quelque MAJ

[kahina_paper1.git] / paper.tex

diff --git a/paper.tex b/paper.tex
index c8a669875ef7f21354062b4e62411a0c98328977..a72d1779e2de46874625a8f75decf67bbbd30972 100644 (file)
--- a/paper.tex
+++ b/paper.tex
@@ -4,6 +4,7 @@
 %%\usepackage[utf8]{inputenc}
 %%\usepackage[T1]{fontenc}
 %%\usepackage[french]{babel}
 %%\usepackage[utf8]{inputenc}
 %%\usepackage[T1]{fontenc}
 %%\usepackage[french]{babel}

+\usepackage{float} 

 \usepackage{amsmath,amsfonts,amssymb}
 \usepackage[ruled,vlined]{algorithm2e}
 %\usepackage[french,boxed,linesnumbered]{algorithm2e}
 \usepackage{amsmath,amsfonts,amssymb}
 \usepackage[ruled,vlined]{algorithm2e}
 %\usepackage[french,boxed,linesnumbered]{algorithm2e}


@@ -53,7 +54,7 @@
 
 \begin{frontmatter}
 
 
 \begin{frontmatter}
 

-\title{Parallel polynomial root finding  using GPU}
+\title{Rapid solution of very high degree polynomials root finding using GPU}

 
 %% Group authors per affiliation:
 \author{Elsevier\fnref{myfootnote}}
 
 %% Group authors per affiliation:
 \author{Elsevier\fnref{myfootnote}}


@@ -78,14 +79,12 @@
 \address[mysecondaryaddress]{FEMTO-ST Institute, University of Franche-Compté }
 
 \begin{abstract}
 \address[mysecondaryaddress]{FEMTO-ST Institute, University of Franche-Compté }
 
 \begin{abstract}

-in this article we present a parallel implementation
-of the Aberth algorithm for the problem root finding for
-high degree polynomials on GPU architecture (Graphics
-Processing Unit).
+Polynomials are mathematical algebraic structures that play a great role in science and engineering. But the process of solving them  for high and large degrees is computationally demanding and still not solved. In this paper, we present the results of a parallel implementation of the Ehrlish-Aberth algorithm for the problem root finding for
+high degree polynomials on GPU architectures (Graphics Processing Unit). The main result of this work is to be able to solve high and very large degree polynomials (up to 100000) very efficiently. We also compare the results with a sequential implementation and the Durand-Kerner method on full and sparse polynomials.

 \end{abstract}
 
 \begin{keyword}
 \end{abstract}
 
 \begin{keyword}

-root finding of polynomials, high degree, iterative methods, Durant-Kerner, GPU, CUDA, CPU , Parallelization
+root finding of polynomials, high degree, iterative methods, Ehrlish-Aberth, Durant-Kerner, GPU, CUDA, CPU , Parallelization

 \end{keyword}
 
 \end{frontmatter}
 \end{keyword}
 
 \end{frontmatter}


@@ -93,14 +92,19 @@ root finding of polynomials, high degree, iterative methods, Durant-Kerner, GPU,
 \linenumbers
 
 \section{The problem of finding roots of a polynomial}
 \linenumbers
 
 \section{The problem of finding roots of a polynomial}

-Polynomials are algebraic structures used in mathematics that capture physical phenomenons and that express the outcome in the form of a function of some unknown variable. Formally speaking,  a polynomial $p(x)$ of degree \textit{n} having $n$ coefficients in the complex plane \textit{C} and zeros $\alpha_{i},\textit{i=1,...,n}$ 
+Polynomials are mathematical algebraic structures used in science and engineering to capture physical phenomenons and to express any outcome in the form of a function of some unknown variables. Formally speaking,  a polynomial $p(x)$ of degree \textit{n} having $n$ coefficients in the complex plane \textit{C} is :

 %%\begin{center}
 \begin{equation}
 %%\begin{center}
 \begin{equation}

-     {\Large p(x)=\sum{a_{i}x^{i}}=a_{n}\prod(x-\alpha_{i}),a_{0} a_{n}\neq 0}.
+     {\Large p(x)=\sum_{i=0}^{n}{a_{i}x^{i}}}.

