modification algo 1 et 2

[kahina_paper2.git] / paper.tex

diff --git a/paper.tex b/paper.tex
index 69d42aedfeff7a9175d8036ce5c68ba664f8483f..bae5b946a9464c92cc243cb25f207bccdb6c1b07 100644 (file)
--- a/paper.tex
+++ b/paper.tex
@@ -336,7 +336,6 @@
 
 
 
 
 
 

-

 \begin{document}
 %
 % paper title
 \begin{document}
 %
 % paper title


@@ -663,29 +662,15 @@ z^{k+1}_{i}=z_{i}^{k}-\frac{\frac{p(z_{i}^{k})}{p'(z_{i}^{k})}}
 {1-\frac{p(z_{i}^{k})}{p'(z_{i}^{k})}\sum_{j=1,j\neq i}^{j=n}{\frac{1}{(z_{i}^{k}-z_{j}^{k})}}}, i=1,\ldots,n
 \end{equation}
 
 {1-\frac{p(z_{i}^{k})}{p'(z_{i}^{k})}\sum_{j=1,j\neq i}^{j=n}{\frac{1}{(z_{i}^{k}-z_{j}^{k})}}}, i=1,\ldots,n
 \end{equation}
 

-This method contains 4 steps. The first step consists of the initial
-approximations of all the roots of the polynomial. The second step
-initializes the solution vector $Z$ using the Guggenheimer
-method~\cite{Gugg86} to ensure the distinction of the initial vector
-roots. In step 3, the iterative function based on the Newton's
-method~\cite{newt70} and Weiestrass operator~\cite{Weierstrass03} is
-applied. With this step the computation of roots will converge,
-provided that all roots are different.
-
-
-In order to stop the iterative function, a stop condition is
-applied. This condition checks that all the root modules are lower
-than a fixed value $\xi$.
+This method contains 4 steps. The first step consists in the initializing the polynomial. The second step initializes the solution vector $Z$ using the Guggenheimer method~\cite{Gugg86} to ensure that initial roots are all distinct from each other. In step 3, the iterative function based on the Newton's method~\cite{newt70} and Weiestrass operator~\cite{Weierstrass03} is applied. In our case, the Ehrlich-Aberth is applied as in~(\ref{Eq:EA1}). Iterations of the Ehrlich-Aberth method will converge to the roots of the considered polynomial. In order to stop the iterative function, a stop condition is applied, this is the 4th step. This condition checks that all the root modules are lower than a fixed value $\epsilon$.

 
 \begin{equation}
 \label{eq:Aberth-Conv-Cond}
 
 \begin{equation}
 \label{eq:Aberth-Conv-Cond}

-\forall i \in [1,n];\vert\frac{z_{i}^{k}-z_{i}^{k-1}}{z_{i}^{k}}\vert<\xi
+\forall i\in[1,n],~\vert\frac{z_i^k-z_i^{k-1}}{z_i^k}\vert<\epsilon

 \end{equation}
 \end{equation}

+

 \subsection{Improving Ehrlich-Aberth method}
 \subsection{Improving Ehrlich-Aberth method}

-With high degree polynomials, the Ehrlich-Aberth method suffers from
-floating point overflows due to the mantissa of floating points
-representations. This induces errors in the computation of $p(z)$ when
-$z$ is large.
+With high degree polynomials, the Ehrlich-Aberth method suffers from floating point overflows due to the mantissa of floating points representations. This induces errors in the computation of $p(z)$ when $z$ is large.

  
 %Experimentally, it is very difficult to solve polynomials with the Ehrlich-Aberth method and have roots which except the circle of unit, represented by the radius $r$ evaluated as: 
 
  
 %Experimentally, it is very difficult to solve polynomials with the Ehrlich-Aberth method and have roots which except the circle of unit, represented by the radius $r$ evaluated as: 
 


@@ -702,33 +687,28 @@ In order to solve this problem, we propose to modify the iterative
 function by using the logarithm and the exponential of a complex and
 we propose a new version of the Ehrlich-Aberth method.  This method
 allows us to exceed the computation of the polynomials of degree
 function by using the logarithm and the exponential of a complex and
 we propose a new version of the Ehrlich-Aberth method.  This method
 allows us to exceed the computation of the polynomials of degree

