Move CPU/GPU files from Core/Runtime to the respective backend folders

Legacy structure contained two libraries core/runtime with two backends
in each.
We reduce the core/runtime libraries to a single library thus merging
the backend files

Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I69545765fe7a730368105cdbd067d3135ec7a174
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6155
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>

35 files changed, 41 insertions, 41 deletions

diff --git a/src/runtime/CL/functions/CLActivationLayer.cpp b/src/runtime/CL/functions/CLActivationLayer.cpp
index 9c71b2aa7d..bf69868663 100644
--- a/src/runtime/CL/functions/CLActivationLayer.cpp
+++ b/src/runtime/CL/functions/CLActivationLayer.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/runtime/CL/CLRuntimeContext.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClActivation.h"
+#include "src/gpu/cl/operators/ClActivation.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLCast.cpp b/src/runtime/CL/functions/CLCast.cpp
index 53256ebed4..f9403afcb8 100644
--- a/src/runtime/CL/functions/CLCast.cpp
+++ b/src/runtime/CL/functions/CLCast.cpp
@@ -27,7 +27,7 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClCast.h"
+#include "src/gpu/cl/operators/ClCast.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLConcatenateLayer.cpp b/src/runtime/CL/functions/CLConcatenateLayer.cpp
index ea96e45bf8..8ab50beacd 100644
--- a/src/runtime/CL/functions/CLConcatenateLayer.cpp
+++ b/src/runtime/CL/functions/CLConcatenateLayer.cpp
@@ -25,7 +25,7 @@
 
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClConcatenate.h"
+#include "src/gpu/cl/operators/ClConcatenate.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLConvertFullyConnectedWeights.cpp b/src/runtime/CL/functions/CLConvertFullyConnectedWeights.cpp
index 8189eee402..7780c0a444 100644
--- a/src/runtime/CL/functions/CLConvertFullyConnectedWeights.cpp
+++ b/src/runtime/CL/functions/CLConvertFullyConnectedWeights.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClConvertFullyConnectedWeights.h"
+#include "src/gpu/cl/operators/ClConvertFullyConnectedWeights.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLConvolutionLayer.cpp b/src/runtime/CL/functions/CLConvolutionLayer.cpp
index b295a274bd..1f715d246d 100644
--- a/src/runtime/CL/functions/CLConvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLConvolutionLayer.cpp
@@ -30,7 +30,7 @@
 #include "arm_compute/runtime/CL/functions/CLFFTConvolutionLayer.h"
 #include "src/core/CL/ICLKernel.h"
 #include "src/core/helpers/MemoryHelpers.h"
-#include "src/runtime/gpu/cl/operators/ClConv2d.h"
+#include "src/gpu/cl/operators/ClConv2d.h"
 #include "support/Cast.h"
 
 namespace arm_compute
diff --git a/src/runtime/CL/functions/CLCopy.cpp b/src/runtime/CL/functions/CLCopy.cpp
index 98916bf38a..e8aaf85876 100644
--- a/src/runtime/CL/functions/CLCopy.cpp
+++ b/src/runtime/CL/functions/CLCopy.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClCopy.h"
+#include "src/gpu/cl/operators/ClCopy.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLCrop.cpp b/src/runtime/CL/functions/CLCrop.cpp
index 20cab4df5f..ff30837506 100644
--- a/src/runtime/CL/functions/CLCrop.cpp
+++ b/src/runtime/CL/functions/CLCrop.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClCrop.h"
+#include "src/gpu/cl/operators/ClCrop.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLDepthConvertLayer.cpp b/src/runtime/CL/functions/CLDepthConvertLayer.cpp
index 6aa370b23c..5930ff19f8 100644
--- a/src/runtime/CL/functions/CLDepthConvertLayer.cpp
+++ b/src/runtime/CL/functions/CLDepthConvertLayer.cpp
@@ -27,7 +27,7 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClCast.h"
+#include "src/gpu/cl/operators/ClCast.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLDequantizationLayer.cpp b/src/runtime/CL/functions/CLDequantizationLayer.cpp
index 3b104017e7..e11802ed1b 100644
--- a/src/runtime/CL/functions/CLDequantizationLayer.cpp
+++ b/src/runtime/CL/functions/CLDequantizationLayer.cpp
@@ -27,7 +27,7 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClDequantize.h"
+#include "src/gpu/cl/operators/ClDequantize.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLDirectConvolutionLayer.cpp b/src/runtime/CL/functions/CLDirectConvolutionLayer.cpp
index 907e69d8d7..7bbb7e8e4a 100644
--- a/src/runtime/CL/functions/CLDirectConvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLDirectConvolutionLayer.cpp
@@ -28,8 +28,8 @@
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Validate.h"
 #include "arm_compute/runtime/CL/CLScheduler.h"
-#include "src/runtime/gpu/cl/operators/ClActivation.h"
-#include "src/runtime/gpu/cl/operators/ClDirectConv2d.h"
+#include "src/gpu/cl/operators/ClActivation.h"
+#include "src/gpu/cl/operators/ClDirectConv2d.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLElementwiseOperations.cpp b/src/runtime/CL/functions/CLElementwiseOperations.cpp
index 60c699cbb8..936b37fb31 100644
--- a/src/runtime/CL/functions/CLElementwiseOperations.cpp
+++ b/src/runtime/CL/functions/CLElementwiseOperations.cpp
@@ -28,9 +28,9 @@
 #include "arm_compute/core/Types.h"
 #include "src/core/CL/ICLKernel.h"
 
