COMPMID-3637: Move utility headers from arm_compute to src

Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: If9d6fa8c900b68c4b6fd373f2fc1f9abb83ea917
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4145
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

152 files changed, 1172 insertions, 398 deletions

diff --git a/src/core/CL/CLValidate.h b/src/core/CL/CLValidate.h
new file mode 100644
index 0000000000..cbbdf2d9d2
--- /dev/null
+++ b/src/core/CL/CLValidate.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (c) 2018-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CL_VALIDATE_H
+#define ARM_COMPUTE_CL_VALIDATE_H
+
+#include "arm_compute/core/Validate.h"
+
+namespace arm_compute
+{
+#define ARM_COMPUTE_ERROR_ON_F16_UNSUPPORTED(tensor) \
+    ARM_COMPUTE_ERROR_THROW_ON(::arm_compute::error_on_unsupported_fp16(__func__, __FILE__, __LINE__, tensor, CLKernelLibrary::get().fp16_supported()))
+
+#define ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED(tensor) \
+    ARM_COMPUTE_RETURN_ON_ERROR(::arm_compute::error_on_unsupported_fp16(__func__, __FILE__, __LINE__, tensor, CLKernelLibrary::get().fp16_supported()))
+
+/** Return an error if int64_base_atomics extension is not supported by the device.
+ *
+ * @param[in] function Function in which the error occurred.
+ * @param[in] file     Name of the file where the error occurred.
+ * @param[in] line     Line on which the error occurred.
+ *
+ * @return Status
+ */
+inline arm_compute::Status error_on_unsupported_int64_base_atomics(const char *function, const char *file, const int line)
+{
+    if(!CLKernelLibrary::get().int64_base_atomics_supported())
+    {
+        return ARM_COMPUTE_CREATE_ERROR_LOC(arm_compute::ErrorCode::UNSUPPORTED_EXTENSION_USE, function, file, line, "Atomic functions are not supported");
+    }
+    return arm_compute::Status{};
+}
+
+#define ARM_COMPUTE_ERROR_ON_INT64_BASE_ATOMICS_UNSUPPORTED() \
+    ARM_COMPUTE_ERROR_THROW_ON(::arm_compute::error_on_unsupported_int64_base_atomics(__func__, __FILE__, __LINE__));
+
+#define ARM_COMPUTE_RETURN_ERROR_ON_INT64_BASE_ATOMICS_UNSUPPORTED() \
+    ARM_COMPUTE_RETURN_ON_ERROR(::arm_compute::error_on_unsupported_int64_base_atomics(__func__, __FILE__, __LINE__));
+
+} // namespace arm_compute
+#endif /* ARM_COMPUTE_CL_VALIDATE_H */
diff --git a/src/core/CL/ICLGEMMKernelConfiguration.h b/src/core/CL/ICLGEMMKernelConfiguration.h
new file mode 100644
index 0000000000..ac0e7ab7ff
--- /dev/null
+++ b/src/core/CL/ICLGEMMKernelConfiguration.h
@@ -0,0 +1,68 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_ICLGEMMKERNELCONFIGURATION_H
+#define ARM_COMPUTE_ICLGEMMKERNELCONFIGURATION_H
+
+#include "arm_compute/core/GPUTarget.h"
+#include "arm_compute/core/Types.h"
+
+namespace arm_compute
+{
+/** Basic interface for the GEMM kernel configuration */
+class ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] arch GPU target
+     */
+    ICLGEMMKernelConfiguration(GPUTarget arch)
+        : _target(arch)
+    {
+    }
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    ICLGEMMKernelConfiguration(const ICLGEMMKernelConfiguration &) = delete;
+    /** Prevent instances of this class from being copied (As this class contains pointers) */
+    ICLGEMMKernelConfiguration &operator=(const ICLGEMMKernelConfiguration &) = delete;
+    /** Default Move Constructor. */
+    ICLGEMMKernelConfiguration(ICLGEMMKernelConfiguration &&) = default;
+    /** Default move assignment operator */
+    ICLGEMMKernelConfiguration &operator=(ICLGEMMKernelConfiguration &&) = default;
+    /** Virtual destructor */
+    virtual ~ICLGEMMKernelConfiguration() = default;
+    /** Given M, N, K and B, this method returns the @ref GEMMLHSMatrixInfo and @ref GEMMRHSMatrixInfo to be used
+     *
+     * @param[in] m         Number of rows LHS matrix
+     * @param[in] n         Number of columns RHS matrix
+     * @param[in] k         Number of columns LHS matrix or number of rows RHS matrix
+     * @param[in] b         Batch size
+     * @param[in] data_type Data type
+     */
+    virtual std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) = 0;
+
+protected:
+    GPUTarget _target;
+};
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_ICLGEMMKERNELCONFIGURATION_H */
diff --git a/src/core/CL/ICLKernel.cpp b/src/core/CL/ICLKernel.cpp
index be633746a2..f91510b4a7 100644
--- a/src/core/CL/ICLKernel.cpp
+++ b/src/core/CL/ICLKernel.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2019 Arm Limited.
+ * Copyright (c) 2016-2020 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -23,14 +23,9 @@
  */
 #include "arm_compute/core/CL/ICLKernel.h"
 
-#include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/Utils.h"
 
 #include <cstddef>
 
diff --git a/src/core/CL/ICLSimple2DKernel.cpp b/src/core/CL/ICLSimple2DKernel.cpp
index ce95495fff..dfef5822b2 100644
--- a/src/core/CL/ICLSimple2DKernel.cpp
+++ b/src/core/CL/ICLSimple2DKernel.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2018 Arm Limited.
+ * Copyright (c) 2017-2020 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -23,10 +23,7 @@
  */
 #include "arm_compute/core/CL/ICLSimple2DKernel.h"
 
-#include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 using namespace arm_compute;
 
diff --git a/src/core/CL/ICLSimpleKernel.cpp b/src/core/CL/ICLSimpleKernel.cpp
index d2f09a3478..90b5be8069 100644
--- a/src/core/CL/ICLSimpleKernel.cpp
+++ b/src/core/CL/ICLSimpleKernel.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2018 Arm Limited.
+ * Copyright (c) 2016-2020 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -27,6 +27,7 @@
 #include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 using namespace arm_compute;
 
