mld2p4:

copyright and internal doc adjustments for version 1.1.

docs/html/index.html

@@ -65,9 +65,9 @@ University of Rome ``Tor Vergata'', Italy
 <BR>
 <BR>
 <BR>
-Software version: 1.0
+Software version: 1.1
 <BR>
-Sept. 9th, 2008
+March 13, 2009
 
 <BR>
 

docs/html/node1.html

@@ -64,7 +64,7 @@ MLD2P4 (M<SMALL>ULTI-</SMALL>L<SMALL>EVEL </SMALL>D<SMALL>OMAIN </SMALL>D<SMALL>
 It implements various versions of one-level additive and of multi-level additive
 and hybrid Schwarz algorithms. In the multi-level case, a purely algebraic approach
 is applied to generate coarse-level corrections, so that no geometric background is needed
-concerning the matrix to be preconditioned. The matrix is required to be square, real
+concerning the matrix to be preconditioned. The matrix is assumed to be square, real
 or complex, with a symmetric sparsity pattern. 
 
 <P>

docs/html/node11.html

@@ -135,11 +135,11 @@ of this algorithm is implemented, where the smoothed aggregation is applied loca
 to each submatrix [<A
  HREF="node25.html#TUMINARO_TONG">23</A>]. In the next two subsections we provide
 a brief description of the multi-level Schwarz preconditioners and of the smoothed
-aggregation technique as implemented in MLD2P4. For further details the user
+aggregation technique as implemented in MLD2P4. For further details the reader
 is referred to [<A
  HREF="node25.html#para_04">2</A>,<A
  HREF="node25.html#aaecc_07">3</A>,<A
- HREF="node25.html#apnum_07">4</A>,<A
+ HREF="node25.html#apnum_07">4</A>,,<A
  HREF="node25.html#dd2_96">20</A>].
 
 <P>

docs/html/node12.html

@@ -276,7 +276,7 @@ three steps:
  ALT="$i=1,\ldots,m$">;
 </LI>
 <LI>prolongation and sum of the <IMG
- WIDTH="22" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ WIDTH="23" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
  SRC="img32.png"
  ALT="$w_i$">'s, i.e. <!-- MATH
  $w = \sum_{i=1}^m (R_i^{\delta})^T w_i$
@@ -309,7 +309,7 @@ time on parallel distributed-memory computers is the so-called <I>Restricted AS
  HREF="node25.html#CAI_SARKIS">5</A>,<A
  HREF="node25.html#EFSTATHIOU">13</A>]. It
 is obtained by zeroing the components of <IMG
- WIDTH="22" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ WIDTH="23" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
  SRC="img32.png"
  ALT="$w_i$"> corresponding to the
 overlapping vertices when applying the prolongation. Therefore,
@@ -405,7 +405,7 @@ In a pure algebraic setting, <IMG
  WIDTH="29" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
  SRC="img43.png"
  ALT="$A_C$"> is usually built with
-a Galerkin approach. Given a set <IMG
+the Galerkin approach. Given a set <IMG
  WIDTH="32" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
  SRC="img44.png"
  ALT="$W_C$"> of <I>coarse vertices</I>,
@@ -683,7 +683,11 @@ and the corresponding basic preconditioner at each level <IMG
  ALT="$M_l$">, respectively, with <IMG
  WIDTH="61" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
  SRC="img65.png"
- ALT="$A_1=A$">.
+ ALT="$A_1=A$">, while the related restriction operator is
+denoted by <IMG
+ WIDTH="23" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
+ SRC="img66.png"
+ ALT="$R_l$">.
 
 <DIV ALIGN="CENTER"><A NAME="fig:mlhpost_alg"></A><A NAME="508"></A>
 <TABLE>
@@ -720,14 +724,14 @@ $w = y_1$;
 }$
  -->
 <IMG
- WIDTH="430" HEIGHT="435" ALIGN="BOTTOM" BORDER="0"
- SRC="img66.png"
+ WIDTH="429" HEIGHT="435" ALIGN="BOTTOM" BORDER="0"
+ SRC="img67.png"
  ALT="\framebox{
 \begin{minipage}{.85\textwidth} {\small
 \begin{tabbing}
 \quad \=\quad...
 ...= y_l+r_l$\\
-\textbf{endfor}  [1mm]
+\textbf{endfor} \\ [1mm]
 $w = y_1$;
 \end{tabbing}}
 \end{minipage}}">