-100,000 and to reach a degree up to more than 1,000,000. This new
-version of the Ehrlich-Aberth method with exponential and logarithm is
-defined as follows:
+100,000 and to reach a degree up to more than 1,000,000. The reformulation of the iteration~(\ref{Eq:EA1}) of the Ehrlich-Aberth method with exponential and logarithm is defined as follows, for $i=1,\dots,n$:

 
 \begin{equation}
 \label{Log_H2}
 
 \begin{equation}
 \label{Log_H2}

-z^{k+1}_{i}=z_{i}^{k}-\exp \left(\ln \left(
-p(z_{i}^{k})\right)-\ln\left(p'(z^{k}_{i})\right)- \ln\left(1-Q(z^{k}_{i})\right)\right),
+z^{k+1}_i = z_i^k - \exp(\ln(p(z_i^k)) - \ln(p'(z^k_i)) - \ln(1-Q(z^k_i))),

 \end{equation}
 
 where:
 
 \end{equation}
 
 where:
 

-\begin{eqnarray}
+\begin{equation}

 \label{Log_H1}
 \label{Log_H1}

-Q(z^{k}_{i})=\exp\left( \ln (p(z^{k}_{i}))-\ln(p'(z^{k}_{i}))+\ln \left(
-\sum_{i\neq j}^{n}\frac{1}{z^{k}_{i}-z^{k}_{j}}\right)\right) \nonumber  \\
-i=1,...,n  
-\end{eqnarray}
+Q(z^k_i) = \exp(\ln(p(z^k_i)) - \ln(p'(z^k_i)) + \ln(\sum_{i\neq j}^n\frac{1}{z^k_i-z^k_j})).
+\end{equation}

 
 
 %We propose to use the logarithm and the exponential of a complex in order to compute the power at a high exponent. 
 
 
 %We propose to use the logarithm and the exponential of a complex in order to compute the power at a high exponent. 

-Using the logarithm  and the exponential operators, we can replace any multiplications and divisions with additions and subtractions. Consequently, computations manipulate lower absolute values~\cite{Karimall98}.
+Using the logarithm  and the exponential operators, we can replace any multiplications and divisions with additions and subtractions. Consequently, computations manipulate lower values in absolute values~\cite{Karimall98}. 

 
 %This problem was discussed earlier in~\cite{Karimall98} for the Durand-Kerner method. The authors
 %propose to use the logarithm and the exponential of a complex in order to compute the power at a high exponent. Using the logarithm  and the exponential operators, we can replace any multiplications and divisions with additions and subtractions. Consequently, computations manipulate lower absolute values and the roots for large polynomial degrees can be looked for successfully~\cite{Karimall98}.
 
 
 %This problem was discussed earlier in~\cite{Karimall98} for the Durand-Kerner method. The authors
 %propose to use the logarithm and the exponential of a complex in order to compute the power at a high exponent. Using the logarithm  and the exponential operators, we can replace any multiplications and divisions with additions and subtractions. Consequently, computations manipulate lower absolute values and the roots for large polynomial degrees can be looked for successfully~\cite{Karimall98}.
 

-\subsection{Ehrlich-Aberth parallel implementation on CUDA}
+\subsection{The Ehrlich-Aberth parallel implementation on CUDA}

 %We introduced three paradigms of parallel programming.
 
 Our objective consists in implementing a root finding polynomial
 %We introduced three paradigms of parallel programming.
 
 Our objective consists in implementing a root finding polynomial


@@ -737,26 +717,17 @@ to manage CUDA contexts of different GPUs. A direct method for
 controlling the various GPUs is to use as many threads or processes as
 GPU devices. We can choose the GPU index based on the identifier of
 OpenMP thread or the rank of the MPI process. Both approaches will be
 controlling the various GPUs is to use as many threads or processes as
 GPU devices. We can choose the GPU index based on the identifier of
 OpenMP thread or the rank of the MPI process. Both approaches will be

-investigated.
+investigated. \LZK{Répétition! Le même texte est déjà écrit comme
+  intro dans la section II. Sinon ici on parle seulement de
+  l'implémentation cuda sans mpi et openmp! \RC{Je suis d'accord à
+    revoir après, quand les 2 parties suivantes seront plus stables}}

 
 
 
 
 
 
 
 

