Update list of supported operators in documentation

Resolves: COMPMID-6633

Change-Id: I1e78df468876ec3569fa46597734e7de328b06f4
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10663
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLNormalizePlanarYUVLayer.h b/arm_compute/runtime/CL/functions/CLNormalizePlanarYUVLayer.h
index 3473af1..cdccc16 100644
--- a/arm_compute/runtime/CL/functions/CLNormalizePlanarYUVLayer.h
+++ b/arm_compute/runtime/CL/functions/CLNormalizePlanarYUVLayer.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-2020 Arm Limited.
+ * Copyright (c) 2018-2020, 2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_CLNORMALIZEPLANARYUVLAYER_H
-#define ARM_COMPUTE_CLNORMALIZEPLANARYUVLAYER_H
+#ifndef ACL_ARM_COMPUTE_RUNTIME_CL_FUNCTIONS_CLNORMALIZEPLANARYUVLAYER_H
+#define ACL_ARM_COMPUTE_RUNTIME_CL_FUNCTIONS_CLNORMALIZEPLANARYUVLAYER_H
 
 #include "arm_compute/core/Types.h"
 #include "arm_compute/runtime/CL/ICLSimpleFunction.h"
@@ -44,6 +44,18 @@
 public:
     /** Set the input and output tensors.
      *
+     * Valid data layouts:
+     * - NHWC
+     * - NCHW
+     *
+     * Valid data type configurations:
+     * |src            |dst            |
+     * |:--------------|:--------------|
+     * |F32            |F32            |
+     * |F16            |F16            |
+     * |QASYMM8        |QASYMM8        |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED |
+     *
      * @param[in]  input  Source tensor. 3 lower dimensions represent a single input with dimensions [width, height, channels].
      *                    Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.
      * @param[out] output Destinationfeature tensor. Data type supported: same as @p input
@@ -82,4 +94,4 @@
     validate(const ITensorInfo *input, const ITensorInfo *output, const ITensorInfo *mean, const ITensorInfo *std);
 };
 } // namespace arm_compute
-#endif /* ARM_COMPUTE_CLNORMALIZEPLANARYUVLAYER_H */
+#endif // ACL_ARM_COMPUTE_RUNTIME_CL_FUNCTIONS_CLNORMALIZEPLANARYUVLAYER_H
diff --git a/arm_compute/runtime/OperatorList.h b/arm_compute/runtime/OperatorList.h
index 92b5079..8bcdf5d 100644
--- a/arm_compute/runtime/OperatorList.h
+++ b/arm_compute/runtime/OperatorList.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021-2022 Arm Limited.
+ * Copyright (c) 2021-2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_OPERATOR_LIST_H
-#define ARM_COMPUTE_OPERATOR_LIST_H
+#ifndef ACL_ARM_COMPUTE_RUNTIME_OPERATORLIST_H
+#define ACL_ARM_COMPUTE_RUNTIME_OPERATORLIST_H
 
 /** ActivationLayer
  *
@@ -40,6 +40,16 @@
  *
  */
 
+/** AddMulAdd
+ *
+ * Description:
+ * Performs a fused Add + Mul + Add [+ Relu-based-Activation] operation.
+ *
+ * Equivalent Android NNAPI Op:
+ * n/a
+ *
+ */
+
 /** ArgMinMaxLayer
  *
  * Description:
@@ -647,6 +657,16 @@
  *
  */
 
+/** MatMul
+ *
+ * Description:
+ * Computes a matrix multiplication in batches.
+ *
+ * Equivalent Android NNAPI Op:
+ * ANEURALNETWORKS_BATCH_MATMUL
+ *
+ */
+
 /** MaxUnpoolingLayer
  *
  * Description:
@@ -677,6 +697,16 @@
  *
  */
 
+/** NormalizePlanarYUVLayer
+ *
+ * Description:
+ * Function to compute normalization planar YUV layer.
+ *
+ * Equivalent Android NNAPI Op:
+ * n/a
+ *
+ */
+
 /** PadLayer
  *
  * Description:
@@ -814,6 +844,16 @@
  *
  */
 
+/** ReorderLayer
+ *
+ * Description:
+ * Reorders a tensor to a different weights format.
+ *
+ * Equivalent Android NNAPI Op:
+ * n/a
+ *
+ */
+
 /** ReorgLayer
  *
  * Description:
@@ -1009,4 +1049,4 @@
  *
  */
 