diff --git a/src/core/CL/gemm/CLGEMMHelpers.cpp b/src/core/CL/gemm/CLGEMMHelpers.cpp
index 0a4a4adc31..877bf1e047 100644
--- a/src/core/CL/gemm/CLGEMMHelpers.cpp
+++ b/src/core/CL/gemm/CLGEMMHelpers.cpp
@@ -21,7 +21,7 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
diff --git a/src/core/CL/gemm/CLGEMMHelpers.h b/src/core/CL/gemm/CLGEMMHelpers.h
new file mode 100644
index 0000000000..013c068cf7
--- /dev/null
+++ b/src/core/CL/gemm/CLGEMMHelpers.h
@@ -0,0 +1,73 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMHELPERS_H
+#define ARM_COMPUTE_CLGEMMHELPERS_H
+
+#include "arm_compute/core/TensorInfo.h"
+#include "arm_compute/core/Types.h"
+
+namespace arm_compute
+{
+class ITensorInfo;
+struct GEMMRHSMatrixInfo;
+
+namespace cl_gemm
+{
+/** Configure @ref GEMMLHSMatrixInfo and @ref GEMMRHSMatrixInfo
+ *
+ * @param[in] m                  Number of rows (M) in the LHS matrix not reshaped
+ * @param[in] n                  Number of columns (N) in the RHS matrix not reshaped
+ * @param[in] m0                 Number of rows processed by each thread/work-item
+ * @param[in] n0                 Number of columns processed by each thread/work-item
+ * @param[in] k0                 Number of inner accumulation performed by each thread/work-item
+ * @param[in] v0                 Number of vertical blocks of size (m0xk0) stored on the same output row
+ * @param[in] h0                 Number of horizontal blocks of size (k0xn0) stored on the same output row
+ * @param[in] lhs_interleave     True if the v0 (m0xk0) blocks have to be interleaved in the output row
+ * @param[in] rhs_interleave     True if the h0 (k0xn0) blocks have to be interleaved in the output row
+ * @param[in] lhs_transpose      True if the (m0xk0) block has to be transposed before been stored
+ * @param[in] rhs_transpose      True if the (k0xn0) block has to be transposed before been stored
+ * @param[in] export_to_cl_image (Optional) True if the RHS reshaped matrix has to be exported to cl_image
+ *
+ * @return @ref GEMMLHSMatrixInfo and @ref GEMMRHSMatrixInfo
+ */
+std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_lhs_rhs_info(unsigned int m, unsigned int n, unsigned int m0, unsigned int n0, unsigned int k0, unsigned int v0, unsigned int h0,
+                                                                       bool lhs_interleave, bool rhs_interleave, bool lhs_transpose, bool rhs_transpose, bool export_to_cl_image = false);
+
+/** Update padding required to export the OpenCL buffer to OpenCL image2d
+ *
+ * @param[in,out] tensor ITensorInfo of the tensor required to be exported to OpenCL image2d
+ */
+void update_padding_for_cl_image(ITensorInfo *tensor);
+
+/** Utility function to validate the image2d OpenCL object support on the RHS reshaped matrix
+ *
+ * @param[in] tensor_reshaped_info TensorInfo for the RHS reshaped matrix
+ * @param[in] rhs_info             @ref GEMMRHSMatrixInfo
+ *
+ * @return Status reporting if we can use the image2d OpenCL object on the RHS reshaped matrix
+ */
+Status validate_image2d_support_on_rhs(const ITensorInfo &tensor_reshaped_info, const GEMMRHSMatrixInfo &rhs_info);
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMHELPERS_H */
diff --git a/src/core/CL/gemm/native/CLGEMMNativeKernelConfiguration.h b/src/core/CL/gemm/native/CLGEMMNativeKernelConfiguration.h
new file mode 100644
index 0000000000..aecf5a8aa8
--- /dev/null
+++ b/src/core/CL/gemm/native/CLGEMMNativeKernelConfiguration.h
@@ -0,0 +1,65 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATION_H
+#define ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATION_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+#include "src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.h"
+#include "src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.h"
+#include "src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.h"
+
+#include "support/MemorySupport.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** CLGEMMNative factory class */
+class CLGEMMNativeKernelConfigurationFactory final
+{
+public:
+    /** Static method to construct CLGEMMNative kernel object accordingly with the GPU target
+     *
+     * @param[in] gpu GPU target
+     *
+     * @return CLGEMMNative kernel configuration class
+     */
+    static std::unique_ptr<ICLGEMMKernelConfiguration> create(GPUTarget gpu)
+    {
+        switch(get_arch_from_target(gpu))
+        {
+            case GPUTarget::MIDGARD:
+                return support::cpp14::make_unique<CLGEMMNativeKernelConfigurationMidgard>(gpu);
+            case GPUTarget::BIFROST:
+                return support::cpp14::make_unique<CLGEMMNativeKernelConfigurationBifrost>(gpu);
+            case GPUTarget::VALHALL:
+                return support::cpp14::make_unique<CLGEMMNativeKernelConfigurationValhall>(gpu);
+            default:
+                ARM_COMPUTE_ERROR("Not supported GPU target");
+        }
+    }
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATION_H */
diff --git a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.cpp b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.cpp
index 51b7fc7190..4cc3d6ae74 100644
--- a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.cpp
+++ b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.cpp
@@ -21,12 +21,12 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.h"
+#include "src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
 #include "arm_compute/core/GPUTarget.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include <map>
 #include <utility>
diff --git a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.h b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.h
new file mode 100644
index 0000000000..1e7432c89a
--- /dev/null
+++ b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationBifrost.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONBIFROST_H
+#define ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONBIFROST_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** Bifrost based OpenCL GEMMNative configuration */
+class CLGEMMNativeKernelConfigurationBifrost final : public ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] gpu GPU target
+     */
+    CLGEMMNativeKernelConfigurationBifrost(GPUTarget gpu);
+
+    // Inherited overridden method
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) override;
+
+private:
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G71_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G71_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_default_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_default_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONBIFROST_H */
diff --git a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.cpp b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.cpp
index 3e7c17664a..fd699a08f7 100644
--- a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.cpp
+++ b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.cpp
@@ -21,12 +21,12 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.h"
+#include "src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
 #include "arm_compute/core/GPUTarget.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include <map>
 #include <utility>
diff --git a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.h b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.h
new file mode 100644
index 0000000000..2f6671706e
--- /dev/null
+++ b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationMidgard.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright (c) 2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONMIDGARD_H
+#define ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONMIDGARD_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** Midgard based OpenCL GEMMNative configuration */
+class CLGEMMNativeKernelConfigurationMidgard final : public ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] gpu GPU target
+     */
+    CLGEMMNativeKernelConfigurationMidgard(GPUTarget gpu);
+
+    // Inherited overridden method
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) override;
+
+private:
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> default_q8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONMIDGARD_H */
diff --git a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.cpp b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.cpp
index efc82fb78c..2c82340eef 100644
--- a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.cpp
+++ b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.cpp
@@ -21,12 +21,12 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.h"
+#include "src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
 #include "arm_compute/core/GPUTarget.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include <map>
 #include <utility>
diff --git a/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.h b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.h
new file mode 100644
index 0000000000..fb51b02edf
--- /dev/null
+++ b/src/core/CL/gemm/native/CLGEMMNativeKernelConfigurationValhall.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONVALHALL_H
+#define ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONVALHALL_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** Valhall based OpenCL GEMMNative configuration */
+class CLGEMMNativeKernelConfigurationValhall final : public ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] gpu GPU target
+     */
+    CLGEMMNativeKernelConfigurationValhall(GPUTarget gpu);
+
+    // Inherited overridden method
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) override;
+
+private:
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMNATIVEKERNELCONFIGURATIONVALHALL_H */
diff --git a/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfiguration.h b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfiguration.h
new file mode 100644
index 0000000000..21ccf2d647
--- /dev/null
+++ b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfiguration.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATION_H
+#define ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATION_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+#include "src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h"
+#include "src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.h"
+
+#include "support/MemorySupport.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** CLGEMMReshaped factory class */
+class CLGEMMReshapedKernelConfigurationFactory final
+{
+public:
+    /** Static method to call the CLGEMMReshaped kernel configuration class accordingly with the GPU target
+     *
+     * @param[in] gpu GPU target
+     *
+     * @return CLGEMMReshaped kernel configuration class
+     */
+    static std::unique_ptr<ICLGEMMKernelConfiguration> create(GPUTarget gpu)
+    {
+        switch(get_arch_from_target(gpu))
+        {
+            case GPUTarget::MIDGARD:
+            case GPUTarget::BIFROST:
+                return support::cpp14::make_unique<CLGEMMReshapedKernelConfigurationBifrost>(gpu);
+            case GPUTarget::VALHALL:
+                return support::cpp14::make_unique<CLGEMMReshapedKernelConfigurationValhall>(gpu);
+            default:
+                ARM_COMPUTE_ERROR("Not supported GPU target");
+        }
+    }
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATION_H */
diff --git a/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.cpp b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.cpp
index b5fc074fb4..00c284facc 100644
--- a/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.cpp
+++ b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.cpp
@@ -21,15 +21,15 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h"
+#include "src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
 #include "arm_compute/core/GPUTarget.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/TensorShape.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include <map>
 #include <utility>
@@ -216,17 +216,17 @@ std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> CLGEMMReshapedKernelConfiguratio
         {
             if(workload <= 790.39f)
             {
-                return configure_lhs_rhs_info(m,n,2,4,4,2,2,false,false,true,false,false);
+                return configure_lhs_rhs_info(m, n, 2, 4, 4, 2, 2, false, false, true, false, false);
             }
             else
             {
                 if(workload <= 982.39f)
                 {
-                    return configure_lhs_rhs_info(m,n,4,2,4,4,4,false,false,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 2, 4, 4, 4, false, false, true, false, false);
                 }
                 else
                 {
-                    return configure_lhs_rhs_info(m,n,2,4,4,2,1,false,true,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 2, 4, 4, 2, 1, false, true, true, false, false);
                 }
             }
         }
@@ -236,16 +236,16 @@ std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> CLGEMMReshapedKernelConfiguratio
             {
                 if(r_mn <= 0.11f)
                 {
-                    return configure_lhs_rhs_info(m,n,2,4,4,2,2,false,false,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 2, 4, 4, 2, 2, false, false, true, false, false);
                 }
                 else
                 {
-                    return configure_lhs_rhs_info(m,n,4,4,4,4,4,false,true,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 4, 4, 4, 4, false, true, true, false, false);
                 }
             }
             else
             {
-                return configure_lhs_rhs_info(m,n,2,4,4,2,2,false,false,true,false,false);
+                return configure_lhs_rhs_info(m, n, 2, 4, 4, 2, 2, false, false, true, false, false);
             }
         }
     }
@@ -257,22 +257,22 @@ std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> CLGEMMReshapedKernelConfiguratio
             {
                 if(m <= 64.5)
                 {
-                    return configure_lhs_rhs_info(m,n,4,4,4,2,4,true,false,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 4, 4, 2, 4, true, false, true, false, false);
                 }
                 else
                 {
-                    return configure_lhs_rhs_info(m,n,4,4,4,2,2,false,true,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 4, 4, 2, 2, false, true, true, false, false);
                 }
             }
             else
             {
                 if(r_mn <= 1.09f)
                 {
-                    return configure_lhs_rhs_info(m,n,4,4,4,4,4,false,true,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 4, 4, 4, 4, false, true, true, false, false);
                 }
                 else
                 {
-                    return configure_lhs_rhs_info(m,n,4,4,4,2,2,true,true,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 4, 4, 2, 2, true, true, true, false, false);
                 }
             }
         }
@@ -280,17 +280,17 @@ std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> CLGEMMReshapedKernelConfiguratio
         {
             if(m <= 43)
             {
-                return configure_lhs_rhs_info(m,n,4,4,4,2,4,true,false,true,false,false);
+                return configure_lhs_rhs_info(m, n, 4, 4, 4, 2, 4, true, false, true, false, false);
             }
             else
             {
                 if(workload <= 26364.79f)
                 {
-                    return configure_lhs_rhs_info(m,n,4,4,4,2,2,false,true,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 4, 4, 2, 2, false, true, true, false, false);
                 }
                 else
                 {
-                    return configure_lhs_rhs_info(m,n,4,4,4,4,4,false,true,true,false,false);
+                    return configure_lhs_rhs_info(m, n, 4, 4, 4, 4, 4, false, true, true, false, false);
                 }
             }
         }
diff --git a/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h
new file mode 100644
index 0000000000..e3b62ced6a
--- /dev/null
+++ b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationBifrost.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATIONBIFROST_H
+#define ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATIONBIFROST_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** Bifrost based OpenCL GEMMReshaped configuration */
+class CLGEMMReshapedKernelConfigurationBifrost final : public ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] gpu GPU target
+     */
+    CLGEMMReshapedKernelConfigurationBifrost(GPUTarget gpu);
+
+    // Inherited overridden method
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) override;
+
+private:
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATIONBIFROST_H */
diff --git a/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.cpp b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.cpp
index 0c09f5084a..519e903a5a 100644
--- a/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.cpp
+++ b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.cpp
@@ -21,12 +21,12 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.h"
+#include "src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
 #include "arm_compute/core/GPUTarget.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include <map>
 #include <utility>
diff --git a/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.h b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.h
new file mode 100644
index 0000000000..5f7e701e0e
--- /dev/null
+++ b/src/core/CL/gemm/reshaped/CLGEMMReshapedKernelConfigurationValhall.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATIONVALHALL_H
+#define ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATIONVALHALL_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** Valhall based OpenCL GEMMReshaped configuration */
+class CLGEMMReshapedKernelConfigurationValhall final : public ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] gpu GPU target
+     */
+    CLGEMMReshapedKernelConfigurationValhall(GPUTarget gpu);
+
+    // Inherited overridden method
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) override;
+
+private:
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMRESHAPEDKERNELCONFIGURATIONVALHALL_H */
diff --git a/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfiguration.h b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfiguration.h
new file mode 100644
index 0000000000..4efe28ce69
--- /dev/null
+++ b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfiguration.h
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATION_H
+#define ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATION_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+#include "src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.h"
+#include "src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.h"
+
+#include "support/MemorySupport.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** CLGEMMReshapedOnlyRHS factory class */
+class CLGEMMReshapedOnlyRHSKernelConfigurationFactory final
+{
+public:
+    /** Static method to call the CLGEMMReshapedOnlyRHS kernel configuration class accordingly with the GPU target
+     *
+     * @param[in] gpu GPU target
+     *
+     * @return CLGEMMReshapedOnlyRHS kernel configuration class
+     */
+    static std::unique_ptr<ICLGEMMKernelConfiguration> create(GPUTarget gpu)
+    {
+        switch(get_arch_from_target(gpu))
+        {
+            case GPUTarget::MIDGARD:
+            case GPUTarget::BIFROST:
+                return support::cpp14::make_unique<CLGEMMReshapedOnlyRHSKernelConfigurationBifrost>(gpu);
+            case GPUTarget::VALHALL:
+                return support::cpp14::make_unique<CLGEMMReshapedOnlyRHSKernelConfigurationValhall>(gpu);
+            default:
+                ARM_COMPUTE_ERROR("Not supported GPU target");
+        }
+    }
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATION_H */
diff --git a/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.cpp b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.cpp
index 16eabf069c..0a0fc5d152 100644
--- a/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.cpp
+++ b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.cpp
@@ -21,15 +21,15 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.h"
+#include "src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
 #include "arm_compute/core/GPUTarget.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/TensorShape.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include <map>
 #include <utility>
@@ -122,13 +122,13 @@ std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> CLGEMMReshapedOnlyRHSKernelConfi
 