docs/html/node13.html

@@ -62,7 +62,7 @@ Smoothed Aggregation
 <P>
 In order to define the restriction operator <IMG
  WIDTH="29" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
- SRC="img67.png"
+ SRC="img68.png"
  ALT="$R_C$">, which is used to compute
 the coarse-level matrix <IMG
  WIDTH="29" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
@@ -81,7 +81,7 @@ The basic idea of this algorithm is to build a coarse set of vertices
  ALT="$W$"> into disjoint subsets
 (aggregates), and to define the coarse-to-fine space transfer operator <IMG
  WIDTH="29" HEIGHT="40" ALIGN="MIDDLE" BORDER="0"
- SRC="img68.png"
+ SRC="img69.png"
  ALT="$R_C^T$"> by
 applying a suitable smoother to a simple piecewise constant
 prolongation operator, to improve the quality of the coarse-space correction.
@@ -100,15 +100,15 @@ Three main steps can be identified in the smoothed aggregation procedure:
 </LI>
 <LI>construction of the prolongator <IMG
  WIDTH="29" HEIGHT="40" ALIGN="MIDDLE" BORDER="0"
- SRC="img68.png"
+ SRC="img69.png"
  ALT="$R_C^T$">;
 </LI>
 <LI>application of <IMG
  WIDTH="29" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
- SRC="img67.png"
+ SRC="img68.png"
  ALT="$R_C$"> and <IMG
  WIDTH="29" HEIGHT="40" ALIGN="MIDDLE" BORDER="0"
- SRC="img68.png"
+ SRC="img69.png"
  ALT="$R_C^T$"> to build <IMG
  WIDTH="29" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
  SRC="img43.png"
@@ -124,14 +124,14 @@ in [<A
 this algorithm has been actually considered,
 in which each aggregate <IMG
  WIDTH="26" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
- SRC="img69.png"
+ SRC="img70.png"
  ALT="$N_r$"> is made of vertices of <IMG
  WIDTH="24" HEIGHT="15" ALIGN="BOTTOM" BORDER="0"
  SRC="img10.png"
  ALT="$W$"> that are <I>strongly coupled</I>
 to a certain root vertex <IMG
  WIDTH="53" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
- SRC="img70.png"
+ SRC="img71.png"
  ALT="$r \in W$">, i.e. <BR><P></P>
 <DIV ALIGN="CENTER">
 <!-- MATH
@@ -143,7 +143,7 @@ N_r = \left\{s \in W: |a_{rs}| > \theta \sqrt{|a_{rr}a_{ss}|} \right\}
 
 <IMG
  WIDTH="319" HEIGHT="38" BORDER="0"
- SRC="img71.png"
+ SRC="img72.png"
  ALT="\begin{displaymath}N_r = \left\{s \in W: \vert a_{rs}\vert &gt; \theta \sqrt{\vert a_{rr}a_{ss}\vert} \right\}
 \cup \left\{ r \right\} ,
 \end{displaymath}">
@@ -155,16 +155,16 @@ for a given <!-- MATH
  -->
 <IMG
  WIDTH="69" HEIGHT="36" ALIGN="MIDDLE" BORDER="0"
- SRC="img72.png"
+ SRC="img73.png"
  ALT="$\theta \in [0,1]$">.
 Since this algorithm has a sequential nature, a <I>decoupled</I> version of
 it has been chosen, where each processor <IMG
- WIDTH="10" HEIGHT="18" ALIGN="BOTTOM" BORDER="0"
- SRC="img73.png"
+ WIDTH="11" HEIGHT="18" ALIGN="BOTTOM" BORDER="0"
+ SRC="img74.png"
  ALT="$i$"> independently applies the algorithm to
 the set of vertices <IMG
  WIDTH="31" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
- SRC="img74.png"
+ SRC="img75.png"
  ALT="$W_i^0$"> assigned to it in the initial data distribution. This
 version is embarrassingly parallel, since it does not require any data communication.
 On the other hand, it may produce non-uniform aggregates near boundary vertices,
@@ -183,14 +183,14 @@ since it has been shown to produce good results in practice
 <P>
 The prolongator <IMG
  WIDTH="75" HEIGHT="40" ALIGN="MIDDLE" BORDER="0"
- SRC="img75.png"
+ SRC="img76.png"
  ALT="$P_C=R_C^T$"> is built starting from a <I>tentative prolongator</I>
 <!-- MATH
  $P \in \Re^{n \times n_C}$
  -->
 <IMG
- WIDTH="90" HEIGHT="38" ALIGN="MIDDLE" BORDER="0"
- SRC="img76.png"
+ WIDTH="89" HEIGHT="38" ALIGN="MIDDLE" BORDER="0"
+ SRC="img77.png"
  ALT="$P \in \Re^{n \times n_C}$">, defined as
 <BR>
 <DIV ALIGN="RIGHT">
@@ -207,7 +207,7 @@ P=(p_{ij}), \quad  p_{ij}=
 <TABLE WIDTH="100%" ALIGN="CENTER">
 <TR VALIGN="MIDDLE"><TD ALIGN="CENTER" NOWRAP><A NAME="eq:tent_prol"></A><IMG
  WIDTH="290" HEIGHT="52" BORDER="0"
- SRC="img77.png"
+ SRC="img78.png"
  ALT="\begin{displaymath}
 P=(p_{ij}), \quad p_{ij}=
 \left\{ \begin{array}{ll}
@@ -222,17 +222,17 @@ P=(p_{ij}), \quad p_{ij}=
 <BR CLEAR="ALL"></DIV><P></P>
 <IMG
  WIDTH="27" HEIGHT="32" ALIGN="MIDDLE" BORDER="0"
- SRC="img78.png"
+ SRC="img79.png"
  ALT="$P_C$"> is obtained by
 applying to <IMG
  WIDTH="18" HEIGHT="15" ALIGN="BOTTOM" BORDER="0"
- SRC="img79.png"
+ SRC="img80.png"
  ALT="$P$"> a smoother <!-- MATH
  $S \in \Re^{n \times n}$
  -->
 <IMG
  WIDTH="78" HEIGHT="38" ALIGN="MIDDLE" BORDER="0"
- SRC="img80.png"
+ SRC="img81.png"
  ALT="$S \in \Re^{n \times n}$">:
 <BR>
 <DIV ALIGN="RIGHT">
@@ -245,7 +245,7 @@ P_C = S P,
 <TABLE WIDTH="100%" ALIGN="CENTER">
 <TR VALIGN="MIDDLE"><TD ALIGN="CENTER" NOWRAP><A NAME="eq:smoothed_prol"></A><IMG
  WIDTH="73" HEIGHT="30" BORDER="0"
- SRC="img81.png"
+ SRC="img82.png"
  ALT="\begin{displaymath}
 P_C = S P,
 \end{displaymath}"></TD>
@@ -260,7 +260,7 @@ Schwarz method [<A
  HREF="node25.html#StubenGMD69_99">22</A>].
 A simple choice for <IMG
  WIDTH="16" HEIGHT="15" ALIGN="BOTTOM" BORDER="0"
- SRC="img82.png"
+ SRC="img83.png"
  ALT="$S$"> is the damped Jacobi smoother:
 <BR>
 <DIV ALIGN="RIGHT">
@@ -273,7 +273,7 @@ S = I - \omega D^{-1} A ,
 <TABLE WIDTH="100%" ALIGN="CENTER">
 <TR VALIGN="MIDDLE"><TD ALIGN="CENTER" NOWRAP><A NAME="eq:jac_smoother"></A><IMG
  WIDTH="126" HEIGHT="30" BORDER="0"
- SRC="img83.png"
+ SRC="img84.png"
  ALT="\begin{displaymath}
 S = I - \omega D^{-1} A ,
 \end{displaymath}"></TD>
@@ -283,11 +283,11 @@ S = I - \omega D^{-1} A ,
 <BR CLEAR="ALL"></DIV><P></P>
 where the value of <IMG
  WIDTH="16" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
- SRC="img84.png"
+ SRC="img85.png"
  ALT="$\omega$"> can be chosen
 using some estimate of the spectral radius of <IMG
- WIDTH="50" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
- SRC="img85.png"
+ WIDTH="51" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
+ SRC="img86.png"
  ALT="$D^{-1}A$"> [<A
  HREF="node25.html#BREZINA_VANEK">1</A>].
 

