COMPMID-926 Add depth multiplier support to NEON/CL/GLES depthwise convolution
Change-Id: I03f32c62350e5ea43e77bb15fc5a832d83719e3b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/126657
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
index 4ecc07a..62b9a86 100644
--- a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
+++ b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
@@ -40,29 +40,31 @@
/** Default move assignment operator. */
/** Initialize the function's source, destination, conv and border_size.
*
- * @param[in] input Source tensor. DataType supported: QASYMM8.
- * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, 3, 3]. Data type supported: Same as @p input.
- * @param[in] biases (Optional) Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
- * Data type supported: Same as @p input.
- * @param[out] output Destination tensor. Data type supported: Same as @p input.
- * @param[in] conv_info Padding and stride information to use for the convolution.
- * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU are supported.
+ * @param[in] input Source tensor. DataType supported: QASYMM8.
+ * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, 3, 3]. Data type supported: Same as @p input.
+ * @param[in] biases (Optional) Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
+ * Data type supported: Same as @p input.
+ * @param[out] output Destination tensor. Data type supported: Same as @p input.
+ * @param[in] conv_info Padding and stride information to use for the convolution.
+ * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.
+ * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU are supported.
*/
- void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info,
+ void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier,
ActivationLayerInfo act_info) override;
/** Static function to check if given info will lead to a valid configuration of @ref CLDepthwiseConvolutionLayer3x3NHWCKernel
*
- * @param[in] input Source tensor. DataType supported: QASYMM8.
- * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, 3, 3]. Data type supported: Same as @p input.
- * @param[in] biases (Optional) Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
- * Data type supported: Same as @p input.
- * @param[in] output Destination tensor. Data type supported: Same as @p input.
- * @param[in] conv_info Padding and stride information to use for the convolution.
- * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU are supported.
+ * @param[in] input Source tensor. DataType supported: QASYMM8.
+ * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, 3, 3]. Data type supported: Same as @p input.
+ * @param[in] biases (Optional) Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
+ * Data type supported: Same as @p input.
+ * @param[in] output Destination tensor. Data type supported: Same as @p input.
+ * @param[in] conv_info Padding and stride information to use for the convolution.
+ * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.
+ * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU are supported.
*
* @return a status
*/
- static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info,
+ static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier,
ActivationLayerInfo act_info = ActivationLayerInfo());
void run(const Window &window, cl::CommandQueue &queue) override;