     if(m == 1)
     {
-        if ( n <= 2548 )
+        if(n <= 2548)
         {
-            return configure_lhs_rhs_info(m,n,1,2,16,1,4,false,true,false,true,false);
+            return configure_lhs_rhs_info(m, n, 1, 2, 16, 1, 4, false, true, false, true, false);
         }
         else
         {
-            return configure_lhs_rhs_info(m,n,1,4,16,1,8,false,true,false,true,false);
+            return configure_lhs_rhs_info(m, n, 1, 4, 16, 1, 8, false, true, false, true, false);
         }
     }
     else
@@ -251,7 +251,7 @@ std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> CLGEMMReshapedOnlyRHSKernelConfi
 
     if(m == 1)
     {
-        return configure_lhs_rhs_info(m,n,1,2,16,1,32,false,true,false,true,false);
+        return configure_lhs_rhs_info(m, n, 1, 2, 16, 1, 32, false, true, false, true, false);
     }
     else
     {
diff --git a/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.h b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.h
new file mode 100644
index 0000000000..618dbd9923
--- /dev/null
+++ b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationBifrost.h
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2019-2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATIONBIFROST_H
+#define ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATIONBIFROST_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** Bifrost based OpenCL GEMMReshapedOnlyRHS configuration */
+class CLGEMMReshapedOnlyRHSKernelConfigurationBifrost final : public ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] gpu GPU target
+     */
+    CLGEMMReshapedOnlyRHSKernelConfigurationBifrost(GPUTarget gpu);
+
+    // Inherited overridden method
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) override;
+
+private:
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G51_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G51_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G7x_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G76_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G51_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATIONBIFROST_H */
diff --git a/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.cpp b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.cpp
index 23bf02c61a..f7939d29c0 100644
--- a/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.cpp
+++ b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.cpp
@@ -21,15 +21,15 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#include "arm_compute/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.h"
+#include "src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
 #include "arm_compute/core/GPUTarget.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/TensorShape.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
 
 #include <map>
 #include <utility>
diff --git a/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.h b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.h
new file mode 100644
index 0000000000..b9289923b9
--- /dev/null
+++ b/src/core/CL/gemm/reshaped_only_rhs/CLGEMMReshapedOnlyRHSKernelConfigurationValhall.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2020 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATIONVALHALL_H
+#define ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATIONVALHALL_H
+
+#include "src/core/CL/ICLGEMMKernelConfiguration.h"
+
+namespace arm_compute
+{
+namespace cl_gemm
+{
+/** Valhall based OpenCL GEMMReshapedOnlyRHS configuration */
+class CLGEMMReshapedOnlyRHSKernelConfigurationValhall final : public ICLGEMMKernelConfiguration
+{
+public:
+    /** Constructor
+     *
+     * @param[in] gpu GPU target
+     */
+    CLGEMMReshapedOnlyRHSKernelConfigurationValhall(GPUTarget gpu);
+
+    // Inherited overridden method
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure(unsigned int m, unsigned int n, unsigned int k, unsigned int b, DataType data_type) override;
+
+private:
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_f32(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_f16(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+    std::pair<GEMMLHSMatrixInfo, GEMMRHSMatrixInfo> configure_G77_u8(unsigned int m, unsigned int n, unsigned int k, unsigned int b);
+};
+} // namespace cl_gemm
+} // namespace arm_compute
+#endif /*ARM_COMPUTE_CLGEMMRESHAPEDONLYRHSKERNELCONFIGURATIONVALHALL_H */
diff --git a/src/core/CL/kernels/CLAbsoluteDifferenceKernel.cpp b/src/core/CL/kernels/CLAbsoluteDifferenceKernel.cpp
index 9deb16524e..29745beee7 100644
--- a/src/core/CL/kernels/CLAbsoluteDifferenceKernel.cpp
+++ b/src/core/CL/kernels/CLAbsoluteDifferenceKernel.cpp
@@ -27,12 +27,9 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <string>
diff --git a/src/core/CL/kernels/CLActivationLayerKernel.cpp b/src/core/CL/kernels/CLActivationLayerKernel.cpp
index 5a9434ee5a..f0e3047796 100644
--- a/src/core/CL/kernels/CLActivationLayerKernel.cpp
+++ b/src/core/CL/kernels/CLActivationLayerKernel.cpp
@@ -25,14 +25,14 @@
 
 #include "arm_compute/core/CL/CLCoreRuntimeContext.h"
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/helpers/float_ops.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
+
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp b/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp
index b78ac27cfa..b5a801a97f 100644
--- a/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp
+++ b/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp
@@ -23,16 +23,17 @@
  */
 #include "arm_compute/core/CL/kernels/CLArgMinMaxLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLBatchConcatenateLayerKernel.cpp b/src/core/CL/kernels/CLBatchConcatenateLayerKernel.cpp
index dd9c234c56..7a8c9ad0fb 100644
--- a/src/core/CL/kernels/CLBatchConcatenateLayerKernel.cpp
+++ b/src/core/CL/kernels/CLBatchConcatenateLayerKernel.cpp
@@ -25,12 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLBatchNormalizationLayerKernel.cpp b/src/core/CL/kernels/CLBatchNormalizationLayerKernel.cpp
index 1c1df6c4eb..09b668d6cd 100644
--- a/src/core/CL/kernels/CLBatchNormalizationLayerKernel.cpp
+++ b/src/core/CL/kernels/CLBatchNormalizationLayerKernel.cpp
@@ -25,12 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLBatchToSpaceLayerKernel.cpp b/src/core/CL/kernels/CLBatchToSpaceLayerKernel.cpp
index c74f7e055b..6eb22c9ada 100644
--- a/src/core/CL/kernels/CLBatchToSpaceLayerKernel.cpp
+++ b/src/core/CL/kernels/CLBatchToSpaceLayerKernel.cpp
@@ -24,9 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLBatchToSpaceLayerKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute::misc::shape_calculator;
diff --git a/src/core/CL/kernels/CLBitwiseAndKernel.cpp b/src/core/CL/kernels/CLBitwiseAndKernel.cpp
index 44378c8239..53a438dcf6 100644
--- a/src/core/CL/kernels/CLBitwiseAndKernel.cpp
+++ b/src/core/CL/kernels/CLBitwiseAndKernel.cpp
@@ -27,9 +27,8 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 using namespace arm_compute;
 
diff --git a/src/core/CL/kernels/CLBitwiseOrKernel.cpp b/src/core/CL/kernels/CLBitwiseOrKernel.cpp
index 77c48e6e82..0e2e5d4f3c 100644
--- a/src/core/CL/kernels/CLBitwiseOrKernel.cpp
+++ b/src/core/CL/kernels/CLBitwiseOrKernel.cpp
@@ -27,9 +27,8 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 using namespace arm_compute;
 
diff --git a/src/core/CL/kernels/CLBitwiseXorKernel.cpp b/src/core/CL/kernels/CLBitwiseXorKernel.cpp
index a15305e3b7..65b17c02bd 100644
--- a/src/core/CL/kernels/CLBitwiseXorKernel.cpp
+++ b/src/core/CL/kernels/CLBitwiseXorKernel.cpp
@@ -27,9 +27,8 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 using namespace arm_compute;
 
