MAGMA  2.3.0
Matrix Algebra for GPU and Multicore Architectures
 All Classes Files Functions Friends Groups Pages
getmatrix: GPU => CPU

Macros

#define magma_igetmatrix(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix() for magma_int_t arrays.
 
#define magma_igetmatrix_async(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix_async() for magma_int_t arrays.
 
#define magma_index_getmatrix(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix() for magma_index_t arrays.
 
#define magma_index_getmatrix_async(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix_async() for magma_index_t arrays.
 
#define magma_cgetmatrix(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix() for magmaFloatComplex arrays.
 
#define magma_cgetmatrix_async(m, n, dA_src, ldda, hB_dst, ldb, queue)
 Type-safe version of magma_getmatrix_async() for magmaFloatComplex arrays.
 
#define magma_dgetmatrix(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix() for double arrays.
 
#define magma_dgetmatrix_async(m, n, dA_src, ldda, hB_dst, ldb, queue)
 Type-safe version of magma_getmatrix_async() for double arrays.
 
#define magma_sgetmatrix(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix() for float arrays.
 
#define magma_sgetmatrix_async(m, n, dA_src, ldda, hB_dst, ldb, queue)
 Type-safe version of magma_getmatrix_async() for float arrays.
 
#define magma_zgetmatrix(m, n, dA_src, ldda, hB_dst, ldb,queue)
 Type-safe version of magma_getmatrix() for magmaDoubleComplex arrays.
 
#define magma_zgetmatrix_async(m, n, dA_src, ldda, hB_dst, ldb, queue)
 Type-safe version of magma_getmatrix_async() for magmaDoubleComplex arrays.
 
#define magma_getmatrix(m, n, elemSize, dA_src, ldda, hB_dst, ldb,queue)
 Copy all or part of matrix dA_src on GPU device to hB_dst on CPU host. More...
 
#define magma_getmatrix_async(m, n, elemSize, dA_src, ldda, hB_dst, ldb,queue)
 Copy all or part of matrix dA_src on GPU device to hB_dst on CPU host. More...
 

Detailed Description

Macro Definition Documentation

magma_getmatrix (   m,
  n,
  elemSize,
  dA_src,
  ldda,
  hB_dst,
  ldb,
  queue 
)

Copy all or part of matrix dA_src on GPU device to hB_dst on CPU host.

Elements may be arbitrary size. Type-safe versions set elemSize appropriately.

This version synchronizes the queue after the transfer. See magma_getmatrix_async() for an asynchronous version.

Parameters
[in]mNumber of rows of matrix A. m >= 0.
[in]nNumber of columns of matrix A. n >= 0.
[in]elemSizeSize of each element, e.g., sizeof(double).
[in]dA_srcSource array of dimension (ldda,n), on GPU device.
[in]lddaLeading dimension of matrix A. ldda >= m.
[out]hB_dstDestination array of dimension (ldb,n), on CPU host.
[in]ldbLeading dimension of matrix B. ldb >= m.
[in]queueQueue to execute in.
magma_getmatrix_async (   m,
  n,
  elemSize,
  dA_src,
  ldda,
  hB_dst,
  ldb,
  queue 
)

Copy all or part of matrix dA_src on GPU device to hB_dst on CPU host.

Elements may be arbitrary size. Type-safe versions set elemSize appropriately.

This version is asynchronous: it may return before the transfer finishes, if hB_dst is pinned CPU memory. See magma_getmatrix() for a synchronous version.

Parameters
[in]mNumber of rows of matrix A. m >= 0.
[in]nNumber of columns of matrix A. n >= 0.
[in]elemSizeSize of each element, e.g., sizeof(double).
[in]dA_srcSource array of dimension (ldda,n), on GPU device.
[in]lddaLeading dimension of matrix A. ldda >= m.
[out]hB_dstDestination array of dimension (ldb,n), on CPU host.
[in]ldbLeading dimension of matrix B. ldb >= m.
[in]queueQueue to execute in.