root / man / man3 / HPL_perm.3
Historique | Voir | Annoter | Télécharger (1,65 ko)
| 1 | 1 | equemene | .TH HPL_perm 3 "September 10, 2008" "HPL 2.0" "HPL Library Functions" |
|---|---|---|---|
| 2 | 1 | equemene | .SH NAME |
| 3 | 1 | equemene | HPL_perm \- Combine 2 index arrays - Generate the permutation. |
| 4 | 1 | equemene | .SH SYNOPSIS |
| 5 | 1 | equemene | \fB\&#include "hpl.h"\fR |
| 6 | 1 | equemene | |
| 7 | 1 | equemene | \fB\&void\fR |
| 8 | 1 | equemene | \fB\&HPL_perm(\fR |
| 9 | 1 | equemene | \fB\&const int\fR |
| 10 | 1 | equemene | \fI\&N\fR, |
| 11 | 1 | equemene | \fB\&int *\fR |
| 12 | 1 | equemene | \fI\&LINDXA\fR, |
| 13 | 1 | equemene | \fB\&int *\fR |
| 14 | 1 | equemene | \fI\&LINDXAU\fR, |
| 15 | 1 | equemene | \fB\&int *\fR |
| 16 | 1 | equemene | \fI\&IWORK\fR |
| 17 | 1 | equemene | \fB\&);\fR |
| 18 | 1 | equemene | .SH DESCRIPTION |
| 19 | 1 | equemene | \fB\&HPL_perm\fR |
| 20 | 1 | equemene | combines two index arrays and generate the corresponding |
| 21 | 1 | equemene | permutation. First, this function computes the inverse of LINDXA, and |
| 22 | 1 | equemene | then combine it with LINDXAU. Second, in order to be able to perform |
| 23 | 1 | equemene | the permutation in place, LINDXAU is overwritten by the sequence of |
| 24 | 1 | equemene | permutation producing the same result. What we ultimately want to |
| 25 | 1 | equemene | achieve is: U[LINDXAU[i]] := U[LINDXA[i]] for i in [0..N). After the |
| 26 | 1 | equemene | call to this function, this in place permutation can be performed by |
| 27 | 1 | equemene | for i in [0..N) swap U[i] with U[LINDXAU[i]]. |
| 28 | 1 | equemene | .SH ARGUMENTS |
| 29 | 1 | equemene | .TP 8 |
| 30 | 1 | equemene | N (global input) const int |
| 31 | 1 | equemene | On entry, N specifies the length of the arrays LINDXA and |
| 32 | 1 | equemene | LINDXAU. N should be at least zero. |
| 33 | 1 | equemene | .TP 8 |
| 34 | 1 | equemene | LINDXA (global input/output) int * |
| 35 | 1 | equemene | On entry, LINDXA is an array of dimension N containing the |
| 36 | 1 | equemene | source indexes. On exit, LINDXA contains the combined index |
| 37 | 1 | equemene | array. |
| 38 | 1 | equemene | .TP 8 |
| 39 | 1 | equemene | LINDXAU (global input/output) int * |
| 40 | 1 | equemene | On entry, LINDXAU is an array of dimension N containing the |
| 41 | 1 | equemene | target indexes. On exit, LINDXAU contains the sequence of |
| 42 | 1 | equemene | permutation, that should be applied in increasing order to |
| 43 | 1 | equemene | permute the underlying array U in place. |
| 44 | 1 | equemene | .TP 8 |
| 45 | 1 | equemene | IWORK (workspace) int * |
| 46 | 1 | equemene | On entry, IWORK is a workarray of dimension N. |
| 47 | 1 | equemene | .SH SEE ALSO |
| 48 | 1 | equemene | .BR HPL_plindx1 \ (3), |
| 49 | 1 | equemene | .BR HPL_pdlaswp01N \ (3), |
| 50 | 1 | equemene | .BR HPL_pdlaswp01T \ (3). |