diff --git a/src/core/CL/kernels/CLBoundingBoxTransformKernel.cpp b/src/core/CL/kernels/CLBoundingBoxTransformKernel.cpp
index 95ea3d7df5..b8c0d2f2b8 100644
--- a/src/core/CL/kernels/CLBoundingBoxTransformKernel.cpp
+++ b/src/core/CL/kernels/CLBoundingBoxTransformKernel.cpp
@@ -23,17 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLBoundingBoxTransformKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLArray.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLBox3x3Kernel.cpp b/src/core/CL/kernels/CLBox3x3Kernel.cpp
index 7916dce241..2f6c09df0b 100644
--- a/src/core/CL/kernels/CLBox3x3Kernel.cpp
+++ b/src/core/CL/kernels/CLBox3x3Kernel.cpp
@@ -26,9 +26,8 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/IAccessWindow.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <string>
diff --git a/src/core/CL/kernels/CLCannyEdgeKernel.cpp b/src/core/CL/kernels/CLCannyEdgeKernel.cpp
index b8a53650e8..c76ec6769e 100644
--- a/src/core/CL/kernels/CLCannyEdgeKernel.cpp
+++ b/src/core/CL/kernels/CLCannyEdgeKernel.cpp
@@ -29,6 +29,7 @@
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLChannelCombineKernel.cpp b/src/core/CL/kernels/CLChannelCombineKernel.cpp
index b0e5111417..d574f352ae 100644
--- a/src/core/CL/kernels/CLChannelCombineKernel.cpp
+++ b/src/core/CL/kernels/CLChannelCombineKernel.cpp
@@ -27,14 +27,12 @@
 #include "arm_compute/core/CL/ICLMultiImage.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/MultiImageInfo.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <string>
diff --git a/src/core/CL/kernels/CLChannelExtractKernel.cpp b/src/core/CL/kernels/CLChannelExtractKernel.cpp
index 13ae8f5ef4..7911b948ae 100644
--- a/src/core/CL/kernels/CLChannelExtractKernel.cpp
+++ b/src/core/CL/kernels/CLChannelExtractKernel.cpp
@@ -28,14 +28,13 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Coordinates.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/MultiImageInfo.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <string>
diff --git a/src/core/CL/kernels/CLChannelShuffleLayerKernel.cpp b/src/core/CL/kernels/CLChannelShuffleLayerKernel.cpp
index ad000ba17f..301a762850 100644
--- a/src/core/CL/kernels/CLChannelShuffleLayerKernel.cpp
+++ b/src/core/CL/kernels/CLChannelShuffleLayerKernel.cpp
@@ -25,12 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLCol2ImKernel.cpp b/src/core/CL/kernels/CLCol2ImKernel.cpp
index 4050b24e0c..3dc007d9e0 100644
--- a/src/core/CL/kernels/CLCol2ImKernel.cpp
+++ b/src/core/CL/kernels/CLCol2ImKernel.cpp
@@ -25,13 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cmath>
diff --git a/src/core/CL/kernels/CLColorConvertKernel.cpp b/src/core/CL/kernels/CLColorConvertKernel.cpp
index e14b871ae6..0f82d87348 100644
--- a/src/core/CL/kernels/CLColorConvertKernel.cpp
+++ b/src/core/CL/kernels/CLColorConvertKernel.cpp
@@ -27,14 +27,12 @@
 #include "arm_compute/core/CL/ICLMultiImage.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/MultiImageInfo.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <sstream>
diff --git a/src/core/CL/kernels/CLComparisonKernel.cpp b/src/core/CL/kernels/CLComparisonKernel.cpp
index 5bb1d56690..2b72946f49 100644
--- a/src/core/CL/kernels/CLComparisonKernel.cpp
+++ b/src/core/CL/kernels/CLComparisonKernel.cpp
@@ -24,8 +24,10 @@
 #include "arm_compute/core/CL/kernels/CLComparisonKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <map>
diff --git a/src/core/CL/kernels/CLConvertFullyConnectedWeightsKernel.cpp b/src/core/CL/kernels/CLConvertFullyConnectedWeightsKernel.cpp
index 7c6114640c..b4e42bf3bc 100644
--- a/src/core/CL/kernels/CLConvertFullyConnectedWeightsKernel.cpp
+++ b/src/core/CL/kernels/CLConvertFullyConnectedWeightsKernel.cpp
@@ -25,10 +25,11 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLConvolutionKernel.cpp b/src/core/CL/kernels/CLConvolutionKernel.cpp
index ca07e68345..48b185f78d 100644
--- a/src/core/CL/kernels/CLConvolutionKernel.cpp
+++ b/src/core/CL/kernels/CLConvolutionKernel.cpp
@@ -31,9 +31,9 @@
 #include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLCopyKernel.cpp b/src/core/CL/kernels/CLCopyKernel.cpp
index 37c3241302..0b7e9aff53 100644
--- a/src/core/CL/kernels/CLCopyKernel.cpp
+++ b/src/core/CL/kernels/CLCopyKernel.cpp
@@ -23,15 +23,15 @@
  */
 #include "arm_compute/core/CL/kernels/CLCopyKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLCropKernel.cpp b/src/core/CL/kernels/CLCropKernel.cpp
index f828162177..2c99d46929 100644
--- a/src/core/CL/kernels/CLCropKernel.cpp
+++ b/src/core/CL/kernels/CLCropKernel.cpp
@@ -26,16 +26,11 @@
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/CPP/Validate.h"
 #include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CPP/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
-#include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
-#include "arm_compute/core/utils/helpers/bit_ops.h"
-#include "arm_compute/core/utils/helpers/tensor_transform.h"
-#include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "support/StringSupport.h"
 
 #include <map>
diff --git a/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp b/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp
index e8f12d5d9d..9ba3dc3d8f 100644
--- a/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp
+++ b/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp
@@ -25,12 +25,11 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 namespace arm_compute
 {
diff --git a/src/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.cpp b/src/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.cpp
index 69730346fe..1514d906dc 100644
--- a/src/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.cpp
+++ b/src/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.cpp
@@ -30,6 +30,8 @@
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLDepthConcatenateLayerKernel.cpp b/src/core/CL/kernels/CLDepthConcatenateLayerKernel.cpp
index 87067cf717..cb5d727e9b 100644
--- a/src/core/CL/kernels/CLDepthConcatenateLayerKernel.cpp
+++ b/src/core/CL/kernels/CLDepthConcatenateLayerKernel.cpp
@@ -25,12 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLDepthConvertLayerKernel.cpp b/src/core/CL/kernels/CLDepthConvertLayerKernel.cpp
index 11297e7901..24f638f8c4 100644
--- a/src/core/CL/kernels/CLDepthConvertLayerKernel.cpp
+++ b/src/core/CL/kernels/CLDepthConvertLayerKernel.cpp
@@ -25,13 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLDepthToSpaceLayerKernel.cpp b/src/core/CL/kernels/CLDepthToSpaceLayerKernel.cpp
index e6f909e884..50bb3b827c 100644
--- a/src/core/CL/kernels/CLDepthToSpaceLayerKernel.cpp
+++ b/src/core/CL/kernels/CLDepthToSpaceLayerKernel.cpp
@@ -24,9 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLDepthToSpaceLayerKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute::misc::shape_calculator;
diff --git a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp
index 066e9a5a40..7958230aac 100644
--- a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp
+++ b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.cpp
@@ -23,19 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NCHWKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp
index 0930fee712..5a0d2d0a62 100644
--- a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp
+++ b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp
@@ -23,19 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.cpp b/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.cpp
index a538ab51cb..5a3a0ec435 100644
--- a/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.cpp
+++ b/src/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.cpp
@@ -25,17 +25,16 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLDepthwiseConvolutionLayerReshapeWeightsKernel.cpp b/src/core/CL/kernels/CLDepthwiseConvolutionLayerReshapeWeightsKernel.cpp
index 07f25a80cf..0ff3c520ba 100644
--- a/src/core/CL/kernels/CLDepthwiseConvolutionLayerReshapeWeightsKernel.cpp
+++ b/src/core/CL/kernels/CLDepthwiseConvolutionLayerReshapeWeightsKernel.cpp
@@ -23,19 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerReshapeWeightsKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
-#include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLDequantizationLayerKernel.cpp b/src/core/CL/kernels/CLDequantizationLayerKernel.cpp
index 72eac858ad..e653c59550 100644
--- a/src/core/CL/kernels/CLDequantizationLayerKernel.cpp
+++ b/src/core/CL/kernels/CLDequantizationLayerKernel.cpp
@@ -23,15 +23,16 @@
  */
 #include "arm_compute/core/CL/kernels/CLDequantizationLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLDerivativeKernel.cpp b/src/core/CL/kernels/CLDerivativeKernel.cpp
index ab5f9dab76..659a7cb209 100644
--- a/src/core/CL/kernels/CLDerivativeKernel.cpp
+++ b/src/core/CL/kernels/CLDerivativeKernel.cpp
@@ -26,11 +26,9 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLDilateKernel.cpp b/src/core/CL/kernels/CLDilateKernel.cpp
index ae948314a3..1e59c349e7 100644
--- a/src/core/CL/kernels/CLDilateKernel.cpp
+++ b/src/core/CL/kernels/CLDilateKernel.cpp
@@ -26,8 +26,8 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 using namespace arm_compute;
 
diff --git a/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp b/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp
index d5d808a80f..161b221e81 100644
--- a/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp
+++ b/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp
@@ -23,19 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLDirectConvolutionLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/ITensor.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLElementWiseUnaryLayerKernel.cpp b/src/core/CL/kernels/CLElementWiseUnaryLayerKernel.cpp
index c8c7fb03b8..c7f9df0baa 100644
--- a/src/core/CL/kernels/CLElementWiseUnaryLayerKernel.cpp
+++ b/src/core/CL/kernels/CLElementWiseUnaryLayerKernel.cpp
@@ -24,9 +24,10 @@
 #include "arm_compute/core/CL/kernels/CLElementWiseUnaryLayerKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLElementwiseOperationKernel.cpp b/src/core/CL/kernels/CLElementwiseOperationKernel.cpp
index ec33500f20..f0712f5863 100644
--- a/src/core/CL/kernels/CLElementwiseOperationKernel.cpp
+++ b/src/core/CL/kernels/CLElementwiseOperationKernel.cpp
@@ -24,9 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLElementwiseOperationKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 #include "support/StringSupport.h"
 #include <map>
 
diff --git a/src/core/CL/kernels/CLErodeKernel.cpp b/src/core/CL/kernels/CLErodeKernel.cpp
index a5eb79f73b..29a32979a3 100644
--- a/src/core/CL/kernels/CLErodeKernel.cpp
+++ b/src/core/CL/kernels/CLErodeKernel.cpp
@@ -26,8 +26,8 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 using namespace arm_compute;
 
diff --git a/src/core/CL/kernels/CLFFTDigitReverseKernel.cpp b/src/core/CL/kernels/CLFFTDigitReverseKernel.cpp
index 30bca2f0f9..0478f550f9 100644
--- a/src/core/CL/kernels/CLFFTDigitReverseKernel.cpp
+++ b/src/core/CL/kernels/CLFFTDigitReverseKernel.cpp
@@ -24,11 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLFFTDigitReverseKernel.h"
 