docs/html/node14.html

@@ -144,7 +144,7 @@ compilers.
 
 <P>
 <BR><P></P>
-<DIV ALIGN="CENTER"><A NAME="923"></A>
+<DIV ALIGN="CENTER"><A NAME="925"></A>
 <TABLE>
 <CAPTION><STRONG>Table 1:</STRONG>
 Preconditioner types, corresponding strings and default choices.
@@ -185,12 +185,12 @@ Preconditioner types, corresponding strings and default choices.
                                     Aggregation: decoupled smoothed aggregation with
                                     threshold <IMG
  WIDTH="45" HEIGHT="15" ALIGN="BOTTOM" BORDER="0"
- SRC="img86.png"
+ SRC="img87.png"
  ALT="$\theta = 0$">.
                                     Coarsest matrix: distributed among the processors.
                                     Coarsest-level solver: 
                                     4 sweeps of the block-Jacobi solver, 
-                                    with LU (or ILU) factorization of the blocks
+                                    with LU or ILU factorization of the blocks
                                     (UMFPACK for the double precision versions and
                                     SuperLU for the single precision ones, if the packages
                                     have been installed; ILU(0), otherwise).</TD>

docs/html/node15.html

@@ -90,7 +90,7 @@ the corresponding Fortran 95 codes are available in <code>examples/fileread/</co
 
 <P>
 
-<DIV ALIGN="CENTER"><A NAME="fig:ex_default"></A><A NAME="926"></A>
+<DIV ALIGN="CENTER"><A NAME="fig:ex_default"></A><A NAME="928"></A>
 <TABLE>
 <CAPTION ALIGN="BOTTOM"><STRONG>Figure 2:</STRONG>
 Setup and application of the default multi-level Schwarz preconditioner.
@@ -207,7 +207,7 @@ and linked to the MLD2P4 library.
 <BR>
 <P>
 
-<DIV ALIGN="CENTER"><A NAME="fig:ex_3lh"></A><A NAME="928"></A>
+<DIV ALIGN="CENTER"><A NAME="fig:ex_3lh"></A><A NAME="930"></A>
 <TABLE>
 <CAPTION ALIGN="BOTTOM"><STRONG>Figure 3:</STRONG>
 Setup of a hybrid three-level Schwarz preconditioner.</CAPTION>
@@ -239,7 +239,7 @@ Setup of a hybrid three-level Schwarz preconditioner.</CAPTION>
 
 <P>
 
-<DIV ALIGN="CENTER"><A NAME="fig:ex_3la"></A><A NAME="930"></A>
+<DIV ALIGN="CENTER"><A NAME="fig:ex_3la"></A><A NAME="932"></A>
 <TABLE>
 <CAPTION ALIGN="BOTTOM"><STRONG>Figure 4:</STRONG>
 Setup of an additive three-level Schwarz preconditioner.</CAPTION>
@@ -271,7 +271,7 @@ Setup of an additive three-level Schwarz preconditioner.</CAPTION>
 
 <P>
 
-<DIV ALIGN="CENTER"><A NAME="fig:ex_1l"></A><A NAME="932"></A>
+<DIV ALIGN="CENTER"><A NAME="fig:ex_1l"></A><A NAME="934"></A>
 <TABLE>
 <CAPTION ALIGN="BOTTOM"><STRONG>Figure 5:</STRONG>
 Setup of a one-level Schwarz preconditioner.</CAPTION>

docs/html/node16.html

@@ -90,8 +90,8 @@ i.e.
  WIDTH="13" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
  SRC="img21.png"
  ALT="$v$"> and <IMG
- WIDTH="17" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
- SRC="img87.png"
+ WIDTH="18" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
+ SRC="img88.png"
  ALT="$w$"> involved in
   the preconditioner application <IMG
  WIDTH="87" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"

docs/html/node18.html

@@ -137,7 +137,7 @@ refer to Section&nbsp;<A HREF="node11.html#sec:background">4</A>.
 
