commit cbbed288a71f2f048123db3cf396361e5d66ce93
author Michele Di Giorgio <michele.digiorgio@arm.com> Fri Dec 20 13:26:08 2019 +0000
committer Michele Di Giorgio <michele.digiorgio@arm.com> Tue Jan 14 17:21:26 2020 +0000
tree bd48122e283272adb668a42097ea69ca3f0473a6
parent 70d33bdfd36e1b44b0573189dca67ed7c63dd59e

COMPMID-2991: Add support for QASYMM8_SIGNED in CL kernels/functions - part 2

Adding support for QASYMM8_SIGNED to the following CL kernels/functions:

- CLActivationLayerKernel/CLActivationLayer
- CLComparisonKernel/CLComparison
- CLConvertFullyConnectedWeightsKernel/CLConvertFullyConnectedWeights
- CLDeconvolutionLayerUpsampleKernel/CLDeconvolutionLayerUpsample
- CLDepthToSpaceLayerKernel/CLDepthToSpaceLayer
- CLDequantizationLayerKernel/CLDequantizationLayer
- CLGEMMMatrixVectorMultiplyKernel
- CLNormalizePlanarYUVLayerKernel
- CLPReluLayer
- CLPixelWiseMultiplicationKernel/CLPixelWiseMultiplication
- CLPoolingLayerKernel/CLPoolingLayer

Change-Id: I874bbb7c2b08baa9c5ff4c9e6bc8778b42a6bec5
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2539
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>

src/core/CL/cl_kernels/dequantization_layer.cl

diff --git a/src/core/CL/cl_kernels/dequantization_layer.cl b/src/core/CL/cl_kernels/dequantization_layer.cl
index 7550b4b..add86e3 100644
--- a/src/core/CL/cl_kernels/dequantization_layer.cl
+++ b/src/core/CL/cl_kernels/dequantization_layer.cl
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2019 ARM Limited.
+ * Copyright (c) 2017-2020 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -33,7 +33,7 @@
  * @note Quantization scale of input tensor is passed in with -DSCALE=scale.
  * @note Quantization offset of input tensor is passed in with -DOFFSET=offset.
  *
- * @param[in]  input_ptr                            Pointer to the source tensor. Supported data types: QASYMM8/QSYMM8
+ * @param[in]  input_ptr                            Pointer to the source tensor. Supported data types: QASYMM8/QASYMM8_SIGNED/QSYMM8
  * @param[in]  input_stride_x                       Stride of the source tensor in X dimension (in bytes)
  * @param[in]  input_step_x                         input_stride_x * number of elements along X processed per workitem(in bytes)
  * @param[in]  input_stride_y                       Stride of the source tensor in Y dimension (in bytes)