COMPMID-3280: Make all ML primitives for CL use the new interface - Part1 - Fix2

- const fix in the CLKernels part 2

Change-Id: Ia12845e291b4137cbaf76eb8438e381c4fd0368a
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3071
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLPoolingLayerKernel.h b/arm_compute/core/CL/kernels/CLPoolingLayerKernel.h
index 4ab6955..3957504 100644
--- a/arm_compute/core/CL/kernels/CLPoolingLayerKernel.h
+++ b/arm_compute/core/CL/kernels/CLPoolingLayerKernel.h
@@ -67,7 +67,7 @@
      * @param[in]  pool_info       Contains pooling operation information described in @ref PoolingLayerInfo.
      * @param[out] indices         (optional) The indices of the maximal values. Data type supported: U32.
      */
-    void configure(CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output, const PoolingLayerInfo &pool_info, ICLTensor *indices = nullptr);
+    void configure(const CLCompileContext &compile_context, const ICLTensor *input, ICLTensor *output, const PoolingLayerInfo &pool_info, ICLTensor *indices = nullptr);
     /** Static function to check if given info will lead to a valid configuration of @ref CLPoolingLayerKernel
      *
      * @param[in] input     Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32.