-#include "src/runtime/gpu/cl/operators/ClAdd.h"
-#include "src/runtime/gpu/cl/operators/ClElementwiseOperations.h"
-#include "src/runtime/gpu/cl/operators/ClSub.h"
+#include "src/gpu/cl/operators/ClAdd.h"
+#include "src/gpu/cl/operators/ClElementwiseOperations.h"
+#include "src/gpu/cl/operators/ClSub.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLElementwiseUnaryLayer.cpp b/src/runtime/CL/functions/CLElementwiseUnaryLayer.cpp
index a45dd6f9a6..9dcd2d1891 100644
--- a/src/runtime/CL/functions/CLElementwiseUnaryLayer.cpp
+++ b/src/runtime/CL/functions/CLElementwiseUnaryLayer.cpp
@@ -26,7 +26,7 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClElementwiseUnary.h"
+#include "src/gpu/cl/operators/ClElementwiseUnary.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLFill.cpp b/src/runtime/CL/functions/CLFill.cpp
index b22d79fea4..6019a84aba 100644
--- a/src/runtime/CL/functions/CLFill.cpp
+++ b/src/runtime/CL/functions/CLFill.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClFill.h"
+#include "src/gpu/cl/operators/ClFill.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLFlattenLayer.cpp b/src/runtime/CL/functions/CLFlattenLayer.cpp
index 9563055276..32fc37552c 100644
--- a/src/runtime/CL/functions/CLFlattenLayer.cpp
+++ b/src/runtime/CL/functions/CLFlattenLayer.cpp
@@ -30,7 +30,7 @@
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 #include "src/core/CL/ICLKernel.h"
 #include "src/core/helpers/AutoConfiguration.h"
-#include "src/runtime/gpu/cl/operators/ClFlatten.h"
+#include "src/gpu/cl/operators/ClFlatten.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLFloor.cpp b/src/runtime/CL/functions/CLFloor.cpp
index 4c5e482b10..8739e1803e 100644
--- a/src/runtime/CL/functions/CLFloor.cpp
+++ b/src/runtime/CL/functions/CLFloor.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClFloor.h"
+#include "src/gpu/cl/operators/ClFloor.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLFullyConnectedLayer.cpp b/src/runtime/CL/functions/CLFullyConnectedLayer.cpp
index 4f9759c590..02b2042a6c 100644
--- a/src/runtime/CL/functions/CLFullyConnectedLayer.cpp
+++ b/src/runtime/CL/functions/CLFullyConnectedLayer.cpp
@@ -26,7 +26,7 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/runtime/CL/CLScheduler.h"
 #include "src/core/helpers/MemoryHelpers.h"
-#include "src/runtime/gpu/cl/operators/ClFullyConnected.h"
+#include "src/gpu/cl/operators/ClFullyConnected.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLGEMM.cpp b/src/runtime/CL/functions/CLGEMM.cpp
index 14b0633e09..cc6689c504 100644
--- a/src/runtime/CL/functions/CLGEMM.cpp
+++ b/src/runtime/CL/functions/CLGEMM.cpp
@@ -32,7 +32,7 @@
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/runtime/CL/functions/CLGEMM.h"
 #include "src/core/helpers/MemoryHelpers.h"
-#include "src/runtime/gpu/cl/operators/ClGemm.h"
+#include "src/gpu/cl/operators/ClGemm.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLGEMMConvolutionLayer.cpp b/src/runtime/CL/functions/CLGEMMConvolutionLayer.cpp
index 563dbd414f..837527bac3 100644
--- a/src/runtime/CL/functions/CLGEMMConvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLGEMMConvolutionLayer.cpp
@@ -32,7 +32,7 @@
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
 #include "arm_compute/runtime/CL/CLScheduler.h"
 #include "src/core/helpers/MemoryHelpers.h"
-#include "src/runtime/gpu/cl/operators/ClGemmConv2d.h"
+#include "src/gpu/cl/operators/ClGemmConv2d.h"
 #include "support/Cast.h"
 
