diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-07-31 22:21:38 +0100 |
|---|---|---|
| committer | Michalis Spyrou <michalis.spyrou@arm.com> | 2020-08-05 09:13:13 +0000 |
| commit | 0499dff9293a86d3d53f72fed0a38b2823563674 (patch) | |
| tree | bb76735e53f46cc8e362a7b528e549cdc7a2e346 /arm_compute/runtime/CL/CLScheduler.h | |
| parent | ac4c03042d7a3020f87cea641e69aa38a684ddd7 (diff) | |
| download | ComputeLibrary-0499dff9293a86d3d53f72fed0a38b2823563674.tar.gz | |
COMPMID-3392: Collapse TensorMaps into a single TensorPack
Collapse InputTensorMap and OutputTensorMap to a single TensorPack
mechanism.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: Ie2fdfc6b07d84ad589169ec99ca64fcf45a00bec
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/253783
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3641
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Sheri Zhang <sheri.zhang@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/CLScheduler.h')
| -rw-r--r-- | arm_compute/runtime/CL/CLScheduler.h | 7 |
1 files changed, 3 insertions, 4 deletions
diff --git a/arm_compute/runtime/CL/CLScheduler.h b/arm_compute/runtime/CL/CLScheduler.h index 93595c65c7..8a22832792 100644 --- a/arm_compute/runtime/CL/CLScheduler.h +++ b/arm_compute/runtime/CL/CLScheduler.h @@ -76,11 +76,10 @@ public: /** Schedule the execution of the passed kernel if possible. * * @param[in] kernel Kernel to execute. - * @param[in] inputs Vector containing the input tensors. - * @param[in] outputs Vector containing the output tensors. + * @param[in] tensors Vector containing the tensors to operate on. * @param[in] flush (Optional) Specifies if the command queue will be flushed after running the kernel. */ - void enqueue_op(ICLKernel &kernel, const InputTensorMap &inputs, const OutputTensorMap &outputs, bool flush = true); + void enqueue_op(ICLKernel &kernel, ITensorPack &tensors, bool flush = true); /** Initialises the context and command queue to be used by the scheduler. * @@ -152,7 +151,7 @@ public: bool is_initialised() const; private: - void enqueue_common(ICLKernel &kernel, const InputTensorMap &inputs, const OutputTensorMap &outputs, bool flush); + void enqueue_common(ICLKernel &kernel, ITensorPack &tensors, bool flush); /** Flag to ensure symbols initialisation is happening before Scheduler creation */ static std::once_flag _initialize_symbols; |