper]{article}

% Packages
\usepackage{fancyhdr}           % For header and footer
\usepackage{multicol}           % Allows multicols in tables
\usepackage{tabularx}           % Intelligent column widths
\usepackage{tabulary}           % Used in header and footer
\usepackage{hhline}             % Border under tables
\usepackage{graphicx}           % For images
\usepackage{xcolor}             % For hex colours
%\usepackage[utf8x]{inputenc}    % For unicode character support
\usepackage[T1]{fontenc}        % Without this we get weird character replacements
\usepackage{colortbl}           % For coloured tables
\usepackage{setspace}           % For line height
\usepackage{lastpage}           % Needed for total page number
\usepackage{seqsplit}           % Splits long words.
%\usepackage{opensans}          % Can't make this work so far. Shame. Would be lovely.
\usepackage[normalem]{ulem}     % For underlining links
% Most of the following are not required for the majority
% of cheat sheets but are needed for some symbol support.
\usepackage{amsmath}            % Symbols
\usepackage{MnSymbol}           % Symbols
\usepackage{wasysym}            % Symbols
%\usepackage[english,german,french,spanish,italian]{babel}              % Languages

% Document Info
\author{mtelias2}
\pdfinfo{
  /Title (parallels.pdf)
  /Creator (Cheatography)
  /Author (mtelias2)
  /Subject (parallels Cheat Sheet)
}

% Lengths and widths
\addtolength{\textwidth}{6cm}
\addtolength{\textheight}{-1cm}
\addtolength{\hoffset}{-3cm}
\addtolength{\voffset}{-2cm}
\setlength{\tabcolsep}{0.2cm} % Space between columns
\setlength{\headsep}{-12pt} % Reduce space between header and content
\setlength{\headheight}{85pt} % If less, LaTeX automatically increases it
\renewcommand{\footrulewidth}{0pt} % Remove footer line
\renewcommand{\headrulewidth}{0pt} % Remove header line
\renewcommand{\seqinsert}{\ifmmode\allowbreak\else\-\fi} % Hyphens in seqsplit
% This two commands together give roughly
% the right line height in the tables
\renewcommand{\arraystretch}{1.3}
\onehalfspacing

% Commands
\newcommand{\SetRowColor}[1]{\noalign{\gdef\RowColorName{#1}}\rowcolor{\RowColorName}} % Shortcut for row colour
\newcommand{\mymulticolumn}[3]{\multicolumn{#1}{>{\columncolor{\RowColorName}}#2}{#3}} % For coloured multi-cols
\newcolumntype{x}[1]{>{\raggedright}p{#1}} % New column types for ragged-right paragraph columns
\newcommand{\tn}{\tabularnewline} % Required as custom column type in use

% Font and Colours
\definecolor{HeadBackground}{HTML}{333333}
\definecolor{FootBackground}{HTML}{666666}
\definecolor{TextColor}{HTML}{333333}
\definecolor{DarkBackground}{HTML}{A3A3A3}
\definecolor{LightBackground}{HTML}{F3F3F3}
\renewcommand{\familydefault}{\sfdefault}
\color{TextColor}

% Header and Footer
\pagestyle{fancy}
\fancyhead{} % Set header to blank
\fancyfoot{} % Set footer to blank
\fancyhead[L]{
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{C}
    \SetRowColor{DarkBackground}
    \vspace{-7pt}
    {\parbox{\dimexpr\textwidth-2\fboxsep\relax}{\noindent
        \hspace*{-6pt}\includegraphics[width=5.8cm]{/web/www.cheatography.com/public/images/cheatography_logo.pdf}}
    }
\end{tabulary}
\columnbreak
\begin{tabulary}{11cm}{L}
    \vspace{-2pt}\large{\bf{\textcolor{DarkBackground}{\textrm{parallels Cheat Sheet}}}} \\
    \normalsize{by \textcolor{DarkBackground}{mtelias2} via \textcolor{DarkBackground}{\uline{cheatography.com/50550/cs/13933/}}}
\end{tabulary}
\end{multicols}}

\fancyfoot[L]{ \footnotesize
\noindent
\begin{multicols}{3}
\begin{tabulary}{5.8cm}{LL}
  \SetRowColor{FootBackground}
  \mymulticolumn{2}{p{5.377cm}}{\bf\textcolor{white}{Cheatographer}}  \\
  \vspace{-2pt}mtelias2 \\
  \uline{cheatography.com/mtelias2} \\
  \end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}}  \\
   \vspace{-2pt}Not Yet Published.\\
   Updated 12th December, 2017.\\
   Page {\thepage} of \pageref{LastPage}.
\end{tabulary}
\vfill
\columnbreak
\begin{tabulary}{5.8cm}{L}
  \SetRowColor{FootBackground}
  \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Sponsor}}  \\
  \SetRowColor{white}
  \vspace{-5pt}
  %\includegraphics[width=48px,height=48px]{dave.jpeg}
  Measure your website readability!\\
  www.readability-score.com
\end{tabulary}
\end{multicols}}




\begin{document}
\raggedright
\raggedcolumns

% Set font size to small. Switch to any value
% from this page to resize cheat sheet text:
% www.emerson.emory.edu/services/latex/latex_169.html
\footnotesize % Small font.

