Merge branch 'development' of github.com:sfilippone/amg4psblas into development

2026-10-19 20:32:13 +00:00 · 2021-06-14 12:27:38 -04:00
parent 1fa94d0372 0fcbdd74cd
commit 4e177ce926
22 changed files with 123 additions and 110 deletions
@@ -31,7 +31,7 @@ class="cmr-12">University of Rome Tor-Vergata and IAC-CNR</span><br
 class="newline" /> <span 
 class="cmr-12">Software version: 1.0</span><br 
 class="newline" /><span 
-class="cmr-12">April 12, 2021</span>
+class="cmr-12">May 11th, 2021</span>
                                                                               

                                                                               
@@ -149,6 +149,7 @@ div.abstract {width:100%;}
 .Ovalbox-thick { padding-left:3pt; padding-right:3pt; border:solid thick; }
 .shadowbox { padding-left:3pt; padding-right:3pt; border:solid thin; border-right:solid thick; border-bottom:solid thick; }
 .doublebox { padding-left:3pt; padding-right:3pt; border-style:double; border:solid thick; }
+.rotatebox{display: inline-block;}
 .figure img.graphics {margin-left:10%;}
 .lstlisting .label{margin-right:0.5em; }
 div.lstlisting{font-family: monospace; white-space: nowrap; margin-top:0.5em; margin-bottom:0.5em; }
@@ -31,7 +31,7 @@ class="cmr-12">University of Rome Tor-Vergata and IAC-CNR</span><br
 class="newline" /> <span 
 class="cmr-12">Software version: 1.0</span><br 
 class="newline" /><span 
-class="cmr-12">April 12, 2021</span>
+class="cmr-12">May 11th, 2021</span>
                                                                               

                                                                               
@@ -211,7 +211,7 @@ class="cmr-12">&#x00A0;Pothen,  </span><span
 class="cmti-12">Distributed-memory parallel algorithms for matching and</span>
     <span 
 class="cmti-12">coloring</span><span 
-class="cmr-12">, in PCO11 New Trends in Parallel Computing and Optimization,</span>
+class="cmr-12">, in PCO&#8217;11 New Trends in Parallel Computing and Optimization,</span>
     <span 
 class="cmr-12">IEEE  International  Symposium  on  Parallel  and  Distributed  Processing</span>
     <span 
@@ -122,7 +122,7 @@ class="cmr-12">abide by its terms:</span>
 &#x00A0;<br />
 </div>
 <!--l. 87--><p class="nopar" > <span 
-class="cmr-12">AMG4PSBLAS is distributed together with (a small part) of the graph-matching</span>
+class="cmr-12">AMG4PSBLAS is distributed together with (a small part of) the graph-matching</span>
                                                                               

                                                                               
@@ -133,7 +133,7 @@ class="cmr-12">[</span><a
 href="userhtmlli5.html#XMatchBoxP"><span 
 class="cmr-12">9</span></a><span 
 class="cmr-12">]</span></span><span 
-class="cmr-12">. Per the license requirements, we reproduce the relative part</span>
+class="cmr-12">. Per the license requirements, we reproduce the relevant part</span>
 <span 
 class="cmr-12">here.</span>
                                                                               