-Like any parallel code, a GPU parallel implementation first requires
-to determine the sequential tasks and the parallelizable parts of the
-sequential version of the program/algorithm. In our case, all the
-operations that are easy to execute in parallel must be made by the
-GPU to accelerate the execution of the application, like the step 3
-and step 4. On the other hand, all the sequential operations and the
-operations that have data dependencies between threads or recursive
-computations must be executed by only one CUDA or CPU thread (step 1
-and step 2). Initially, we specify the organization of parallel
-threads, by specifying the dimension of the grid Dimgrid, the number
-of blocks per grid DimBlock and the number of threads per block.
+Like any parallel code, a GPU parallel implementation first requires to determine the sequential code and the data-parallel operations of a algorithm. In fact, all the operations that are easy to execute in parallel must be made by the GPU to accelerate the execution, like the steps 3 and 4. On the other hand, all the sequential operations and the operations that have data dependencies between CUDA threads or recursive computations must be executed by only one CUDA thread or a CPU thread (the steps 1 and 2).\LZK{La méthode est déjà mal présentée, dans ce cas c'est encore plus difficile de comprendre que représentent ces différentes étapes!} Initially, we specify the organization of parallel threads by specifying the dimension of the grid \verb+Dimgrid+, the number of blocks per grid \verb+DimBlock+ and the number of threads per block.

 
 

-The code is organized kernels which are part of code that are run on
-GPU devices. For step 3, there are two kernels, the first named
-\textit{save} is used to save vector $Z^{K-1}$ and the second one is
+The code is organized as kernels which are parts of code that are run on GPU devices. For step 3, there are two kernels, the first is named \textit{save} is used to save vector $Z^{K-1}$ and the second one is

 named \textit{update} and is used to update the $Z^{K}$ vector. For
 step 4, a kernel tests the convergence of the method. In order to
 compute the function H, we have two possibilities: either to use the
 named \textit{update} and is used to update the $Z^{K}$ vector. For
 step 4, a kernel tests the convergence of the method. In order to
 compute the function H, we have two possibilities: either to use the


@@ -775,58 +746,79 @@ comes in particular from the fact that it is very difficult to debug
 CUDA running threads like threads on a CPU host. In the following
 paragraph Algorithm~\ref{alg1-cuda} shows the GPU parallel
 implementation of Ehrlich-Aberth method.
 CUDA running threads like threads on a CPU host. In the following
 paragraph Algorithm~\ref{alg1-cuda} shows the GPU parallel
 implementation of Ehrlich-Aberth method.

+\LZK{Vaut mieux expliquer l'implémentation en faisant référence à l'algo séquentiel que de parler des différentes steps.}

 
 

-\begin{algorithm}[htpb]
-\label{alg1-cuda}
-\LinesNumbered
-\SetAlgoNoLine
-\caption{CUDA Algorithm to find roots with the Ehrlich-Aberth method}
-
-\KwIn{$Z^{0}$ (Initial root's vector), $\varepsilon$ (Error tolerance
-  threshold), P (Polynomial to solve), Pu (Derivative of P), $n$ (Polynomial degrees), $\Delta z_{max}$ (Maximum value of stop condition)}
-
-\KwOut {$Z$ (Solution root's vector), $ZPrec$ (Previous solution root's vector)}
+%\begin{algorithm}[htpb]
+%\label{alg1-cuda}
+%\LinesNumbered
+%\SetAlgoNoLine
+%\caption{CUDA Algorithm to find polynomial roots with the Ehrlich-Aberth method}
+%\KwIn{$Z^{0}$ (Initial vector of roots), $\epsilon$ (Error tolerance threshold), P (Polynomial to solve), Pu (Derivative of P), $n$ (Polynomial degree), $\Delta z_{max}$ (Maximum value of stop condition)}
+%\KwOut{$Z$ (Solution vector of roots)}

 
 %\BlankLine
 
 
 %\BlankLine
 

-Initialization of P\;
-Initialization of Pu\;
-Initialization of the solution vector $Z^{0}$\;
-Allocate and copy initial data to the GPU global memory\;
-\While {$\Delta z_{max} > \epsilon$}{
-   $ kernel\_save(ZPrec,Z)$\;
-   $ kernel\_update(Z,P,Pu)$\;
- $\Delta z_{max}=kernel\_testConverge(Z,ZPrec)$\;
+%Initialization of P\; 
+%Initialization of Pu\;
+%Initialization of the solution vector $Z^{0}$\;
+%Allocate and copy initial data to the GPU global memory\;
+%\While {$\Delta z_{max} > \epsilon$}{
+%   $ ZPres=kernel\_save(Z)$\;
+%   $ Z=kernel\_update(Z,P,Pu)$\;
+% $\Delta z_{max}=kernel\_testConv(Z,ZPrec)$\;

