From 1246b63ca04cb067f26ae860688647224d6ba24e Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Wed, 16 Aug 2017 18:38:32 +0100 Subject: COMPMID-477 - Optimized Direct Convolution 3x3 and 5x5 (f32) for Bifrost. Each work-item computes 4x3 output elements in case of 3x3 convolution and 4x2 in case of 5x5 convolution Change-Id: I6ebbaff8b7e971c1f90d5845c0b58d2a40f39df5 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/84345 Reviewed-by: Anthony Barbier Tested-by: Kaizen --- arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h') diff --git a/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h b/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h index e225b64bae..cdde8d4bfd 100644 --- a/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h +++ b/arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h @@ -56,7 +56,7 @@ public: * 5x5 convolution with stride_x = 1/2, stride_y = 1/2 * * @param[in] input The input tensor to convolve. 3 lower dimensions represent a single input [width, height, IFM], - * while every optional dimension from 4 and above represent a batch of inputs. Data types supported: F16/F32. + * while every optional dimension from 4 and above represent a batch of inputs. Data types supported: QS8/QS16/F16/F32. * @param[in] weights Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. * The 3rd dimension must be the same as the input's volume 3rd dimension. * Data type supported:Same as @p input. -- cgit v1.2.1