Update operator list documentation

All the common information for the operators are stored in OperatorList.h.

All data type and data layout information for the operators are store in the function header files.

Partially resolve: COMPMID-4199

Signed-off-by: Sheri Zhang <sheri.zhang@arm.com>
Change-Id: I272948cfb3f84e42232a82dd84c0158d84642099
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5511
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>

21 files changed, 235 insertions, 49 deletions

diff --git a/arm_compute/runtime/CL/functions/CLActivationLayer.h b/arm_compute/runtime/CL/functions/CLActivationLayer.h
index aa62183909..e6bb192532 100644
--- a/arm_compute/runtime/CL/functions/CLActivationLayer.h
+++ b/arm_compute/runtime/CL/functions/CLActivationLayer.h
@@ -59,6 +59,19 @@ public:
     CLActivationLayer &operator=(CLActivationLayer &&);
     /** Set the input and output tensor.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |QASYMM8        |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |
+     * |QSYMM16        |QSYMM16        |
+     * |F16            |F16            |
+     * |F32            |F32            |
+     *
+     *
      * @note If the output tensor is a nullptr or is equal to the input, the activation function will be performed in-place
      *
      * @param[in, out] input    Source tensor. In case of @p output tensor = nullptr, this tensor will store the result
diff --git a/arm_compute/runtime/CL/functions/CLConcatenateLayer.h b/arm_compute/runtime/CL/functions/CLConcatenateLayer.h
index bfc8a39ac9..71e84e21b5 100644
--- a/arm_compute/runtime/CL/functions/CLConcatenateLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConcatenateLayer.h
@@ -64,11 +64,22 @@ public:
     CLConcatenateLayer &operator=(CLConcatenateLayer &&);
     /** Initialise the kernel's inputs vector and output.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |QASYMM8        |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |
+     * |F16            |F16            |
+     * |F32            |F32            |
+     *
      * @note Input and output tensor dimensions preconditions defer depending on the concatenation axis.
      * @note Preconditions can be found respectively at @ref opencl::kernels::ClWidthConcatenateKernel,
      *       @ref opencl::kernels::ClHeightConcatenateKernel and @ref opencl::kernels::ClDepthConcatenateKernel.
      *
-     * @param[in,out] inputs_vector The vectors containing all the tensors to concatenate. Data types supported: All
+     * @param[in,out] inputs_vector The vectors containing all the tensors to concatenate. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
      * @param[out]    output        Output tensor. Data types supported: Same as @p input.
      * @param[in]     axis          Concatenation axis. Supported underlying concatenation axis are 0, 1, 2 and 3.
      */
@@ -80,7 +91,7 @@ public:
      *       @ref opencl::kernels::ClHeightConcatenateKernel and @ref opencl::kernels::ClDepthConcatenateKernel.
      *
      * @param[in]     compile_context The compile context to be used.
-     * @param[in,out] inputs_vector   The vectors containing all the tensors to concatenate. Data types supported: All
+     * @param[in,out] inputs_vector   The vectors containing all the tensors to concatenate. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
      * @param[out]    output          Output tensor. Data types supported: Same as @p input.
      * @param[in]     axis            Concatenation axis. Supported underlying concatenation axis are 0, 1, 2 and 3.
      */
@@ -91,7 +102,7 @@ public:
      * @note Preconditions can be found respectively at @ref opencl::kernels::ClWidthConcatenateKernel,
      *       @ref opencl::kernels::ClHeightConcatenateKernel and @ref opencl::kernels::ClDepthConcatenateKernel.
      *
-     * @param[in] inputs_vector The vectors containing all the tensors info to concatenate. Data types supported: All.
+     * @param[in] inputs_vector The vectors containing all the tensors info to concatenate. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
      * @param[in] output        Output tensor info. Data types supported: Same as @p input.
      * @param[in] axis          Concatenation axis. Supported underlying concatenation axis are 0, 1, 2 and 3.