 <P>
 <BR><P></P>
-<DIV ALIGN="CENTER"><A NAME="1260"></A>
+<DIV ALIGN="CENTER"><A NAME="1262"></A>
 <TABLE>
 <CAPTION><STRONG>Table 2:</STRONG>
 Parameters defining the type of multi-level preconditioner.
@@ -181,7 +181,7 @@ Parameters defining the type of multi-level preconditioner.
 
 <P>
 <BR><P></P>
-<DIV ALIGN="CENTER"><A NAME="1262"></A>
+<DIV ALIGN="CENTER"><A NAME="1264"></A>
 <TABLE>
 <CAPTION><STRONG>Table 3:</STRONG>
 Parameters defining the one-level preconditioner used as smoother.
@@ -198,8 +198,8 @@ Parameters defining the one-level preconditioner used as smoother.
 <TR><TD ALIGN="LEFT"><code>mld_sub_ovr_</code></TD>
 <TD ALIGN="LEFT"><code>integer</code></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=91>any&nbsp;int.&nbsp;num.&nbsp;<IMG
- WIDTH="32" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img88.png"
+ WIDTH="31" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img89.png"
  ALT="$\ge 0$"></TD>
 <TD ALIGN="LEFT">1</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Number of overlap layers.</TD>
@@ -240,8 +240,8 @@ Parameters defining the one-level preconditioner used as smoother.
 <TR><TD ALIGN="LEFT"><code>mld_sub_fillin_</code></TD>
 <TD ALIGN="LEFT"><code>integer</code></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=91>Any&nbsp;int.&nbsp;num.&nbsp;<IMG
- WIDTH="32" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img88.png"
+ WIDTH="31" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img89.png"
  ALT="$\ge 0$"></TD>
 <TD ALIGN="LEFT">0</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Fill-in level <IMG
@@ -252,13 +252,13 @@ Parameters defining the one-level preconditioner used as smoother.
 <TR><TD ALIGN="LEFT"><code>mld_sub_iluthrs_</code></TD>
 <TD ALIGN="LEFT"><code>real(</code><I>kind_parameter</I><code>)</code></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=91>Any&nbsp;real&nbsp;num.&nbsp;<IMG
- WIDTH="32" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img88.png"
+ WIDTH="31" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img89.png"
  ALT="$\ge 0$"></TD>
 <TD ALIGN="LEFT">0</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Drop tolerance <IMG
  WIDTH="11" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
- SRC="img89.png"
+ SRC="img90.png"
  ALT="$t$"> in the ILU(<IMG
  WIDTH="27" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
  SRC="img35.png"
@@ -281,7 +281,7 @@ Parameters defining the one-level preconditioner used as smoother.
 
 <P>
 <BR><P></P>
-<DIV ALIGN="CENTER"><A NAME="1264"></A>
+<DIV ALIGN="CENTER"><A NAME="1266"></A>
 <TABLE>
 <CAPTION><STRONG>Table 4:</STRONG>
 Parameters defining the aggregation algorithm.
@@ -304,20 +304,21 @@ Parameters defining the aggregation algorithm.
 </TR>
 <TR><TD ALIGN="LEFT"><code>mld_aggr_kind_</code></TD>
 <TD ALIGN="LEFT"><code>character(len=*)</code></TD>
-<TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68><TT>'SMOOTH'</TT>   <TT>'RAW'</TT></TD>
-<TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68><TT>'SMOOTH'</TT></TD>
-<TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Type of aggregation: smoothed, raw (i.e. using the tentative prolongator).</TD>
+<TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68><TT>'SMOOTHED'</TT>   <TT>'NONSMOOTHED'</TT></TD>
+<TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68><TT>'SMOOTHED'</TT></TD>
+<TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Type of aggregation: smoothed, nonsmoothed
+                         (i.e. using the tentative prolongator).</TD>
 </TR>
 <TR><TD ALIGN="LEFT"><code>mld_aggr_thresh_</code></TD>
 <TD ALIGN="LEFT"><code>real(</code><I>kind_parameter</I><code>)</code></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68>Any&nbsp;real&nbsp;num. <IMG
  WIDTH="56" HEIGHT="36" ALIGN="MIDDLE" BORDER="0"
- SRC="img90.png"
+ SRC="img91.png"
  ALT="$\in [0, 1]$"></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68>0</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Threshold <IMG
  WIDTH="13" HEIGHT="15" ALIGN="BOTTOM" BORDER="0"
- SRC="img91.png"
+ SRC="img92.png"
  ALT="$\theta$"> in the aggregation algorithm.</TD>
 </TR>
 <TR><TD ALIGN="LEFT"><code>mld_aggr_omega_alg_</code></TD>
@@ -326,13 +327,13 @@ Parameters defining the aggregation algorithm.
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68><TT>'EIG_EST'</TT></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>How the damping parameter <IMG
  WIDTH="16" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
- SRC="img84.png"
+ SRC="img85.png"
  ALT="$\omega$"> in the
                          smoothed aggregation should be computed:
                          either via an estimate of the spectral radius of
                          <IMG
- WIDTH="50" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
- SRC="img85.png"
+ WIDTH="51" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
+ SRC="img86.png"
  ALT="$D^{-1}A$">, or explicily
                          specified by the user.</TD>
 </TR>
@@ -341,8 +342,8 @@ Parameters defining the aggregation algorithm.
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68><TT>'A_NORMI'</TT></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=68><TT>'A_NORMI'</TT></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>How to estimate the spectral radius of <IMG
- WIDTH="50" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
- SRC="img85.png"
+ WIDTH="51" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
+ SRC="img86.png"
  ALT="$D^{-1}A$">.
                            Currently only the infinity norm estimate
                            is available.</TD>
@@ -355,11 +356,11 @@ Parameters defining the aggregation algorithm.
  -->
 <IMG
  WIDTH="113" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
- SRC="img92.png"
+ SRC="img93.png"
  ALT="$4/(3\rho(D^{-1}A))$"></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Damping parameter <IMG
  WIDTH="16" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
- SRC="img84.png"
+ SRC="img85.png"
  ALT="$\omega$"> in the smoothed aggregation algorithm. 
                            It must be set by the user if
                            <code>USER_CHOICE</code> was specified for 
@@ -367,11 +368,11 @@ Parameters defining the aggregation algorithm.
                            otherwise it is computed by the library, using the
                            selected estimate of the spectral radius <IMG
  WIDTH="73" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
- SRC="img93.png"
+ SRC="img94.png"
  ALT="$\rho(D^{-1}A)$"> of
                            <IMG
- WIDTH="50" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
- SRC="img85.png"
+ WIDTH="51" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
+ SRC="img86.png"
  ALT="$D^{-1}A$">.</TD>
 </TR>
 </TABLE>
@@ -383,7 +384,7 @@ Parameters defining the aggregation algorithm.
 