 
 

+%}
+%Copy results from GPU memory to CPU memory\;
+%\end{algorithm}
+
+\begin{algorithm}[htpb]
+\LinesNumbered
+\SetAlgoNoLine
+\caption{Finding roots of polynomials with the Ehrlich-Aberth method on a GPU}
+\KwIn{$n$ (polynomial's degree), $\epsilon$ (tolerance threshold)}
+\KwOut{$Z$ (solution vector of roots)}
+Initialize the polynomial $P$ and its derivative $P'$\;
+Set the initial values of vector $Z$\;
+Copy $P$, $P'$ and $Z$ from CPU to GPU\;
+\While{\emph{not convergence}}{
+  $Z^{prev}$ = KernelSave($Z,n$)\;
+  $Z$ = KernelUpdate($P,P',Z^{prev},n$)\;
+  $\Delta Z$ = KernelComputeError($Z,Z^{prev},n$)\;
+  $\Delta Z_{max}$ = CudaMaxFunction($\Delta Z,n$)\;
+  TestConvergence($\Delta Z_{max},\epsilon$)\;

 }
 }

-Copy results from GPU memory to CPU memory\;
+Copy $Z$ from GPU to CPU\;
+\label{alg1-cuda}
+\RC{Si l'algo vous convient, il faudrait le détailler précisément\LZK{J'ai modifié l'algo. Sinon, est ce qu'on doit mettre en paramètre $Z^{prev}$ ou $Z$ tout court (dans le cas où on exploite l'asynchronisme des threads cuda!) pour le Kernel\_Update? }}

 \end{algorithm}
 
  
 \section{The EA algorithm on Multiple GPUs}
 \label{sec4}
 \end{algorithm}
 
  
 \section{The EA algorithm on Multiple GPUs}
 \label{sec4}

-\subsection{M-GPU : an OpenMP-CUDA approach}
+\subsection{an OpenMP-CUDA approach}

 Our OpenMP-CUDA implementation of EA algorithm is based on the hybrid
 Our OpenMP-CUDA implementation of EA algorithm is based on the hybrid

-OpenMP and CUDA programming model.  All the data
-are shared with OpenMP amoung all the OpenMP threads. The shared data
-are the solution vector $Z$, the polynomial to solve $P$, and the
-error vector $\Delta z$. The number of OpenMP threads is equal to the
-number of GPUs, each OpenMP thread binds to one GPU, and it controls a
-part of the shared memory. More precisely each OpenMP thread owns of
-the vector Z, that is $(n/num\_gpu)$ roots where $n$ is the
-polynomial's degree and $num\_gpu$ the total number of available
-GPUs. Then all GPUs will have a grid of computation organized
+OpenMP and CUDA programming model.  All the data are shared with
+OpenMP amoung all the OpenMP threads. The shared data are the solution
+vector $Z$, the polynomial to solve $P$, and the error vector $\Delta
+z$. The number of OpenMP threads is equal to the number of GPUs, each
+OpenMP thread binds to one GPU, and it controls a part of the shared
+memory. More precisely each OpenMP thread will be responsible to
+update its owns part of the vector Z. This part is call $Z_{loc}$ in
+the following. Then all GPUs will have a grid of computation organized

 according to the device performance and the size of data on which it
 runs the computation kernels.
 
 To compute one iteration of the EA method each GPU performs the
 according to the device performance and the size of data on which it
 runs the computation kernels.
 
 To compute one iteration of the EA method each GPU performs the

-followings steps. First roots are shared with OpenMP. Each thread
-starts by copying all the previous roots inside its GPU. Then each GPU
-will compute an iteration of the EA method on its own roots. For that
-all the other roots are used. At the end of an iteration, the updated
-roots are copied from the GPU to the CPU. The convergence is checked
-on the new roots. Finally each CPU will update its own roots in the
-shared memory arrays containing all the roots.
+followings steps. First roots are shared with OpenMP and the
+computation of the local size for each GPU is performed (lines 5-7 in
+Algo\ref{alg2-cuda-openmp}). Each thread starts by copying all the
+previous roots inside its GPU (line 9). Then each GPU will copy the
+previous roots (line 10) and it will compute an iteration of the EA
+method on its own roots (line 11).  For that all the other roots are
+used. The convergence is checked on the new roots (line 12). At the end
+of an iteration, the updated roots are copied from the GPU to the
+CPU (line 14) by direcly updating its own roots in the shared memory
+arrays containing all the roots.

