PLASMA
2.4.5
PLASMA - Parallel Linear Algebra for Scalable Multi-core Architectures
|
Go to the source code of this file.
Macros | |
#define | A(_m, _n) (PLASMA_Complex32_t *)plasma_geteltaddr(A, ((_m)-1), ((_n)-1), eltsize) |
#define | V(_m) &(V[(_m)-1]) |
#define | TAU(_m) &(TAU[(_m)-1]) |
Functions | |
int | CORE_cgbelr (int uplo, int N, PLASMA_desc *A, PLASMA_Complex32_t *V, PLASMA_Complex32_t *TAU, int st, int ed, int eltsize) |
PLASMA core_blas kernel PLASMA is a software package provided by Univ. of Tennessee, Univ. of California Berkeley and Univ. of Colorado Denver
Definition in file core_cgbelr.c.
#define A | ( | _m, | |
_n | |||
) | (PLASMA_Complex32_t *)plasma_geteltaddr(A, ((_m)-1), ((_n)-1), eltsize) |
CORE_cgbelr is a kernel that will operate on a region (triangle) of data bounded by st and ed. This kernel eliminate a column by an element-wise annihiliation, and for each annihiliation, it apply a left update, followed by an right update on the diagonal 2x2 element, where it create a new nnz, eliminate it and update V and TAU, then it continue until finishing the the whole column. When this is done, it take advantage that data are on cache and will apply the right on the remaining part of this region that has not been updated by the right yet. Note that the column to be eliminated is located at st-1.
[in] | uplo |
|
[in] | N | The order of the matrix A. |
[in,out] | A | A pointer to the descriptor of the matrix A. |
[out] | V | PLASMA_Complex32_t array, dimension (N). The scalar elementary reflectors are written in this array. So it is used as a workspace for V at each step of the bulge chasing algorithm. |
[out] | TAU | PLASMA_Complex32_t array, dimension (N). The scalar factors of the elementary reflectors are written in thisarray. So it is used as a workspace for TAU at each step of the bulge chasing algorithm. |
[in] | st | A pointer to the start index where this kernel will operate. |
[in] | ed | A pointer to the end index where this kernel will operate. |
[in] | eltsize | PLASMA internal value which refer to the size of the precision. |
PLASMA_SUCCESS | successful exit |
<0 | if -i, the i-th argument had an illegal value TYPE 1-BDL Householder add -1 because of C |
Definition at line 74 of file core_cgbelr.c.
#define TAU | ( | _m | ) | &(TAU[(_m)-1]) |
Definition at line 76 of file core_cgbelr.c.
#define V | ( | _m | ) | &(V[(_m)-1]) |
Definition at line 75 of file core_cgbelr.c.
int CORE_cgbelr | ( | int | uplo, |
int | N, | ||
PLASMA_desc * | A, | ||
PLASMA_Complex32_t * | V, | ||
PLASMA_Complex32_t * | TAU, | ||
int | st, | ||
int | ed, | ||
int | eltsize | ||
) |
Definition at line 78 of file core_cgbelr.c.
References A, CORE_clarfx2(), CORE_clarfx2ce(), coreblas_error, ELTLDD, max, plasma_desc_t::mb, min, PLASMA_SUCCESS, PlasmaLeft, PlasmaLower, PlasmaRight, PlasmaUpper, TAU, and V.