 <P>
 <BR><P></P>
-<DIV ALIGN="CENTER"><A NAME="1267"></A>
+<DIV ALIGN="CENTER"><A NAME="1269"></A>
 <TABLE>
 <CAPTION><STRONG>Table 5:</STRONG>
 Parameters defining the coarse-space correction at the coarsest
@@ -440,8 +441,8 @@ level.</CAPTION>
 <TR><TD ALIGN="LEFT"><code>mld_coarse_sweeps_</code></TD>
 <TD ALIGN="LEFT"><code>integer</code></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=91>Any&nbsp;int.&nbsp;num.&nbsp;<IMG
- WIDTH="32" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img94.png"
+ WIDTH="31" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img95.png"
  ALT="$&gt; 0$"></TD>
 <TD ALIGN="LEFT">4</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Number of Block-Jacobi sweeps when 'BJAC' is used as
@@ -450,8 +451,8 @@ level.</CAPTION>
 <TR><TD ALIGN="LEFT"><code>mld_coarse_fillin_</code></TD>
 <TD ALIGN="LEFT"><code>integer</code></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=91>Any&nbsp;int.&nbsp;num.&nbsp;<IMG
- WIDTH="32" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img88.png"
+ WIDTH="31" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img89.png"
  ALT="$\ge 0$"></TD>
 <TD ALIGN="LEFT">0</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Fill-in level <IMG
@@ -462,24 +463,24 @@ level.</CAPTION>
 <TR><TD ALIGN="LEFT"><code>mld_coarse_iluthrs_</code></TD>
 <TD ALIGN="LEFT"><code>real(</code><I>kind_parameter</I><code>)</code></TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=91>Any&nbsp;real.&nbsp;num.&nbsp;<IMG
- WIDTH="32" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img88.png"
+ WIDTH="31" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img89.png"
  ALT="$\ge 0$"></TD>
 <TD ALIGN="LEFT">0</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=198>Drop tolerance <IMG
  WIDTH="11" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
- SRC="img89.png"
+ SRC="img90.png"
  ALT="$t$"> in the ILU(<IMG
  WIDTH="27" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
  SRC="img35.png"
  ALT="$p,t$">) factorization.</TD>
 </TR>
-<TR><TD ALIGN="LEFT" COLSPAN=5><B>Note</B> Defaults for
+<TR><TD ALIGN="LEFT" COLSPAN=5><B>Note:</B> defaults for
   <TT>m</TT>ld_coarse_subsolve_ are chosen as</TD>
 </TR>
-<TR><TD ALIGN="LEFT" COLSPAN=5>Single precision version: 'SLU' if installed, 'ILU' otherwise</TD>
+<TR><TD ALIGN="LEFT" COLSPAN=5>single precision version: 'SLU' if installed, 'ILU' otherwise</TD>
 </TR>
-<TR><TD ALIGN="LEFT" COLSPAN=5>Double precision version: 'UMF' if installed,
+<TR><TD ALIGN="LEFT" COLSPAN=5>double precision version: 'UMF' if installed,
   else 'SLU' if installed, 'ILU' otherwise</TD>
 </TR>
 </TABLE>

docs/html/node20.html

@@ -72,20 +72,20 @@ This routine computes <!-- MATH
  $y = op(M^{-1})\, x$
  -->
 <IMG
- WIDTH="117" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
- SRC="img95.png"
+ WIDTH="118" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
+ SRC="img96.png"
  ALT="$y = op(M^{-1})\, x$">, where <IMG
  WIDTH="23" HEIGHT="15" ALIGN="BOTTOM" BORDER="0"
  SRC="img59.png"
  ALT="$M$"> is a previously built
 preconditioner, stored into <code>p</code>, and <IMG
- WIDTH="22" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img96.png"
+ WIDTH="21" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img97.png"
  ALT="$op$">
 denotes the preconditioner itself or its transpose, according to
 the value of <code>trans</code>.
 Note that, when MLD2P4 is used with a Krylov solver from PSBLAS,
-<code>mld_precaply</code> is called within the PSBLAS routine <code>mld_krylov</code>
+<code>mld_precaply</code> is called within the PSBLAS routine <code>psb_krylov</code>
 and hence it is completely transparent to the user.
 