 \end{equation}
 %%\end{center}
 
 \end{equation}
 %%\end{center}
 

-The root finding problem consists in finding the values of all the $n$ values of the variable $x$ for which \textit{p(x)} is nullified. Such values are called zeroes of $p$. The problem of finding a root is equivalent to that of solving a fixed-point problem. To see this, consider the fixed-point problem of finding the $n$-dimensional
+The root finding problem consists in finding the values of all the $n$ values of the variable $x$ for which \textit{p(x)} is nullified. Such values are called zeroes of $p$. If zeros are $\alpha_{i},\textit{i=1,...,n}$ the $p(x)$ can be written as :
+\begin{equation}
+     {\Large p(x)=a_{n}\prod_{i=1}^{n}(x-\alpha_{i}), a_{0} a_{n}\neq 0}.
+\end{equation}
+
+The problem of finding a root is equivalent to that of solving a fixed-point problem. To see this, consider the fixed-point problem of finding the $n$-dimensional

 vector $x$ such that
 \begin{center}
 $x=g(x)$
 vector $x$ such that
 \begin{center}
 $x=g(x)$


@@ -317,6 +321,7 @@ Applying this solution for the Aberth method we obtain the
 iteration function with logarithm:
 %%$$ \exp \bigl(  \ln(p(z)_{k})-ln(\ln(p(z)_{k}^{'}))- \ln(1- \exp(\ln(p(z)_{k})-ln(\ln(p(z)_{k}^{'})+\ln\sum_{i\neq j}^{n}\frac{1}{z_{k}-z_{j}})$$
 \begin{equation}
 iteration function with logarithm:
 %%$$ \exp \bigl(  \ln(p(z)_{k})-ln(\ln(p(z)_{k}^{'}))- \ln(1- \exp(\ln(p(z)_{k})-ln(\ln(p(z)_{k}^{'})+\ln\sum_{i\neq j}^{n}\frac{1}{z_{k}-z_{j}})$$
 \begin{equation}

+\label{Log_H2}

 H_{i}(z)=z_{i}^{k}-\exp \left(\ln \left(
 p(z_{k})\right)-\ln\left(p(z_{k}^{'})\right)- \ln
 \left(1-Q(z_{k})\right)\right),
 H_{i}(z)=z_{i}^{k}-\exp \left(\ln \left(
 p(z_{k})\right)-\ln\left(p(z_{k}^{'})\right)- \ln
 \left(1-Q(z_{k})\right)\right),


@@ -325,11 +330,17 @@ p(z_{k})\right)-\ln\left(p(z_{k}^{'})\right)- \ln
 where:
 
 \begin{equation}
 where:
 
 \begin{equation}

+\label{Log_H1}

 Q(z_{k})=\exp\left( \ln (p(z_{k}))-\ln(p(z_{k}^{'}))+\ln \left(
 \sum_{k\neq j}^{n}\frac{1}{z_{k}-z_{j}}\right)\right).
 \end{equation}
 
 Q(z_{k})=\exp\left( \ln (p(z_{k}))-\ln(p(z_{k}^{'}))+\ln \left(
 \sum_{k\neq j}^{n}\frac{1}{z_{k}-z_{j}}\right)\right).
 \end{equation}
 

-This solution is applied when it is necessary ??? When ??? (SIDER)
+This solution is applied when the root except the circle unit, represented by the radius $R$ evaluated as:
+\begin{equation}
+\label{R}
+R = \exp( \log(DBL\_MAX) / (2*n) )
+\end{equation}
+ where $DBL\_MAX$ stands for the maximum representable double value.

 
 \section{The implementation of simultaneous methods in a parallel computer}
 \label{secStateofArt}   
 
 \section{The implementation of simultaneous methods in a parallel computer}
 \label{secStateofArt}   


@@ -355,7 +366,7 @@ parallelism that can be suitably exploited by SIMD machines.
 Moreover, they have fast rate of convergence (quadratic for the
 Durand-Kerner and cubic for the Ehrlisch-Aberth). Various parallel
 algorithms reported for these methods can be found
 Moreover, they have fast rate of convergence (quadratic for the
 Durand-Kerner and cubic for the Ehrlisch-Aberth). Various parallel
 algorithms reported for these methods can be found

-in~\cite{Cosnard90, Freeman89,Freemanall90,,Jana99,Janall99}.
+in~\cite{Cosnard90, Freeman89,Freemanall90,Jana99,Janall99}.