@@ -91,7 +91,7 @@ class="cmr-12">Trolling, insulting or derogatory comments, and personal or polit
 class="cmr-12">Public or private harassment</span>
     </li>
     <li class="itemize"><span 
-class="cmr-12">Publishing others private information, such as a physical or email address,</span>
+class="cmr-12">Publishing others&#8217; private information, such as a physical or email address,</span>
     <span 
 class="cmr-12">without their explicit permission</span>
     </li>
@@ -234,7 +234,7 @@ class="cmr-12">_of</span><span
 class="cmr-12">_conduct</span>
 <span 
 class="cmr-12">.html</span></a><span 
-class="cmr-12">. Community Impact Guidelines were inspired by Mozillas code of conduct</span>
+class="cmr-12">. Community Impact Guidelines were inspired by Mozilla&#8217;s code of conduct</span>
 <span 
 class="cmr-12">enforcement ladder. For answers to common questions about this code of conduct, see</span>
 <span 
@@ -4227,9 +4227,9 @@ class="cmtt-12">github</span><span
 class="cmtt-12">.</span><span 
 class="cmtt-12">com</span><span 
 class="cmtt-12">/</span><span 
-class="cmtt-12">sfilippone</span><span 
+class="cmtt-12">psctoolkit</span><span 
 class="cmtt-12">/</span><span 
-class="cmtt-12">amg4psblas</span><span 
+class="cmtt-12">psctoolkit</span><span 
 class="cmtt-12">/</span><span 
 class="cmtt-12">issues</span><span 
 class="cmtt-12">&#x003E;.</span>
@@ -36,8 +36,8 @@ class="cmr-12">If you find any bugs in our codes, please report them through our
 <span 
 class="cmr-12">on</span><br 
 class="newline" /> <a 
-href="https://github.com/psctoolkit/amg4psblas/issues" class="url" ><span 
-class="cmtt-12">https://github.com/psctoolkit/amg4psblas/issues</span></a><br 
+href="https://github.com/psctoolkit/psctoolkit/issues" class="url" ><span 
+class="cmtt-12">https://github.com/psctoolkit/psctoolkit/issues</span></a><br 
 class="newline" />
 <!--l. 195--><p class="indent" >   <span 
 class="cmr-12">To enable us to track the bug, please provide a log from the failing application, the</span>
@@ -29,40 +29,41 @@ class="cmr-12">3.5   </span></span> <a
 id="x13-120003.5"></a><span 
 class="cmr-12">Example and test programs</span></h4>
 <!--l. 200--><p class="noindent" ><span 
-class="cmr-12">The package contains the </span><span class="obeylines-h"><span class="verb"><span 
-class="cmtt-12">examples</span></span></span> <span 
-class="cmr-12">and </span><span class="obeylines-h"><span class="verb"><span 
-class="cmtt-12">tests</span></span></span> <span 
-class="cmr-12">directories; both of them are</span>
-<span 
-class="cmr-12">further divided into </span><span class="obeylines-h"><span class="verb"><span 
+class="cmr-12">The package contains a </span><span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">samples</span></span></span> <span 
+class="cmr-12">directory, divided in two subdirs </span><span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">simple</span></span></span> <span 
+class="cmr-12">and</span>
+<span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">advanced</span></span></span><span 
+class="cmr-12">; both of them are further divided into </span><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">fileread</span></span></span> <span 
 class="cmr-12">and </span><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">pdegen</span></span></span> <span 
-class="cmr-12">subdirectories. Their purpose is as</span>
+class="cmr-12">subdirectories.</span>
 <span 
-class="cmr-12">follows:</span>
+class="cmr-12">Their purpose is as follows:</span>
     <dl class="description"><dt class="description">
 <span 
-class="cmtt-12">examples</span> </dt><dd 
+class="cmtt-12">simple</span> </dt><dd 
 class="description"><span 
-class="cmr-12">contains a set of simple example programs with a predefined choice</span>
+class="cmr-12">contains a set of simple example programs with a predefined choice of</span>
     <span 
-class="cmr-12">of preconditioners, selectable via integer values. These are intended to get</span>
+class="cmr-12">preconditioners,  selectable  via  integer  values.  These  are  intended  to  get</span>
     <span 
