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, 17 insertions, 11 deletions

diff --git a/compute_kernel_writer/src/cl/helpers/CLMemoryOpImage2dHelper.h b/compute_kernel_writer/src/cl/helpers/CLMemoryOpImage2dHelper.h
index fd9b097a24..6c42c132d9 100644
--- a/compute_kernel_writer/src/cl/helpers/CLMemoryOpImage2dHelper.h
+++ b/compute_kernel_writer/src/cl/helpers/CLMemoryOpImage2dHelper.h
@@ -35,6 +35,8 @@ namespace ckw
 // Forward Declarations
 class CLKernelWriter;
 class CLTile;
+template <class CLTile>
+class TileView;
 enum class MemoryOperation;
 
 /** Helper class to write memory operations (like load/store) in OpenCL for Image2d type */
@@ -42,29 +44,33 @@ class CLMemoryOpImage2dHelper : public ICLMemoryOpHelper
 {
 public:
     /** Constructor similar to @ref ICLMemoryOpHelper() */
-    CLMemoryOpImage2dHelper(CLKernelWriter *writer, ITensor *tensor, TensorSampler *sampler, MemoryOperation op)
-        : ICLMemoryOpHelper(writer, tensor, sampler, op)
+    CLMemoryOpImage2dHelper(CLKernelWriter         *writer,
+                            ITensor                *tensor,
+                            TensorSampler          *sampler,
+                            MemoryOperation         op,
+                            const TileView<CLTile> &dst)
+        : ICLMemoryOpHelper(writer, tensor, sampler, op, dst)
     {
     }
 
     /** Copy constructor */
-    CLMemoryOpImage2dHelper(const CLMemoryOpImage2dHelper &) = default;
+    CLMemoryOpImage2dHelper(const CLMemoryOpImage2dHelper &) = delete;
 
     /** Assignment operator overload */
-    CLMemoryOpImage2dHelper &operator=(const CLMemoryOpImage2dHelper &) = default;
+    CLMemoryOpImage2dHelper &operator=(const CLMemoryOpImage2dHelper &) = delete;
 
     // Methods overridden
-    void initialize(const CLTile *dst, const CLTile *x, const CLTile *z, const CLTile *b) override;
+    void initialize(const CLTile *x, const CLTile *z, const CLTile *b) override;
     void write_row(int32_t row_id, const std::string &coord_y) override;
     void finalize() override;
 
 private:
-    static bool validate(const CLKernelWriter *writer,
-                         const ITensor        *tensor,
-                         const TensorSampler  *sampler,
-                         const Tensor3dMapper *mapper,
-                         MemoryOperation       op,
-                         const CLTile         *dst);
+    static bool validate(const CLKernelWriter   *writer,
+                         const ITensor          *tensor,
+                         const TensorSampler    *sampler,
+                         const Tensor3dMapper   *mapper,
+                         MemoryOperation         op,
+                         const TileView<CLTile> &dst);
 
     void out_of_bound_initialize_y(const std::string &coord);
     void out_of_bound_finalize_y();