Visible to Intel only — GUID: GUID-F88D2786-0D28-4109-9482-9F036E75433C
Visible to Intel only — GUID: GUID-F88D2786-0D28-4109-9482-9F036E75433C
mkl_graph_transpose
Computes a (masked) transpose of a graph matrix.
mkl_graph_status_t mkl_graph_transpose (mkl_graph_matrix_t C, mkl_graph_matrix_t Mask, mkl_graph_accumulator_t accum, mkl_graph_matrix_t A, mkl_graph_descriptor_t desc);
mkl_graph.h
The mkl_graph_transpose routine computes a (masked) transpose of a graph matrix. An optional mask can be provided through the Mask parameter. Also, an optional binary operator can be passed through accum parameter to be used as an accumulator. The transposition operation can be modified by a desc parameter.
For example, setting the value MKL_GRAPH_MOD_ONLY_STRUCTURE for the output field of the descriptor will make the operation ignore the values of the matrix and create transposed data only for the matrix structure.
Only in-place transposition (when the output matrix C is the same as the input matrix A) is supported currently.
- Mask
-
A graph matrix which will be used as a mask. Ignored if NULL.
NOTE:Currently, mask is not supported by this operation.
- accum
-
Binary operator to be used as an accumulator. Refer to Graph API Glossary for a list of possible options.
NOTE:Currently only MKL_GRAPH_ACCUMULATOR_NONE is supported by this routine.
- A
-
A graph matrix to be transposed.
- desc
-
An operation descriptor. Refer to Graph API Glossary for a list of possible options. If NULL, no extra modifiers are used for the operation.
- C
-
A graph matrix which holds the transposed data of the input matrix (with modifications as provided through the operation descriptor).
The function returns a value indicating whether the operation was successful or not and why. Refer to Graph API Glossary for a list of possible options.
Product and Performance Information |
---|
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex. Notice revision #20201201 |