miopenConvSolution_t Struct Reference#
Performance struct for forward, backward filter, or backward data algorithms in immediate mode. More...
#include <miopen.h>
Public Attributes | |
float | time |
size_t | workspace_size |
uint64_t | solution_id |
miopenConvAlgorithm_t | algorithm |
Detailed Description
Performance struct for forward, backward filter, or backward data algorithms in immediate mode.
Contains a 64-bit integer identifying the solution and the algorithm for the solution, as well as the runtime, workspace size and a boolean flag indicating whether the returned solution is a heuristic or resulting from an actual run
Member Data Documentation
◆ algorithm
miopenConvAlgorithm_t miopenConvSolution_t::algorithm |
The algorithm used to compute the solution
◆ solution_id
uint64_t miopenConvSolution_t::solution_id |
Identifier for the returned solution
◆ time
float miopenConvSolution_t::time |
Represents the approximate time required to execute this solution on the GPU, in milliseconds. This value may either be based on an acutal kernel run or an estimate based on a heuristic.
◆ workspace_size
size_t miopenConvSolution_t::workspace_size |
Workspace required to run the selected algorithm represented in the union
The documentation for this struct was generated from the following file:
- /home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-miopen/checkouts/develop/include/miopen/miopen.h