COMPMID-661: Add QASYMM8 support (and basic tests) to CLDepthwiseConvolution3x3 kernel (#28)

Change-Id: I51bebe74e3814c1245812ad575fe7854d460674f
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/109864
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: BSG Visual Compute Jenkins server to access repositories on http://mpd-gerrit.cambridge.arm.com <bsgcomp@arm.com>
diff --git a/arm_compute/runtime/CL/functions/CLDepthwiseConvolution.h b/arm_compute/runtime/CL/functions/CLDepthwiseConvolution.h
index 7c35c2a..40eb852 100644
--- a/arm_compute/runtime/CL/functions/CLDepthwiseConvolution.h
+++ b/arm_compute/runtime/CL/functions/CLDepthwiseConvolution.h
@@ -51,7 +51,7 @@
     CLDepthwiseConvolution3x3();
     /** Initialize the function's source, destination, conv and border_size.
      *
-     * @param[in, out] input     Source tensor. Data type supported: F32. (Written to only for border filling).
+     * @param[in, out] input     Source tensor. Data type supported: QASYMM8/F32. (Written to only for border filling).
      * @param[in]      weights   Weights tensor. A 3D tensor with shape [3, 3, IFM]. Data type supported: Same as @p input.
      * @param[in]      biases    (Optional) Biases tensor. A 1D tensor with shape [IFM]. Must be nullptr if not needed.
      *                           Data type supported: Same as @p input.