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>
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h
index 100100b..06a73f1 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -32,7 +32,9 @@
/** OpenCL kernel to multiply matrices when both the input matrices LHS (input0) and RHS (input1) have been reshaped
*
- * @note The input matrices @p input0 and @p input1 must be reshaped through @ref CLGEMMReshapeLHSMatrixKernel and @ref CLGEMMReshapeRHSMatrixKernel
+ * @note The input matrices @p input0 and @p input1 must be reshaped through:
+ * - @ref opencl::kernels::ClGemmReshapeLhsMatrixKernel
+ * - @ref opencl::kernels::ClGemmReshapeRhsMatrixKernel
*/
class CLGEMMLowpMatrixMultiplyReshapedKernel : public ICLKernel
{