TensorReduce#
Macros | |
| #define | MIOPEN_API_VERSION_REDUCE_TENSOR 1 |
| Version of TensorReduce API. Applications may use it to ensure backward compatibility with older library versions. More... | |
Enumerations | |
| enum | miopenReduceTensorOp_t { MIOPEN_REDUCE_TENSOR_ADD = 0 , MIOPEN_REDUCE_TENSOR_MUL , MIOPEN_REDUCE_TENSOR_MIN , MIOPEN_REDUCE_TENSOR_MAX , MIOPEN_REDUCE_TENSOR_AMAX , MIOPEN_REDUCE_TENSOR_AVG , MIOPEN_REDUCE_TENSOR_NORM1 , MIOPEN_REDUCE_TENSOR_NORM2 = 7 } |
| enum | miopenNanPropagation_t { MIOPEN_NOT_PROPAGATE_NAN = 0 , MIOPEN_PROPAGATE_NAN = 1 } |
| enum | miopenReduceTensorIndices_t { MIOPEN_REDUCE_TENSOR_NO_INDICES = 0 , MIOPEN_REDUCE_TENSOR_FLATTENED_INDICES = 1 } |
| enum | miopenIndicesType_t { MIOPEN_32BIT_INDICES = 0 , MIOPEN_64BIT_INDICES = 1 , MIOPEN_16BIT_INDICES = 2 , MIOPEN_8BIT_INDICES = 3 } |
Functions | |
| MIOPEN_DECLARE_OBJECT (miopenReduceTensorDescriptor) | |
| Creates the miopenReduceTensorDescriptor_t type. More... | |
| miopenStatus_t | miopenCreateReduceTensorDescriptor (miopenReduceTensorDescriptor_t *reduceTensorDesc) |
| Creates the ReduceTensor descriptor object. More... | |
| miopenStatus_t | miopenDestroyReduceTensorDescriptor (miopenReduceTensorDescriptor_t reduceTensorDesc) |
| Destroy the ReduceTensor descriptor object. More... | |
| miopenStatus_t | miopenSetReduceTensorDescriptor (miopenReduceTensorDescriptor_t reduceTensorDesc, miopenReduceTensorOp_t reduceTensorOp, miopenDataType_t reduceTensorCompType, miopenNanPropagation_t reduceTensorNanOpt, miopenReduceTensorIndices_t reduceTensorIndices, miopenIndicesType_t reduceTensorIndicesType) |
| Initialize a ReduceTensor descriptor object. More... | |
| miopenStatus_t | miopenGetReduceTensorDescriptor (const miopenReduceTensorDescriptor_t reduceTensorDesc, miopenReduceTensorOp_t *reduceTensorOp, miopenDataType_t *reduceTensorCompType, miopenNanPropagation_t *reduceTensorNanOpt, miopenReduceTensorIndices_t *reduceTensorIndices, miopenIndicesType_t *reduceTensorIndicesType) |
| Query a ReduceTensor descriptor object. More... | |
| miopenStatus_t | miopenGetReductionIndicesSize (miopenHandle_t handle, const miopenReduceTensorDescriptor_t reduceTensorDesc, const miopenTensorDescriptor_t aDesc, const miopenTensorDescriptor_t cDesc, size_t *sizeInBytes) |
| Helper function to query the minimum index space size required by the ReduceTensor call. More... | |
| miopenStatus_t | miopenGetReductionWorkspaceSize (miopenHandle_t handle, const miopenReduceTensorDescriptor_t reduceTensorDesc, const miopenTensorDescriptor_t aDesc, const miopenTensorDescriptor_t cDesc, size_t *sizeInBytes) |
| Helper function to query the minimum workspace size required by the ReduceTensor call. More... | |
| miopenStatus_t | miopenReduceTensor (miopenHandle_t handle, const miopenReduceTensorDescriptor_t reduceTensorDesc, void *indices, size_t indicesSizeInBytes, void *workspace, size_t workspaceSizeInBytes, const void *alpha, const miopenTensorDescriptor_t aDesc, const void *A, const void *beta, const miopenTensorDescriptor_t cDesc, void *C) |
| TensorReduce function doing reduction on tensor A by implementing C = alpha * reduceOp(A) More... | |
Detailed Description
Macro Definition Documentation
◆ MIOPEN_API_VERSION_REDUCE_TENSOR
| #define MIOPEN_API_VERSION_REDUCE_TENSOR 1 |
Version of TensorReduce API. Applications may use it to ensure backward compatibility with older library versions.