 <P>
@@ -109,8 +109,8 @@ and hence it is completely transparent to the user.
 </TR>
 <TR><TD ALIGN="LEFT" VALIGN="TOP" WIDTH=34>&nbsp;</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=340>The local part of the vector <IMG
- WIDTH="14" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
- SRC="img97.png"
+ WIDTH="15" HEIGHT="14" ALIGN="BOTTOM" BORDER="0"
+ SRC="img98.png"
  ALT="$x$">. Note that <I>type</I> and   
                 <I>kind_parameter</I> must be chosen according
                 to the real/complex, single/double precision version of MLD2P4 under use.</TD>
@@ -120,8 +120,8 @@ and hence it is completely transparent to the user.
 </TR>
 <TR><TD ALIGN="LEFT" VALIGN="TOP" WIDTH=34>&nbsp;</TD>
 <TD ALIGN="LEFT" VALIGN="TOP" WIDTH=340>The local part of the vector <IMG
- WIDTH="14" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
- SRC="img98.png"
+ WIDTH="13" HEIGHT="31" ALIGN="MIDDLE" BORDER="0"
+ SRC="img99.png"
  ALT="$y$">. Note that <I>type</I> and
                 <I>kind_parameter</I> must be chosen according
                 to the real/complex, single/double precision version of MLD2P4 under use.</TD>
@@ -148,28 +148,28 @@ and hence it is completely transparent to the user.
  -->
 <IMG
  WIDTH="132" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
- SRC="img99.png"
+ SRC="img100.png"
  ALT="$op(M^{-1}) = M^{-1}$">;
                 if <code>trans</code> = <code>'T','t'</code> then <!-- MATH
  $op(M^{-1}) = M^{-T}$
  -->
 <IMG
  WIDTH="135" HEIGHT="40" ALIGN="MIDDLE" BORDER="0"
- SRC="img100.png"
+ SRC="img101.png"
  ALT="$op(M^{-1}) = M^{-T}$">
                 (transpose of <IMG
  WIDTH="48" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
- SRC="img101.png"
+ SRC="img102.png"
  ALT="$M^{-1})$">;  if <code>trans</code> = <code>'C','c'</code> then <!-- MATH
  $op(M^{-1}) = M^{-C}$
  -->
 <IMG
  WIDTH="136" HEIGHT="40" ALIGN="MIDDLE" BORDER="0"
- SRC="img102.png"
+ SRC="img103.png"
  ALT="$op(M^{-1}) = M^{-C}$">
                 (conjugate transpose of <IMG
  WIDTH="48" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
- SRC="img101.png"
+ SRC="img102.png"
  ALT="$M^{-1})$">.</TD>
 </TR>
 <TR><TD ALIGN="LEFT" VALIGN="TOP" WIDTH=34><code>work</code></TD>

docs/html/node24.html

@@ -63,11 +63,11 @@ License
 <P>
 The MLD2P4 is freely distributable under the following copyright
 terms: <PRE> 
-                         MLD2P4  version 1.0
+                         MLD2P4  version 1.1
 MultiLevel Domain Decomposition Parallel Preconditioners Package
            based on PSBLAS (Parallel Sparse BLAS version 2.3)
 
-(C) Copyright 2008
+(C) Copyright 2008, 2009
 
                     Salvatore Filippone  University of Rome Tor Vergata       
                     Alfredo Buttari      University of Rome Tor Vergata

docs/html/node26.html

@@ -67,7 +67,7 @@ Mathematics Department, Macquarie University, Sydney.
 The command line arguments were: <BR>
  <STRONG>latex2html</STRONG> <TT>-noaddress -dir ../../html userhtml.tex</TT>
 <P>
-The translation was initiated by Salvatore Filippone on 2008-09-12
+The translation was initiated by Salvatore Filippone on 2009-03-13
 <BR><HR>
 
 </BODY>

docs/html/node3.html

@@ -75,7 +75,7 @@ Ax=b,
  -->
 <TABLE WIDTH="100%" ALIGN="CENTER">
 <TR VALIGN="MIDDLE"><TD ALIGN="CENTER" NOWRAP><A NAME="system1"></A><IMG
- WIDTH="58" HEIGHT="30" BORDER="0"
+ WIDTH="57" HEIGHT="30" BORDER="0"
  SRC="img1.png"
  ALT="\begin{displaymath}
 Ax=b,
@@ -151,7 +151,6 @@ On the other hand, the routines of the middle and lower layer can be used and ex
 by expert users to build new versions of multi-level Schwarz preconditioners.
 We provide here a description of the upper-layer routines, but not of the
 medium-layer ones.
-
 <P>
 This guide is organized as follows. General information on the distribution of the source code
 is reported in Section&nbsp;<A HREF="node4.html#sec:distribution">2</A>, while details on the configuration

docs/html/node8.html

@@ -75,7 +75,7 @@ be specified with an <EM>absolute</EM> path).
 The full set of options may be looked at by issuing the command
 <code>./configure --help</code>, which produces:
 <PRE>
-`configure' configures MLD2P4 1.0 to adapt to many kinds of systems.
+`configure' configures MLD2P4 1.1 to adapt to many kinds of systems.
 
