.TH HPL_indxg2l 3 "September 10, 2008" "HPL 2.0" "HPL Library Functions" .SH NAME HPL_indxg2l \- Map a global index into a local one. .SH SYNOPSIS \fB\&#include "hpl.h"\fR \fB\&int\fR \fB\&HPL_indxg2l(\fR \fB\&const int\fR \fI\&IG\fR, \fB\&const int\fR \fI\&INB\fR, \fB\&const int\fR \fI\&NB\fR, \fB\&const int\fR \fI\&SRCPROC\fR, \fB\&const int\fR \fI\&NPROCS\fR \fB\&);\fR .SH DESCRIPTION \fB\&HPL_indxg2l\fR computes the local index of a matrix entry pointed to by the global index IG. This local returned index is the same in all processes. .SH ARGUMENTS .TP 8 IG (input) const int On entry, IG specifies the global index of the matrix entry. IG must be at least zero. .TP 8 INB (input) const int On entry, INB specifies the size of the first block of the global matrix. INB must be at least one. .TP 8 NB (input) const int On entry, NB specifies the blocking factor used to partition and distribute the matrix. NB must be larger than one. .TP 8 SRCPROC (input) const int On entry, if SRCPROC = -1, the data is not distributed but replicated, in which case this routine returns IG in all processes. Otherwise, the value of SRCPROC is ignored. .TP 8 NPROCS (input) const int On entry, NPROCS specifies the total number of process rows or columns over which the matrix is distributed. NPROCS must be at least one. .SH SEE ALSO .BR HPL_indxg2lp \ (3), .BR HPL_indxg2p \ (3), .BR HPL_indxl2g \ (3), .BR HPL_numroc \ (3), .BR HPL_numrocI \ (3).