 class="cmr-12">acquainted with the multilevel preconditioners available in AMG4PSBLAS.</span>
     </dd><dt class="description">
 <span 
-class="cmtt-12">tests</span> </dt><dd 
+class="cmtt-12">advanced</span> </dt><dd 
 class="description"><span 
-class="cmr-12">contains a set of more sophisticated examples that will allow the user, via</span>
+class="cmr-12">contains a set of more sophisticated examples that will allow the user,</span>
     <span 
-class="cmr-12">the input files in the </span><span class="obeylines-h"><span class="verb"><span 
+class="cmr-12">via the input files in the </span><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">runs</span></span></span> <span 
-class="cmr-12">subdirectories, to experiment with the full range</span>
+class="cmr-12">subdirectories, to experiment with the full</span>
     <span 
-class="cmr-12">of preconditioners implemented in the package.</span></dd></dl>
-<!--l. 213--><p class="noindent" ><span 
+class="cmr-12">range of preconditioners implemented in the package.</span></dd></dl>
+<!--l. 214--><p class="noindent" ><span 
 class="cmr-12">The </span><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">fileread</span></span></span> <span 
 class="cmr-12">directories contain sample programs that read sparse matrices from files,</span>
@@ -71,38 +71,39 @@ class="cmr-12">The part of the code dealing with reading and assembling the spar
 <span 
 class="cmr-12">right-hand side vector and the deallocation of the relevant data structures, performed</span>
 <span 
-class="cmr-12">through the PSBLAS routines for sparse matrix and vector management, is not</span>
+class="cmr-12">through the PSBLAS routines for sparse matrix and vector management,</span>
 <span 
-class="cmr-12">reported here for the sake of conciseness. The complete code can be found in the</span>
+class="cmr-12">is not reported here for the sake of conciseness. The complete code can be</span>
 <span 
-class="cmr-12">example program file </span><span class="obeylines-h"><span class="verb"><span 
+class="cmr-12">found in the example program file </span><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">amg_dexample_ml.f90</span></span></span><span 
-class="cmr-12">, in the directory </span><span class="obeylines-h"><span class="verb"><span 
-class="cmtt-12">examples/fileread</span></span></span> <span 
-class="cmr-12">of</span>
-<span 
-class="cmr-12">the AMG4PSBLAS implementation (see Section</span><span 
+class="cmr-12">, in the directory</span>
+<span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">samples/simple/file</span></span></span><span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">read</span></span></span> <span 
+class="cmr-12">of the AMG4PSBLAS implementation (see Section</span><span 
 class="cmr-12">&#x00A0;</span><a 
 href="userhtmlsu5.html#x13-120003.5"><span 
 class="cmr-12">3.5</span><!--tex4ht:ref: sec:ex_and_test --></a><span 
-class="cmr-12">). A sample test problem along</span>
+class="cmr-12">). A</span>
 <span 
-class="cmr-12">with the relevant input data is available in </span><span class="obeylines-h"><span class="verb"><span 
-class="cmtt-12">examples/fileread/runs</span></span></span><span 
-class="cmr-12">. For details on</span>
+class="cmr-12">sample test problem along with the relevant input data is available in</span>
+<span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">samples/simple/fileread/runs</span></span></span><span 
+class="cmr-12">. For details on the use of the PSBLAS routines, see</span>
 <span 
-class="cmr-12">the use of the PSBLAS routines, see the PSBLAS User&#8217;s Guide</span><span 
+class="cmr-12">the PSBLAS User&#8217;s Guide</span><span 
 class="cmr-12">&#x00A0;</span><span class="cite"><span 
 class="cmr-12">[</span><a 
 href="userhtmlli5.html#XPSBLASGUIDE"><span 
 class="cmr-12">20</span></a><span 
 class="cmr-12">]</span></span><span 
 class="cmr-12">.</span>
-<!--l. 138--><p class="indent" >   <span 
-class="cmr-12">The setup and application of the default multilevel preconditioner for the real single</span>
                                                                               