 Usage: ./configure [OPTION]... [VAR=VALUE]...
 

docs/html/userhtml.html

@@ -65,9 +65,9 @@ University of Rome ``Tor Vergata'', Italy
 <BR>
 <BR>
 <BR>
-Software version: 1.0
+Software version: 1.1
 <BR>
-Sept. 9th, 2008
+March 13, 2009
 
 <BR>
 

docs/src/Makefile

@@ -139,7 +139,7 @@ PDF      = $(join $(BASEFILE),.pdf)
 PS       = $(join $(BASEFILE),.ps)
 GXS      = $(join $(BASEFILE),.gxs)
 GLX      = $(join $(BASEFILE),.glx)
-TARGETPDF= ../mld2p4-1.0-guide.pdf
+TARGETPDF= ../mld2p4-1.1-guide.pdf
 BASEHTML = $(patsubst %.tex,%,$(HTMLFILE))
 HTML     = $(join $(HTMLFILE),.html)
 HTMLDIR  = ../html

docs/src/abstract.tex

@@ -5,7 +5,7 @@ PSBLAS}) is a package of parallel algebraic multi-level preconditioners.
 It implements various versions of one-level additive and of multi-level additive
 and hybrid Schwarz algorithms. In the multi-level case, a purely algebraic approach
 is applied to generate coarse-level corrections, so that no geometric background is needed
-concerning the matrix to be preconditioned. The matrix is required to be square, real
+concerning the matrix to be preconditioned. The matrix is assumed to be square, real
 or complex, with a symmetric sparsity pattern. 
 
 MLD2P4 has been designed to provide scalable and easy-to-use preconditioners in the

docs/src/background.tex

@@ -62,8 +62,8 @@ aggregation} algorithm \cite{BREZINA_VANEK,VANEK_MANDEL_BREZINA}. A decoupled ve
 of this algorithm is implemented, where the smoothed aggregation is applied locally
 to each submatrix \cite{TUMINARO_TONG}. In the next two subsections we provide
 a brief description of the multi-level Schwarz preconditioners and of the smoothed
-aggregation technique as implemented in MLD2P4. For further details the user
-is referred to \cite{para_04,aaecc_07,apnum_07,dd2_96}.
+aggregation technique as implemented in MLD2P4. For further details the reader
+is referred to \cite{para_04,aaecc_07,apnum_07,MLD2P4_TOMS,dd2_96}.
 
 
 \subsection{Multi-level Schwarz Preconditioners\label{sec:multilevel}}
@@ -144,7 +144,7 @@ of the number of iterations on the degree of parallelism we may
 introduce a global coupling among the overlapping partitions by defining 
 a coarse-space approximation $A_C$ of the matrix $A$. 
 In a pure algebraic setting, $A_C$ is usually built with
-a Galerkin approach. Given a set $W_C$ of \emph{coarse vertices},
+the Galerkin approach. Given a set $W_C$ of \emph{coarse vertices},
 with size $n_C$, and a suitable restriction operator
 $R_C \in \Re^{n_C \times n}$, $A_C$ is defined as
 \[
@@ -225,7 +225,8 @@ example, in Figure~\ref{fig:mlhpost_alg}. Here the number of levels
 is denoted by $nlev$ and the levels are numbered in increasing order starting
 from the finest one, i.e.\ the finest level is level 1; the coarse matrix
 and the corresponding basic preconditioner at each level $l$ are denoted by $A_l$ and
-$M_l$, respectively, with $A_1=A$.
+$M_l$, respectively, with $A_1=A$, while the related restriction operator is
+denoted by $R_l$.
 % 
 \begin{figure}[t]
 \begin{center}

docs/src/bibliography.tex

@@ -69,7 +69,14 @@ T.~Chan and T.~Mathew,
 {\em Domain Decomposition Algorithms},
 in A.~Iserles, editor, Acta Numerica 1994, 61--143.
 Cambridge University Press.
-% 
+%
+%% \bibitem{MLD2P4_TOMS} 
+%% P.~D'Ambra, D.~di~Serafino, S.~Filippone,
+%% \emph{MLD2P4: a Package of Parallel Multilevel
+%% Algebraic Domain Decomposition Preconditioners
+%% in Fortran 95},
+%% COMPLETARE.
+%
 \bibitem{UMFPACK}
 T.A.~Davis, 
 {\em Algorithm 832: UMFPACK - an Unsymmetric-pattern Multifrontal

docs/src/building.tex

@@ -96,7 +96,7 @@ be specified with an {\em absolute} path).
 The full set of options may be looked at by issuing the command
 \verb|./configure --help|, which produces:
 \begin{verbatim}
-`configure' configures MLD2P4 1.0 to adapt to many kinds of systems.
+`configure' configures MLD2P4 1.1 to adapt to many kinds of systems.
 