      *
diff --git a/arm_compute/runtime/CL/functions/CLConvertFullyConnectedWeights.h b/arm_compute/runtime/CL/functions/CLConvertFullyConnectedWeights.h
index 8892dbad6c..6c7d9e52e8 100644
--- a/arm_compute/runtime/CL/functions/CLConvertFullyConnectedWeights.h
+++ b/arm_compute/runtime/CL/functions/CLConvertFullyConnectedWeights.h
@@ -55,6 +55,15 @@ public:
     CLConvertFullyConnectedWeights &operator=(CLConvertFullyConnectedWeights &&) = default;
     /** Initialize the function.
      *
+     * Valid data layouts:
+     * - NHWC
+     * - NCHW
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @param[in]  input                Source weights tensor to convert. Must be 2 dimensional. Data types supported: All.
      * @param[out] output               The converted weights tensor. Shape and Data Type: Same as @p input.
      * @param[in]  original_input_shape Shape of the original input tensor (the one entering fully connected layer).
diff --git a/arm_compute/runtime/CL/functions/CLCopy.h b/arm_compute/runtime/CL/functions/CLCopy.h
index 795a183e1f..4fc4183d3e 100644
--- a/arm_compute/runtime/CL/functions/CLCopy.h
+++ b/arm_compute/runtime/CL/functions/CLCopy.h
@@ -53,6 +53,14 @@ public:
     CLCopy &operator=(CLCopy &&);
     /** Initialise the function's source and destination.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @param[in]  input      Source tensor. Data types supported: All.
      * @param[out] output     Output tensor. Data types supported: Same as @p input.
      * @param[in]  dst_window (Optional) Window to be used in case only copying into part of a tensor. Default is nullptr.
diff --git a/arm_compute/runtime/CL/functions/CLDequantizationLayer.h b/arm_compute/runtime/CL/functions/CLDequantizationLayer.h
index 7ecf094df3..4a5c3a3203 100644
--- a/arm_compute/runtime/CL/functions/CLDequantizationLayer.h
+++ b/arm_compute/runtime/CL/functions/CLDequantizationLayer.h
@@ -54,6 +54,23 @@ public:
     CLDequantizationLayer &operator=(CLDequantizationLayer &&) = default;
     /** Set the input and output tensors.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src                |dst            |
+     * |:------------------|:--------------|
+     * |QASYMM8            |F16            |
+     * |QASYMM8            |F32            |
+     * |QASYMM8_SIGNED     |F16            |
+     * |QASYMM8_SIGNED     |F32            |
+     * |QSYMM8_PER_CHANNEL |F16            |
+     * |QSYMM8_PER_CHANNEL |F32            |
+     * |QSYMM8             |F16            |
+     * |QSYMM8             |F32            |
+     * |QSYMM16            |F16            |
+     * |QSYMM16            |F32            |
+     *
      * @param[in]  input  Source tensor with at least 3 dimensions. The dimensions over the third will be interpreted as batches.
      *                    Data types supported: QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL/QSYMM8/QSYMM16.
      * @param[out] output Destination tensor with the same dimensions of input. Data type supported: F16/F32.
diff --git a/arm_compute/runtime/CL/functions/CLDirectConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLDirectConvolutionLayer.h
index 6e9e2161b9..3fd0c63782 100644
--- a/arm_compute/runtime/CL/functions/CLDirectConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLDirectConvolutionLayer.h
@@ -55,6 +55,18 @@ public:
     CLDirectConvolutionLayer &operator=(CLDirectConvolutionLayer &&);
     /** Set the input and output tensors.