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLFFTRadixStageKernel.cpp b/src/core/CL/kernels/CLFFTRadixStageKernel.cpp
index 6c36338dae..7b17a227e1 100644
--- a/src/core/CL/kernels/CLFFTRadixStageKernel.cpp
+++ b/src/core/CL/kernels/CLFFTRadixStageKernel.cpp
@@ -25,12 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cmath>
diff --git a/src/core/CL/kernels/CLFFTScaleKernel.cpp b/src/core/CL/kernels/CLFFTScaleKernel.cpp
index ac5f2b38c3..49fcbb6c7b 100644
--- a/src/core/CL/kernels/CLFFTScaleKernel.cpp
+++ b/src/core/CL/kernels/CLFFTScaleKernel.cpp
@@ -24,11 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLFFTScaleKernel.h"
 
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLFastCornersKernel.cpp b/src/core/CL/kernels/CLFastCornersKernel.cpp
index e71b47228e..ebdfd2741f 100644
--- a/src/core/CL/kernels/CLFastCornersKernel.cpp
+++ b/src/core/CL/kernels/CLFastCornersKernel.cpp
@@ -26,11 +26,9 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLFillBorderKernel.cpp b/src/core/CL/kernels/CLFillBorderKernel.cpp
index 1ea654b5cc..e92619a242 100644
--- a/src/core/CL/kernels/CLFillBorderKernel.cpp
+++ b/src/core/CL/kernels/CLFillBorderKernel.cpp
@@ -27,13 +27,11 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLFlattenLayerKernel.cpp b/src/core/CL/kernels/CLFlattenLayerKernel.cpp
index 6bd1149612..dc1d33869f 100644
--- a/src/core/CL/kernels/CLFlattenLayerKernel.cpp
+++ b/src/core/CL/kernels/CLFlattenLayerKernel.cpp
@@ -23,9 +23,10 @@
  */
 #include "arm_compute/core/CL/kernels/CLFlattenLayerKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute::misc::shape_calculator;
diff --git a/src/core/CL/kernels/CLFloorKernel.cpp b/src/core/CL/kernels/CLFloorKernel.cpp
index 09f5f61a50..8884f3fe36 100644
--- a/src/core/CL/kernels/CLFloorKernel.cpp
+++ b/src/core/CL/kernels/CLFloorKernel.cpp
@@ -25,14 +25,14 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLFuseBatchNormalizationKernel.cpp b/src/core/CL/kernels/CLFuseBatchNormalizationKernel.cpp
index b582295f44..61e2b2700a 100644
--- a/src/core/CL/kernels/CLFuseBatchNormalizationKernel.cpp
+++ b/src/core/CL/kernels/CLFuseBatchNormalizationKernel.cpp
@@ -25,12 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp
index d30a9e5d18..cc98845e0f 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp
@@ -23,19 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
@@ -137,7 +136,7 @@ std::pair<Status, Window> validate_and_configure_window(ITensorInfo *input0, ITe
     num_elems_processed_per_iteration_x = rhs_info.n0;
     num_elems_processed_per_iteration_y = lhs_info.m0;
 
-    win     = calculate_max_window(tmp_info, Steps(num_elems_processed_per_iteration_x, num_elems_processed_per_iteration_y));
+    win = calculate_max_window(tmp_info, Steps(num_elems_processed_per_iteration_x, num_elems_processed_per_iteration_y));
     output->set_valid_region(ValidRegion(Coordinates(), output->tensor_shape()));
 
     // Collapse along the Z direction
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp
index 56b92a3d41..5469c89c30 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp
@@ -23,19 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
index 4770329b7d..4a3ac2da81 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
@@ -23,19 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLGEMMLowpOffsetContributionKernel.cpp b/src/core/CL/kernels/CLGEMMLowpOffsetContributionKernel.cpp
index 6ef9fd2565..7ab96e5fa9 100644
--- a/src/core/CL/kernels/CLGEMMLowpOffsetContributionKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpOffsetContributionKernel.cpp
@@ -23,15 +23,13 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
@@ -148,7 +146,8 @@ void CLGEMMLowpOffsetContributionKernel::configure(ICLTensor *mm_result, const I
     configure(CLKernelLibrary::get().get_compile_context(), mm_result, vector_sum_col, vector_sum_row, bias, k, a_offset, b_offset);
 }
 
-void CLGEMMLowpOffsetContributionKernel::configure(const CLCompileContext &compile_context, ICLTensor *mm_result, const ICLTensor *vector_sum_col, const ICLTensor *vector_sum_row, const ICLTensor *bias,
+void CLGEMMLowpOffsetContributionKernel::configure(const CLCompileContext &compile_context, ICLTensor *mm_result, const ICLTensor *vector_sum_col, const ICLTensor *vector_sum_row,
+                                                   const ICLTensor *bias,
                                                    int32_t k, int32_t a_offset,
                                                    int32_t b_offset)
 {
diff --git a/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp b/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp
index 6d3aa6fbf6..85285d6704 100644
--- a/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp
@@ -23,16 +23,15 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel.cpp b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel.cpp
index eae66413a6..ab1b5a2203 100644
--- a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFixedPointKernel.cpp
@@ -25,14 +25,14 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFloatKernel.cpp b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFloatKernel.cpp
index 430a84cfa0..ad5bac015b 100644
--- a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFloatKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleByFloatKernel.cpp
@@ -25,14 +25,14 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleKernel.cpp b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleKernel.cpp
index 79888cdba2..8e4b291dbe 100644
--- a/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpQuantizeDownInt32ScaleKernel.cpp
@@ -25,12 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLGEMMLowpReductionKernel.cpp b/src/core/CL/kernels/CLGEMMLowpReductionKernel.cpp
index 31a97ca32b..826b265dbf 100644
--- a/src/core/CL/kernels/CLGEMMLowpReductionKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpReductionKernel.cpp
@@ -23,10 +23,12 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMLowpReductionKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/KernelDescriptors.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
index c2dd92c0fd..aa69ed06d1 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
@@ -23,20 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/helpers/float_ops.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "src/core/utils/helpers/float_ops.h"
 #include "support/StringSupport.h"
 
 #include <set>
@@ -310,7 +309,8 @@ void CLGEMMMatrixMultiplyKernel::configure(const ICLTensor *input0, const ICLTen
     configure(CLKernelLibrary::get().get_compile_context(), input0, input1, input2, output, alpha, beta, is_interleaved_transposed, reshape_info, fp_mixed_precision, activation_info);
 }
 
-void CLGEMMMatrixMultiplyKernel::configure(const CLCompileContext &compile_context, const ICLTensor *input0, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float alpha, float beta,
+void CLGEMMMatrixMultiplyKernel::configure(const CLCompileContext &compile_context, const ICLTensor *input0, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float alpha,
+                                           float beta,
                                            bool is_interleaved_transposed, const GEMMReshapeInfo &reshape_info, bool fp_mixed_precision, const ActivationLayerInfo &activation_info)
 {
     ARM_COMPUTE_ERROR_ON_NULLPTR(input0, input1, output);
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp
index da57aa447f..cea147b10c 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp
@@ -23,20 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/helpers/float_ops.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "src/core/utils/helpers/float_ops.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp
index b0f0e8a81f..eaf57086a3 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp
@@ -23,23 +23,22 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/helpers/float_ops.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
 #include "src/core/CL/CLUtils.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "src/core/utils/helpers/float_ops.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp
index 0ae30ed30e..912c763ed5 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp
@@ -23,17 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/utils/helpers/float_ops.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
 #include "src/core/CL/CLUtils.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "src/core/utils/helpers/float_ops.h"
 #include "support/StringSupport.h"
 