 
 %In principle a grid is set by two parameter DimGrid, the number of block per grid, DimBloc: the number of threads per block. The following schema  shows the architecture of (CUDA,OpenMP).
 
 
 %In principle a grid is set by two parameter DimGrid, the number of block per grid, DimBloc: the number of threads per block. The following schema  shows the architecture of (CUDA,OpenMP).
 


@@ -858,43 +850,68 @@ shared memory arrays containing all the roots.
 %% roots sufficiently converge.
 
 
 %% roots sufficiently converge.
 
 

+%% \begin{algorithm}[h]
+%%   \label{alg2-cuda-openmp}
+%%   \LinesNumbered
+%%   \SetAlgoNoLine
+%%   \caption{CUDA-OpenMP Algorithm to find roots with the Ehrlich-Aberth method}
+
+%%   \KwIn{$Z^{0}$ (Initial root's vector), $\varepsilon$ (Error tolerance
+%%     threshold), P (Polynomial to solve), Pu (Derivative of P), $n$ (Polynomial degree), $\Delta z$ ( Vector of errors for stop condition), $num\_gpus$ (number of OpenMP threads/ Number of GPUs), $Size$ (number of roots)}
+
+%%   \KwOut {$Z$ ( Root's vector), $ZPrec$ (Previous root's vector)}
+
+%%   \BlankLine
+
+%%   Initialization of P\;
+%%   Initialization of Pu\;
+%%   Initialization of the solution vector $Z^{0}$\;
+%%   Start of a parallel part with OpenMP (Z, $\Delta z$, P are shared variables)\;
+%%   gpu\_id=cudaGetDevice()\; 
+%%   Allocate memory on GPU\;
+%%   Compute local size and offet according to gpu\_id\;
+%%   \While {$error > \epsilon$}{
+%%     copy Z from CPU to GPU\;
+%%     $ ZPrec_{loc}=kernel\_save(Z_{loc})$\;
+%%     $ Z_{loc}=kernel\_update(Z,P,Pu)$\;
+%%     $\Delta z[gpu\_id] = kernel\_testConv(Z_{loc},ZPrec_{loc})$\;
+%%     $  error= Max(\Delta z)$\;
+%%     copy $Z_{loc}$ from GPU to Z in CPU
+%%   }
+%%\end{algorithm}
+

 \begin{algorithm}[htpb]
 \begin{algorithm}[htpb]

