COMPMID-1498 - Enable grouping in CLGEMMConvolutionLayer
Change-Id: I15c7df21773145b03f42b6f78bd7ad2e5b8a5219
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/144126
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
index c9a74f2..8270e97 100644
--- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
@@ -60,10 +60,11 @@
* @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
* @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
- * available which may introduce a drop of accuracy as well. Default is false
+ * available which may introduce a drop of accuracy as well. Default is false
+ * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
*/
void configure(ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info, const WeightsInfo &weights_info = WeightsInfo(),
- const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false);
+ const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false, unsigned int num_groups = 1);
/** Static function to check if given info will lead to a valid configuration of @ref CLConvolutionLayer
*
* @param[in] input Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
@@ -79,11 +80,13 @@
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
* @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
* available which may introduce a drop of accuracy as well. Default is false
+ * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info,
- const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false);
+ const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false,
+ unsigned int num_groups = 1);
/** Static function to check if given info will return the convolution called by @ref CLConvolutionLayer
*
* @param[in] input Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
diff --git a/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h
index 8538d83..c6ae535 100644
--- a/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h
@@ -59,22 +59,24 @@
CLConvolutionLayerReshapeWeights();
/** Set the input and output tensors.
*
- * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
- * Data type supported: QASYMM8/F16/F32.
- * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p weights.
- * @param[out] output Destination tensor. Data types supported: Same as @p weights.
+ * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+ * Data type supported: QASYMM8/F16/F32.
+ * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p weights.
+ * @param[out] output Destination tensor. Data types supported: Same as @p weights.
+ * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
*/
- void configure(const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output);
+ void configure(const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, unsigned int num_groups = 1);
/** Static function to check if given info will lead to a valid configuration of @ref CLConvolutionLayerReshapeWeights
*
- * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
- * Data type supported: QASYMM8/F16/F32.
- * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p weights.
- * @param[in] output Destination tensor. Data types supported: Same as @p weights.
+ * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+ * Data type supported: QASYMM8/F16/F32.
+ * @param[in] biases Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p weights.
+ * @param[in] output Destination tensor. Data types supported: Same as @p weights.
+ * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
*
* @return a status
*/
- static Status validate(const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output);
+ static Status validate(const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, unsigned int num_groups = 1);
// Inherited methods overridden:
void run() override;
@@ -122,9 +124,10 @@
* tensor has also been transposed with CLGEMMTranspose1xWKernel. Data type supported: Same as @p input.
* @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+ * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
*/
void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info, const WeightsInfo &weights_info = WeightsInfo(),
- const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo());
+ const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), unsigned int num_groups = 1);
/** Static function to check if given info will lead to a valid configuration of @ref CLGEMMConvolutionLayer.
*
* @param[in] input Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
@@ -140,11 +143,12 @@
* tensor has also been transposed with CLGEMMTranspose1xWKernel. Data type supported: Same as @p input.
* @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
+ * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info,
- const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo());
+ const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), unsigned int num_groups = 1);
// Inherited methods overridden:
void run() override;