 #include <tuple>
diff --git a/src/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.cpp
index f52384593b..04aa061e98 100644
--- a/src/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.cpp
@@ -23,15 +23,14 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMMatrixVectorMultiplyKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.cpp b/src/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.cpp
index 156a657f28..f2ad677976 100644
--- a/src/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.cpp
@@ -23,19 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMReshapeLHSMatrixKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLGEMMReshapeRHSMatrixKernel.cpp b/src/core/CL/kernels/CLGEMMReshapeRHSMatrixKernel.cpp
index ce294646a0..d94e834d2c 100644
--- a/src/core/CL/kernels/CLGEMMReshapeRHSMatrixKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMReshapeRHSMatrixKernel.cpp
@@ -23,20 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLGEMMReshapeRHSMatrixKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/CL/gemm/CLGEMMHelpers.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/CL/gemm/CLGEMMHelpers.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLGatherKernel.cpp b/src/core/CL/kernels/CLGatherKernel.cpp
index 57759fc1c1..a8508bed2d 100644
--- a/src/core/CL/kernels/CLGatherKernel.cpp
+++ b/src/core/CL/kernels/CLGatherKernel.cpp
@@ -23,8 +23,9 @@
  */
 #include "arm_compute/core/CL/kernels/CLGatherKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <string>
diff --git a/src/core/CL/kernels/CLGaussian3x3Kernel.cpp b/src/core/CL/kernels/CLGaussian3x3Kernel.cpp
index 08e7e27b3c..c9ed1ac0d7 100644
--- a/src/core/CL/kernels/CLGaussian3x3Kernel.cpp
+++ b/src/core/CL/kernels/CLGaussian3x3Kernel.cpp
@@ -26,8 +26,8 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <string>
diff --git a/src/core/CL/kernels/CLGaussianPyramidKernel.cpp b/src/core/CL/kernels/CLGaussianPyramidKernel.cpp
index 0e20187d1c..2686e8b32e 100644
--- a/src/core/CL/kernels/CLGaussianPyramidKernel.cpp
+++ b/src/core/CL/kernels/CLGaussianPyramidKernel.cpp
@@ -28,6 +28,7 @@
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLGenerateProposalsLayerKernel.cpp b/src/core/CL/kernels/CLGenerateProposalsLayerKernel.cpp
index 3108ad87d0..a2fcbbab78 100644
--- a/src/core/CL/kernels/CLGenerateProposalsLayerKernel.cpp
+++ b/src/core/CL/kernels/CLGenerateProposalsLayerKernel.cpp
@@ -23,17 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLGenerateProposalsLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLArray.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLHOGDescriptorKernel.cpp b/src/core/CL/kernels/CLHOGDescriptorKernel.cpp
index 7f618b294b..eaf5ea4880 100644
--- a/src/core/CL/kernels/CLHOGDescriptorKernel.cpp
+++ b/src/core/CL/kernels/CLHOGDescriptorKernel.cpp
@@ -27,12 +27,10 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLHOGDetectorKernel.cpp b/src/core/CL/kernels/CLHOGDetectorKernel.cpp
index fbd2208894..6e14996732 100644
--- a/src/core/CL/kernels/CLHOGDetectorKernel.cpp
+++ b/src/core/CL/kernels/CLHOGDetectorKernel.cpp
@@ -27,12 +27,10 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLHOG.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLHarrisCornersKernel.cpp b/src/core/CL/kernels/CLHarrisCornersKernel.cpp
index 08e670f5d2..19c4e579a0 100644
--- a/src/core/CL/kernels/CLHarrisCornersKernel.cpp
+++ b/src/core/CL/kernels/CLHarrisCornersKernel.cpp
@@ -23,17 +23,16 @@
  */
 #include "arm_compute/core/CL/kernels/CLHarrisCornersKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLHeightConcatenateLayerKernel.cpp b/src/core/CL/kernels/CLHeightConcatenateLayerKernel.cpp
index 22b2cfcbc5..1ae2599721 100644
--- a/src/core/CL/kernels/CLHeightConcatenateLayerKernel.cpp
+++ b/src/core/CL/kernels/CLHeightConcatenateLayerKernel.cpp
@@ -25,13 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/misc/Cast.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLHistogramKernel.cpp b/src/core/CL/kernels/CLHistogramKernel.cpp
index b8a4e8619d..a85429c1a0 100644
--- a/src/core/CL/kernels/CLHistogramKernel.cpp
+++ b/src/core/CL/kernels/CLHistogramKernel.cpp
@@ -27,12 +27,10 @@
 #include "arm_compute/core/CL/ICLDistribution1D.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstring>
diff --git a/src/core/CL/kernels/CLIm2ColKernel.cpp b/src/core/CL/kernels/CLIm2ColKernel.cpp
index c94e313b9a..76490f82f6 100644
--- a/src/core/CL/kernels/CLIm2ColKernel.cpp
+++ b/src/core/CL/kernels/CLIm2ColKernel.cpp
@@ -23,18 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLIm2ColKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cmath>
diff --git a/src/core/CL/kernels/CLInstanceNormalizationLayerKernel.cpp b/src/core/CL/kernels/CLInstanceNormalizationLayerKernel.cpp
index 2ad5233de8..e97b856456 100644
--- a/src/core/CL/kernels/CLInstanceNormalizationLayerKernel.cpp
+++ b/src/core/CL/kernels/CLInstanceNormalizationLayerKernel.cpp
@@ -25,12 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLIntegralImageKernel.cpp b/src/core/CL/kernels/CLIntegralImageKernel.cpp
index aff4bd9cea..82f6da85a5 100644
--- a/src/core/CL/kernels/CLIntegralImageKernel.cpp
+++ b/src/core/CL/kernels/CLIntegralImageKernel.cpp
@@ -28,9 +28,8 @@
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLL2NormalizeLayerKernel.cpp b/src/core/CL/kernels/CLL2NormalizeLayerKernel.cpp
index a68d8db3c0..9936e29c5f 100644
--- a/src/core/CL/kernels/CLL2NormalizeLayerKernel.cpp
+++ b/src/core/CL/kernels/CLL2NormalizeLayerKernel.cpp
@@ -25,13 +25,14 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLLKTrackerKernel.cpp b/src/core/CL/kernels/CLLKTrackerKernel.cpp
index fae5fe2c8e..0fa2e703ec 100644
--- a/src/core/CL/kernels/CLLKTrackerKernel.cpp
+++ b/src/core/CL/kernels/CLLKTrackerKernel.cpp
@@ -23,16 +23,15 @@
  */
 #include "arm_compute/core/CL/kernels/CLLKTrackerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLArray.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Coordinates.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <cmath>
 
