commit e52a3000d2c13bc1b66ca66b3d12b6b836982394
author Gian Marco Iodice <gianmarco.iodice@arm.com> Wed Apr 11 15:59:10 2018 +0100
committer Anthony Barbier <anthony.barbier@arm.com> Fri Nov 02 16:49:37 2018 +0000
tree 70e8ef5ba216762604f84228805aac9bd65747b6
parent dd03870b63784abe499761da2b26b209b33f2db2

COMPMID-1026 - Add support for 4x4 output tile in CLWinogradConvolutionLayer

The performance achieved can be found at the following confluence page:
https://confluence.arm.com/display/MLENG/GEMM-based+convolution+vs+Winograd-based+convolution+on+OpenCL

Change-Id: I4b690cfdd4eb4ff0cd17b14fdd49ccaa1d1dc85c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/127729
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>

arm_compute/runtime/CL/functions/CLConvolutionLayer.h

diff --git a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
index 7df7659..a1cd155 100644
--- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
@@ -26,6 +26,7 @@
 
 #include "arm_compute/runtime/CL/functions/CLDirectConvolutionLayer.h"
 #include "arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h"
+#include "arm_compute/runtime/CL/functions/CLWinogradConvolutionLayer.h"
 #include "arm_compute/runtime/IFunction.h"
 #include "arm_compute/runtime/IMemoryManager.h"
 
@@ -84,7 +85,6 @@
      *                         while every optional dimension from 4 and above represent a batch of inputs.
      *                         Data types supported: QS8/QASYMM8/QS16/F16/F32.
      * @param[in] weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input.
-     * @param[in] biases       Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported:Same as @p input.
      * @param[in] output       Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
      *                         Data types supported: Same as @p input.
      * @param[in] conv_info    Contains padding and stride information described in @ref PadStrideInfo.
@@ -95,7 +95,7 @@
      *
      * @return a status
      */
-    static ConvolutionMethod get_convolution_method(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info,
+    static ConvolutionMethod get_convolution_method(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *output, const PadStrideInfo &conv_info,
                                                     const WeightsInfo &weights_info, const ActivationLayerInfo &act_info, const GPUTarget gpu_target, const Size2D &dilation = Size2D(1U, 1U));
     // Inherited methods overridden:
     void run() override;