diff options
author | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-04-22 21:13:21 +0100 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-05-18 14:48:39 +0000 |
commit | 856f66e6c61b77d03f754cd0fa8439891f0e4aca (patch) | |
tree | f9379cd0853ac407109e54c3d53b385ceee066c2 /src/runtime/ITensorAllocator.cpp | |
parent | 37f4b2ef1ea225a90ccb563fcb2c08f8fb0fb5d5 (diff) | |
download | ComputeLibrary-856f66e6c61b77d03f754cd0fa8439891f0e4aca.tar.gz |
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>
Diffstat (limited to 'src/runtime/ITensorAllocator.cpp')
-rw-r--r-- | src/runtime/ITensorAllocator.cpp | 18 |
1 files changed, 10 insertions, 8 deletions
diff --git a/src/runtime/ITensorAllocator.cpp b/src/runtime/ITensorAllocator.cpp index ae648d4dd2..fe3d2804cb 100644 --- a/src/runtime/ITensorAllocator.cpp +++ b/src/runtime/ITensorAllocator.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016-2018 Arm Limited. + * Copyright (c) 2016-2021 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -30,25 +30,27 @@ using namespace arm_compute; -ITensorAllocator::ITensorAllocator() - : _info(), _alignment(0) +void ITensorAllocator::init(const TensorInfo &input, size_t alignment) { + _info_owned = input; + _info_external = nullptr; + _alignment = alignment; } -void ITensorAllocator::init(const TensorInfo &input, size_t alignment) +void ITensorAllocator::soft_init(TensorInfo &input, size_t alignment) { - _info = input; - _alignment = alignment; + _info_external = &input; + _alignment = alignment; } TensorInfo &ITensorAllocator::info() { - return _info; + return (_info_external != nullptr) ? *_info_external : _info_owned; } const TensorInfo &ITensorAllocator::info() const { - return _info; + return (_info_external != nullptr) ? *_info_external : _info_owned; } size_t ITensorAllocator::alignment() const |