tvm
|
This is a composite node that is produced by extract_buffer_info analysis pass that contains useful global information that could be useful for memory planning algorithms. More...
#include <utils.h>
Public Member Functions | |
void | VisitAttrs (tvm::AttrVisitor *v) |
bool | SEqualReduce (const BufferInfoAnalysisNode *other, SEqualReducer equal) const |
void | SHashReduce (SHashReducer hash_reduce) const |
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) |
Public Attributes | |
Map< BufferInfo, tir::Stmt > | buffer_info_stmts |
The BufferInfo object and its associated TIR statement. More... | |
Integer | memory_pressure |
This represent maximum amount of memory being used at any point of time in the inference. This value is largely the best allocation an algorithm could achieve. Due to the complexities of conflict graphs, it would not be feasible to achieve this value, practically. However, it can be useful for iterative algorithms to know this value to define termination criteria. More... | |
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 () |
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 |
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... | |
This is a composite node that is produced by extract_buffer_info analysis pass that contains useful global information that could be useful for memory planning algorithms.
|
inline |
|
inline |
|
inline |
Map<BufferInfo, tir::Stmt> tvm::tir::usmp::BufferInfoAnalysisNode::buffer_info_stmts |
The BufferInfo object and its associated TIR statement.
Integer tvm::tir::usmp::BufferInfoAnalysisNode::memory_pressure |
This represent maximum amount of memory being used at any point of time in the inference. This value is largely the best allocation an algorithm could achieve. Due to the complexities of conflict graphs, it would not be feasible to achieve this value, practically. However, it can be useful for iterative algorithms to know this value to define termination criteria.