quelque MAJ

[kahina_paper1.git] / paper.tex

diff --git a/paper.tex b/paper.tex
index a6e1cf8792fbcf69e33a09596d00cf25387669d6..a72d1779e2de46874625a8f75decf67bbbd30972 100644 (file)
--- a/paper.tex
+++ b/paper.tex
@@ -4,8 +4,10 @@
 %%\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{amsmath,amsfonts,amssymb}
 \usepackage[ruled,vlined]{algorithm2e}

+%\usepackage[french,boxed,linesnumbered]{algorithm2e}

 \usepackage{array,multirow,makecell}
 \setcellgapes{1pt}
 \makegapedcells
 \usepackage{array,multirow,makecell}
 \setcellgapes{1pt}
 \makegapedcells


@@ -52,7 +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}}


@@ -77,14 +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}


@@ -92,14 +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}
 $x=g(x)$


@@ -232,6 +237,7 @@ The initialization of a polynomial p(z) is done by setting each of the $n$ compl
 :
 
 \begin{equation}
 :
 
 \begin{equation}

+\label{eq:SimplePolynome}

   p(z)=\sum{a_{i}z^{n-i}} , a_{n} \neq 0,a_{0}=1, a_{i}\subset C
 \end{equation}
 
   p(z)=\sum{a_{i}z^{n-i}} , a_{n} \neq 0,a_{0}=1, a_{i}\subset C
 \end{equation}
 


@@ -248,6 +254,7 @@ performed this choice by selecting complex numbers along different
 circles and relies on the result of~\cite{Ostrowski41}.
 
 \begin{equation}
 circles and relies on the result of~\cite{Ostrowski41}.
 
 \begin{equation}

+\label{eq:radiusR}

 %%\begin{align}
 \sigma_{0}=\frac{u+v}{2};u=\frac{\sum_{i=1}^{n}u_{i}}{n.max_{i=1}^{n}u_{i}};
 v=\frac{\sum_{i=0}^{n-1}v_{i}}{n.min_{i=0}^{n-1}v_{i}};\\
 %%\begin{align}
 \sigma_{0}=\frac{u+v}{2};u=\frac{\sum_{i=1}^{n}u_{i}}{n.max_{i=1}^{n}u_{i}};
 v=\frac{\sum_{i=0}^{n-1}v_{i}}{n.min_{i=0}^{n-1}v_{i}};\\


@@ -272,9 +279,10 @@ i}{\frac{1}{z_{i}-z_{j}}}}
 \subsection{Convergence Condition}
 The convergence condition determines the termination of the algorithm. It consists in stopping from running
 the iterative function $H_{i}(z)$ when the roots are sufficiently stable. We consider that the method
 \subsection{Convergence Condition}
 The convergence condition determines the termination of the algorithm. It consists in stopping from running
 the iterative function $H_{i}(z)$ when the roots are sufficiently stable. We consider that the method

-converges sufficiently when:
+converges sufficiently when :

 
 \begin{equation}
 
 \begin{equation}

+\label{eq:Aberth-Conv-Cond}

 \forall i \in
 [1,n];\frac{z_{i}^{(k)}-z_{i}^{(k-1)}}{z_{i}^{(k)}}<\xi
 \end{equation}
 \forall i \in
 [1,n];\frac{z_{i}^{(k)}-z_{i}^{(k-1)}}{z_{i}^{(k)}}<\xi
 \end{equation}


@@ -306,13 +314,14 @@ propose to use the logarithm and the exponential of a complex in order to comput
 \end{align}
 %%\end{equation}
 
 \end{align}
 %%\end{equation}
 

-Using the logarithm (eq. \ref{deflncomplex}) and the exponential (eq. \ref{defexpcomplex}) operators, we can replace any multiplications and divisions with additions and subtractions. Consequently, computations
+Using the logarithm (eq.~\ref{deflncomplex}) and the exponential (eq.~\ref{defexpcomplex}) operators, we can replace any multiplications and divisions with additions and subtractions. Consequently, computations

 manipulate lower absolute values and the roots for large polynomial's degrees can be looked for successfully~\cite{Karimall98}.
 
 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}
 manipulate lower absolute values and the roots for large polynomial's degrees can be looked for successfully~\cite{Karimall98}.
 
 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}

+\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),


@@ -321,11 +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}   


@@ -351,7 +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


@@ -376,7 +391,9 @@ polynomials of 48000. In this paper we present a parallel implementation of Ehli
 GPUs, which details are discussed in the sequel.
 
 
 GPUs, which details are discussed in the sequel.
 
