Loadable Function: ocl_mat = ocl_double (octave_mat)
Loadable Function: ocl_mat = ocl_single (octave_mat)
Loadable Function: ocl_mat = ocl_int8 (octave_mat)
Loadable Function: ocl_mat = ocl_int16 (octave_mat)
Loadable Function: ocl_mat = ocl_int32 (octave_mat)
Loadable Function: ocl_mat = ocl_int64 (octave_mat)
Loadable Function: ocl_mat = ocl_uint8 (octave_mat)
Loadable Function: ocl_mat = ocl_uint16 (octave_mat)
Loadable Function: ocl_mat = ocl_uint32 (octave_mat)
Loadable Function: ocl_mat = ocl_uint64 (octave_mat)

Construct an OCL matrix of specific type from an octave matrix.

All the above constructor functions take as input a conventional numeric octave matrix octave_mat (actually an N-dimensional array) of any numeric data type. The constructors create a new OCL matrix ocl_mat (as an N-dimensional array) of the specified numeric data type, allocate storage space on the OpenCL device hardware, and copy the octave data into the OpenCL device memory. The data then remains in device memory until the OCL matrix is cleared from the octave workspace (or as long as the OpenCL context exists). ocl_double and ocl_single allow operation on real and complex data.

Copying data from an OCL matrix back to an octave matrix is possible via the corresponding standard type casting function (e.g., double, single, int16).

For further explanation on using OCL matrices and example code, see oclArray.

The constructor functions automatically assure that the OpenCL library is loaded (see ocl_lib) and that an OpenCL context is created with an OpenCL device (see ocl_context).

See also: oclArray, ocl_tests, ocl_program, ocl_context, ocl_lib.

Package: ocl