      *
+     * Valid data layouts:
+     * - NHWC
+     * - NCHW
+     *
+     * Valid data type configurations:
+     * |src0           |src1           |src2   |dst            |
+     * |:--------------|:--------------|:------|:--------------|
+     * |F16            |F16            |F16    |F16            |
+     * |F32            |F32            |F32    |F32            |
+     * |QASYMM8        |QASYMM8        |S32    |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |S32    |QASYMM8_SIGNED |
+     *
      * @param[in]  input     Source tensor. 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: QASYMM8_SIGNED/QASYMM8/F16/F32.
diff --git a/arm_compute/runtime/CL/functions/CLFFT1D.h b/arm_compute/runtime/CL/functions/CLFFT1D.h
index 731bad5c32..c7112dc737 100644
--- a/arm_compute/runtime/CL/functions/CLFFT1D.h
+++ b/arm_compute/runtime/CL/functions/CLFFT1D.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -61,6 +61,15 @@ public:
     ~CLFFT1D();
     /** Initialise the function's source, destinations and border mode.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src    |dst    |
+     * |:------|:------|
+     * |F32    |F32    |
+     * |F16    |F16    |
+     *
      * @param[in]  input  Source tensor. Data types supported: F16/F32.
      * @param[out] output Destination tensor. Data types and data layouts supported: Same as @p input.
      * @param[in]  config FFT related configuration
diff --git a/arm_compute/runtime/CL/functions/CLFFT2D.h b/arm_compute/runtime/CL/functions/CLFFT2D.h
index adc8e46cb2..3d20327bf1 100644
--- a/arm_compute/runtime/CL/functions/CLFFT2D.h
+++ b/arm_compute/runtime/CL/functions/CLFFT2D.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -58,6 +58,15 @@ public:
     ~CLFFT2D();
     /** Initialise the function's source, destinations and border mode.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src    |dst    |
+     * |:------|:------|
+     * |F32    |F32    |
+     * |F16    |F16    |
+     *
      * @param[in]  input  Source tensor. Data types supported: F16/F32.
      * @param[out] output Destination tensor. Data types and data layouts supported: Same as @p input.
      * @param[in]  config FFT related configuration
diff --git a/arm_compute/runtime/CL/functions/CLFFTConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLFFTConvolutionLayer.h
index 5085f5a66c..f873cb0b86 100644
--- a/arm_compute/runtime/CL/functions/CLFFTConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLFFTConvolutionLayer.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -71,6 +71,15 @@ public:
     CLFFTConvolutionLayer &operator=(CLFFTConvolutionLayer &&) = default;
     /** Set the input and output tensors.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src    |dst    |
+     * |:------|:------|
+     * |F32    |F32    |
+     * |F16    |F16    |
+     *
      * @note: This function only works with any square kernel size and unit strides for both NCHW and NHWC data layout
      *
      * @param[in]  input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
diff --git a/arm_compute/runtime/CL/functions/CLFill.h b/arm_compute/runtime/CL/functions/CLFill.h
index 9a27d158a6..a01e0c3188 100644
--- a/arm_compute/runtime/CL/functions/CLFill.h
+++ b/arm_compute/runtime/CL/functions/CLFill.h
@@ -52,6 +52,14 @@ public:
     CLFill &operator=(CLFill &&);
     /** Initialize the kernel's tensor and filling value
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @param[in,out] tensor         Input tensor to fill. Supported data types: All.
      * @param[in]     constant_value The value used to fill the planes of the tensor
      * @param[in]     window         Window to be used in case setting only part of a tensor. Default is nullptr.
diff --git a/arm_compute/runtime/CL/functions/CLFloor.h b/arm_compute/runtime/CL/functions/CLFloor.h
index 7c7607002d..87cd5b44c7 100644
--- a/arm_compute/runtime/CL/functions/CLFloor.h
+++ b/arm_compute/runtime/CL/functions/CLFloor.h
@@ -54,6 +54,15 @@ public:
     CLFloor &operator=(CLFloor &&);
     /** Set the source, destination of the kernel
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src    |dst    |
+     * |:------|:------|
+     * |F32    |F32    |
+     * |F16    |F16    |
+     *
      * @param[in]  input  Source tensor. Data type supported: F16/F32.