- 0 or undefined - Initial API. Supported operations: ADD, MIN, MIN, MAX.
- 1 - Added AMAX, AVG, NORM1, NORM2 ops.
Enumeration Type Documentation
◆ miopenIndicesType_t
| enum miopenIndicesType_t |
◆ miopenNanPropagation_t
◆ miopenReduceTensorIndices_t
◆ miopenReduceTensorOp_t
Tensor Reduction operation types
Function Documentation
◆ MIOPEN_DECLARE_OBJECT()
| MIOPEN_DECLARE_OBJECT | ( | miopenReduceTensorDescriptor | ) |
Creates the miopenReduceTensorDescriptor_t type.
◆ miopenCreateReduceTensorDescriptor()
| miopenStatus_t miopenCreateReduceTensorDescriptor | ( | miopenReduceTensorDescriptor_t * | reduceTensorDesc | ) |
Creates the ReduceTensor descriptor object.
- Parameters
-
reduceTensorDesc Pointer to a ReduceTensor descriptor type
- Returns
- miopenStatus_t
◆ miopenDestroyReduceTensorDescriptor()
| miopenStatus_t miopenDestroyReduceTensorDescriptor | ( | miopenReduceTensorDescriptor_t | reduceTensorDesc | ) |
Destroy the ReduceTensor descriptor object.
- Parameters
-
reduceTensorDesc ReduceTensor descriptor type (input)
- Returns
- miopenStatus_t
◆ miopenGetReduceTensorDescriptor()
| miopenStatus_t miopenGetReduceTensorDescriptor | ( | const miopenReduceTensorDescriptor_t | reduceTensorDesc, |
| miopenReduceTensorOp_t * | reduceTensorOp, | ||
| miopenDataType_t * | reduceTensorCompType, | ||
| miopenNanPropagation_t * | reduceTensorNanOpt, | ||
| miopenReduceTensorIndices_t * | reduceTensorIndices, | ||
| miopenIndicesType_t * | reduceTensorIndicesType | ||
| ) |
Query a ReduceTensor descriptor object.
- Parameters
-
reduceTensorDesc Pointer to the ReduceTensor descriptor object (input) reduceTensorOp Pointer to enumerant specifying the operation used by ReduceTensor (output) reduceTensorCompType Pointer to enumerant specifying the data type used with ReduceTensor operation (output) reduceTensorNanOpt Pointer to enumerant specifying the NaN number propagation mode (output) reduceTensorIndices Pointer to enumerant specifying the indices modes used by ReduceTensor (output) reduceTensorIndicesType Pointer to enumerant specifying the data type of the indices (output)
- Returns
- miopenStatus_t
◆ miopenGetReductionIndicesSize()
| miopenStatus_t miopenGetReductionIndicesSize | ( | miopenHandle_t | handle, |
| const miopenReduceTensorDescriptor_t | reduceTensorDesc, | ||
| const miopenTensorDescriptor_t | aDesc, | ||
| const miopenTensorDescriptor_t | cDesc, | ||
| size_t * | sizeInBytes | ||
| ) |
Helper function to query the minimum index space size required by the ReduceTensor call.
- Parameters
-
handle MIOpen Handle (input) reduceTensorDesc Pointer to the ReduceTensor descriptor object (input) aDesc Pointer to the input tensor descriptor (input) cDesc Pointer to the output tensor descriptor (input) sizeInBytes Pointer to data to return the minimum index space size
- Returns
- miopenStatus_t
◆ miopenGetReductionWorkspaceSize()
| miopenStatus_t miopenGetReductionWorkspaceSize | ( | miopenHandle_t | handle, |
| const miopenReduceTensorDescriptor_t | reduceTensorDesc, | ||
| const miopenTensorDescriptor_t | aDesc, | ||
| const miopenTensorDescriptor_t | cDesc, | ||
| size_t * | sizeInBytes | ||
| ) |
Helper function to query the minimum workspace size required by the ReduceTensor call.