 

-\section {A parallel implementation of 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


@@ -387,9 +404,9 @@ Processors (SPs) organized in several blocks called Streaming
 Multiprocessors (SMs). It also has a memory hierarchy. It has a
 private read-write local memory per SP, fast shared memory and
 read-only constant and texture caches per SM and a read-write
 Multiprocessors (SMs). It also has a memory hierarchy. It has a
 private read-write local memory per SP, fast shared memory and
 read-only constant and texture caches per SM and a read-write

-global memory shared by all its SPs~\cite{NVIDIA10}
+global memory shared by all its SPs~\cite{NVIDIA10}.

 
 

-    On a CPU equipped with a GPU, all the data-parallel and intensive
+On a CPU equipped with a GPU, all the data-parallel and intensive

 functions of an application running on the CPU are off-loaded onto
 the GPU in order to accelerate their computations. A similar
 data-parallel function is executed on a GPU as a kernel by
 functions of an application running on the CPU are off-loaded onto
 the GPU in order to accelerate their computations. A similar
 data-parallel function is executed on a GPU as a kernel by


@@ -408,12 +425,12 @@ transferred in and out of the GPU. However, the speed of memory
 copy between the GPU and the CPU is slower than the memory
 bandwidths of the GPU memories and, thus, it dramatically affects
 the performances of GPU computations. Accordingly, it is necessary
 copy between the GPU and the CPU is slower than the memory
 bandwidths of the GPU memories and, thus, it dramatically affects
 the performances of GPU computations. Accordingly, it is necessary

-to limit data transfers between the GPU and its CPU during the
+to limit as much as possible, data transfers between the GPU and its CPU during the

 computations.
 \subsection{Background on the CUDA Programming Model}
 
 The CUDA programming model is similar in style to a single program
 computations.
 \subsection{Background on the CUDA Programming Model}
 
 The CUDA programming model is similar in style to a single program

-multiple-data (SPMD) softwaremodel. The GPU is treated as a
+multiple-data (SPMD) software model. The GPU is viewed as a

 coprocessor that executes data-parallel kernel functions. CUDA
 provides three key abstractions, a hierarchy of thread groups,
 shared memories, and barrier synchronization. Threads have a three
 coprocessor that executes data-parallel kernel functions. CUDA
 provides three key abstractions, a hierarchy of thread groups,
 shared memories, and barrier synchronization. Threads have a three


@@ -441,12 +458,12 @@ read-only caches.
 
 
 \subsubsection{A sequential Aberth algorithm}
 
 
 \subsubsection{A sequential Aberth algorithm}

-The means steps of Aberth method can expressed as an algorithm
-like:
+The main steps of Aberth method are shown in Algorithm.~\ref{alg1-seq} :

   
 \begin{algorithm}[H]
   
 \begin{algorithm}[H]

+\label{alg1-seq}

 %\LinesNumbered
 %\LinesNumbered

-\caption{Algorithm to find root polynomial with Aberth method}
+\caption{A sequential algorithm to find roots with the Aberth method}

 
 \KwIn{$Z^{0}$(Initial root's vector),$\varepsilon$ (error
 tolerance threshold),P(Polynomial to solve)}
 
 \KwIn{$Z^{0}$(Initial root's vector),$\varepsilon$ (error
 tolerance threshold),P(Polynomial to solve)}


@@ -455,7 +472,7 @@ tolerance threshold),P(Polynomial to solve)}
 
 \BlankLine
 
 
 \BlankLine
 

-Initialization of the parameter of the polynomial to solve\;
+Initialization of the coefficients of the polynomial to solve\;

 Initialization of the solution vector $Z^{0}$\;
 
 \While {$\Delta z_{max}\succ \epsilon$}{
 Initialization of the solution vector $Z^{0}$\;
 
 \While {$\Delta z_{max}\succ \epsilon$}{


@@ -474,57 +491,62 @@ $\Delta z_{max}$=c\;}
 \end{algorithm}
 
 ~\\ 
 \end{algorithm}
 
 ~\\ 

-In this sequential algorithm one thread CPU execute all steps. Let see the step 3 the execution of the iterative function, 2 instructions are needed, the first instruction \textit{save} the solution vector for the previous iteration, the second instruction \textit{update} or compute a new values of the roots.
-We have two manner to execute the iterative function, taking a Jacobi iteration who need all the previous value $z^{(k)}_{i}$ to compute the new value $z^{(k+1)}_{i}$we have:
+In this sequential algorithm, one CPU thread  executes all the steps. Let us look to the $3^{rd}$ step i.e. the execution of the iterative function, 2 sub-steps are needed. The first sub-step \textit{save}s the solution vector of the previous iteration, the second sub-step \textit{update}s or computes the new values of the roots vector.
+There exists two ways to execute the iterative function that we call a Jacobi one and a Gauss-Seidel one. With the Jacobi iteration, at iteration $k+1$ we need all the previous values $z^{(k)}_{i}$ to compute the new values $z^{(k+1)}_{i}$, that is :

 
 \begin{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}
 
 
 \begin{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}
 

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

 \begin{equation}
 \begin{equation}

-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.
+\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.

