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

Functions

void zgeqrf_copy_upper_batched (magma_int_t n, magma_int_t nb, magmaDoubleComplex **dV_array, magma_int_t lddv, magmaDoubleComplex **dR_array, magma_int_t lddr, magma_int_t batchCount, magma_queue_t queue)
 These are internal routines that might have many assumption. More...
 

Detailed Description

Function Documentation

void zgeqrf_copy_upper_batched ( magma_int_t  n,
magma_int_t  nb,
magmaDoubleComplex **  dV_array,
magma_int_t  lddv,
magmaDoubleComplex **  dR_array,
magma_int_t  lddr,
magma_int_t  batchCount,
magma_queue_t  queue 
)

These are internal routines that might have many assumption.

They are used in zgeqrf_batched.cpp

Copy part of the data in dV to dR

Parameters
[in]nINTEGER The order of the matrix . N >= 0.
[in]nbINTEGER Tile size in matrix. nb <= N.
[in]dV_arrayArray of pointers, dimension (batchCount). Each is a COMPLEX_16 array on the GPU, dimension (LDDA,N).
[in]lddvINTEGER The leading dimension of each array V. LDDV >= max(1,N).
[in,out]dR_arrayArray of pointers, dimension (batchCount). Each is a COMPLEX_16 array on the GPU, dimension (LDDR,N).
[in]lddrINTEGER The leading dimension of each array R. LDDR >= max(1,N).
[in]batchCountINTEGER The number of matrices to operate on.
[in]queuemagma_queue_t Queue to execute in.