diff options
| author | Giorgio Arena <giorgio.arena@arm.com> | 2021-08-20 15:24:03 +0100 |
|---|---|---|
| committer | Giorgio Arena <giorgio.arena@arm.com> | 2021-08-24 11:46:13 +0000 |
| commit | 9c67d3883adaa8a65e3567579cf99937deaab21a (patch) | |
| tree | e3b11c5918b4121e8e7d5ad728847ce74a8ed77f /arm_compute/graph/backends/NEON/NEDeviceBackend.h | |
| parent | 87a74effff65f6fa1b0e565818e02c3b414ae1cf (diff) | |
| download | ComputeLibrary-9c67d3883adaa8a65e3567579cf99937deaab21a.tar.gz | |
Remove map/unmap overhead for input/output accessor when using DummyAccessor
Don't map/unmap when the tensor data is not accessed in the input or output accessor.
This is so to avoid measuring CPU overhead when benchmarking on the GPU backend.
Resolve COMPMID-4712
Change-Id: I5baba1b93e7a51fe13525bcce6c0cfdecb14493e
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6140
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/graph/backends/NEON/NEDeviceBackend.h')
| -rw-r--r-- | arm_compute/graph/backends/NEON/NEDeviceBackend.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/arm_compute/graph/backends/NEON/NEDeviceBackend.h b/arm_compute/graph/backends/NEON/NEDeviceBackend.h index 0b343c0d67..9cb37d4553 100644 --- a/arm_compute/graph/backends/NEON/NEDeviceBackend.h +++ b/arm_compute/graph/backends/NEON/NEDeviceBackend.h @@ -52,6 +52,7 @@ public: Status validate_node(INode &node) override; std::shared_ptr<arm_compute::IMemoryManager> create_memory_manager(MemoryManagerAffinity affinity) override; std::shared_ptr<arm_compute::IWeightsManager> create_weights_manager() override; + void sync() override; private: Allocator _allocator; /**< Backend allocator */ |