 #include <cmath>
diff --git a/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp b/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp
index 1ae2dfbad6..d9029478a1 100644
--- a/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp
+++ b/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp
@@ -37,7 +37,7 @@
 #include "arm_compute/runtime/IMemoryManager.h"
 #include "src/core/helpers/MemoryHelpers.h"
 
-#include "src/runtime/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.h"
+#include "src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp b/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp
index 94d4c33fa2..6feed0d713 100644
--- a/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp
+++ b/src/runtime/CL/functions/CLGEMMLowpOutputStage.cpp
@@ -32,7 +32,7 @@
 #include "arm_compute/core/Types.h"
 
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClGemmLowpOutputStage.h"
+#include "src/gpu/cl/operators/ClGemmLowpOutputStage.h"
 
 #include <algorithm>
 
diff --git a/src/runtime/CL/functions/CLLSTMLayer.cpp b/src/runtime/CL/functions/CLLSTMLayer.cpp
index 9754bdcb82..0122162073 100644
--- a/src/runtime/CL/functions/CLLSTMLayer.cpp
+++ b/src/runtime/CL/functions/CLLSTMLayer.cpp
@@ -30,7 +30,7 @@
 #include "arm_compute/core/utils/quantization/AsymmHelpers.h"
 #include "arm_compute/runtime/CL/CLScheduler.h"
 #include "src/core/CL/kernels/CLFillBorderKernel.h"
-#include "src/core/gpu/cl/kernels/ClTransposeKernel.h"
+#include "src/gpu/cl/kernels/ClTransposeKernel.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLLogicalAnd.cpp b/src/runtime/CL/functions/CLLogicalAnd.cpp
index 98c98abed5..306957a8d1 100644
--- a/src/runtime/CL/functions/CLLogicalAnd.cpp
+++ b/src/runtime/CL/functions/CLLogicalAnd.cpp
@@ -23,7 +23,7 @@
  */
 #include "arm_compute/runtime/CL/functions/CLLogicalAnd.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "src/core/gpu/cl/kernels/ClElementwiseKernel.h"
+#include "src/gpu/cl/kernels/ClElementwiseKernel.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLLogicalNot.cpp b/src/runtime/CL/functions/CLLogicalNot.cpp
index 388d2bce86..a0504d7852 100644
--- a/src/runtime/CL/functions/CLLogicalNot.cpp
+++ b/src/runtime/CL/functions/CLLogicalNot.cpp
@@ -26,7 +26,7 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClLogicalNot.h"
+#include "src/gpu/cl/operators/ClLogicalNot.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLLogicalOr.cpp b/src/runtime/CL/functions/CLLogicalOr.cpp
index 897963ab50..63524213f7 100644
--- a/src/runtime/CL/functions/CLLogicalOr.cpp
+++ b/src/runtime/CL/functions/CLLogicalOr.cpp
@@ -23,7 +23,7 @@
  */
 #include "arm_compute/runtime/CL/functions/CLLogicalOr.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "src/core/gpu/cl/kernels/ClElementwiseKernel.h"
+#include "src/gpu/cl/kernels/ClElementwiseKernel.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLPReluLayer.cpp b/src/runtime/CL/functions/CLPReluLayer.cpp
index bb7aff218d..186e7b4ba2 100644
--- a/src/runtime/CL/functions/CLPReluLayer.cpp
+++ b/src/runtime/CL/functions/CLPReluLayer.cpp
@@ -24,8 +24,8 @@
 #include "arm_compute/runtime/CL/functions/CLPReluLayer.h"
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
-#include "src/core/gpu/cl/IClKernel.h"
-#include "src/runtime/gpu/cl/operators/ClPRelu.h"
+#include "src/gpu/cl/IClKernel.h"
+#include "src/gpu/cl/operators/ClPRelu.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLPermute.cpp b/src/runtime/CL/functions/CLPermute.cpp
index c1da2a9eca..556e943152 100644
--- a/src/runtime/CL/functions/CLPermute.cpp
+++ b/src/runtime/CL/functions/CLPermute.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClPermute.h"
+#include "src/gpu/cl/operators/ClPermute.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLPixelWiseMultiplication.cpp b/src/runtime/CL/functions/CLPixelWiseMultiplication.cpp
index 932659268d..9d91e58367 100644
--- a/src/runtime/CL/functions/CLPixelWiseMultiplication.cpp
+++ b/src/runtime/CL/functions/CLPixelWiseMultiplication.cpp
@@ -26,7 +26,7 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/runtime/CL/CLScheduler.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClMul.h"
+#include "src/gpu/cl/operators/ClMul.h"
 