 \end{equation}
 
 \end{equation}
 

-In formula(16), the Gauss-seidel iteration converge more quickly because they used the most fresh computed root $z^{k+1}_{i}$ , at this reason we used Gauss-seidel iteration.
+Using Equation.~\ref{eq:Aberth-H-GS} for the update sub-step of $H(i,z^{k+1})$, we expect the Gauss-Seidel iteration to converge more quickly because, just as its ancestor (for solving linear systems of equations), it uses the most fresh computed roots $z^{k+1}_{i}$.

 
 

-The steps 4 of the Aberth method compute the convergence of the roots, using(9) formula.
-Both steps 3 and 4 use 1 thread to compute N roots on CPU, which is harmful for the large polynomial's roots finding.
+The $4^{th}$ step of the algorithm checks the convergence condition using Equation.~\ref{eq:Aberth-Conv-Cond}.
+Both steps 3 and 4 use 1 thread to compute all the $n$ roots on CPU, which is very harmful for performance in case of the large degree polynomials.

 
 \paragraph{The execution time}
 
 \paragraph{The execution time}

-Let $T_{i}(N)$: the time to compute one new root's value of the step 3,$T_{i}$ depend on the polynomial's degrees N, when N increase $T_{i}$ increase to. We need $N.T_{i}(N)$ to compute all the new root's value in one iteration on the step 3.
+Let $T_{i}(n)$ be the time to compute one new root value at step 3, $T_{i}$ depends on the polynomial's degree $n$. When $n$ increase $T_{i}(n)$ increases too. We need $n.T_{i}(n)$ to compute all the new values in one iteration at step 3.

 
 

-Let $T_{j}$: the time to compute one root's convergence value of the step 4, we need $N.T_{j}$ to compute all the root's convergence value in one iteration on the step 4.
+Let $T_{j}$ be the time needed to check the convergence of one root value at the step 4, so we need $n.T_{j}$ to compute global convergence condition in each iteration at step 4.

 
 

-The execution time for both steps 3 and 4 can see like:
+Thus, the execution time for both steps 3 and 4 is:

 \begin{equation}
 \begin{equation}

-T_{exe}=N(T_{i}(N)+T_{j})+O(n).
+T_{iter}=n(T_{i}(n)+T_{j})+O(n).

 \end{equation}
 \end{equation}

-Let Nbr\_iter the number of iteration necessary to compute all the roots, so the total execution time $Total\_time_{exe}$ can give like:
+Let $K$ be the number of iterations necessary to compute all the roots, so the total execution time $T$ can be given as:

 
 \begin{equation}
 
 \begin{equation}

-Total\_time_{exe}=\left[N\left(T_{i}(N)+T_{j}\right)+O(n)\right].Nbr\_iter
+\label{eq:T-global}
+T=\left[n\left(T_{i}(n)+T_{j}\right)+O(n)\right].K

 \end{equation}
 \end{equation}

-The execution time increase with the increasing of the polynomial's root, which take necessary to parallelize this step to reduce the execution time. In the following paper you explain how we parrallelize  this step using GPU architecture with CUDA platform.
+The execution time increases with the increasing of the polynomial degree, which justifies to parallelise these steps  in order to reduce the global execution time. In the following,  we explain how we did parrallelize these steps on a GPU architecture using the CUDA platform.

 
 

-\subsubsection{Parallelize the steps on GPU }
-On the CPU Aberth algorithm both steps 3 and 4 contain the loop \verb=for=, it use one thread to execute all the instruction in the loop N times. Here we explain how the GPU architecture can compute this loop and reduce the execution time.
-The GPU architecture assign the execution of this loop to a groups of parallel threads organized as a grid of blocks each block contain a number of threads. All threads within a block are executed concurrently in parallel. The instruction are executed as a kernel.
+\subsubsection{A Parallel implementation with CUDA }
+On the CPU,  both steps 3 and 4 contain the loop \verb=for= and a single thread executes all the instructions in the loop $n$ times. In this subsection, we explain how the GPU architecture can compute this loop and reduce the execution time.
+In the GPU, the schduler assigns the execution of this loop to a group of threads organised as a grid of blocks with block containing a number of threads. All threads within a block are executed concurrently in parallel. The instructions run on the GPU are grouped in special function called kernels. It's up to the programmer, to describe the execution context, that is the size of the Grid, the number of blocks and the number of threads per block upon the call of a given kernel, according to a special syntax defined by CUDA.