 Freeman and Bane~\cite{Freemanall90} presented two parallel
 algorithms on a local memory MIMD computer with the compute-to
 communication time ratio O(n). However, their algorithms require
 Freeman and Bane~\cite{Freemanall90} presented two parallel
 algorithms on a local memory MIMD computer with the compute-to
 communication time ratio O(n). However, their algorithms require


@@ -381,6 +392,8 @@ GPUs, which details are discussed in the sequel.
 
 
 \section {A CUDA parallel Ehrlisch-Aberth method}
 
 
 \section {A CUDA parallel Ehrlisch-Aberth method}

+In the following, we describe the parallel implementation of Ehrlisch-Aberth method on GPU 
+for solving high degree polynomials. First, the hardware and software of the GPUs are presented. Then, a CUDA parallel Ehrlisch-Aberth method are presented.

 
 \subsection{Background on the GPU architecture}
 A GPU is viewed as an accelerator for the data-parallel and
 
 \subsection{Background on the GPU architecture}
 A GPU is viewed as an accelerator for the data-parallel and


@@ -485,7 +498,7 @@ There exists two ways to execute the iterative function that we call a Jacobi on
 H(i,z^{k+1})=\frac{p(z^{(k)}_{i})}{p'(z^{(k)}_{i})-p(z^{(k)}_{i})\sum^{n}_{j=1 j\neq i}\frac{1}{z^{(k)}_{i}-z^{(k)}_{j}}}, i=1,...,n.
 \end{equation}
 
 H(i,z^{k+1})=\frac{p(z^{(k)}_{i})}{p'(z^{(k)}_{i})-p(z^{(k)}_{i})\sum^{n}_{j=1 j\neq i}\frac{1}{z^{(k)}_{i}-z^{(k)}_{j}}}, i=1,...,n.
 \end{equation}
 

-With the the Gauss-seidel iteration, we have:
+With the Gauss-seidel iteration, we have:

 \begin{equation}
 \label{eq:Aberth-H-GS}
 H(i,z^{k+1})=\frac{p(z^{(k)}_{i})}{p'(z^{(k)}_{i})-p(z^{(k)}_{i})(\sum^{i-1}_{j=1}\frac{1}{z^{(k)}_{i}-z^{(k+1)}_{j}}+\sum^{n}_{j=i+1}\frac{1}{z^{(k)}_{i}-z^{(k)}_{j}})}, i=1,...,n.
 \begin{equation}
 \label{eq:Aberth-H-GS}
 H(i,z^{k+1})=\frac{p(z^{(k)}_{i})}{p'(z^{(k)}_{i})-p(z^{(k)}_{i})(\sum^{i-1}_{j=1}\frac{1}{z^{(k)}_{i}-z^{(k+1)}_{j}}+\sum^{n}_{j=i+1}\frac{1}{z^{(k)}_{i}-z^{(k)}_{j}})}, i=1,...,n.


@@ -583,33 +596,26 @@ or from GPU memory to CPU memory \verb=(cudaMemcpyDeviceToHost))=.
 \section{Experimental study}
 
 \subsection{Definition of the polynomial used}
 \section{Experimental study}
 
 \subsection{Definition of the polynomial used}

-We use two forms of  polynomials:
-\paragraph{sparse polynomial}:
-in this following form, the roots are distributed on 2 distinct circles:
+We study two forms of  polynomials the sparse polynomials and the full polynomials:
+\paragraph{Sparse polynomial}: in this following form, the roots are distributed on 2 distinct circles:

 \begin{equation}
 \begin{equation}

-       \forall \alpha_{1} \alpha_{2} \in C,\forall n_{1},n_{2} \in N^{*}; P(z)= (z^{n^{1}}-\alpha_{1})(z^{n^{2}}-\alpha_{2})
+       \forall \alpha_{1} \alpha_{2} \in C,\forall n_{1},n_{2} \in N^{*}; P(z)= (z^{n_{1}}-\alpha_{1})(z^{n_{2}}-\alpha_{2})

 \end{equation}
 \end{equation}

-

 This form makes it possible to associate roots having two
 different modules and thus to work on a polynomial constitute
 of four non zero terms.
 
