|
CUDNN Frontend API
8.3.0
|
#include <cudnn_frontend_Tensor.h>


Public Member Functions | |
| std::string | describe () const override |
| Return a string describing the backend Descriptor. More... | |
| int64_t | getPackedElementCount () const |
| int64_t | getDimensionCount () const |
| int64_t const * | getDimArray () const |
| int64_t const * | getStrideArray () const |
| int64_t | getDataType () const |
| Tensor_v8 (Tensor_v8 &&from)=default | |
| Tensor_v8 & | operator= (Tensor_v8 &&)=default |
| ~Tensor_v8 ()=default | |
Public Member Functions inherited from cudnn_frontend::BackendDescriptor | |
| cudnnBackendDescriptor_t | get_raw_desc () const |
| cudnnStatus_t | get_status () const |
| Current status of the descriptor. More... | |
| void | set_status (cudnnStatus_t const status_) const |
| Set status of the descriptor. More... | |
| void | set_error (const char *message) const |
| Set Diagonistic error message. More... | |
| const char * | get_error () const |
| Diagonistic error message if any. More... | |
| ManagedOpaqueDescriptor | get_desc () const |
| Returns a copy of underlying managed descriptor. More... | |
| cudnnStatus_t | initialize_managed_backend_pointer (cudnnBackendDescriptorType_t type) |
| Initializes the underlying managed descriptor. More... | |
Private Member Functions | |
| Tensor_v8 ()=default | |
| Tensor_v8 (Tensor_v8 const &)=delete | |
| Tensor_v8 & | operator= (Tensor_v8 const &)=delete |
Private Attributes | |
| cudnnDataType_t | data_type = CUDNN_DATA_FLOAT |
| int64_t | btensor_dimA [CUDNN_DIM_MAX+1] = {-1} |
| Datatype of the elements. More... | |
| int64_t | btensor_strA [CUDNN_DIM_MAX+1] = {-1} |
| n, g, c, d, h, w More... | |
| int64_t | id = -1 |
| n, g, c, d, h, w More... | |
| int64_t | alignment = -1 |
| Unique id of the tensor. More... | |
| int64_t | nDims = -1 |
| Certain engine config expect minimum alignment of 16B. More... | |
| int64_t | vectorDimension = -1 |
| Number of Dimensions of the tensor. More... | |
| int64_t | vectorCount = 1 |
| Which dimension of the tensor is vectorized (Generally the c dim) More... | |
| bool | isVirtual = false |
| What is the vectorization count (4 or 32) More... | |
| bool | isByValue = false |
| Whether it is an intermediate tensor of an op graph. More... | |
Friends | |
| class | TensorBuilder_v8 |
Additional Inherited Members | |
Protected Member Functions inherited from cudnn_frontend::BackendDescriptor | |
| BackendDescriptor (ManagedOpaqueDescriptor pointer_, cudnnStatus_t status_, std::string err_msg_) | |
| BackendDescriptor ()=default | |
Protected Attributes inherited from cudnn_frontend::BackendDescriptor | |
| ManagedOpaqueDescriptor | pointer |
| cudnnStatus_t | status = CUDNN_STATUS_SUCCESS |
| Shared pointer of the OpaqueBackendPointer. More... | |
| std::string | err_msg |
| Error message if any being set. More... | |
Tensor_v8 Class This class tells the properties of the Tensor_v8 on which the operation will be performed Properties:
Use TensorBuilder_v8 to build this class. Describe returns a string describing the tensor class
Definition at line 52 of file cudnn_frontend_Tensor.h.
|
default |
|
default |
Referenced by getDataType().
|
privatedefault |
Referenced by getDataType().
|
privatedelete |
|
inlineoverridevirtual |
Return a string describing the backend Descriptor.
Implements cudnn_frontend::BackendDescriptor.
Definition at line 56 of file cudnn_frontend_Tensor.h.
References alignment, btensor_dimA, btensor_strA, data_type, isByValue, isVirtual, nDims, cudnn_frontend::to_string(), nlohmann::to_string(), vectorCount, and vectorDimension.
|
inline |
Definition at line 105 of file cudnn_frontend_Tensor.h.
References data_type, operator=(), Tensor_v8(), and ~Tensor_v8().
|
inline |
Definition at line 95 of file cudnn_frontend_Tensor.h.
References btensor_dimA.
Referenced by cudnn_frontend::cudnnReorderFilterAndBiasInt8x32().
|
inline |
Definition at line 90 of file cudnn_frontend_Tensor.h.
References nDims.
Referenced by cudnn_frontend::cudnnReorderFilterAndBiasInt8x32().
|
inline |
Definition at line 81 of file cudnn_frontend_Tensor.h.
References btensor_dimA, nDims, and vectorCount.
|
inline |
Definition at line 100 of file cudnn_frontend_Tensor.h.
References btensor_strA.
Referenced by cudnn_frontend::TensorBuilder_v8::build(), and getDataType().
|
friend |
Definition at line 54 of file cudnn_frontend_Tensor.h.
Referenced by cudnn_frontend::TensorBuilder_v8::build().
|
private |
Unique id of the tensor.
Definition at line 125 of file cudnn_frontend_Tensor.h.
Referenced by describe().
|
private |
Datatype of the elements.
Definition at line 122 of file cudnn_frontend_Tensor.h.
Referenced by describe(), getDimArray(), and getPackedElementCount().
|
private |
n, g, c, d, h, w
Definition at line 123 of file cudnn_frontend_Tensor.h.
Referenced by describe(), and getStrideArray().
|
private |
Definition at line 121 of file cudnn_frontend_Tensor.h.
Referenced by describe(), and getDataType().
|
private |
n, g, c, d, h, w
Definition at line 124 of file cudnn_frontend_Tensor.h.
|
private |
Whether it is an intermediate tensor of an op graph.
Definition at line 131 of file cudnn_frontend_Tensor.h.
Referenced by describe().
|
private |
What is the vectorization count (4 or 32)
Definition at line 130 of file cudnn_frontend_Tensor.h.
Referenced by describe().
|
private |
Certain engine config expect minimum alignment of 16B.
Alignment of the tensor.
Definition at line 127 of file cudnn_frontend_Tensor.h.
Referenced by describe(), getDimensionCount(), and getPackedElementCount().
|
private |
Which dimension of the tensor is vectorized (Generally the c dim)
Definition at line 129 of file cudnn_frontend_Tensor.h.
Referenced by describe(), and getPackedElementCount().
|
private |
Number of Dimensions of the tensor.
Definition at line 128 of file cudnn_frontend_Tensor.h.
Referenced by describe().