 
 

-Let nbr\_thread be the number of threads executed in parallel, so you can easily transform the (18)formula like this: 
+Let N be the number of threads executed in parallel,  Equation.~\ref{eq:T-global} becomes then : 

 
 \begin{equation}
 
 \begin{equation}

-Total\_time_{exe}=\left[\frac{N}{nbr\_thread}\left(T_{i}(N)+T_{j}\right)+O(n)\right].Nbr\_iter.
+T=\left[\frac{n}{N}\left(T_{i}(n)+T_{j}\right)+O(n)\right].K.

 \end{equation}
 
 \end{equation}
 

-In theory, the $Total\_time_{exe}$ on GPU is speed up nbr\_thread times as a $Total\_time_{exe}$ on CPU. We show more details in the experiment part. 
+In theory, total execution time $T$ on GPU is speed up $N$ times as  $T$ on CPU. We will see at what extent this is true in the experimental study hereafter. 

 ~\\
 ~\\
 ~\\
 ~\\

-In CUDA platform, All the instruction of the loop \verb=for= are executed by the GPU as a kernel form. A kernel is a procedure written in CUDA and defined by a heading \verb=__global__=, which means that it is to be executed by the GPU. The following algorithm see the Aberth algorithm on GPU:
+In CUDA programming, all the instructions of the  \verb=for= loop are executed by the GPU as a kernel. A kernel is a function written in CUDA and defined by the  \verb=__global__= qualifier added before a usual ``C`` function, which instructs the compiler to generate appropriate code to pass it to the CUDA runtime in order to be executed on the GPU. 
+
+Algorithm~\ref{alg2-cuda} shows a sketch of the Aberth algorithm usind CUDA.

 
 \begin{algorithm}[H]
 
 \begin{algorithm}[H]

+\label{alg2-cuda}

 %\LinesNumbered
 %\LinesNumbered

-\caption{Algorithm to find root polynomial with Aberth method}
+\caption{CUDA Algorithm to find roots with the Aberth method}

 
 \KwIn{$Z^{0}$(Initial root's vector),$\varepsilon$ (error
 tolerance threshold),P(Polynomial to solve)}
 
 \KwIn{$Z^{0}$(Initial root's vector),$\varepsilon$ (error
 tolerance threshold),P(Polynomial to solve)}


@@ -533,24 +555,25 @@ tolerance threshold),P(Polynomial to solve)}
 
 \BlankLine
 
 
 \BlankLine
 

-Initialization of the parameter of the polynomial to solve\;
+Initialization of the coeffcients of the polynomial to solve\;

 Initialization of the solution vector $Z^{0}$\;
 Initialization of the solution vector $Z^{0}$\;

-Allocate and fill the data in the global memory GPU\;
+Allocate and copy initial data to the GPU global memory\;

 
 \While {$\Delta z_{max}\succ \epsilon$}{
  Let $\Delta z_{max}=0$\;
 
 \While {$\Delta z_{max}\succ \epsilon$}{
  Let $\Delta z_{max}=0$\;

-$ kernel\_save(d\_Z^{k-1})$\;
+$ kernel\_save(d\_z^{k-1})$\;

 $ kernel\_update(d\_z^{k})$\;
 $ kernel\_update(d\_z^{k})$\;

-$kernel\_testConverge (d_?z_{max},d_Z^{k},d_Z^{k-1})$\;
+$kernel\_testConverge(\Delta z_{max},d_z^{k},d_z^{k-1})$\;

 }
 \end{algorithm}
 ~\\ 
 
 }
 \end{algorithm}
 ~\\ 
 

-After the initialization step, all data of the root finding problem to be solved must be copied from the CPU memory to the GPU global memory, because the GPUs only work on the data filled in their memories. Next, all the data-parallel arithmetic operations inside the main loop \verb=(do ... while(...))= are executed as kernels by the GPU. The first kernel \textit{save} in line( 6, Algorithm 2) consist to save the vector of polynomial's root found at the previous time step on GPU memory, in order to test the convergence of the root at each iteration in line (8, Algorithm 2).
+After the initialisation step, all data of the root finding problem to be solved must be copied from the CPU memory to the GPU global memory, because the GPUs only access data already present in their memories. Next, all the data-parallel arithmetic operations inside the main loop \verb=(do ... while(...))= are executed as kernels by the GPU. The first kernel named \textit{save} in line 6 of Algorithm~\ref{alg2-cuda} consists in saving the vector of polynomial's root found at the previous time-step in GPU memory, in order to check the convergence of the roots after each iteration (line 8, Algorithm~\ref{alg2-cuda}).