 This form makes it possible to associate roots having two
 different modules and thus to work on a polynomial constitute
 of four non zero terms.
 

-\paragraph{Full polynomial}:
- the second form used to obtain a full polynomial is:
+\paragraph{Full polynomial}: the second form used to obtain a full polynomial is:

 %%\begin{equation}
        %%\forall \alpha_{i} \in C,\forall n_{i}\in N^{*}; P(z)= \sum^{n}_{i=1}(z^{n^{i}}.a_{i})
 %%\end{equation}
 
 \begin{equation}
 %%\begin{equation}
        %%\forall \alpha_{i} \in C,\forall n_{i}\in N^{*}; P(z)= \sum^{n}_{i=1}(z^{n^{i}}.a_{i})
 %%\end{equation}
 
 \begin{equation}

-     {\Large \forall a_{i} \in C, i\in N; p(x)=\sum^{n-1}_{i=1} a_{i}.x^{i}} 
+     {\Large \forall a_{i} \in C, i\in N;  p(x)=\sum^{n}_{i=0} a_{i}.x^{i}} 

 \end{equation}
 with this form, we can have until \textit{n} non zero terms.
 
 \subsection{The study condition} 
 \end{equation}
 with this form, we can have until \textit{n} non zero terms.
 
 \subsection{The study condition} 

-In order to have representative average values, for each
-point of our curves we measured the roots finding of 10
-different polynomials.
-

 The our experiences results concern two parameters which are
 the polynomial degree and the execution time of our program
 to converge on the solution. The polynomial degree allows us
 The our experiences results concern two parameters which are
 the polynomial degree and the execution time of our program
 to converge on the solution. The polynomial degree allows us


@@ -617,83 +623,79 @@ to validate that our algorithm is powerful with high degree
 polynomials. The execution time remains the
 element-key which justifies our work of parallelization.
        For our tests we used a CPU Intel(R) Xeon(R) CPU
 polynomials. The execution time remains the
 element-key which justifies our work of parallelization.
        For our tests we used a CPU Intel(R) Xeon(R) CPU

-E5620@2.40GHz and a GPU K40 (with 6 Go of ram)
+E5620@2.40GHz and a GPU K40 (with 6 Go of ram).

 
 
 \subsection{Comparative study}
 
 
 \subsection{Comparative study}

-We initially carried out the convergence of Aberth algorithm with various sizes of polynomial, in second we evaluate the influence of the size of the threads per block....
-
-\subsubsection{Aberth algorithm on CPU and GPU}
-
-%\begin{table}[!ht]
-%      \centering
-%              \begin{tabular} {|R{2cm}|L{2.5cm}|L{2.5cm}|L{1.5cm}|L{1.5cm}|}
-%                      \hline Polynomial's degrees & $T_{exe}$ on CPU & $T_{exe}$ on GPU & CPU iteration & GPU iteration\\
-%                              \hline 5000 & 1.90 & 0.40 & 18 & 17\\
-%                              \hline 10000 & 172.723 & 0.59 & 21 & 24\\
-%                              \hline 20000 & 172.723 & 1.52 & 21 & 25\\
-%                              \hline 30000 & 172.723 & 2.77 & 21 & 33\\
-%                              \hline 50000 & 172.723 & 3.92 & 21 & 18\\
-%                              \hline 500000 & $>$1h & 497.109 &  & 24\\
-%                              \hline 1000000 & $>$1h & 1,524.51& & 24\\
-%                              \hline 
-%              \end{tabular}
-%      \caption{the convergence of Aberth algorithm}
-%      \label{tab:theConvergenceOfAberthAlgorithm}
-%\end{table}
- 
-\begin{figure}[htbp]
+In this section, we discuss the performance Ehrlish-Aberth method  of root finding polynomials implemented on CPUs and on GPUs.
+
+We performed a set of experiments on the sequential and the parallel algorithms, for both sparse and full polynomials and different sizes. We took into account the execution time,the  polynomial size and the number of threads per block performed by sum or each experiment on CPUs and on GPUs.
+
+All experimental results obtained from the simulations are made in double precision data, for a convergence tolerance of the methods set to $10^{-7}$. Since we were more interested in the comparison of the performance behaviors of Ehrlish-Aberth and Durand-Kerner methods on CPUs versus on GPUs. The initialization values of the vector solution of the Ehrlich-Aberth method are given in section 2.2. 
+\subsubsection{The execution time in seconds of Ehrlisch-Aberth algorithm on CPU core vs. on a Tesla GPU}
+
+
+\begin{figure}[H]