                                                                               
+<!--l. 138--><p class="indent" >   <span 
+class="cmr-12">The setup and application of the default multilevel preconditioner for the real single</span>
 <span 
 class="cmr-12">precision and the complex, single and double precision, versions are obtained</span>
 <span 
@@ -114,7 +115,8 @@ class="cmr-12">for</span>
 <span 
 class="cmr-12">details). If these versions are installed, the corresponding codes are available in</span>
 <span class="obeylines-h"><span class="verb"><span 
-class="cmtt-12">examples/fileread/</span></span></span><span 
+class="cmtt-12">samples/simple/file</span></span></span><span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">read</span></span></span><span 
 class="cmr-12">.</span>
                                                                               

@@ -278,7 +280,7 @@ class="cmr-12">For all the previous preconditioners, example programs where the
 class="cmr-12">and the right-hand side are generated by discretizing a PDE with Dirichlet</span>
 <span 
 class="cmr-12">boundary conditions are also available in the directory </span><span class="obeylines-h"><span class="verb"><span 
-class="cmtt-12">examples/pdegen</span></span></span><span 
+class="cmtt-12">samples/simple/pdegen</span></span></span><span 
 class="cmr-12">.</span>
                                                                               

@@ -145,7 +145,7 @@ class="cmr-12">GPU environment</span>
                                                                               
 <div class="center" 
 >
-<!--l. 552--><p class="noindent" >
+<!--l. 553--><p class="noindent" >
 <div class="minipage"><div class="verbatim" id="verbatim-12">
 &#x00A0;&#x00A0;call&#x00A0;desc_a%cnv(mold=igmold)
 &#x00A0;<br />&#x00A0;&#x00A0;call&#x00A0;a%cscnv(info,mold=agmold)
@@ -172,7 +172,7 @@ class="cmr-12">GPU environment</span>
 &#x00A0;<br />
 &#x00A0;<br />&#x00A0;
 </div>
-<!--l. 579--><p class="nopar" ></div></div>
+<!--l. 580--><p class="nopar" ></div></div>
 <br /> <div class="caption" 
 ><span class="id">Listing 7: </span><span  
 class="content">setup of a GPU-enabled test program part three.</span></div><!--tex4ht:label?: x16-15003r7 -->
@@ -180,25 +180,30 @@ class="content">setup of a GPU-enabled test program part three.</span></div><!--

                                                                               
   </div><hr class="endfloat" />
-<!--l. 587--><p class="indent" >   <span 
-class="cmr-12">It is very important to employ solvers that are suited to the GPU, i.e. solvers that</span>
+<!--l. 588--><p class="indent" >   <span 
+class="cmr-12">It is very important to employ smoothers and coarsest solvers that are suited to the</span>
 <span 
-class="cmr-12">do NOT employ triangular system solve kernels. Solvers that satisfy this constraint</span>
+class="cmr-12">GPU, i.e. methods that do NOT employ triangular system solve kernels. Methods that</span>
 <span 
-class="cmr-12">include:</span>
+class="cmr-12">satisfy this constraint include:</span>
     <ul class="itemize1">
     <li class="itemize"><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">JACOBI</span></span></span>
     </li>
     <li class="itemize"><span class="obeylines-h"><span class="verb"><span 
+class="cmtt-12">BJAC</span></span></span> <span 
+class="cmr-12">with the following methods on the local blocks:</span>
+          <ul class="itemize2">
+          <li class="itemize"><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">INVK</span></span></span>
-     </li>
-     <li class="itemize"><span class="obeylines-h"><span class="verb"><span 
+          </li>
+          <li class="itemize"><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">INVT</span></span></span>
-     </li>
-     <li class="itemize"><span class="obeylines-h"><span class="verb"><span 
+          </li>
+          <li class="itemize"><span class="obeylines-h"><span class="verb"><span 
 class="cmtt-12">AINV</span></span></span></li></ul>
-<!--l. 596--><p class="noindent" ><span 
+     </li></ul>
+<!--l. 600--><p class="noindent" ><span 
 class="cmr-12">and their </span><span 
 class="cmmi-12">&#x2113;</span><sub><span 
 class="cmr-8">1</span></sub> <span 
@@ -324,8 +324,8 @@ class="td11"><!--l. 124--><p class="noindent" >      </td><td  style="white-spac
 class="td11"><!--l. 124--><p class="noindent" ><span 
 class="cmr-12">An auxiliary input argument that can be passed to the underlying</span>
 <span 
-class="cmr-12">objects.</span>                                                                             </td>
-    </tr></table></div>
+class="cmr-12">objects.</span>                                                                             </td> 
+</tr></table></div>
 <!--l. 129--><p class="noindent" >
 <!--l. 134--><p class="indent" >   <span 
 class="cmr-12">A variety of preconditioners can be obtained by setting the appropriate</span>
@@ -190,22 +190,23 @@ make install
 \subsection{Bug reporting}
 If you find any bugs in our codes, please report them through our
 issues page on \\[2mm]
-\url{https://github.com/psctoolkit/amg4psblas/issues}\\
+\url{https://github.com/psctoolkit/psctoolkit/issues}\\

 To enable us to track the bug, please provide a log from the failing
 application, the test conditions, and ideally a self-contained test
 program reproducing the issue.