-\label{alg2-cuda-openmp}

 \LinesNumbered
 \SetAlgoNoLine
 \LinesNumbered
 \SetAlgoNoLine

-\caption{CUDA-OpenMP Algorithm to find roots with the Ehrlich-Aberth method}
-
-\KwIn{$Z^{0}$ (Initial root's vector), $\varepsilon$ (Error tolerance
-  threshold), P (Polynomial to solve), Pu (Derivative of P), $n$ (Polynomial degree), $\Delta z$ ( Vector of errors for stop condition), $num\_gpus$ (number of OpenMP threads/ Number of GPUs), $Size$ (number of roots)}
-
-\KwOut {$Z$ ( Root's vector), $ZPrec$ (Previous root's vector)}
-
-\BlankLine
-
-Initialization of P\;
-Initialization of Pu\;
-Initialization of the solution vector $Z^{0}$\;
-omp\_set\_num\_threads(num\_gpus)\;
-\#pragma omp parallel shared(Z,$\Delta$ z,P)\;
-\Indp
-{
-gpu\_id=cudaGetDevice()\;
-Allocate memory on GPU\;
-Compute local size and offet according to gpu\_id\;
-\While {$error > \epsilon$}{
-  copy Z from CPU to GPU\;
-$ ZPrec_{loc}=kernel\_save(Z_{loc})$\;
-$ Z_{loc}=kernel\_update(Z,P,Pu)$\;
-$\Delta z[gpu\_id] = kernel\_testConv(Z_{loc},ZPrec_{loc})$\;
-$  error= Max(\Delta z)$\;
-  copy $Z_{loc}$ from GPU to Z in CPU
+\caption{Finding roots of polynomials with the Ehrlich-Aberth method on multiple GPUs using OpenMP}
+\KwIn{$n$ (polynomial's degree), $\epsilon$ (tolerance threshold), $ngpu$ (number of GPUs)}
+\KwOut{$Z$ (solution vector of roots)}
+Initialize the polynomial $P$ and its derivative $P'$\;
+Set the initial values of vector $Z$\;
+Start of a parallel part with OpenMP ($Z$, $\Delta Z$, $\Delta Z_{max}$, $P$ are shared variables)\;
+$id_{gpu}$ = cudaGetDevice()\;
+$n_{loc}$ = $n/ngpu$ (local size)\;
+%$idx$ = $id_{gpu}\times n_{loc}$ (local offset)\;
+Copy $P$, $P'$ from CPU to GPU\;
+\While{\emph{not convergence}}{
+  Copy $Z$ from CPU to GPU\;
+  $Z^{prev}$ = KernelSave($Z,n$)\;
+  $Z_{loc}$ = KernelUpdate($P,P',Z^{prev},n_{loc}$)\;
+  $\Delta Z_{loc}$ = KernelComputeError($Z_{loc},Z^{prev}_{loc},n_{loc}$)\;
+  $\Delta Z_{max}[id_{gpu}]$ = CudaMaxFunction($\Delta Z_{loc},n_{loc}$)\;
+  Copy $Z_{loc}$ from GPU to $Z$ in CPU\;
+  $max$ = MaxFunction($\Delta Z_{max},ngpu$)\;
+  TestConvergence($max,\epsilon$)\;

 }
 }

-\Indm}
+\label{alg2-cuda-openmp}
+\LZK{J'ai modifié l'algo. Le $P$ est mis shared. Qu'en est-il pour $P'$?}

 \end{algorithm}
 
 
 
 \end{algorithm}
 
 
 

-\subsection{Multi-GPU : an MPI-CUDA approach}
+
+
+\subsection{an MPI-CUDA approach}

 %\begin{figure}[htbp]
 %\centering
  % \includegraphics[angle=-90,width=0.2\textwidth]{MPI-CUDA}
 %\begin{figure}[htbp]
 %\centering
  % \includegraphics[angle=-90,width=0.2\textwidth]{MPI-CUDA}


@@ -905,40 +922,33 @@ Our parallel implementation of EA to find root of polynomials using a CUDA-MPI a
 
 Since a GPU works only on data already allocated in its memory, all local input data, $Z_{k}$, $ZPrec$ and $\Delta z_{k}$, must be transferred from CPU memories to the corresponding GPU memories. Afterwards, the same EA algorithm (Algorithm \ref{alg1-cuda}) is run by all processes but on different polynomial subset of roots $ p(x)_{k}=\sum_{i=1}^{n} a_{i}x^{i}, k=1,...,p$.  Each MPI process executes the  loop \verb=(While(...)...do)= containing the CUDA kernels but each MPI process  computes only its own portion of the roots according to the rule ``''owner computes``''. The local range of roots is indicated with the \textit{index} variable initialized at (line 5, Algorithm \ref{alg2-cuda-mpi}), and passed as an input variable to $kernel\_update$ (line 10, Algorithm \ref{alg2-cuda-mpi}). After each iteration, MPI processes synchronize  (\verb=MPI_Allreduce= function) by a reduction on $\Delta z_{k}$ in order to compute the maximum error related to the stop condition.   Finally, processes copy the values of new computed roots  from GPU memories to CPU memories, then communicate their results to other processes with \verb=MPI_Alltoall= broadcast. If the stop condition is not verified ($error > \epsilon$) then processes stay withing the loop \verb= while(...)...do= until all the roots sufficiently converge.
 