 \centering
   \includegraphics[width=0.8\textwidth]{figures/Compar_EA_algorithm_CPU_GPU}
 \centering
   \includegraphics[width=0.8\textwidth]{figures/Compar_EA_algorithm_CPU_GPU}

-\caption{Aberth algorithm on CPU and GPU}
+\caption{The execution time in seconds of Ehrlisch-Aberth algorithm on CPU core vs. on a Tesla GPU}

 \label{fig:01}
 \end{figure}
 
 \label{fig:01}
 \end{figure}
 

+Figure 1 %%show a comparison of execution time between the parallel and sequential version of the Ehrlisch-Aberth algorithm with sparse polynomial exceed 100000, 
+We report the execution times of the Ehrlisch-Aberth method implemented on one core of the Quad-Core Xeon E5620 CPU and those of the same methods implemented on one Nvidia Tesla K40c GPU, with sparse polynomial degrees ranging from 100,000 to 1,000,000. We can see that the methods implemented on the GPU are faster than those implemented on the CPU. This is due to the GPU ability to compute the data-parallel functions faster than its CPU counterpart. However, the execution time for the sequential implementation exceed 16,000 s for 450,000 degrees polynomials, in counterpart  the GPU implementation for the same polynomials need only 350 s, more than again, with 1,000,000 polynomials degrees GPU implementation not reach 2,300 s degrees. While CPU implementation need more than 10 hours. We can also notice that the GPU implementation are almost 47 faster then those implementation on the CPU. Furthermore, we verify that the number of iterations is the same. This reduction of time allows us to compute roots of polynomial of more important degree at the same time than with a CPU.
+ 
+
+
+\subsubsection{Influence of the number of threads on the execution times of different polynomials (sparse and full)}
+It is also interesting to see the influence of the number of threads per block on the execution time. For that, we notice that the maximum number of threads per block for the Nvidia Tesla K40c GPU is 1024, so we varied the number of threads per block from 8 to 1024. We took into account the execution time for both sparse and full polynomials of size 50000 and 500000 degrees.

 
 

-\subsubsection{The impact of the thread's number into the convergence of Aberth  algorithm}
-
-%\begin{table}[!h]
-%      \centering
-%              \begin{tabular} {|R{2.5cm}|L{2.5cm}|L{2.5cm}|}
-%                      \hline Thread's numbers & Execution time &Number of iteration\\
-%                              \hline 1024 & 523 & 27\\
-%                              \hline 512 & 449.426 & 24\\
-%                              \hline 256 & 440.805 & 24\\
-%                              \hline 128 & 456.175 & 22\\
-%                              \hline 64 & 472.862 & 23\\
-%                              \hline 32 & 830.152 & 24\\
-%                              \hline 8 & 2632.78 & 23 \\
-%                              \hline
-%                              \end{tabular}
-%                              \caption{The impact of the thread's number into the convergence of Aberth  algorithm}
-%      \label{tab:Theimpactofthethread'snumberintotheconvergenceofAberthalgorithm}
-%              
-%\end{table}
-
-
-\begin{figure}[htbp]
+\begin{figure}[H]

 \centering
   \includegraphics[width=0.8\textwidth]{figures/influence_nb_threads}
 \caption{Influence of the number of threads on the execution times of different polynomials (sparse and full)}
 \label{fig:01}
 \end{figure}
 
 \centering
   \includegraphics[width=0.8\textwidth]{figures/influence_nb_threads}
 \caption{Influence of the number of threads on the execution times of different polynomials (sparse and full)}
 \label{fig:01}
 \end{figure}
 

+The figure 2 show that, the best execution time for both sparse and full polynomial are given while the threads number varies between 64 and 256 threads per bloc. We notice that with small polynomials the number of threads per block is 64, Whereas, the large polynomials the number of threads per block is 256. However,In the following experiments we specify that the number of thread by block is 256.