diff --git a/src/core/CL/kernels/CLLocallyConnectedMatrixMultiplyKernel.cpp b/src/core/CL/kernels/CLLocallyConnectedMatrixMultiplyKernel.cpp
index 0da0d4ca1f..6e4c45eab7 100644
--- a/src/core/CL/kernels/CLLocallyConnectedMatrixMultiplyKernel.cpp
+++ b/src/core/CL/kernels/CLLocallyConnectedMatrixMultiplyKernel.cpp
@@ -23,15 +23,13 @@
  */
 #include "arm_compute/core/CL/kernels/CLLocallyConnectedMatrixMultiplyKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 namespace arm_compute
 {
diff --git a/src/core/CL/kernels/CLMagnitudePhaseKernel.cpp b/src/core/CL/kernels/CLMagnitudePhaseKernel.cpp
index ef8ebd52e5..dc130d0ff9 100644
--- a/src/core/CL/kernels/CLMagnitudePhaseKernel.cpp
+++ b/src/core/CL/kernels/CLMagnitudePhaseKernel.cpp
@@ -27,11 +27,10 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLMaxUnpoolingLayerKernel.cpp b/src/core/CL/kernels/CLMaxUnpoolingLayerKernel.cpp
index 08c74642f4..a78996ddae 100644
--- a/src/core/CL/kernels/CLMaxUnpoolingLayerKernel.cpp
+++ b/src/core/CL/kernels/CLMaxUnpoolingLayerKernel.cpp
@@ -23,19 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLMaxUnpoolingLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLMeanStdDevKernel.cpp b/src/core/CL/kernels/CLMeanStdDevKernel.cpp
index 33099c928d..5acc3ac3d6 100644
--- a/src/core/CL/kernels/CLMeanStdDevKernel.cpp
+++ b/src/core/CL/kernels/CLMeanStdDevKernel.cpp
@@ -25,14 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <cmath>
 #include <set>
diff --git a/src/core/CL/kernels/CLMeanStdDevNormalizationKernel.cpp b/src/core/CL/kernels/CLMeanStdDevNormalizationKernel.cpp
index 5ecbb4b2a6..82a22a9f19 100644
--- a/src/core/CL/kernels/CLMeanStdDevNormalizationKernel.cpp
+++ b/src/core/CL/kernels/CLMeanStdDevNormalizationKernel.cpp
@@ -25,14 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLMedian3x3Kernel.cpp b/src/core/CL/kernels/CLMedian3x3Kernel.cpp
index 5f8c9e5a93..4b899502f9 100644
--- a/src/core/CL/kernels/CLMedian3x3Kernel.cpp
+++ b/src/core/CL/kernels/CLMedian3x3Kernel.cpp
@@ -26,8 +26,8 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLMemsetKernel.cpp b/src/core/CL/kernels/CLMemsetKernel.cpp
index f591c2f6d5..186ed2a38c 100644
--- a/src/core/CL/kernels/CLMemsetKernel.cpp
+++ b/src/core/CL/kernels/CLMemsetKernel.cpp
@@ -23,8 +23,8 @@
  */
 #include "arm_compute/core/CL/kernels/CLMemsetKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLMinMaxLayerKernel.cpp b/src/core/CL/kernels/CLMinMaxLayerKernel.cpp
index 5f0e48dbb9..bf645f82e9 100644
--- a/src/core/CL/kernels/CLMinMaxLayerKernel.cpp
+++ b/src/core/CL/kernels/CLMinMaxLayerKernel.cpp
@@ -23,14 +23,15 @@
  */
 #include "arm_compute/core/CL/kernels/CLMinMaxLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <climits>
diff --git a/src/core/CL/kernels/CLMinMaxLocationKernel.cpp b/src/core/CL/kernels/CLMinMaxLocationKernel.cpp
index 9bbda40782..634b58077a 100644
--- a/src/core/CL/kernels/CLMinMaxLocationKernel.cpp
+++ b/src/core/CL/kernels/CLMinMaxLocationKernel.cpp
@@ -28,7 +28,8 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <climits>
diff --git a/src/core/CL/kernels/CLNonLinearFilterKernel.cpp b/src/core/CL/kernels/CLNonLinearFilterKernel.cpp
index 16e5113c62..0a8472bf04 100644
--- a/src/core/CL/kernels/CLNonLinearFilterKernel.cpp
+++ b/src/core/CL/kernels/CLNonLinearFilterKernel.cpp
@@ -27,12 +27,11 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <algorithm>
 #include <cmath>
diff --git a/src/core/CL/kernels/CLNonMaximaSuppression3x3Kernel.cpp b/src/core/CL/kernels/CLNonMaximaSuppression3x3Kernel.cpp
index 958d94ce11..9c6d44b6c5 100644
--- a/src/core/CL/kernels/CLNonMaximaSuppression3x3Kernel.cpp
+++ b/src/core/CL/kernels/CLNonMaximaSuppression3x3Kernel.cpp
@@ -30,6 +30,7 @@
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <string>
diff --git a/src/core/CL/kernels/CLNormalizationLayerKernel.cpp b/src/core/CL/kernels/CLNormalizationLayerKernel.cpp
index 7d8e5db2b4..686e6f1b26 100644
--- a/src/core/CL/kernels/CLNormalizationLayerKernel.cpp
+++ b/src/core/CL/kernels/CLNormalizationLayerKernel.cpp
@@ -23,15 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLNormalizationLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/NormalizationHelpers.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLNormalizePlanarYUVLayerKernel.cpp b/src/core/CL/kernels/CLNormalizePlanarYUVLayerKernel.cpp
index 00bdac3441..407ce6626b 100644
--- a/src/core/CL/kernels/CLNormalizePlanarYUVLayerKernel.cpp
+++ b/src/core/CL/kernels/CLNormalizePlanarYUVLayerKernel.cpp
@@ -23,15 +23,16 @@
  */
 #include "arm_compute/core/CL/kernels/CLNormalizePlanarYUVLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLPadLayerKernel.cpp b/src/core/CL/kernels/CLPadLayerKernel.cpp
index b2432a058d..45729738fb 100644
--- a/src/core/CL/kernels/CLPadLayerKernel.cpp
+++ b/src/core/CL/kernels/CLPadLayerKernel.cpp
@@ -26,6 +26,8 @@
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLPermuteKernel.cpp b/src/core/CL/kernels/CLPermuteKernel.cpp
index dc2d6fe4b4..620665791f 100644
--- a/src/core/CL/kernels/CLPermuteKernel.cpp
+++ b/src/core/CL/kernels/CLPermuteKernel.cpp
@@ -23,8 +23,9 @@
  */
 #include "arm_compute/core/CL/kernels/CLPermuteKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLPixelWiseMultiplicationKernel.cpp b/src/core/CL/kernels/CLPixelWiseMultiplicationKernel.cpp
index 229937ef31..a7bd4dad60 100644
--- a/src/core/CL/kernels/CLPixelWiseMultiplicationKernel.cpp
+++ b/src/core/CL/kernels/CLPixelWiseMultiplicationKernel.cpp
@@ -25,11 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLPoolingLayerKernel.cpp b/src/core/CL/kernels/CLPoolingLayerKernel.cpp
index 1771834aac..0570887b91 100644
--- a/src/core/CL/kernels/CLPoolingLayerKernel.cpp
+++ b/src/core/CL/kernels/CLPoolingLayerKernel.cpp
@@ -23,18 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLPoolingLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLPriorBoxLayerKernel.cpp b/src/core/CL/kernels/CLPriorBoxLayerKernel.cpp
index 3429ef75d1..202e9fbb37 100644
--- a/src/core/CL/kernels/CLPriorBoxLayerKernel.cpp
+++ b/src/core/CL/kernels/CLPriorBoxLayerKernel.cpp
@@ -25,13 +25,14 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLQLSTMLayerNormalizationKernel.cpp b/src/core/CL/kernels/CLQLSTMLayerNormalizationKernel.cpp
index 2f676d30d1..ff6cc86103 100644
--- a/src/core/CL/kernels/CLQLSTMLayerNormalizationKernel.cpp
+++ b/src/core/CL/kernels/CLQLSTMLayerNormalizationKernel.cpp
@@ -23,8 +23,9 @@
  */
 #include "arm_compute/core/CL/kernels/CLQLSTMLayerNormalizationKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLQuantizationLayerKernel.cpp b/src/core/CL/kernels/CLQuantizationLayerKernel.cpp
index f6b08884e7..983cbedc0f 100644
--- a/src/core/CL/kernels/CLQuantizationLayerKernel.cpp
+++ b/src/core/CL/kernels/CLQuantizationLayerKernel.cpp
@@ -23,16 +23,16 @@
  */
 #include "arm_compute/core/CL/kernels/CLQuantizationLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLROIAlignLayerKernel.cpp b/src/core/CL/kernels/CLROIAlignLayerKernel.cpp
index 3f2a904f58..ca6c6fad1a 100644
--- a/src/core/CL/kernels/CLROIAlignLayerKernel.cpp
+++ b/src/core/CL/kernels/CLROIAlignLayerKernel.cpp
@@ -23,18 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLROIAlignLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLArray.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute::misc::shape_calculator;
diff --git a/src/core/CL/kernels/CLROIPoolingLayerKernel.cpp b/src/core/CL/kernels/CLROIPoolingLayerKernel.cpp
index c2ed32653a..55fe5a5321 100644
--- a/src/core/CL/kernels/CLROIPoolingLayerKernel.cpp
+++ b/src/core/CL/kernels/CLROIPoolingLayerKernel.cpp
@@ -23,17 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLROIPoolingLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLArray.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cmath>
diff --git a/src/core/CL/kernels/CLRangeKernel.cpp b/src/core/CL/kernels/CLRangeKernel.cpp
index d46cdd78da..a4c30b63c2 100644
--- a/src/core/CL/kernels/CLRangeKernel.cpp
+++ b/src/core/CL/kernels/CLRangeKernel.cpp
@@ -24,9 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLRangeKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Utils.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLReductionOperationKernel.cpp b/src/core/CL/kernels/CLReductionOperationKernel.cpp
index 0ba63cc4e0..325e4b994c 100644
--- a/src/core/CL/kernels/CLReductionOperationKernel.cpp
+++ b/src/core/CL/kernels/CLReductionOperationKernel.cpp
@@ -23,17 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLReductionOperationKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLRemapKernel.cpp b/src/core/CL/kernels/CLRemapKernel.cpp
index fe8c81a3b9..8d3f41b35f 100644
--- a/src/core/CL/kernels/CLRemapKernel.cpp
+++ b/src/core/CL/kernels/CLRemapKernel.cpp
@@ -23,15 +23,14 @@
  */
 #include "arm_compute/core/CL/kernels/CLRemapKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <algorithm>
 
diff --git a/src/core/CL/kernels/CLReorgLayerKernel.cpp b/src/core/CL/kernels/CLReorgLayerKernel.cpp
index ab81a8fca3..ade7761b91 100644
--- a/src/core/CL/kernels/CLReorgLayerKernel.cpp
+++ b/src/core/CL/kernels/CLReorgLayerKernel.cpp
@@ -26,12 +26,12 @@
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <string>
diff --git a/src/core/CL/kernels/CLReshapeLayerKernel.cpp b/src/core/CL/kernels/CLReshapeLayerKernel.cpp
index 3daf21a9a7..e08970992e 100644
--- a/src/core/CL/kernels/CLReshapeLayerKernel.cpp
+++ b/src/core/CL/kernels/CLReshapeLayerKernel.cpp
@@ -23,18 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLReshapeLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/misc/Cast.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 
 #include <string>
 
