Port CLGEMM to memory injecting interface

Moves the following kernels:
 - CLGEMMMatrixMultiplyKernel
 - CLGEMMMatrixMultiplyNativeKernel
 - CLGEMMMatrixMultipluReshapedKernel
 - CLGEMMMatrixMultiplyReshapedOnlyRHSKernel

 Moves the following functions
 - CLGEMM

Introduces facilities to easy handling of auxiliary temporary buffers
under then new run interface. Such are:
 - CLAuxTensorHandler: That allows wrapping of workspace buffers memory
 to CLBuffer objects
 - Ability to inject TensorInfo to allocator without transferring
 ownership. This reduce the copy overhead if needed.

Resolves: COMPMID-4188

Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I7055435d831b05b749b26302082e4ac45f26dfb0
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5498
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 8 insertions, 2 deletions

diff --git a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h
index e7f4cb9d01..e5de45c34f 100644
--- a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h
+++ b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h
@@ -41,7 +41,13 @@ class CLGEMMLowpOffsetContributionKernel;
 class CLGEMMLowpOffsetContributionOutputStageKernel;
 class CLGEMMLowpMatrixAReductionKernel;
 class CLGEMMLowpMatrixBReductionKernel;
-class CLGEMMReshapeRHSMatrixKernel;
+namespace opencl
+{
+namespace kernels
+{
+class ClGemmReshapeRhsMatrixKernel;
+} // namespace kernels
+} // namespace opencl
 
 /** Basic function to execute GEMMLowpMatrixMultiplyCore on OpenCL. */
 class CLGEMMLowpMatrixMultiplyCore : public IFunction
@@ -140,7 +146,7 @@ private:
     std::unique_ptr<CLDepthConvertLayerKernel>                     _weights_to_qasymm8;
     std::unique_ptr<CLGEMMLowpMatrixMultiplyNativeKernel>          _mm_native_kernel;
     std::unique_ptr<CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel> _mm_reshaped_only_rhs_kernel;
-    std::unique_ptr<CLGEMMReshapeRHSMatrixKernel>                  _mtx_b_reshape_kernel;
+    std::unique_ptr<opencl::kernels::ClGemmReshapeRhsMatrixKernel> _mtx_b_reshape_kernel;
     std::unique_ptr<CLGEMMLowpMatrixAReductionKernel>              _mtx_a_reduction_kernel;
     std::unique_ptr<CLGEMMLowpMatrixBReductionKernel>              _mtx_b_reduction_kernel;
     std::unique_ptr<CLGEMMLowpOffsetContributionKernel>            _offset_contribution_kernel;