- Parameters
-
handle MIOpen Handle (input) reduceTensorDesc Pointer to the ReduceTensor descriptor object (input) aDesc Pointer to the input tensor descriptor (input) cDesc Pointer to the output tensor descriptor (input) sizeInBytes Pointer to data to return the minimum workspace size
- Returns
- miopenStatus_t
◆ miopenReduceTensor()
| miopenStatus_t miopenReduceTensor | ( | miopenHandle_t | handle, |
| const miopenReduceTensorDescriptor_t | reduceTensorDesc, | ||
| void * | indices, | ||
| size_t | indicesSizeInBytes, | ||
| void * | workspace, | ||
| size_t | workspaceSizeInBytes, | ||
| const void * | alpha, | ||
| const miopenTensorDescriptor_t | aDesc, | ||
| const void * | A, | ||
| const void * | beta, | ||
| const miopenTensorDescriptor_t | cDesc, | ||
| void * | C | ||
| ) |
TensorReduce function doing reduction on tensor A by implementing C = alpha * reduceOp(A)
- beta * C
The length of each dimension of output tensor C must match the length of the corresponding dimension of input tensor A or must be equal to 1. The dimensions with length equal to 1 indicate the dimensions of A to be reduced.
The scale factors alpha and beta are read as float, or as double when the data type of tensor A is double, and are passed to the kernels as float; they are converted to the compute type of the reduce descriptor. The reduction, the scaling by alpha and the blend with the prior content of tensor C are made in the compute type, and the result is converted once to the data type of C (rounded for a floating point type, truncated for an integer type). An integer compute type truncates a fractional alpha, beta and prior content of C. The prior content of C is not read when beta, converted to the compute type, is zero. A compute type that cannot hold every value of the data type of C (for example FP16 compute for FP32 data) rounds the prior content of C to the compute type.
- Parameters
-
handle MIOpen Handle (input) reduceTensorDesc Pointer to the ReduceTensor descriptor object (input) indices Address of the allocated indices data space (output) indicesSizeInBytes Size in bytes of the allocated indices data space (input) workspace Address of the allocated workspace data (input) workspaceSizeInBytes Size in bytes of the allocated workspace data (input) alpha Pointer to scale factor for data in input tensor A (input) aDesc Pointer to the tensor descriptor for input tensor A (input) A Pointer to the data of input tensor A (input) beta Pointer to scale factor for data in output tensor C (input) cDesc Pointer to the tensor descriptor for output tensor C (input) C Pointer to the data of output tensor C (output)
- Returns
- miopenStatus_t
◆ miopenSetReduceTensorDescriptor()
| miopenStatus_t miopenSetReduceTensorDescriptor | ( | miopenReduceTensorDescriptor_t | reduceTensorDesc, |
| miopenReduceTensorOp_t | reduceTensorOp, | ||
| miopenDataType_t | reduceTensorCompType, | ||
| miopenNanPropagation_t | reduceTensorNanOpt, | ||
| miopenReduceTensorIndices_t | reduceTensorIndices, | ||
| miopenIndicesType_t | reduceTensorIndicesType | ||
| ) |
Initialize a ReduceTensor descriptor object.
- Parameters
-
reduceTensorDesc Pointer to the ReduceTensor descriptor object (output) reduceTensorOp Enumerant specifying the operation used by ReduceTensor (input) reduceTensorCompType Enumerant specifying the data type used with ReduceTensor operation (input) reduceTensorNanOpt Enumerant specifying the NaN number propagation mode (input) reduceTensorIndices Enumerant specifying the indices modes used by ReduceTensor (input) reduceTensorIndicesType Enumerant specifying the data type of the indices (input)
- Returns
- miopenStatus_t