ReduceExtreme#
ReduceExtreme
Enumerations | |
enum | miopenReduceExtremeOp_t { MIOPEN_REDUCE_EXTREME_ARGMIN , MIOPEN_REDUCE_EXTREME_ARGMAX , MIOPEN_REDUCE_EXTREME_MIN , MIOPEN_REDUCE_EXTREME_MAX } |
Functions | |
miopenStatus_t | miopenReduceExtremeForward (miopenHandle_t handle, const miopenTensorDescriptor_t xDesc, const void *x, const int32_t dim, const miopenReduceExtremeOp_t reduceExtremeOp, const miopenTensorDescriptor_t yDesc, void *y, const miopenTensorDescriptor_t indiceDesc, void *indice) |
Find the the extreme (minimum, maximum) value and index of a tensor across Dimension. More... | |
Detailed Description
Enumeration Type Documentation
◆ miopenReduceExtremeOp_t
Reduction Extreme operation types
Function Documentation
◆ miopenReduceExtremeForward()
miopenStatus_t miopenReduceExtremeForward | ( | miopenHandle_t | handle, |
const miopenTensorDescriptor_t | xDesc, | ||
const void * | x, | ||
const int32_t | dim, | ||
const miopenReduceExtremeOp_t | reduceExtremeOp, | ||
const miopenTensorDescriptor_t | yDesc, | ||
void * | y, | ||
const miopenTensorDescriptor_t | indiceDesc, | ||
void * | indice | ||
) |
Find the the extreme (minimum, maximum) value and index of a tensor across Dimension.
- Parameters
-
handle MIOpen handle (input) xDesc Tensor descriptor for data input tensor x (input) x Data tensor x (input) dim Dimension to reduce argmax. (input) reduceExtremeOp Enumerant specifying the operation used by ReduceExtreme (input) yDesc Tensor descriptor for reduce data tensor y (input) y Data tensor y (output) indiceDesc Tensor descriptor for reduce data tensor indice only int32_t (input) indice Data tensor indice (output)
- Returns
- miopenStatus_t