 
 Since a GPU works only on data already allocated in its memory, all local input data, $Z_{k}$, $ZPrec$ and $\Delta z_{k}$, must be transferred from CPU memories to the corresponding GPU memories. Afterwards, the same EA algorithm (Algorithm \ref{alg1-cuda}) is run by all processes but on different polynomial subset of roots $ p(x)_{k}=\sum_{i=1}^{n} a_{i}x^{i}, k=1,...,p$.  Each MPI process executes the  loop \verb=(While(...)...do)= containing the CUDA kernels but each MPI process  computes only its own portion of the roots according to the rule ``''owner computes``''. The local range of roots is indicated with the \textit{index} variable initialized at (line 5, Algorithm \ref{alg2-cuda-mpi}), and passed as an input variable to $kernel\_update$ (line 10, Algorithm \ref{alg2-cuda-mpi}). After each iteration, MPI processes synchronize  (\verb=MPI_Allreduce= function) by a reduction on $\Delta z_{k}$ in order to compute the maximum error related to the stop condition.   Finally, processes copy the values of new computed roots  from GPU memories to CPU memories, then communicate their results to other processes with \verb=MPI_Alltoall= broadcast. If the stop condition is not verified ($error > \epsilon$) then processes stay withing the loop \verb= while(...)...do= until all the roots sufficiently converge.
 

-%% \begin{enumerate}
-%% \begin{algorithm}[htpb]
-%% \label{alg2-cuda-mpi}
-%% %\LinesNumbered
-%% \caption{CUDA-MPI Algorithm to find roots with the Ehrlich-Aberth method}
-
-%% \KwIn{$Z^{0}$ (Initial root's vector), $\varepsilon$ (Error tolerance
-%%   threshold), P (Polynomial to solve), Pu (Derivative of P), $n$ (Polynomial degrees), $\Delta z$ ( error of stop condition), $num_gpus$ (number of MPI processes/ number of GPUs), Size (number of roots)}
-
-%% \KwOut {$Z$ (Solution root's vector), $ZPrec$ (Previous solution root's vector)}
-
-%% \BlankLine
-%% \item Initialization of P\;
-%% \item Initialization of Pu\;
-%% \item Initialization of the solution vector $Z^{0}$\;
-%% \item Allocate and copy initial data from CPU memories to GPU global memories\;
-%% \item $index= Size/num_gpus$\;
-%% \item k=0\;
-%% \While {$error > \epsilon$}{
-%% \item Let $\Delta z=0$\;
-%% \item $kernel\_save(ZPrec,Z)$\;
-%% \item  k=k+1\;
-%% \item $kernel\_update(Z,P,Pu,index)$\;
-%% \item $kernel\_testConverge(\Delta z,Z,ZPrec)$\;
-%% \item ComputeMaxError($\Delta z$,error)\;
-%% \item Copy results from GPU memories to CPU memories\;
-%% \item Send $Z[id]$ to all processes\;
-%% \item Receive $Z[j]$ from every other process j\;
-%% }
-%% \end{algorithm}
-%% \end{enumerate}
-%% ~\\ 
-
-%% \RC{ENCORE ENCORE PIRE}
+\begin{algorithm}[htpb]
+\label{alg2-cuda-mpi}
+%\LinesNumbered
+\caption{CUDA-MPI Algorithm to find roots with the Ehrlich-Aberth method}
+
+\KwIn{$Z^{0}$ (Initial root's vector), $\varepsilon$ (Error tolerance
+  threshold), P (Polynomial to solve), Pu (Derivative of P), $n$ (Polynomial degrees), $\Delta z$ ( error of stop condition), $num_gpus$ (number of MPI processes/ number of GPUs), Size (number of roots)}
+
+\KwOut {$Z$ (Solution root's vector), $ZPrec$ (Previous solution root's vector)}
+
+\BlankLine
+Initialization of P\;
+Initialization of Pu\;
+Initialization of the solution vector $Z^{0}$\;
+Distribution of Z\;
+Allocate memory to GPU\;
+\While {$error > \epsilon$}{
+copy Z from CPU to GPU\;
+$ZPrec_{loc}=kernel\_save(Z_{loc})$\;
+$Z_{loc}=kernel\_update(Z,P,Pu)$\;
+$\Delta z=kernel\_testConv(Z_{loc},ZPrec_{loc})$\;
+$error=MPI\_Reduce(\Delta z)$\;
+Copy $Z_{loc}$ from GPU to CPU\;
+$Z=MPI\_AlltoAll(Z_{loc})$\;
+}
+\end{algorithm}
+

 
 \section{Experiments}
 \label{sec5}
 
 \section{Experiments}
 \label{sec5}