 Usage: ./configure [OPTION]... [VAR=VALUE]...
 

docs/src/gettingstarted.tex

@@ -94,7 +94,7 @@ Multilevel        &\verb|'ML'|    & Multi-level hybrid preconditioner (additive
                                     Coarsest matrix: distributed among the processors.
                                     Coarsest-level solver: 
                                     4 sweeps of the block-Jacobi solver, 
-                                    with LU (or ILU) factorization of the blocks
+                                    with LU or ILU factorization of the blocks
                                     (UMFPACK for the double precision versions and
                                     SuperLU for the single precision ones, if the packages
                                     have been installed; ILU(0), otherwise).         \\

docs/src/license.tex

@@ -5,11 +5,11 @@
 The MLD2P4 is freely distributable under the following copyright
 terms: {\small
 \begin{verbatim} 
-                         MLD2P4  version 1.0
+                         MLD2P4  version 1.1
 MultiLevel Domain Decomposition Parallel Preconditioners Package
            based on PSBLAS (Parallel Sparse BLAS version 2.3)
 
-(C) Copyright 2008
+(C) Copyright 2008, 2009
 
                     Salvatore Filippone  University of Rome Tor Vergata       
                     Alfredo Buttari      University of Rome Tor Vergata
@@ -41,4 +41,4 @@ CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 POSSIBILITY OF SUCH DAMAGE.
 \end{verbatim}
-}
+}

docs/src/overview.tex

@@ -69,7 +69,8 @@ build any preconditioner available in MLD2P4 and to apply it within a PSBLAS Kry
 On the other hand, the routines of the middle and lower layer can be used and extended
 by expert users to build new versions of multi-level Schwarz preconditioners.
 We provide here a description of the upper-layer routines, but not of the
-medium-layer ones.
+medium-layer ones.%%  For a detailed description of the overall software architecture
+%% of MLD2P4 the reader is referred to~\cite{MLD2P4_TOMS}.
 
 This guide is organized as follows. General information on the distribution of the source code
 is reported in Section~\ref{sec:distribution}, while details on the configuration

docs/src/userguide.tex

@@ -27,7 +27,7 @@
 \pdfcompresslevel=0             %-- 0 = none, 9 = best
 \pdfinfo{                       %-- Info dictionary of PDF output  /Author (PD, DdS, SF)
   /Title    (MultiLevel Domain Decomposition Parallel Preconditioners Package
-             based on PSBLAS, V. 1.0)
+             based on PSBLAS, V. 1.1)
   /Subject  (MultiLevel Domain Decomposition Parallel Preconditioners Package)
   /Keywords (Parallel Numerical Software, Algebraic Multilevel Preconditioners, Sparse Iterative Solvers, PSBLAS, MPI)
   /Creator  (pdfLaTeX)
@@ -125,9 +125,9 @@ based on PSBLAS}
 \vspace{\stretch{1}}
 \noindent\hspace*{\centeroffset}\makebox[0pt][l]{\begin{minipage}{\textwidth}
 \flushright
-\large Software version: 1.0\\
+\large Software version: 1.1\\
 %\today
-\large Sept. 9th, 2008
+\large March 13, 2009
 \end{minipage}}
 %\addtolength{\textwidth}{\centeroffset}
 \vspace{\stretch{2}}

docs/src/userhtml.tex

@@ -102,9 +102,9 @@ based on PSBLAS}\\[3ex]
  University of Rome ``Tor Vergata'', Italy\\[2ex]
 %\\[10ex]
 %\today
-Software version: 1.0\\
+Software version: 1.1\\
 %\today
-Sept. 9th, 2008
+March 13, 2009
 \clearpage
 \ \\
 \thispagestyle{empty}

docs/src/userinterface.tex

@@ -228,9 +228,10 @@ refer to Section~\ref{sec:background}.
                          & Aggregation algorithm. Currently, only the
                          decoupled aggregation is available. \\ \hline 
 \verb|mld_aggr_kind_|    & \verb|character(len=*)|
-                         & \texttt{'SMOOTH'} \hspace{2.5cm} \texttt{'RAW'}
-                         & \texttt{'SMOOTH'}
-                         & Type of aggregation: smoothed, raw (i.e.\ using the tentative prolongator). \\ \hline
+                         & \texttt{'SMOOTHED'} \hspace{2.5cm} \texttt{'NONSMOOTHED'}
+                         & \texttt{'SMOOTHED'}
+                         & Type of aggregation: smoothed, nonsmoothed
+                         (i.e.\ using the tentative prolongator). \\ \hline
 \verb|mld_aggr_thresh_|  & \verb|real(|\emph{kind\_parameter}\verb|)|
                          & Any~real~num. $\in [0, 1]$
                          & 0
@@ -312,10 +313,10 @@ refer to Section~\ref{sec:background}.
                          & 0
                          & Drop tolerance $t$ in the ILU($p,t$) factorization. \\
 \hline
-\multicolumn{5}{|l|}{{\bfseries Note} Defaults for
+\multicolumn{5}{|l|}{{\bfseries Note:} defaults for
   {\texttt mld\_coarse\_subsolve\_} are chosen as }\\ 
-\multicolumn{5}{|l|}{Single precision version: 'SLU' if installed, 'ILU' otherwise}\\
-\multicolumn{5}{|l|}{Double precision version: 'UMF' if installed,
+\multicolumn{5}{|l|}{single precision version: 'SLU' if installed, 'ILU' otherwise}\\
+\multicolumn{5}{|l|}{double precision version: 'UMF' if installed,
   else 'SLU' if installed, 'ILU' otherwise}\\
 \hline
 \end{tabular}
@@ -379,7 +380,7 @@ preconditioner, stored into \verb|p|, and $op$
 denotes the preconditioner itself or its transpose, according to
 the value of \verb|trans|.
 Note that, when MLD2P4 is used with a Krylov solver from PSBLAS,
-\verb|mld_precaply| is called within the PSBLAS routine \verb|mld_krylov|
+\verb|mld_precaply| is called within the PSBLAS routine \verb|psb_krylov|
 and hence it is completely transparent to the user.
 
 {\vskip2\baselineskip\noindent\large\bfseries Arguments}