 \subsection{Example and test programs\label{sec:ex_and_test}}
-The package contains the \verb|examples| and \verb|tests| directories;
+The package contains a \verb|samples| directory, divided in two
+subdirs  \verb|simple| and \verb|advanced|;
 both of them are further divided into \verb|fileread| and
 \verb|pdegen| subdirectories. Their purpose is as follows:
 \begin{description}
-\item[\tt examples] contains a set of simple example programs with a
+\item[\tt simple] contains a set of simple example programs with a
  predefined choice of preconditioners, selectable via integer
  values. These are intended to get  acquainted with the
  multilevel preconditioners available in AMG4PSBLAS.
-\item[\tt tests] contains a set of more sophisticated examples that
+\item[\tt advanced] contains a set of more sophisticated examples that
  will allow the user, via the input files in the \verb|runs|
  subdirectories, to experiment with the full range of preconditioners
  implemented in the package.
@@ -159,4 +159,4 @@ Some influential environment variables:
 Use these variables to override the choices made by `configure' or to help
 it to find libraries and programs with nonstandard names/locations.

-Report bugs to <https://github.com/sfilippone/amg4psblas/issues>.
+Report bugs to <https://github.com/psctoolkit/psctoolkit/issues>.
@@ -129,9 +129,9 @@ relevant data structures, performed
 through the PSBLAS routines for sparse matrix and vector management, is not reported
 here for the sake of conciseness.
 The complete code can be found in the example program file \verb|amg_dexample_ml.f90|,
-in the directory \verb|examples/fileread| of the AMG4PSBLAS implementation (see
+in the directory \verb|samples/simple/file|\-\verb|read| of the AMG4PSBLAS implementation (see
 Section~\ref{sec:ex_and_test}). A sample test problem along with the relevant
-input data is available in \verb|examples/fileread/runs|.
+input data is available in \verb|samples/simple/fileread/runs|.
 For details on the use of the PSBLAS routines, see the PSBLAS User's
 Guide~\cite{PSBLASGUIDE}.

@@ -139,7 +139,7 @@ The setup and application of the default multilevel preconditioner
 for the real single precision and the complex, single and double
 precision, versions are obtained with straightforward modifications of the previous
 example (see Section~\ref{sec:userinterface} for details). If these versions are installed,
-the corresponding codes are available in \verb|examples/fileread/|.
+the corresponding codes are available in \verb|samples/simple/file|\-\verb|read|.

 \begin{listing}[tbp]
 \begin{center}
@@ -300,7 +300,7 @@ The corresponding example program is available in the file

 For all the previous preconditioners, example programs where the sparse matrix and
 the right-hand side are generated by discretizing a PDE with Dirichlet
-boundary conditions are also available in the directory \verb|examples/pdegen|.
+boundary conditions are also available in the directory \verb|samples/simple/pdegen|.
 \vspace{-1em}\begin{listing}[tbh]
 \ifpdf%
 \begin{minted}[breaklines=true,bgcolor=bg,fontsize=\small]{fortran}
@@ -535,7 +535,8 @@ Krylov method. At the end of the code, we close the GPU environment
  call prec%allocate_wrk(info)
  t1 = psb_wtime()
  call psb_krylov(s_choice%kmethd,a,prec,b,x,s_choice%eps,&
-       & desc_a,info,itmax=s_choice%itmax,iter=iter,err=err,itrace=s_choice%itrace,&
+       & desc_a,info,itmax=s_choice%itmax,iter=iter,err=err,&
+       & itrace=s_choice%itrace,&
       & istop=s_choice%istopc,irst=s_choice%irst)
  call prec%deallocate_wrk(info)
  call psb_barrier(ctxt)
@@ -584,15 +585,18 @@ Krylov method. At the end of the code, we close the GPU environment
 \caption{setup of a GPU-enabled test program part three.\label{fig:gpu-ex3}}
 \end{listing}

-It is very important to employ solvers that are suited
-to the GPU, i.e.  solvers that do NOT  employ triangular
-system solve kernels.  Solvers that satisfy this constraint include:
+It is very important to employ smoothers and coarsest solvers that are suited
+to the GPU, i.e.  methods that do NOT employ triangular
+system solve kernels. Methods that satisfy this constraint include:
 \begin{itemize}
 \item \verb|JACOBI|
+\item \verb|BJAC| with the following methods on the local blocks:
+\begin{itemize}
 \item \verb|INVK|
 \item \verb|INVT|
 \item \verb|AINV|
 \end{itemize}
+\end{itemize}
 and their $\ell_1$ variants. 