\begin{multicols*}{3}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{unroll}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{int H\_out = H – K + 1; \newline int W\_out = W – K + 1; \newline for (int b = 0; b \textless{} B; ++b) \newline for (int c = 0; c \textless{} C; ++c) \{ int w\_base = c (KK); for (int p = 0; p \textless{} K; ++p) \newline for (int q = 0; q \textless{} K; ++q) \{ for(inth=0;h\textless{} H\_out;++h) \newline for (int w = 0; w \textless{} W\_out; ++w) \{ \newline int w\_unroll = w\_base + p {\emph{ K + q; \newline int h\_unroll = h }} W\_out + w; \newline X\_unroll{[}b, h\_unroll, w\_unroll{]} = X{[}b, c, h + p, w + q{]};} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{replicate}}  \tn
% Row 0
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{Unroll size CKK x H\_out*W\_out} \tn 
% Row Count 1 (+ 1)
% Row 1
\SetRowColor{white}
\mymulticolumn{1}{x{5.377cm}}{Input (/ for rep) \seqsplit{C(H\_out+K-1)(W\_out+K-1)}} \tn 
% Row Count 3 (+ 2)
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{convo forward}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{int m = blockIdx.x; \newline int h = blockIdx.y / W\_grid + threadIdx.y; \newline int w = blockIdx.y \% W\_grid + threadIdx.x; \newline float acc = 0.; \newline for(intc=0; c\textless{}C;c++)\{ \newline for(intp=0;p\textless{}K;p++) KxK filter for (int q = 0; q \textless{} K; q++)acc += X{[}c, h + p, w + q{]} * W{[}m, c, p, q{]}; \newline \}Y{[}m, h, w{]} = acc;} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{matrix}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{int X\_tile\_width = TILE\_WIDTH + K-1; \newline extern \_\_shared\_\_ float shmem{[}{]}; \newline float* X\_shared = \&shmem{[}0{]}; \newline float W\_shared = \&shmem{[}X\_tile\_width X\_tile\_width{]}; \newline m = blockIdx.x; \newline h\_base = (blockIdx.z / W\_grid) TILE\_SIZE; the block w\_base = (blockIdx.z \% W\_grid) TILE\_SIZE; x = threadIdx.x; ty = threadIdx.y; h = h\_base + tx; w = w\_base + ty; \newline float acc = 0.; \newline for (c = 0; c \textless{} C; c++) \newline tx and ty used as shorthand for threadIdx.x and threadIdx.y \newline if (( ty \textless{} K) \&\& ( tx \textless{} K)) W\_shared{[}ty, tx{]}= W {[}m, c, ty, tx{]}; \newline \_\_syncthreads(); \newline for (int i = h; i \textless{} h\_base + X\_tile\_width; i += TILE\_WIDTH) \{ for (int j = w; j \textless{} w\_base + X\_tile\_width; j += TILE\_WIDTH) \newline X\_shared{[}i - h\_base, j - w\_base{]} = X{[}n, c, i, j{]}\}\_\_syncthreads();\}Y{[}n, m, h, w{]} = acc;} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{Histogram}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{\_\_shared\_\_ unsigned int histo\_private{[}256{]}; \newline if (threadIdx.x \textless{} 256) histo\_private{[}threadidx.x{]} = 0; \newline \_\_syncthreads(); \newline int i = threadIdx.x + blockIdx.x {\emph{ blockDim.x; \newline int stride = blockDim.x }} gridDim.x; while (i \textless{} size) \{ \newline atomicAdd( \&(private\_histo{[}buffer{[}i{]}), 1); \newline i += stride; \} \newline \_\_syncthreads(); \newline if (threadIdx.x \textless{} 256) \newline atomicAdd( \&(histo{[}threadIdx.x{]}), private\_histo{[}threadIdx.x{]} );} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}

\begin{tabularx}{5.377cm}{X}
\SetRowColor{DarkBackground}
\mymulticolumn{1}{x{5.377cm}}{\bf\textcolor{white}{CSR ELL COO JDS JDST}}  \tn
\SetRowColor{LightBackground}
\mymulticolumn{1}{x{5.377cm}}{int row = blockIdx.x {\emph{ blockDim.x + threadIdx.x; \newline if (row \textless{} num\_rows)\{ \newline float dot = 0; \newline  \newline int row\_start = row\_ptr{[}row{]}; \newline int row\_end = row\_ptr{[}row+1{]}; \newline for (int elem = row\_start; elem \textless{} row\_end; elem++) \{ \newline dot += data{[}elem{]} }} x{[}col\_index{[}elem{]}{]}; \} \newline y{[}row{]} = dot; \newline  \newline for(inti=0;i\textless{}num\_elem;i++)\{ \newline dot += data{[}row+i{\emph{num\_rows{]}}}x{[}col\_index{[}row+i{\emph{num\_rows{]}{]}; y{[}row{]} = dot; \newline  \newline for (int i = 0; i \textless{} num\_elem; row++) \newline y{[}row\_index{[}i{]}{]} += data{[}i{]} }} x{[}col\_index{[}i{]}{]}; \newline  \newline int row\_start = jds\_row\_ptr{[}row{]}; \newline int row\_end = jds\_row\_ptr{[}row+1{]}; \newline for (int elem = row\_start; elem \textless{} row\_end; elem++) \{ \newline dot += data{[}elem{]} {\emph{ x{[}col\_index{[}elem{]}{]}; y{[}jds\_row\_index{[}row{]}{]} = dot; \newline  \newline unsigned in sec = 0; \newline while (jds\_t\_col\_ptr{[}sec+1{]}-jds\_t\_col\_ptr{[}sec{]} \textgreater{} row)\{ dot += data{[}jds\_t\_col\_ptr{[}sec{]}+row{]} }} \newline x{[}col\_index{[}jds\_t\_col\_ptr{[}sec{]}+row{]}{]}; \newline    sec++; \newline y{[}jds\_row\_index{[}row{]}{]} = dot; \newline \}} \tn 
\hhline{>{\arrayrulecolor{DarkBackground}}-}
\end{tabularx}
\par\addvspace{1.3em}


% That's all folks
\end{multicols*}

\end{document}