      * @param[out] output Destination tensor. Same as @p input
      */
diff --git a/arm_compute/runtime/CL/functions/CLPReluLayer.h b/arm_compute/runtime/CL/functions/CLPReluLayer.h
index 7b6667044e..b123d0e46e 100644
--- a/arm_compute/runtime/CL/functions/CLPReluLayer.h
+++ b/arm_compute/runtime/CL/functions/CLPReluLayer.h
@@ -53,6 +53,17 @@ public:
     CLPReluLayer &operator=(CLPReluLayer &&);
     /** Set the input and output tensor.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |QASYMM8        |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |
+     * |F16            |F16            |
+     * |F32            |F32            |
+     *
      * @note If the output tensor is a nullptr or is equal to the input, the activation function will be performed in-place
      *
      * @param[in]  input  Source tensor. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
diff --git a/arm_compute/runtime/CL/functions/CLPermute.h b/arm_compute/runtime/CL/functions/CLPermute.h
index e59cca2a67..8e15da2287 100644
--- a/arm_compute/runtime/CL/functions/CLPermute.h
+++ b/arm_compute/runtime/CL/functions/CLPermute.h
@@ -53,6 +53,15 @@ public:
     CLPermute &operator=(CLPermute &&) = default;
     /** Set the input and output tensors.
      *
+     * Valid data layouts:
+     * - NHWC
+     * - NCHW
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @note Arbitrary permutation vectors are supported with rank not greater than 4
      *
      * @param[in] input  The input tensor to permute. Data types supported: All.
diff --git a/arm_compute/runtime/CL/functions/CLPixelWiseMultiplication.h b/arm_compute/runtime/CL/functions/CLPixelWiseMultiplication.h
index 9f70b05a35..14422383ad 100644
--- a/arm_compute/runtime/CL/functions/CLPixelWiseMultiplication.h
+++ b/arm_compute/runtime/CL/functions/CLPixelWiseMultiplication.h
@@ -52,19 +52,23 @@ public:
     CLPixelWiseMultiplication &operator=(CLPixelWiseMultiplication &&);
     /** Initialise the kernel's inputs, output and convertion policy.
      *
-     * Valid configurations (Input1,Input2) -> Output :
+     * Valid data layouts:
+     * - All
      *
-     *   - (U8,U8)                         -> U8
-     *   - (U8,U8)                         -> S16
-     *   - (U8,S16)                        -> S16
-     *   - (S16,U8)                        -> S16
-     *   - (S16,S16)                       -> S16
-     *   - (F16,F16)                       -> F16
-     *   - (F32,F32)                       -> F32
-     *   - (QASYMM8,QASYMM8)               -> QASYMM8
-     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
-     *   - (QSYMM16,QSYMM16)               -> QSYMM16
-     *   - (QSYMM16,QSYMM16)               -> S32
+     * Valid data type configurations:
+     * |src0           |src1           |dst            |
+     * |:--------------|:--------------|:--------------|
+     * |QASYMM8        |QASYMM8        |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |QASYMM8_SIGNED |
+     * |QSYMM16        |QSYMM16        |QASYMM16       |
+     * |QSYMM16        |QSYMM16        |S32            |
+     * |U8             |U8             |U8             |
+     * |U8             |U8             |S16            |
+     * |U8             |S16            |S16            |
+     * |S16            |U8             |S16            |
+     * |S16            |S16            |S16            |
+     * |F16            |F16            |F16            |
+     * |F32            |S32            |F32            |
      *
      * @param[in, out] input1          An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
      *                                 The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
@@ -81,20 +85,6 @@ public:
                    ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
     /** Initialise the kernel's inputs, output and convertion policy.
