IVGCVSW-6620 Update the async api to use ExecutionData
* ExecutionData holds a void* which can be assigned to data required
for execution in a backend. WorkingMemDescriptors are used in the Ref
backend which hold TensorHandles for inputs and outputs.
* Updated ExecuteAsync functions to take ExecutionData.
* Added CreateExecutionData and UpdateExectutionData to IBackendInternal.
* Streamlined experimental IWorkingMemHandle API by removing map related
function and unused m_workingMemDescriptorMap from WorkingMemHandle.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I54b0aab12872011743a141eb42dae200227769af
diff --git a/src/backends/reference/workloads/RefConvertFp32ToBf16Workload.hpp b/src/backends/reference/workloads/RefConvertFp32ToBf16Workload.hpp
index cd3cfa4..c1e57ec 100644
--- a/src/backends/reference/workloads/RefConvertFp32ToBf16Workload.hpp
+++ b/src/backends/reference/workloads/RefConvertFp32ToBf16Workload.hpp
@@ -1,5 +1,5 @@
//
-// Copyright © 2020 Arm Ltd. All rights reserved.
+// Copyright © 2022 Arm Ltd and Contributors. All rights reserved.
// SPDX-License-Identifier: MIT
//
@@ -16,7 +16,7 @@
public:
using Float32ToBFloat16Workload<ConvertFp32ToBf16QueueDescriptor>::Float32ToBFloat16Workload;
void Execute() const override;
- void ExecuteAsync(WorkingMemDescriptor& workingMemDescriptor) override;
+ void ExecuteAsync(ExecutionData& executionData) override;
private:
void Execute(std::vector<ITensorHandle*> inputs, std::vector<ITensorHandle*> outputs) const;
};