 %%% Local Variables:
@@ -87,9 +87,9 @@ terms: {\small
 \end{verbatim}
   }
 \pagebreak
-AMG4PSBLAS is distributed together with (a small part) of the graph-matching
+AMG4PSBLAS is distributed together with (a small part of) the graph-matching
 library MatchBox-P~\cite{MatchBoxP}. Per the license requirements, we reproduce
-the relative part here.
+the relevant part here.
 {\small
 \begin{verbatim}
 // ***********************************************************************
@@ -154,7 +154,7 @@ Preconditioners Package based on PSBLAS}
 \flushright
 \large Software version: 1.0\\
 %\todaym
-\large April 12, 2021
+\large May 11th, 2021
 \end{minipage}}
 %\addtolength{\textwidth}{\centeroffset}
 \vspace{\stretch{2}}
@@ -114,7 +114,7 @@
 %\today
 Software version: 1.0\\
 %\today
- April 12, 2021
+ May 11th, 2021
 \clearpage
 \ \\
 \thispagestyle{empty}
@@ -39,23 +39,18 @@
 !
 ! This sample program solves a linear system obtained by discretizing a
 ! PDE with Dirichlet BCs. The solver is CG, coupled with one of the
-! following multi-level preconditioner, as explained in Section 4.1 of
+! following multi-level preconditioner, as explained in Section 4.2 of
 ! the AMG4PSBLAS User's and Reference Guide:
 !
-! - choice = 1, the default multi-level preconditioner solver, i.e., 
-! V-cycle with decoupled smoothed aggregation, 1 hybrid forward/backward
-! GS sweep as pre/post-smoother and UMFPACK as coarsest-level
-! solver (Sec. 4.1, Listing 1)
+! - choice = 1, a V-cycle with decoupled smoothed aggregation, 4 Jacobi
+! sweeps as pre/post-smoother and 8 Jacobi sweeps as coarsest-level
+! solver with replicated coarsest matrix
 !
-! - choice = 2, a V-cycle preconditioner with 1 block-Jacobi sweep
-! (with ILU(0) on the blocks) as pre- and post-smoother, and 8 block-Jacobi
-! sweeps (with ILU(0) on the blocks) as coarsest-level solver (Sec. 4.1, Listing 2)
-!
-! - choice = 3,  W-cycle preconditioner based on the coupled aggregation relying
-! on matching, with maximum size of aggregates equal to 8 and smoothed prolongators,
-! 2 hybrid forward/backward GS sweeps as pre/post-smoother, a distributed coarsest
-! matrix, and preconditioned Flexible Conjugate Gradient as coarsest-level solver
-! (Sec. 4.1, Listing 3)
+! - choice = 2, a W-cycle based on the coupled aggregation relying on matching,
+! with maximum size of aggregates equal to 8 and smoothed prolongators,
+! 2 sweeps of Block-Jacobi ipre/post-smoother using approximate inverse INVK and
+! 4 sweeps of Block-Jacobi with INVK as coarsest-level solver on distributed
+! coarsest matrix 
 !
 ! The matrix and the rhs are read from files (if an rhs is not available, the
 ! unit rhs is set).
@@ -183,8 +178,9 @@ program amg_dexample_gpu

 case(1)

-    ! initialize a V-cycle preconditioner with 4 Jacobi sweep 
-    ! and 8 Jacobi sweeps as coarsest-level solver
+    ! initialize a V-cycle preconditioner, relying on decoupled smoothed aggregation 
+    ! with 4 Jacobi sweeps as pre/post-smoother
+    ! and 8 Jacobi sweeps as coarsest-level solver on replicated coarsest matrix

    call P%init(ctxt,'ML',info)
    call P%set('SMOOTHER_TYPE','JACOBI',info)
@@ -195,19 +191,22 @@ program amg_dexample_gpu

  case(2)