 #include <utility>
 
diff --git a/src/runtime/CL/functions/CLPoolingLayer.cpp b/src/runtime/CL/functions/CLPoolingLayer.cpp
index 7ba911c342..0ebce318fa 100644
--- a/src/runtime/CL/functions/CLPoolingLayer.cpp
+++ b/src/runtime/CL/functions/CLPoolingLayer.cpp
@@ -26,7 +26,7 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClPool2d.h"
+#include "src/gpu/cl/operators/ClPool2d.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLQLSTMLayer.cpp b/src/runtime/CL/functions/CLQLSTMLayer.cpp
index 5df895a91c..6ddf555b5c 100644
--- a/src/runtime/CL/functions/CLQLSTMLayer.cpp
+++ b/src/runtime/CL/functions/CLQLSTMLayer.cpp
@@ -32,8 +32,8 @@
 #include "arm_compute/runtime/CL/CLScheduler.h"
 #include "src/core/CL/kernels/CLFillBorderKernel.h"
 #include "src/core/CL/kernels/CLQLSTMLayerNormalizationKernel.h"
-#include "src/core/gpu/cl/kernels/ClGemmLowpReductionKernel.h"
 #include "src/core/helpers/WindowHelpers.h"
+#include "src/gpu/cl/kernels/ClGemmLowpReductionKernel.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLQuantizationLayer.cpp b/src/runtime/CL/functions/CLQuantizationLayer.cpp
index e6451b2eb4..b249bdd1db 100644
--- a/src/runtime/CL/functions/CLQuantizationLayer.cpp
+++ b/src/runtime/CL/functions/CLQuantizationLayer.cpp
@@ -26,7 +26,7 @@
 #include "arm_compute/core/CL/CLKernelLibrary.h"
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClQuantize.h"
+#include "src/gpu/cl/operators/ClQuantize.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLReshapeLayer.cpp b/src/runtime/CL/functions/CLReshapeLayer.cpp
index 060eddb96c..c51a3298c1 100644
--- a/src/runtime/CL/functions/CLReshapeLayer.cpp
+++ b/src/runtime/CL/functions/CLReshapeLayer.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClReshape.h"
+#include "src/gpu/cl/operators/ClReshape.h"
 
 /** [CLReshapeLayer snippet] **/
 namespace arm_compute
diff --git a/src/runtime/CL/functions/CLScale.cpp b/src/runtime/CL/functions/CLScale.cpp
index cbd93c1086..5b78989bfa 100644
--- a/src/runtime/CL/functions/CLScale.cpp
+++ b/src/runtime/CL/functions/CLScale.cpp
@@ -27,7 +27,7 @@
 #include "arm_compute/core/CL/ICLTensor.h"
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClScale.h"
+#include "src/gpu/cl/operators/ClScale.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLSoftmaxLayer.cpp b/src/runtime/CL/functions/CLSoftmaxLayer.cpp
index de58bf1b02..d52352fc8d 100644
--- a/src/runtime/CL/functions/CLSoftmaxLayer.cpp
+++ b/src/runtime/CL/functions/CLSoftmaxLayer.cpp
@@ -28,10 +28,10 @@
 #include "arm_compute/core/KernelDescriptors.h"
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Utils.h"
-#include "src/core/gpu/cl/kernels/ClSoftmaxKernel.h"
 #include "src/core/helpers/MemoryHelpers.h"
-#include "src/runtime/gpu/cl/operators/ClPermute.h"
-#include "src/runtime/gpu/cl/operators/ClSoftmax.h"
+#include "src/gpu/cl/kernels/ClSoftmaxKernel.h"
+#include "src/gpu/cl/operators/ClPermute.h"
+#include "src/gpu/cl/operators/ClSoftmax.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLTranspose.cpp b/src/runtime/CL/functions/CLTranspose.cpp
index 142cf73259..e63c92eeb4 100644
--- a/src/runtime/CL/functions/CLTranspose.cpp
+++ b/src/runtime/CL/functions/CLTranspose.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/Validate.h"
 #include "src/core/CL/ICLKernel.h"
-#include "src/runtime/gpu/cl/operators/ClTranspose.h"
+#include "src/gpu/cl/operators/ClTranspose.h"
 
 namespace arm_compute
 {
diff --git a/src/runtime/CL/functions/CLWinogradConvolutionLayer.cpp b/src/runtime/CL/functions/CLWinogradConvolutionLayer.cpp
index fa01c914c5..b416d0fcf1 100644
--- a/src/runtime/CL/functions/CLWinogradConvolutionLayer.cpp
+++ b/src/runtime/CL/functions/CLWinogradConvolutionLayer.cpp
@@ -28,7 +28,7 @@
 #include "arm_compute/core/KernelDescriptors.h"
 #include "src/core/CL/ICLKernel.h"
 #include "src/core/helpers/MemoryHelpers.h"
-#include "src/runtime/gpu/cl/operators/ClWinogradConv2d.h"
+#include "src/gpu/cl/operators/ClWinogradConv2d.h"
 #include "support/Cast.h"
 
 namespace arm_compute