tvm
|
The base class for cost model. More...
#include <cost_model.h>
Public Member Functions | |
virtual void | Update (const Array< MeasureInput > &inputs, const Array< MeasureResult > &results)=0 |
Update the cost model according to new measurement results (training data). More... | |
virtual void | Predict (const SearchTask &task, const Array< State > &states, std::vector< float > *scores)=0 |
Predict the scores of states. More... | |
virtual void | PredictStages (const SearchTask &task, const Array< State > &states, std::vector< float > *state_scores, std::vector< std::vector< float >> *stage_scores) |
Predict the scores of all stages in states. This is the breakdown version of Predict More... | |
virtual | ~CostModelNode () |
Default virtual destructor. More... | |
TVM_DECLARE_BASE_OBJECT_INFO (CostModelNode, Object) | |
Public Member Functions inherited from tvm::runtime::Object | |
uint32_t | type_index () const |
std::string | GetTypeKey () const |
size_t | GetTypeKeyHash () const |
template<typename TargetType > | |
bool | IsInstance () const |
bool | unique () const |
Object () | |
Object (const Object &other) | |
Object (Object &&other) | |
Object & | operator= (const Object &other) |
Object & | operator= (Object &&other) |
Static Public Attributes | |
static constexpr const char * | _type_key = "auto_scheduler.CostModel" |
Static Public Attributes inherited from tvm::runtime::Object | |
static constexpr const char * | _type_key = "runtime.Object" |
static constexpr bool | _type_final = false |
static constexpr uint32_t | _type_child_slots = 0 |
static constexpr bool | _type_child_slots_can_overflow = true |
static constexpr bool | _type_has_method_visit_attrs = true |
static constexpr bool | _type_has_method_sequal_reduce = false |
static constexpr bool | _type_has_method_shash_reduce = false |
static constexpr uint32_t | _type_index = TypeIndex::kDynamic |
Additional Inherited Members | |
Public Types inherited from tvm::runtime::Object | |
typedef void(* | FDeleter) (Object *self) |
Object deleter. More... | |
using | RefCounterType = std::atomic< int32_t > |
Static Public Member Functions inherited from tvm::runtime::Object | |
static std::string | TypeIndex2Key (uint32_t tindex) |
Get the type key of the corresponding index from runtime. More... | |
static size_t | TypeIndex2KeyHash (uint32_t tindex) |
Get the type key hash of the corresponding index from runtime. More... | |
static uint32_t | TypeKey2Index (const std::string &key) |
Get the type index of the corresponding key from runtime. More... | |
static uint32_t | _GetOrAllocRuntimeTypeIndex () |
static uint32_t | RuntimeTypeIndex () |
Protected Member Functions inherited from tvm::runtime::Object | |
void | IncRef () |
developer function, increases reference counter. More... | |
void | DecRef () |
developer function, decrease reference counter. More... | |
Static Protected Member Functions inherited from tvm::runtime::Object | |
static uint32_t | GetOrAllocRuntimeTypeIndex (const std::string &key, uint32_t static_tindex, uint32_t parent_tindex, uint32_t type_child_slots, bool type_child_slots_can_overflow) |
Get the type index using type key. More... | |
Protected Attributes inherited from tvm::runtime::Object | |
uint32_t | type_index_ {0} |
Type index(tag) that indicates the type of the object. More... | |
RefCounterType | ref_counter_ {0} |
The internal reference counter. More... | |
FDeleter | deleter_ = nullptr |
deleter of this object to enable customized allocation. If the deleter is nullptr, no deletion will be performed. The creator of the object must always set the deleter field properly. More... | |
The base class for cost model.
|
inlinevirtual |
Default virtual destructor.
|
pure virtual |
Predict the scores of states.
task | The search task of states |
states | The input states |
scores | The predicted scores for all states |
Implemented in tvm::auto_scheduler::PythonBasedModelNode, and tvm::auto_scheduler::RandomModelNode.
|
inlinevirtual |
Predict the scores of all stages in states. This is the breakdown version of Predict
task | The search task |
states | The input states |
state_scores | The predicted scores for all states |
stage_scores | The predicted scores for all stages in all stages |
Reimplemented in tvm::auto_scheduler::PythonBasedModelNode.
tvm::auto_scheduler::CostModelNode::TVM_DECLARE_BASE_OBJECT_INFO | ( | CostModelNode | , |
Object | |||
) |
|
pure virtual |
Update the cost model according to new measurement results (training data).
inputs | The measure inputs |
results | The measure results |
Implemented in tvm::auto_scheduler::PythonBasedModelNode, and tvm::auto_scheduler::RandomModelNode.
|
staticconstexpr |