 
 

-The second kernel executes the iterative function and update Z(k),as formula (), we notice that the kernel update are called in two forms,  separated with  the value of \emph{R} which determines the radius beyond which we apply the logarithm formula like this: 
+The second kernel executes the iterative function $H$ and updates $z^{k}$, according to Algorithm~\ref{alg3-update}. We notice that the update kernel is called in two forms, separated with the value of \emph{R} which determines the radius beyond which we apply the logarithm computation of the power of a complex. 

 
 \begin{algorithm}[H]
 
 \begin{algorithm}[H]

+\label{alg3-update}

 %\LinesNumbered
 \caption{A global Algorithm for the iterative function}
 
 %\LinesNumbered
 \caption{A global Algorithm for the iterative function}
 


@@ -561,42 +584,38 @@ $kernel\_update\_Log(d\_z^{k})$\;
 }
 \end{algorithm}
 
 }
 \end{algorithm}
 

-The first form execute the formula(8) if all the module's $( |Z(k)|<= R)$, else the kernel execute the formulas(13,14).the radius R was computed like:
+The first form executes formula \ref{eq:SimplePolynome} if the modulus of the current complex is less than the a certain value called the radius i.e. ($ |z^{k}_{i}|<= R$), else the kernel executes formulas (Eq.~\ref{deflncomplex},Eq.~\ref{defexpcomplex}). The radius $R$ is evaluated as :

 
 

-$$R = \exp( \log(DBL\_MAX) / (2*(double)P.degrePolynome) )$$
+$$R = \exp( \log(DBL\_MAX) / (2*n) )$$ where $DBL\_MAX$ stands for the maximum representable double value.

 
 

-The last kernel verify the convergence of the root after each update of $Z^{(k)}$, as formula(), we used the function of the CUBLAS Library (CUDA Basic Linear Algebra Subroutines) to implement this kernel. 
+The last kernel verifies the convergence of the roots after each update of $Z^{(k)}$, according to formula. We used the functions of the CUBLAS Library (CUDA Basic Linear Algebra Subroutines) to implement this kernel. 

 
 

-The kernels terminates its computations when all the root are converged. Finally, the solution of the  root finding problem is copied back from the GPU global memory to the CPU memory. We use the communication functions of CUDA for the memory allocations in the GPU \verb=(cudaMalloc())= and the data transfers from the CPU memory to the GPU memory \verb=(cudaMemcpyHostToDevice)=
-or from the GPU memory to the CPU memory \verb=(cudaMemcpyDeviceToHost))=. 
-\subsection{Experimental study}
+The kernels terminate it computations when all the roots converge. Finally, the solution of the root finding problem is copied back from GPU global memory to CPU memory. We use the communication functions of CUDA for the memory allocation in the GPU \verb=(cudaMalloc())= and for data transfers from the CPU memory to the GPU memory \verb=(cudaMemcpyHostToDevice)=
+or from GPU memory to CPU memory \verb=(cudaMemcpyDeviceToHost))=. 
+%%HIER END MY REVISIONS (SIDER)
+\section{Experimental study}

 
 

-\subsubsection{Definition of the polynomial used}
-We use a polynomial of the following form for which the
-roots are distributed on 2 distinct circles:
+\subsection{Definition of the polynomial used}
+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.

-\\
- An other form of the polynomial 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; 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}
 \end{equation}

-with this formula, we can have until \textit{n} non zero terms.
-
-\subsubsection{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.
+with this form, we can have until \textit{n} non zero terms.

 
 

+\subsection{The study condition} 

 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


@@ -604,65 +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 Tesla C2070 (with 6 Go of ram)
-
-\subsubsection{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....
-
-\paragraph{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}
+E5620@2.40GHz and a GPU K40 (with 6 Go of ram).
+
+
+\subsection{Comparative study}
+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}
+\caption{The execution time in seconds of Ehrlisch-Aberth algorithm on CPU core vs. on a Tesla GPU}
+\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.

  
  

-\paragraph{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}
-
-\paragraph{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}

 
 
 
 

+\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.
+
+\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}
+
+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}
+
+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}