diff --git a/src/core/CL/kernels/CLReverseKernel.cpp b/src/core/CL/kernels/CLReverseKernel.cpp
index 6546ced72e..f8240984d1 100644
--- a/src/core/CL/kernels/CLReverseKernel.cpp
+++ b/src/core/CL/kernels/CLReverseKernel.cpp
@@ -25,12 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLScaleKernel.cpp b/src/core/CL/kernels/CLScaleKernel.cpp
index 2e7ee36bcb..8233f210b4 100644
--- a/src/core/CL/kernels/CLScaleKernel.cpp
+++ b/src/core/CL/kernels/CLScaleKernel.cpp
@@ -23,16 +23,17 @@
  */
 #include "arm_compute/core/CL/kernels/CLScaleKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include "src/core/utils/ScaleUtils.h"
diff --git a/src/core/CL/kernels/CLScharr3x3Kernel.cpp b/src/core/CL/kernels/CLScharr3x3Kernel.cpp
index 3172966b8f..1e33af3047 100644
--- a/src/core/CL/kernels/CLScharr3x3Kernel.cpp
+++ b/src/core/CL/kernels/CLScharr3x3Kernel.cpp
@@ -26,11 +26,9 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <string>
diff --git a/src/core/CL/kernels/CLSelectKernel.cpp b/src/core/CL/kernels/CLSelectKernel.cpp
index dcac78cca3..d9a1044e1f 100644
--- a/src/core/CL/kernels/CLSelectKernel.cpp
+++ b/src/core/CL/kernels/CLSelectKernel.cpp
@@ -25,12 +25,13 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLSobel3x3Kernel.cpp b/src/core/CL/kernels/CLSobel3x3Kernel.cpp
index 86dcf22258..89e5207c44 100644
--- a/src/core/CL/kernels/CLSobel3x3Kernel.cpp
+++ b/src/core/CL/kernels/CLSobel3x3Kernel.cpp
@@ -26,11 +26,9 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLSobel5x5Kernel.cpp b/src/core/CL/kernels/CLSobel5x5Kernel.cpp
index e010fdda75..3e765e47fb 100644
--- a/src/core/CL/kernels/CLSobel5x5Kernel.cpp
+++ b/src/core/CL/kernels/CLSobel5x5Kernel.cpp
@@ -26,11 +26,9 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLSobel7x7Kernel.cpp b/src/core/CL/kernels/CLSobel7x7Kernel.cpp
index c2b4bec494..37ceaba502 100644
--- a/src/core/CL/kernels/CLSobel7x7Kernel.cpp
+++ b/src/core/CL/kernels/CLSobel7x7Kernel.cpp
@@ -26,11 +26,9 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
-#include "arm_compute/core/Window.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLSoftmaxLayerKernel.cpp b/src/core/CL/kernels/CLSoftmaxLayerKernel.cpp
index c7881b9f5f..5c0acda41a 100644
--- a/src/core/CL/kernels/CLSoftmaxLayerKernel.cpp
+++ b/src/core/CL/kernels/CLSoftmaxLayerKernel.cpp
@@ -23,18 +23,19 @@
  */
 #include "arm_compute/core/CL/kernels/CLSoftmaxLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/KernelDescriptors.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <set>
diff --git a/src/core/CL/kernels/CLSpaceToBatchLayerKernel.cpp b/src/core/CL/kernels/CLSpaceToBatchLayerKernel.cpp
index 3e0ac74f69..c6f70c3c09 100644
--- a/src/core/CL/kernels/CLSpaceToBatchLayerKernel.cpp
+++ b/src/core/CL/kernels/CLSpaceToBatchLayerKernel.cpp
@@ -24,9 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLSpaceToBatchLayerKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute::misc::shape_calculator;
diff --git a/src/core/CL/kernels/CLSpaceToDepthLayerKernel.cpp b/src/core/CL/kernels/CLSpaceToDepthLayerKernel.cpp
index 4b6c1be8c2..2d46aade34 100644
--- a/src/core/CL/kernels/CLSpaceToDepthLayerKernel.cpp
+++ b/src/core/CL/kernels/CLSpaceToDepthLayerKernel.cpp
@@ -24,9 +24,11 @@
 #include "arm_compute/core/CL/kernels/CLSpaceToDepthLayerKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute::misc::shape_calculator;
diff --git a/src/core/CL/kernels/CLStackLayerKernel.cpp b/src/core/CL/kernels/CLStackLayerKernel.cpp
index c283c440a3..5055065779 100644
--- a/src/core/CL/kernels/CLStackLayerKernel.cpp
+++ b/src/core/CL/kernels/CLStackLayerKernel.cpp
@@ -25,13 +25,14 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLStridedSliceKernel.cpp b/src/core/CL/kernels/CLStridedSliceKernel.cpp
index f7b7290a3f..b632e05d84 100644
--- a/src/core/CL/kernels/CLStridedSliceKernel.cpp
+++ b/src/core/CL/kernels/CLStridedSliceKernel.cpp
@@ -24,10 +24,12 @@
 #include "arm_compute/core/CL/kernels/CLStridedSliceKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/utils/helpers/bit_ops.h"
 #include "arm_compute/core/utils/helpers/tensor_transform.h"
-#include "arm_compute/core/utils/misc/Cast.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "src/core/utils/helpers/bit_ops.h"
+#include "support/Cast.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLTileKernel.cpp b/src/core/CL/kernels/CLTileKernel.cpp
index bba152530c..43c8953363 100644
--- a/src/core/CL/kernels/CLTileKernel.cpp
+++ b/src/core/CL/kernels/CLTileKernel.cpp
@@ -23,8 +23,9 @@
  */
 #include "arm_compute/core/CL/kernels/CLTileKernel.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLTransposeKernel.cpp b/src/core/CL/kernels/CLTransposeKernel.cpp
index a47d956620..bd910196e9 100644
--- a/src/core/CL/kernels/CLTransposeKernel.cpp
+++ b/src/core/CL/kernels/CLTransposeKernel.cpp
@@ -23,18 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLTransposeKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
-#include "arm_compute/core/AccessWindowTranspose.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
-#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/AccessWindowTranspose.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <set>
 #include <sstream>
diff --git a/src/core/CL/kernels/CLUpsampleLayerKernel.cpp b/src/core/CL/kernels/CLUpsampleLayerKernel.cpp
index 101055001c..a4fc10f26a 100644
--- a/src/core/CL/kernels/CLUpsampleLayerKernel.cpp
+++ b/src/core/CL/kernels/CLUpsampleLayerKernel.cpp
@@ -23,16 +23,18 @@
  */
 #include "arm_compute/core/CL/kernels/CLUpsampleLayerKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Error.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLWarpAffineKernel.cpp b/src/core/CL/kernels/CLWarpAffineKernel.cpp
index e8da803628..95a7c1b875 100644
--- a/src/core/CL/kernels/CLWarpAffineKernel.cpp
+++ b/src/core/CL/kernels/CLWarpAffineKernel.cpp
@@ -23,7 +23,6 @@
  */
 #include "arm_compute/core/CL/kernels/CLWarpAffineKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
@@ -32,6 +31,8 @@
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 #include <cstddef>
diff --git a/src/core/CL/kernels/CLWarpPerspectiveKernel.cpp b/src/core/CL/kernels/CLWarpPerspectiveKernel.cpp
index dc7c359849..2fe1feb485 100644
--- a/src/core/CL/kernels/CLWarpPerspectiveKernel.cpp
+++ b/src/core/CL/kernels/CLWarpPerspectiveKernel.cpp
@@ -23,7 +23,6 @@
  */
 #include "arm_compute/core/CL/kernels/CLWarpPerspectiveKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
@@ -32,6 +31,8 @@
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/TensorInfo.h"
 #include "arm_compute/core/Validate.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include <cstddef>
 #include <set>
diff --git a/src/core/CL/kernels/CLWeightsReshapeKernel.cpp b/src/core/CL/kernels/CLWeightsReshapeKernel.cpp
index 267957e51a..f69967265a 100644
--- a/src/core/CL/kernels/CLWeightsReshapeKernel.cpp
+++ b/src/core/CL/kernels/CLWeightsReshapeKernel.cpp
@@ -25,6 +25,8 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Error.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute
diff --git a/src/core/CL/kernels/CLWidthConcatenate2TensorsKernel.cpp b/src/core/CL/kernels/CLWidthConcatenate2TensorsKernel.cpp
index 76100c2a63..27c650894c 100644
--- a/src/core/CL/kernels/CLWidthConcatenate2TensorsKernel.cpp
+++ b/src/core/CL/kernels/CLWidthConcatenate2TensorsKernel.cpp
@@ -23,16 +23,16 @@
  */
 #include "arm_compute/core/CL/kernels/CLWidthConcatenate2TensorsKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/helpers/tensor_info.h"
-#include "arm_compute/core/utils/misc/Cast.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "src/core/utils/helpers/tensor_info.h"
+#include "support/Cast.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLWidthConcatenate4TensorsKernel.cpp b/src/core/CL/kernels/CLWidthConcatenate4TensorsKernel.cpp
index 0377eb76b1..5ef2cc46ee 100644
--- a/src/core/CL/kernels/CLWidthConcatenate4TensorsKernel.cpp
+++ b/src/core/CL/kernels/CLWidthConcatenate4TensorsKernel.cpp
@@ -23,17 +23,16 @@
  */
 #include "arm_compute/core/CL/kernels/CLWidthConcatenate4TensorsKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/helpers/tensor_info.h"
-#include "arm_compute/core/utils/misc/Cast.h"
-#include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "src/core/utils/helpers/tensor_info.h"
+#include "support/Cast.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLWidthConcatenateLayerKernel.cpp b/src/core/CL/kernels/CLWidthConcatenateLayerKernel.cpp
index d40597fbb5..8b0aaf3227 100644
--- a/src/core/CL/kernels/CLWidthConcatenateLayerKernel.cpp
+++ b/src/core/CL/kernels/CLWidthConcatenateLayerKernel.cpp
@@ -25,13 +25,12 @@
 
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/Utils.h"
-#include "arm_compute/core/Window.h"
-#include "arm_compute/core/utils/misc/Cast.h"
-#include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/WindowHelpers.h"
+#include "support/Cast.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLWinogradFilterTransformKernel.cpp b/src/core/CL/kernels/CLWinogradFilterTransformKernel.cpp
index 4a1c48a258..7fab208221 100644
--- a/src/core/CL/kernels/CLWinogradFilterTransformKernel.cpp
+++ b/src/core/CL/kernels/CLWinogradFilterTransformKernel.cpp
@@ -23,10 +23,8 @@
  */
 #include "arm_compute/core/CL/kernels/CLWinogradFilterTransformKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/IAccessWindow.h"
@@ -36,6 +34,10 @@
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLWinogradInputTransformKernel.cpp b/src/core/CL/kernels/CLWinogradInputTransformKernel.cpp
index c4c2b08a81..15c239e849 100644
--- a/src/core/CL/kernels/CLWinogradInputTransformKernel.cpp
+++ b/src/core/CL/kernels/CLWinogradInputTransformKernel.cpp
@@ -23,10 +23,8 @@
  */
 #include "arm_compute/core/CL/kernels/CLWinogradInputTransformKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/CL/OpenCL.h"
 #include "arm_compute/core/Error.h"
@@ -34,6 +32,10 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 #include "support/StringSupport.h"
 
 using namespace arm_compute;
diff --git a/src/core/CL/kernels/CLWinogradOutputTransformKernel.cpp b/src/core/CL/kernels/CLWinogradOutputTransformKernel.cpp
index 19f61b19b3..8ae0255319 100644
--- a/src/core/CL/kernels/CLWinogradOutputTransformKernel.cpp
+++ b/src/core/CL/kernels/CLWinogradOutputTransformKernel.cpp
@@ -23,10 +23,8 @@
  */
 #include "arm_compute/core/CL/kernels/CLWinogradOutputTransformKernel.h"
 
-#include "arm_compute/core/AccessWindowStatic.h"
 #include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/IAccessWindow.h"
@@ -36,6 +34,10 @@
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/core/Window.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
+#include "src/core/AccessWindowStatic.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
 #include "support/StringSupport.h"
 
diff --git a/src/core/CL/kernels/CLYOLOLayerKernel.cpp b/src/core/CL/kernels/CLYOLOLayerKernel.cpp
index 132d5d1cd0..0c7588d740 100644
--- a/src/core/CL/kernels/CLYOLOLayerKernel.cpp
+++ b/src/core/CL/kernels/CLYOLOLayerKernel.cpp
@@ -24,17 +24,19 @@
 #include "arm_compute/core/CL/kernels/CLYOLOLayerKernel.h"
 
 #include "arm_compute/core/CL/CLHelpers.h"
+#include "arm_compute/core/CL/CLHelpers.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
-#include "arm_compute/core/CL/CLValidate.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Helpers.h"
 #include "arm_compute/core/IAccessWindow.h"
 #include "arm_compute/core/TensorInfo.h"
+#include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Window.h"
+#include "src/core/CL/CLValidate.h"
+#include "src/core/helpers/AutoConfiguration.h"
+#include "src/core/helpers/WindowHelpers.h"
 
-#include "arm_compute/core/CL/CLHelpers.h"
-#include "arm_compute/core/Types.h"
 #include "support/StringSupport.h"
 
 namespace arm_compute