      *
-     * Valid configurations (Input1,Input2) -> Output :
-     *
-     *   - (U8,U8)                         -> U8
-     *   - (U8,U8)                         -> S16
-     *   - (U8,S16)                        -> S16
-     *   - (S16,U8)                        -> S16
-     *   - (S16,S16)                       -> S16
-     *   - (F16,F16)                       -> F16
-     *   - (F32,F32)                       -> F32
-     *   - (QASYMM8,QASYMM8)               -> QASYMM8
-     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
-     *   - (QSYMM16,QSYMM16)               -> QSYMM16
-     *   - (QSYMM16,QSYMM16)               -> S32
-     *
      * @param[in]      compile_context The compile context to be used.
      * @param[in, out] input1          An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
      *                                 The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
@@ -111,21 +101,6 @@ public:
                    ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
     /** Static function to check if given info will lead to a valid configuration of @ref CLPixelWiseMultiplication
      *
-     * Valid configurations (Input1,Input2) -> Output :
-     *
-     *   - (U8,U8)                         -> U8
-     *   - (U8,U8)                         -> S16
-     *   - (U8,S16)                        -> S16
-     *   - (S16,U8)                        -> S16
-     *   - (S16,S16)                       -> S16
-     *   - (F16,F16)                       -> F16
-     *   - (F32,F32)                       -> F32
-     *   - (QASYMM8,QASYMM8)               -> QASYMM8
-     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
-     *   - (QSYMM16,QSYMM16)               -> QSYMM16
-     *   - (QSYMM16,QSYMM16)               -> S32
-     *
-     *
      * @param[in] input1          An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
      * @param[in] input2          An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
      * @param[in] output          The output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
diff --git a/arm_compute/runtime/CL/functions/CLPoolingLayer.h b/arm_compute/runtime/CL/functions/CLPoolingLayer.h
index ec1c4eb768..902feca234 100644
--- a/arm_compute/runtime/CL/functions/CLPoolingLayer.h
+++ b/arm_compute/runtime/CL/functions/CLPoolingLayer.h
@@ -54,6 +54,18 @@ public:
     CLPoolingLayer &operator=(CLPoolingLayer &&) = default;
     /** Set the input and output tensors.
      *
+     * Valid data layouts:
+     * - NHWC
+     * - NCHW
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |QASYMM8        |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |
+     * |F16            |F16            |
+     * |F32            |F32            |
+     *
      * @param[in,out] input     Source tensor. (Written to only when padding != 0) Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
      * @param[out]    output    Destination tensor. Data types supported: Same as @p input.
      * @param[in]     pool_info Contains pooling operation information described in @ref PoolingLayerInfo.
diff --git a/arm_compute/runtime/CL/functions/CLQuantizationLayer.h b/arm_compute/runtime/CL/functions/CLQuantizationLayer.h
index c5dad53513..6a44a226d4 100644
--- a/arm_compute/runtime/CL/functions/CLQuantizationLayer.h
+++ b/arm_compute/runtime/CL/functions/CLQuantizationLayer.h
@@ -59,6 +59,25 @@ public:
     CLQuantizationLayer &operator=(CLQuantizationLayer &&) = default;
     /** Set the input and output tensors.
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src                |dst            |
+     * |:------------------|:--------------|
+     * |QASYMM8            |QASYMM8        |
+     * |QASYMM8            |QASYMM8_SIGNED |
+     * |QASYMM8            |QASYMM16       |
+     * |QASYMM8_SIGNED     |QASYMM8        |
+     * |QASYMM8_SIGNED     |QASYMM8_SIGNED |
+     * |QASYMM8_SIGNED     |QASYMM16       |
+     * |F16                |QASYMM8        |
+     * |F16                |QASYMM8_SIGNED |
+     * |F16                |QASYMM16       |
+     * |F32                |QASYMM8        |
+     * |F32                |QASYMM8_SIGNED |
+     * |F32                |QASYMM16       |
+     *
      * @param[in]  input  Source tensor. The dimensions over the third will be interpreted as batches. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/32.
