diff options
Diffstat (limited to 'arm_compute/core/NEON')
-rw-r--r-- | arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h | 9 | ||||
-rw-r--r-- | arm_compute/core/NEON/kernels/NEWeightsReshapeKernel.h | 11 |
2 files changed, 20 insertions, 0 deletions
diff --git a/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h b/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h index aff2671441..9923c31018 100644 --- a/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h +++ b/arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h @@ -61,6 +61,15 @@ public: * @param[in] alpha Weight of the matrix product */ void configure(const ITensor *input0, const ITensor *input1, ITensor *output, float alpha); + /** Static function to check if given info will lead to a valid configuration of @ref NEGEMMMatrixMultiplyKernel + * + * @param[in] input0 Input tensor containing the Matrix A. Data types supported: QS8/QS16/F16/F32 + * @param[in] input1 Input tensor containing the Matrix B. Data type supported: same as @p input0 + * @param[in] output Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0 + * + * @return a status + */ + static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output); // Inherited methods overridden: void run(const Window &window, const ThreadInfo &info) override; diff --git a/arm_compute/core/NEON/kernels/NEWeightsReshapeKernel.h b/arm_compute/core/NEON/kernels/NEWeightsReshapeKernel.h index 5b37d6cc62..84ec736d03 100644 --- a/arm_compute/core/NEON/kernels/NEWeightsReshapeKernel.h +++ b/arm_compute/core/NEON/kernels/NEWeightsReshapeKernel.h @@ -77,6 +77,17 @@ public: * @param[out] output The output tensor. Data types supported: Same as @p input */ void configure(const ITensor *input, const ITensor *bias, ITensor *output); + /** Static function to check if given info will lead to a valid configuration of @ref NEWeightsReshapeKernel + * + * @param[in] input The input tensor to convert. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM] if shared, + * and 5D tensor with dimensions [kernel_x, kernel_y, IFM, OFM, num_patches] if unshared. Data types supported: QS8/QS16/F16/F32 + * @param[in] biases The shared biases tensor to append. Bias is 1D tensor with dimensions [OFM] if shared and 2D tensor with + * dimensions [OFM, num_patches] if unshared. Data types supported: Same as @p input + * @param[in] output The output tensor. Should be a 2D Tensor. Data types supported: Same as @p input + * + * @return a status + */ + static Status validate(const ITensorInfo *input, const ITensorInfo *biases, const ITensorInfo *output); // Inherited methods overridden: void run(const Window &window, const ThreadInfo &info) override; |