MAGMA  2.3.0
Matrix Algebra for GPU and Multicore Architectures
 All Classes Files Functions Friends Groups Pages

\( B = A \) More...

Functions

void magmablas_clacpy (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magmaFloatComplex_const_ptr dA, magma_int_t ldda, magmaFloatComplex_ptr dB, magma_int_t lddb, magma_queue_t queue)
 CLACPY copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_clacpy_sym_in (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaFloatComplex_const_ptr dA, magma_int_t ldda, magmaFloatComplex_ptr dB, magma_int_t lddb, magma_queue_t queue)
 CLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_clacpy_sym_out (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaFloatComplex_const_ptr dA, magma_int_t ldda, magmaFloatComplex_ptr dB, magma_int_t lddb, magma_queue_t queue)
 CLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_dlacpy (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magmaDouble_const_ptr dA, magma_int_t ldda, magmaDouble_ptr dB, magma_int_t lddb, magma_queue_t queue)
 DLACPY copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_dlacpy_sym_in (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaDouble_const_ptr dA, magma_int_t ldda, magmaDouble_ptr dB, magma_int_t lddb, magma_queue_t queue)
 DLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_dlacpy_sym_out (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaDouble_const_ptr dA, magma_int_t ldda, magmaDouble_ptr dB, magma_int_t lddb, magma_queue_t queue)
 DLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_slacpy (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magmaFloat_const_ptr dA, magma_int_t ldda, magmaFloat_ptr dB, magma_int_t lddb, magma_queue_t queue)
 SLACPY copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_slacpy_sym_in (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaFloat_const_ptr dA, magma_int_t ldda, magmaFloat_ptr dB, magma_int_t lddb, magma_queue_t queue)
 SLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_slacpy_sym_out (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaFloat_const_ptr dA, magma_int_t ldda, magmaFloat_ptr dB, magma_int_t lddb, magma_queue_t queue)
 SLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_zlacpy (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magmaDoubleComplex_const_ptr dA, magma_int_t ldda, magmaDoubleComplex_ptr dB, magma_int_t lddb, magma_queue_t queue)
 ZLACPY copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_zlacpy_sym_in (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaDoubleComplex_const_ptr dA, magma_int_t ldda, magmaDoubleComplex_ptr dB, magma_int_t lddb, magma_queue_t queue)
 ZLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 
void magmablas_zlacpy_sym_out (magma_uplo_t uplo, magma_int_t m, magma_int_t n, magma_int_t *rows, magma_int_t *perm, magmaDoubleComplex_const_ptr dA, magma_int_t ldda, magmaDoubleComplex_ptr dB, magma_int_t lddb, magma_queue_t queue)
 ZLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB. More...
 

Detailed Description

\( B = A \)

Function Documentation

void magmablas_clacpy ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magmaFloatComplex_const_ptr  dA,
magma_int_t  ldda,
magmaFloatComplex_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

CLACPY copies all or part of a two-dimensional matrix dA to another matrix dB.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]dACOMPLEX array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBCOMPLEX array, dimension (LDDB,N) The M-by-N matrix dB. On exit, dB = dA in the locations specified by UPLO.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_clacpy_sym_in ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaFloatComplex_const_ptr  dA,
magma_int_t  ldda,
magmaFloatComplex_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

CLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as CLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of rows that are swapped. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the identity permutation array. On exit, it is updated with the new pivots given by rows such that i-th row will be the original perm[i]-th row after the pivots are applied.
[in]dACOMPLEX array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBCOMPLEX array, dimension (LDDB,N) On exit, dB = stores the columns after the pivots are applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_clacpy_sym_out ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaFloatComplex_const_ptr  dA,
magma_int_t  ldda,
magmaFloatComplex_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

CLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as CLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the permutation array such that i-th row will be the original perm[i]-th row after the pivots are applied. On exit, it is restored to be identity permutation.
[in,out]dACOMPLEX array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed. On exit, the matrix after the symmetric pivoting is applied.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[in]dBCOMPLEX array, dimension (LDDB,N) The M-by-N matrix dB. On entry, dB stores the columns after row pivoting is applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_dlacpy ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magmaDouble_const_ptr  dA,
magma_int_t  ldda,
magmaDouble_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

DLACPY copies all or part of a two-dimensional matrix dA to another matrix dB.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]dADOUBLE PRECISION array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBDOUBLE PRECISION array, dimension (LDDB,N) The M-by-N matrix dB. On exit, dB = dA in the locations specified by UPLO.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_dlacpy_sym_in ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaDouble_const_ptr  dA,
magma_int_t  ldda,
magmaDouble_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

DLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as DLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of rows that are swapped. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the identity permutation array. On exit, it is updated with the new pivots given by rows such that i-th row will be the original perm[i]-th row after the pivots are applied.
[in]dADOUBLE PRECISION array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBDOUBLE PRECISION array, dimension (LDDB,N) On exit, dB = stores the columns after the pivots are applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_dlacpy_sym_out ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaDouble_const_ptr  dA,
magma_int_t  ldda,
magmaDouble_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

DLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as DLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the permutation array such that i-th row will be the original perm[i]-th row after the pivots are applied. On exit, it is restored to be identity permutation.
[in,out]dADOUBLE PRECISION array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed. On exit, the matrix after the symmetric pivoting is applied.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[in]dBDOUBLE PRECISION array, dimension (LDDB,N) The M-by-N matrix dB. On entry, dB stores the columns after row pivoting is applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_slacpy ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magmaFloat_const_ptr  dA,
magma_int_t  ldda,
magmaFloat_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

SLACPY copies all or part of a two-dimensional matrix dA to another matrix dB.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]dAREAL array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBREAL array, dimension (LDDB,N) The M-by-N matrix dB. On exit, dB = dA in the locations specified by UPLO.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_slacpy_sym_in ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaFloat_const_ptr  dA,
magma_int_t  ldda,
magmaFloat_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

SLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as SLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of rows that are swapped. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the identity permutation array. On exit, it is updated with the new pivots given by rows such that i-th row will be the original perm[i]-th row after the pivots are applied.
[in]dAREAL array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBREAL array, dimension (LDDB,N) On exit, dB = stores the columns after the pivots are applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_slacpy_sym_out ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaFloat_const_ptr  dA,
magma_int_t  ldda,
magmaFloat_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

SLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as SLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the permutation array such that i-th row will be the original perm[i]-th row after the pivots are applied. On exit, it is restored to be identity permutation.
[in,out]dAREAL array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed. On exit, the matrix after the symmetric pivoting is applied.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[in]dBREAL array, dimension (LDDB,N) The M-by-N matrix dB. On entry, dB stores the columns after row pivoting is applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_zlacpy ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magmaDoubleComplex_const_ptr  dA,
magma_int_t  ldda,
magmaDoubleComplex_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

ZLACPY copies all or part of a two-dimensional matrix dA to another matrix dB.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]dACOMPLEX_16 array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBCOMPLEX_16 array, dimension (LDDB,N) The M-by-N matrix dB. On exit, dB = dA in the locations specified by UPLO.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_zlacpy_sym_in ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaDoubleComplex_const_ptr  dA,
magma_int_t  ldda,
magmaDoubleComplex_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

ZLACPY_SYM_IN copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as ZLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of rows that are swapped. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the identity permutation array. On exit, it is updated with the new pivots given by rows such that i-th row will be the original perm[i]-th row after the pivots are applied.
[in]dACOMPLEX_16 array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[out]dBCOMPLEX_16 array, dimension (LDDB,N) On exit, dB = stores the columns after the pivots are applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.
void magmablas_zlacpy_sym_out ( magma_uplo_t  uplo,
magma_int_t  m,
magma_int_t  n,
magma_int_t *  rows,
magma_int_t *  perm,
magmaDoubleComplex_const_ptr  dA,
magma_int_t  ldda,
magmaDoubleComplex_ptr  dB,
magma_int_t  lddb,
magma_queue_t  queue 
)

ZLACPY_SYM_OUT copies all or part of a two-dimensional matrix dA to another matrix dB.

This is the same as ZLACPY, but adds queue argument.

Parameters
[in]uplomagma_uplo_t Specifies the part of the matrix dA to be copied to dB.
  • = MagmaUpper: Upper triangular part
  • = MagmaLower: Lower triangular part
  • = MagmaFull: All of the matrix dA
[in]mINTEGER The number of rows of the matrix dA. M >= 0.
[in]nINTEGER The number of columns of the matrix dA. N >= 0.
[in]rowsINTEGER array, on GPU, dimension (2*n) On entry, it stores the new pivots such that rows[i]-th and rows[n+i]-th rows are swapped.
[in,out]permINTEGER array, on GPU, dimension (m) On entry, it stores the permutation array such that i-th row will be the original perm[i]-th row after the pivots are applied. On exit, it is restored to be identity permutation.
[in,out]dACOMPLEX_16 array, dimension (LDDA,N) The M-by-N matrix dA. If UPLO = MagmaUpper, only the upper triangle or trapezoid is accessed; if UPLO = MagmaLower, only the lower triangle or trapezoid is accessed. On exit, the matrix after the symmetric pivoting is applied.
[in]lddaINTEGER The leading dimension of the array dA. LDDA >= max(1,M).
[in]dBCOMPLEX_16 array, dimension (LDDB,N) The M-by-N matrix dB. On entry, dB stores the columns after row pivoting is applied.
[in]lddbINTEGER The leading dimension of the array dB. LDDB >= max(1,M).
[in]queuemagma_queue_t Queue to execute in.