| 1 |
<HTML> |
| 2 |
<HEAD> |
| 3 |
<TITLE>HPL_indxg2lp HPL 2.0 Library Functions September 10, 2008</TITLE> |
| 4 |
</HEAD> |
| 5 |
|
| 6 |
<BODY BGCOLOR="WHITE" TEXT = "#000000" LINK = "#0000ff" VLINK = "#000099" |
| 7 |
ALINK = "#ffff00"> |
| 8 |
|
| 9 |
<H1>Name</H1> |
| 10 |
<B>HPL_indxg2lp</B> Map a local index into a global one. |
| 11 |
|
| 12 |
<H1>Synopsis</H1> |
| 13 |
<CODE>#include "hpl.h"</CODE><BR><BR> |
| 14 |
<CODE>void</CODE> |
| 15 |
<CODE>HPL_indxg2lp(</CODE> |
| 16 |
<CODE>int *</CODE> |
| 17 |
<CODE>IL</CODE>, |
| 18 |
<CODE>int *</CODE> |
| 19 |
<CODE>PROC</CODE>, |
| 20 |
<CODE>const int</CODE> |
| 21 |
<CODE>IG</CODE>, |
| 22 |
<CODE>const int</CODE> |
| 23 |
<CODE>INB</CODE>, |
| 24 |
<CODE>const int</CODE> |
| 25 |
<CODE>NB</CODE>, |
| 26 |
<CODE>const int</CODE> |
| 27 |
<CODE>SRCPROC</CODE>, |
| 28 |
<CODE>const int</CODE> |
| 29 |
<CODE>NPROCS</CODE> |
| 30 |
<CODE>);</CODE> |
| 31 |
|
| 32 |
<H1>Description</H1> |
| 33 |
<B>HPL_indxg2lp</B> |
| 34 |
computes the local index of a matrix entry pointed to by |
| 35 |
the global index IG as well as the process coordinate which posseses |
| 36 |
this entry. The local returned index is the same in all processes. |
| 37 |
|
| 38 |
<H1>Arguments</H1> |
| 39 |
<PRE> |
| 40 |
IL (output) int * |
| 41 |
On exit, IL specifies the local index corresponding to IG. IL |
| 42 |
is at least zero. |
| 43 |
</PRE> |
| 44 |
<PRE> |
| 45 |
PROC (output) int * |
| 46 |
On exit, PROC is the coordinate of the process owning the |
| 47 |
entry specified by the global index IG. PROC is at least zero |
| 48 |
and less than NPROCS. |
| 49 |
</PRE> |
| 50 |
<PRE> |
| 51 |
IG (input) const int |
| 52 |
On entry, IG specifies the global index of the matrix entry. |
| 53 |
IG must be at least zero. |
| 54 |
</PRE> |
| 55 |
<PRE> |
| 56 |
INB (input) const int |
| 57 |
On entry, INB specifies the size of the first block of the |
| 58 |
global matrix. INB must be at least one. |
| 59 |
</PRE> |
| 60 |
<PRE> |
| 61 |
NB (input) const int |
| 62 |
On entry, NB specifies the blocking factor used to partition |
| 63 |
and distribute the matrix A. NB must be larger than one. |
| 64 |
</PRE> |
| 65 |
<PRE> |
| 66 |
SRCPROC (input) const int |
| 67 |
On entry, if SRCPROC = -1, the data is not distributed but |
| 68 |
replicated, in which case this routine returns IG in all |
| 69 |
processes. Otherwise, the value of SRCPROC is ignored. |
| 70 |
</PRE> |
| 71 |
<PRE> |
| 72 |
NPROCS (input) const int |
| 73 |
On entry, NPROCS specifies the total number of process rows |
| 74 |
or columns over which the matrix is distributed. NPROCS must |
| 75 |
be at least one. |
| 76 |
</PRE> |
| 77 |
|
| 78 |
<H1>See Also</H1> |
| 79 |
<A HREF="HPL_indxg2l.html">HPL_indxg2l</A>, |
| 80 |
<A HREF="HPL_indxg2p.html">HPL_indxg2p</A>, |
| 81 |
<A HREF="HPL_indxl2g.html">HPL_indxl2g</A>, |
| 82 |
<A HREF="HPL_numroc.html">HPL_numroc</A>, |
| 83 |
<A HREF="HPL_numrocI.html">HPL_numrocI</A>. |
| 84 |
|
| 85 |
</BODY> |
| 86 |
</HTML> |