COMPMID-414 - Port CLConvolutionLayer to support 8 bit fixed point - CLWeightsReshapeKernel
Change-Id: Ie32e6bdd557a8243eb9988aa7eab4e4ca2291e79
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/78701
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
index 6a40396..8030b40 100644
--- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
@@ -53,7 +53,7 @@
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: F32.
+ * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: QS8/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] transpose1xW True if the weights are to undergo a 1xW transposition after reshaping (in case of GEMM operation), false otherwise.
@@ -64,16 +64,16 @@
void run() override;
private:
- CLConvolutionLayerWeightsReshapeKernel _weights_reshape_kernel;
- CLGEMMTranspose1xWKernel _weights_transposed_kernel;
- CLTensor _weights_reshaped;
- bool _transpose1xW;
+ CLWeightsReshapeKernel _weights_reshape_kernel;
+ CLGEMMTranspose1xWKernel _weights_transposed_kernel;
+ CLTensor _weights_reshaped;
+ bool _transpose1xW;
};
/** Basic function to compute the convolution layer. This function calls the following OpenCL kernels:
*
- * -# @ref CLConvolutionLayerWeightsReshapeKernel (executed only once for each configuration)
- * -# @ref CLGEMMTranspose1xWKernel (executed only once for each configuration)
+ * -# @ref CLWeightsReshapeKernel (executed only once for each configuration)
+ * -# @ref CLGEMMTranspose1xWKernel (executed only once for each configuration)
* -# @ref CLIm2ColKernel
* -# @ref CLGEMMInterleave4x4Kernel
* -# @ref CLGEMMMatrixMultiplyKernel