 
 

+\subsubsection{The impact of exp-log solution to compute very high degrees of  polynomial}

 
 

-\subsubsection{A comparative study between Aberth and Durand-kerner algorithm}
-\begin{table}[htbp]
-       \centering
-               \begin{tabular} {|R{2cm}|L{2.5cm}|L{2.5cm}|L{1.5cm}|L{1.5cm}|}
-                       \hline Polynomial's degrees & Aberth $T_{exe}$ & D-Kerner $T_{exe}$ & Aberth iteration & D-Kerner iteration\\
-                       \hline 5000 &  0.40 & 3.42 & 17 & 138 \\
-                       \hline 50000 & 3.92 & 385.266 & 17 & 823\\
-                       \hline 500000 & 497.109 & 4677.36 & 24 & 214\\
-                       \hline                                  
-                                       \end{tabular}
-       \caption{Aberth algorithm compare to Durand-Kerner algorithm}
-       \label{tab:AberthAlgorithCompareToDurandKernerAlgorithm}
-\end{table}
+In this experiment we report the performance of log.exp solution describe in ~\ref{sec2} to compute very high degrees polynomials.   
+\begin{figure}[H]
+\centering
+  \includegraphics[width=0.8\textwidth]{figures/log_exp}
+\caption{The impact of exp-log solution to compute very high degrees of  polynomial.}
+\label{fig:01}
+\end{figure}
+
+The figure 3, show a comparison between the execution time of the Ehrlisch-Aberth algorithm applying log-exp solution and the execution time of the Ehrlisch-Aberth algorithm without applying log-exp solution, with full polynomials degrees. We can see that the execution time for the both algorithms are the same while the polynomials degrees are less than 4500. After,we show clearly that the classical version of Ehrlisch-Aberth algorithm (without applying log.exp) stop to converge and can not solving polynomial exceed 4500, in counterpart, the new version of Ehrlisch-Aberth algorithm (applying log.exp solution) can solve very high and large full polynomial exceed 100,000 degrees.
+
+in fact, when the modulus of the roots are up than \textit{R} given in ~\ref{R},this exceed the limited number in the mantissa of floating points representations and can not compute the iterative function given in ~\ref{eq:Aberth-H-GS} to obtain the root solution, who justify the divergence of the classical Ehrlisch-Aberth algorithm. However, applying log.exp solution given in ~\ref{sec2} took into account the limit of floating using the iterative function in(Eq.~\ref{Log_H1},Eq.~\ref{Log_H2}and allows to solve a very large polynomials degrees . 
+
+
+
+%we report the performances of the exp.log for the Ehrlisch-Aberth algorithm for solving very high degree of polynomial. 
+
+ 
+\subsubsection{A comparative study between Ehrlisch-Aberth algorithm and Durand-kerner algorithm}
+In this part, we are interesting to compare the simultaneous methods, Ehrlisch-Aberth and Durand-Kerner in parallel computer using GPU. We took into account the execution time, the number of iteration and the polynomial's size. for the both sparse and full polynomials.  

 
 

+\begin{figure}[H]
+\centering
+  \includegraphics[width=0.8\textwidth]{figures/EA_DK}
+\caption{The execution time of Ehrlisch-Aberth versus Durand-Kerner algorithm on GPU}
+\label{fig:01}
+\end{figure}
+
+This figure show the execution time of the both algorithm EA and DK with sparse polynomial degrees ranging from 1000 to 1000000. We can see that the Ehrlisch-Aberth algorithm are faster than Durand-Kerner algorithm, with an average of 25 times as fast. Then, when degrees of polynomial exceed 500000 the execution time with EA is of the order 100 whereas DK passes in the order 1000. %with double precision not exceed $10^{-5}$.
+
+\begin{figure}[H]
+\centering
+  \includegraphics[width=0.8\textwidth]{figures/EA_DK_nbr}
+\caption{The iteration number of Ehrlisch-Aberth versus Durand-Kerner algorithm}
+\label{fig:01}
+\end{figure}

 
 \bibliography{mybibfile}
 
 
 \bibliography{mybibfile}