|
| file | auto_schedule.h [code] |
| | The user interface of the auto scheduler.
|
| |
| file | compute_dag.h [code] |
| | The auto-scheduler's computational graph and related program analyses.
|
| |
| file | cost_model.h [code] |
| | Cost models that estimate the performance of programs.
|
| |
| file | feature.h [code] |
| | Feature extraction for the cost model. We extract one feature vector per BufferStoreNode statement in a TIR Stmt, so we call this feature as "per-store" feature. The cost model also does prediction for each BufferStoreNode statement and aggregates the predictions as the whole score for a TVM IR (Stmt).
|
| |
| file | loop_state.h [code] |
| | The definition of the "state" in the search.
|
| |
| file | measure.h [code] |
| | Distributed measurement infrastructure to measure the runtime costs of tensor programs. These functions are responsible for building the tvm module, uploading it to remote devices, recording the running time costs, and checking the correctness of the output.
|
| |
| file | measure_record.h [code] |
| | Json serialization format for dumping and loading measurement records.
|
| |
| file | search_policy.h [code] |
| | The base class of search policies, including the abstract definition of search policy and other supporting data structures.
|
| |
| file | search_task.h [code] |
| | Meta information and hardware parameters for a search task.
|
| |
| file | transform_step.h [code] |
| | Transformation steps. These steps are used to manipulate LoopState. They are similar to the schedule primitives in te::Stage.
|
| |