-#endif /* ARM_COMPUTE_OPERATOR_LIST_H */
\ No newline at end of file
+#endif // ACL_ARM_COMPUTE_RUNTIME_OPERATORLIST_H
diff --git a/docs/user_guide/operator_list.dox b/docs/user_guide/operator_list.dox
index 0c74214..25c856d 100644
--- a/docs/user_guide/operator_list.dox
+++ b/docs/user_guide/operator_list.dox
@@ -109,6 +109,26 @@
     <tr><td>F32<td>F32
     </table>
 <tr>
+  <td rowspan="1">AddMulAdd
+  <td rowspan="1" style="width:200px;"> Performs a fused Add + Mul + Add [+ Relu-based-Activation] operation.
+  <td rowspan="1">
+      <ul>
+       <li>n/a
+      </ul>
+  <td>NEAddMulAdd
+  <td>
+      <ul>
+       <li>Any
+      </ul>
+  <td>
+    <table>
+    <tr><th>input1<th>input2<th>bn_mul<th>bn_add<th>add_output<th>final_output
+    <tr><td>QASYMM8<td>QASYMM8<td>QASYMM8<td>QASYMM8<td>QASYMM8<td>QASYMM8
+    <tr><td>QASYMM8_SIGNED<td>QASYMM8_SIGNED<td>QASYMM8_SIGNED<td>QASYMM8_SIGNED<td>QASYMM8_SIGNED<td>QASYMM8_SIGNED
+    <tr><td>F16<td>F16<td>F16<td>F16<td>F16<td>F16
+    <tr><td>F32<td>F32<td>F32<td>F32<td>F32<td>F32
+    </table>
+<tr>
   <td rowspan="2">ArgMinMaxLayer
   <td rowspan="2" style="width:200px;"> Function to calculate the index of the minimum or maximum values in a tensor based on an axis.
   <td rowspan="2">
@@ -2055,6 +2075,40 @@
     <tr><td>QASYMM8<td>S32<td>QSYMM16<td>QASYMM8<td>QSYMM16<td>QASYMM8
     </table>
 <tr>
+  <td rowspan="2">MatMul
+  <td rowspan="2" style="width:200px;"> Computes a matrix multiplication in batches.
+  <td rowspan="2">
+      <ul>
+       <li>ANEURALNETWORKS_BATCH_MATMUL
+      </ul>
+  <td>NEMatMul
+  <td>
+      <ul>
+       <li>Any
+      </ul>
+  <td>
+    <table>
+    <tr><th>lhs<th>rhs<th>dst
+    <tr><td>F32<td>F32<td>F32
+    <tr><td>F16<td>F16<td>F16
+    <tr><td>QASYMM8_SIGNED<td>QASYMM8_SIGNED<td>QASYMM8_SIGNED
+    <tr><td>QASYMM8<td>QASYMM8<td>QASYMM8
+    </table>
+<tr>
+  <td>CLMatMul
+  <td>
+      <ul>
+       <li>All
+      </ul>
+  <td>
+    <table>
+    <tr><th>lhs<th>rhs<th>dst
+    <tr><td>F32<td>F32<td>F32
+    <tr><td>F16<td>F16<td>F16
+    <tr><td>QASYMM8_SIGNED<td>QASYMM8_SIGNED<td>QASYMM8_SIGNED
+    <tr><td>QASYMM8<td>QASYMM8<td>QASYMM8
+    </table>
+<tr>
   <td rowspan="2">MaxUnpoolingLayer
   <td rowspan="2" style="width:200px;"> Function to perform MaxUnpooling.
   <td rowspan="2">
@@ -2155,6 +2209,27 @@
     <tr><td>F16<td>F16
     </table>
 <tr>
+  <td rowspan="1">NormalizePlanarYUVLayer
+  <td rowspan="1" style="width:200px;"> Function to compute normalization planar YUV layer.
+  <td rowspan="1">
+      <ul>
+       <li>n/a
+      </ul>
+  <td>CLNormalizePlanarYUVLayer
+  <td>
+      <ul>
+       <li>NHWC
+       <li>NCHW
+      </ul>
+  <td>
+    <table>
+    <tr><th>src<th>dst
+    <tr><td>F32<td>F32
+    <tr><td>F16<td>F16
+    <tr><td>QASYMM8<td>QASYMM8
+    <tr><td>QASYMM8_SIGNED<td>QASYMM8_SIGNED
+    </table>
+<tr>
   <td rowspan="2">PadLayer
   <td rowspan="2" style="width:200px;"> Function to pad a tensor.
   <td rowspan="2">
@@ -2582,6 +2657,23 @@
     <tr><td>S32<td>S32
     </table>
 <tr>
+  <td rowspan="1">ReorderLayer
+  <td rowspan="1" style="width:200px;"> Reorders a tensor to a different weights format.
+  <td rowspan="1">
+      <ul>
+       <li>n/a
+      </ul>
+  <td>NEReorderLayer
+  <td>
+      <ul>
+       <li>NCHW
+      </ul>
+  <td>
+    <table>
+    <tr><th>src<th>dst
+    <tr><td>F32<td>F32
+    </table>
+<tr>
   <td rowspan="2">ReorgLayer
   <td rowspan="2" style="width:200px;"> Performs a reorganization layer of input tensor to the output tensor.
   <td rowspan="2">