Use the stable CKW API in the GPU dynamic fusion backend

- Refactor all kernels to work with the CKW stable API
- Add support for sub-tile in the op_load/op_store CKW operator
- Fix mismatch in resize
- Add comments in all kernels written with CKW to help developers
understand the structure of the code
- Add texture image support in depthwise convolution written with CKW
- Add support for different block sizes in depthwise convolution
- Remove the use of the dynamic fusion helper functions.
- Add support for floor in the op_unary() of CKW

Resolves: COMPMID-6708, COMPMID-6743, COMPMID-6530

Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>

Change-Id: I8104ce4d04a3138a1aeb0b84940e1f1c89e76069
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10914
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 1 insertions, 28 deletions

diff --git a/tests/validation/dynamic_fusion/gpu/cl/Pool2d.cpp b/tests/validation/dynamic_fusion/gpu/cl/Pool2d.cpp
index f894ce3cf1..e537826c71 100644
--- a/tests/validation/dynamic_fusion/gpu/cl/Pool2d.cpp
+++ b/tests/validation/dynamic_fusion/gpu/cl/Pool2d.cpp
@@ -55,17 +55,11 @@ const auto PoolingLayerDatasetFP =
                     framework::dataset::make("Stride", {Size2D(1, 1), Size2D(2, 1), Size2D(5, 7)})),
             framework::dataset::make("ExcludePadding", {true}));
 
-const auto pool_fp_mixed_precision_dataset = framework::dataset::make("FpMixedPrecision", {true, false});
-
 template <typename T>
 using DynamicFusionGpuPool2dFixture = DynamicFusionGpuPool2dValidationFixture<CLTensor, CLAccessor, GpuPool2d, T>;
 
 template <typename T>
 using DFSpecialGpuPool2dFixture = DynamicFusionGpuPool2dSpecialValidationFixture<CLTensor, CLAccessor, GpuPool2d, T>;
-
-template <typename T>
-using DFPoolMixedPrecisionFixture =
-    DynamicFusionGpuPool2dMixedPrecisionValidationFixture<CLTensor, CLAccessor, GpuPool2d, T>;
 // *INDENT-OFF*
 // clang-format off
 
@@ -92,7 +86,7 @@ DATA_TEST_CASE(Validate, framework::DatasetMode::ALL, zip(zip(
     GpuWorkloadSketch sketch{ &context };
 
     // Declare GpuPool2d settings
-    const GpuPool2dSettings &settings = GpuPool2dSettings().mixed_precision(false);
+    const GpuPool2dSettings &settings = GpuPool2dSettings();
 
     // Validate Pool2d Configuration
     auto                   src_info    = context.create_tensor_info(input_info);
@@ -175,27 +169,6 @@ TEST_SUITE_END() // GlobalPooling
 TEST_SUITE_END() // FP32
 
 TEST_SUITE(FP16)
-FIXTURE_DATA_TEST_CASE(RunSmall,
-                       DFPoolMixedPrecisionFixture<half>,
-                       framework::DatasetMode::PRECOMMIT,
-                       combine(combine(combine(datasets::SmallNoneUnitShapes(), PoolingLayerDatasetFP),
-                                       framework::dataset::make("DataType", DataType::F16)),
-                               pool_fp_mixed_precision_dataset))
-{
-    // Validate output
-    validate(CLAccessor(_target), _reference, tolerance_f16);
-}
-FIXTURE_DATA_TEST_CASE(RunLarge,
-                       DFPoolMixedPrecisionFixture<half>,
-                       framework::DatasetMode::NIGHTLY,
-                       combine(combine(combine(datasets::LargeShapes(), PoolingLayerDatasetFP),
-                                       framework::dataset::make("DataType", DataType::F16)),
-                               pool_fp_mixed_precision_dataset))
-{
-    // Validate output
-    validate(CLAccessor(_target), _reference, tolerance_f16);
-}
-
 TEST_SUITE(GlobalPooling)
 FIXTURE_DATA_TEST_CASE(
     RunSmall,