      * @param[out] output Destination tensor with the same dimensions of input. Data types supported: QASYMM8/QASYMM8_SIGNED/QASYMM16.
      *
diff --git a/arm_compute/runtime/CL/functions/CLReshapeLayer.h b/arm_compute/runtime/CL/functions/CLReshapeLayer.h
index 60ed81680e..7346b65e9b 100644
--- a/arm_compute/runtime/CL/functions/CLReshapeLayer.h
+++ b/arm_compute/runtime/CL/functions/CLReshapeLayer.h
@@ -52,6 +52,14 @@ public:
     CLReshapeLayer &operator=(CLReshapeLayer &&);
     /** Initialise the kernel's inputs and outputs
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @param[in]  input  First tensor input. Data type supported: All
      * @param[out] output Output tensor. Data type supported: Same as @p input
      */
diff --git a/arm_compute/runtime/CL/functions/CLScale.h b/arm_compute/runtime/CL/functions/CLScale.h
index 8a67f74bb6..ddb4a23531 100644
--- a/arm_compute/runtime/CL/functions/CLScale.h
+++ b/arm_compute/runtime/CL/functions/CLScale.h
@@ -55,6 +55,20 @@ public:
 
     /** Initialize the function's source, destination, interpolation type and border_mode.
      *
+     * Valid data layouts:
+     * - NHWC
+     * - NCHW
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |QASYMM8        |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |
+     * |F16            |F16            |
+     * |F32            |F32            |
+     * |U8             |U8             |
+     * |S16            |S16            |
+     *
      * @param[in,out] input  Source tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/F16/F32. (Written to only for @p border_mode != UNDEFINED)
      * @param[out]    output Destination tensor. Data types supported: Same as @p input
      *                       All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
diff --git a/arm_compute/runtime/CL/functions/CLSlice.h b/arm_compute/runtime/CL/functions/CLSlice.h
index f17e77236d..7a7689c528 100644
--- a/arm_compute/runtime/CL/functions/CLSlice.h
+++ b/arm_compute/runtime/CL/functions/CLSlice.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-2020 Arm Limited.
+ * Copyright (c) 2018-2021 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -91,6 +91,14 @@ public:
     CLSlice &operator=(CLSlice &&);
     /** Configure kernel
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @note Supported tensor rank: up to 4
      * @note Start indices must be non-negative. 0 <= starts[i]
      * @note End coordinates can be negative, which represents the number of elements before the end of that dimension.
diff --git a/arm_compute/runtime/CL/functions/CLStridedSlice.h b/arm_compute/runtime/CL/functions/CLStridedSlice.h
index fdbef81f7d..6fab0c0186 100644
--- a/arm_compute/runtime/CL/functions/CLStridedSlice.h
+++ b/arm_compute/runtime/CL/functions/CLStridedSlice.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-2020 Arm Limited.
+ * Copyright (c) 2018-2021 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -54,6 +54,14 @@ public:
     CLStridedSlice &operator=(CLStridedSlice &&);
     /** Configure kernel
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @note Supported tensor rank: up to 4
      *
      * @param[in]  input            Source tensor. Data type supported: All.
diff --git a/arm_compute/runtime/CL/functions/CLTranspose.h b/arm_compute/runtime/CL/functions/CLTranspose.h
index 43cebeba90..a866aeabaa 100644
--- a/arm_compute/runtime/CL/functions/CLTranspose.h
+++ b/arm_compute/runtime/CL/functions/CLTranspose.h
@@ -53,6 +53,14 @@ public:
     CLTranspose &operator=(CLTranspose &&) = default;
     /** Initialise the kernel's inputs and output
      *
+     * Valid data layouts:
+     * - All
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |All            |All            |
+     *
      * @param[in]  input  Input tensor. Data types supported: All.
      * @param[out] output Output tensor. Data type supported: Same as @p input
      */