-   ! initialize a V-cycle preconditioner based on the coupled aggregation relying on matching,
+   ! initialize a W-cycle preconditioner based on the coupled aggregation relying on matching,
   ! with maximum size of aggregates equal to 8 and smoothed prolongators,
-   ! Block-Jacobi smoother using approximate inverse INVK and
-   ! and 4 sweeps of INVK on he coarsest level 
+   ! 2 sweeps of Block-Jacobi pre/post-smoother using approximate inverse INVK and
+   ! 4 sweeps of Block-Jacobi with INVK on the coarsest level distributed matrix

    call P%init(ctxt,'ML',info)
    call P%set('PAR_AGGR_ALG','COUPLED',info)
    call P%set('AGGR_TYPE','MATCHBOXP',info)
    call P%set('AGGR_SIZE',8,info)
    call P%set('ML_CYCLE','WCYCLE',info)
+    call P%set('SMOOTHER_TYPE','BJAC',info)
    call P%set('SMOOTHER_SWEEPS',2,info)
    call P%set('SUB_SOLVE','INVK',info)  
-    call P%set('COARSE_SOLVE','INVK',info)
+    call P%set('COARSE_SOLVE','BJAC',info)
+    call P%set('COARSE_SUBSOLVE','INVK',info)
+    call P%set('COARSE_SWEEPS',4,info)
    call P%set('COARSE_MAT','DIST',info)
    kmethod = 'CG'

@@ -1,14 +1,14 @@
 !   
 !   
-!                             MLD2P4  version 2.2
-!    MultiLevel Domain Decomposition Parallel Preconditioners Package
-!               based on PSBLAS (Parallel Sparse BLAS version 3.5)
+!                             AMG4PSBLAS version 1.0
+!    Algebraic Multigrid Package
+!               based on PSBLAS (Parallel Sparse BLAS version 3.7)
 !    
-!    (C) Copyright 2008-2018 
+!    (C) Copyright 2021 
 !  
 !        Salvatore Filippone  
 !        Pasqua D'Ambra   
-!        Daniela di Serafino   
+!        Fabio Durastante        
 !   
 !    Redistribution and use in source and binary forms, with or without
 !    modification, are permitted provided that the following conditions
@@ -18,14 +18,14 @@
 !      2. Redistributions in binary form must reproduce the above copyright
 !         notice, this list of conditions, and the following disclaimer in the
 !         documentation and/or other materials provided with the distribution.
-!      3. The name of the MLD2P4 group or the names of its contributors may
+!      3. The name of the AMG4PSBLAS group or the names of its contributors may
 !         not be used to endorse or promote products derived from this
 !         software without specific written permission.
 !   
 !    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 !    ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
 !    TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-!    PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE MLD2P4 GROUP OR ITS CONTRIBUTORS
+!    PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AMG4PSBLAS GROUP OR ITS CONTRIBUTORS
 !    BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 !    CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 !    SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
@@ -1,14 +1,14 @@
 !   
 !   
-!                             MLD2P4  version 2.2
-!    MultiLevel Domain Decomposition Parallel Preconditioners Package
-!               based on PSBLAS (Parallel Sparse BLAS version 3.5)
+!                             AMG4PSBLAS version 1.0
+!    Algebraic Multigrid Package
+!               based on PSBLAS (Parallel Sparse BLAS version 3.7)
 !    
-!    (C) Copyright 2008-2018 
+!    (C) Copyright 2021 
 !  
 !        Salvatore Filippone  
 !        Pasqua D'Ambra   
-!        Daniela di Serafino   
+!        Fabio Durastante        
 !   
 !    Redistribution and use in source and binary forms, with or without
 !    modification, are permitted provided that the following conditions
@@ -18,14 +18,14 @@
 !      2. Redistributions in binary form must reproduce the above copyright
 !         notice, this list of conditions, and the following disclaimer in the
 !         documentation and/or other materials provided with the distribution.
-!      3. The name of the MLD2P4 group or the names of its contributors may
+!      3. The name of the AMG4PSBLAS group or the names of its contributors may
 !         not be used to endorse or promote products derived from this
 !         software without specific written permission.
 !   
 !    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 !    ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
 !    TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-!    PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE MLD2P4 GROUP OR ITS CONTRIBUTORS
+!    PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AMG4PSBLAS GROUP OR ITS CONTRIBUTORS
 !    BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 !    CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 !    SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS