Skip to content
Snippets Groups Projects
Commit 654ed97a authored by Ewan Roche's avatar Ewan Roche
Browse files

Font size changes

parent 496c99e7
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
Showing
with 169 additions and 39 deletions
document.tex
+ 169
− 39
View file @ 654ed97a
......@@ -18,11 +18,27 @@
%---------------------
\begin{frame}
\begin{block}{}
Today we will look at
\end{block}
\begin{itemize}
\item<2-> Hardware
\item<3-> Parallel programming
\item<4-> Compiling and linking
\item<5-> Running on a cluster
\end{itemize}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
\large
Hardware\\ is\\ complicated
\normalsize
\end{center}
\end{block}
......@@ -46,8 +62,8 @@ Pinning processes to cores
\end{block}
\begin{itemize}
\item<1-> \tt{1} - task is allowed
\item<2-> \tt{0} - task is excluded
\item<2-> \tt{1} - task is allowed
\item<3-> \tt{0} - task is excluded
\end{itemize}
\end{frame}
......@@ -56,33 +72,51 @@ Pinning processes to cores
\begin{frame}
\begin{block}{}
CPU masks
CPU masks for a 8 core system
\begin{itemize}
\item<1-> \tt{10000000}
\item<2-> \tt{01000000}
\item<3-> \tt{00110000}
\item<4-> \tt{11110000}
\item<5-> \tt{00001111}
\item<6-> \tt{11111111}
\item<2-> \tt{10000000}
\item<3-> \tt{01000000}
\item<4-> \tt{00110000}
\item<5-> \tt{11110000}
\item<6-> \tt{00001111}
\item<7-> \tt{11111111}
\end{itemize}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
CPU masks for a 8 core system
\begin{itemize}
\item \tt{10000000 = 0x80}
\item \tt{01000000 = 0x40}
\item \tt{00110000 = 0x30}
\item \tt{11110000 = 0xF0}
\item \tt{00001111 = 0xF}
\item \tt{11111111 = 0xFF}
\end{itemize}
\end{block}
\end{frame}
SIMD = Single Instruction Multiple Data\\
\vspace{5mm}
Why processing "power" has increased while clock speeds have decreased.
%---------------------
\end{block}
\begin{frame}
\begin{block}{}
\Large
\textbf{S}ingle\\
\textbf{I}nstruction\\
\textbf{M}ultiple\\
\textbf{D}ata\\
\normalsize
\end{block}
\end{frame}
%---------------------
......@@ -118,7 +152,9 @@ Why processing "power" has increased while clock speeds have decreased.
\begin{frame}
\begin{block}{}
\begin{center}
HPC and HPCG
\large
HPL and HPCG
\normalsize
\end{center}
\end{block}
......@@ -126,20 +162,60 @@ HPC and HPCG
%---------------------
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
SIMD
HPL can use roughly 80\% of the peak performance
\end{center}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
HPCG can use roughly 2\% of the peak performance
\end{center}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
HPCG is representative for lots of scientific codes
\end{center}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
\large
Shared Memory
\normalsize
\end{center}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
Every task sees all the data
\end{center}
\end{block}
......@@ -149,12 +225,33 @@ Shared Memory
\begin{frame}
\begin{block}{}
\begin{center}
\large
Distributed Memory
\normalsize
\end{center}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
Workers have their own data and can't see data belonging to other workers
\end{center}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
\begin{center}
If they need to ask to see something they have to send a message
\end{center}
\end{block}
\end{frame}
%---------------------
......@@ -335,23 +432,19 @@ The recipe
\end{block}
\end{frame}
\begin{frame}[fragile]
\begin{frame}
\begin{block}{}
\begin{verbatim}
$ module load gcc fftw
$ gcc mycode.c \
-lfftw3 \
-L${FFTW_ROOT}/lib \
-I${FFTW_ROOT}/include \
-o mycode.x
\begin{center}
At runtime we need to set \\
\vspace{5mm}
{\tt LD\_LIBRARY\_PATH}\\
\vspace{5mm}
so the system knows where to find the library
\end{center}
\end{block}
\end{verbatim}
\end{block}
\end{frame}
%---------------------
\begin{frame}
\begin{block}{}
......@@ -365,18 +458,19 @@ What's linked?
%---------------------
\begin{frame}[fragile]
\small
\begin{block}{}
\begin{verbatim}
$ ldd hi
$ ldd qmsolve
linux-vdso.so.1 => (0x00007...)
liboutput.so => \
/home/user/mycode/liboutput.so
libfastqm.so => \
/home/user/qmcode/lib/libfastqm.so
libc.so.6 => /lib64/libc.so.6
\end{verbatim}
\normalsize
\end{block}
\end{frame}
......@@ -406,6 +500,29 @@ Libraries to make your life better
\end{block}
\end{frame}
%---------------------
\begin{frame}[fragile]
\begin{block}{}
\small
\begin{verbatim}
$ module load gcc fftw
$ gcc mycode.c \
-lfftw3 \
-L${FFTW_ROOT}/lib \
-I${FFTW_ROOT}/include \
-o mycode.x
\end{verbatim}
\normalsize
\end{block}
\end{frame}
%---------------------
\begin{frame}
......@@ -423,9 +540,9 @@ Optimising code
\begin{block}{}
Do you want to optimise so that:
\begin{itemize}
\item<2-> the executable is as small as possible
\item<3-> the code runs as fast as possible
\item<4-> the code has "perfect" numerical accuracy
\item<2-> the executable is as small as possible?
\item<3-> the code runs as fast as possible?
\item<4-> the code has "perfect" numerical accuracy?
\end{itemize}
\end{block}
......@@ -627,7 +744,7 @@ matest(float, float, float):
\begin{frame}
\begin{block}{}
\begin{center}
Compilers are be stupid \\
Compilers are stupid \\
\footnotesize
\it
or at least not as intelligent as you might like
......@@ -692,7 +809,7 @@ double *prod, int c)
{
for(int x=0; x < c; x=x+8)
{
prod[x] = array1[x] * array2[x];
prod[x] = a1[x] * a2[x];
prod[x+1] = a1[x+1] * a2[x+1];
prod[x+2] = a1[x+2] * a2[x+2];
prod[x+3] = a1[x+3] * a2[x+3];
......@@ -1087,3 +1204,16 @@ stack:
\end{block}
\end{frame}
\begin{frame}
\begin{block}{}
\end{block}
\end{frame}
\begin{frame}
\begin{block}{}
\begin{center}
https://scitas-data.epfl.ch/kb
\end{center}
\end{block}
\end{frame}
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment