Add output operator for dynamic fusion
* The output of the fused operator must be explicitly specified
using GpuOutput operator.
* Any temporary tensors used to connect the output of an operator
to the input of another operator will be marked as no-alloc
and won't be allocated as a tensor in the memory.
Resolves: COMPMID-5771
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I5ae8e800f8f737db23a055a92b01c4f1d78c3bb8
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8794
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/dynamic_fusion/runtime/gpu/cl/ClWorkloadRuntime.cpp b/src/dynamic_fusion/runtime/gpu/cl/ClWorkloadRuntime.cpp
index 36168d1..7e427fe 100644
--- a/src/dynamic_fusion/runtime/gpu/cl/ClWorkloadRuntime.cpp
+++ b/src/dynamic_fusion/runtime/gpu/cl/ClWorkloadRuntime.cpp
@@ -132,10 +132,11 @@
ARM_COMPUTE_ERROR_ON(tensor_info.id() != t_id);
const auto aux_memory_info = workload_arg->memory_descriptor()->aux_memory_info;
tensor_object = aux_tensors->add_aux_tensor(tensor_info, aux_memory_info);
- }
- if(tensor_object == nullptr)
- {
- return ARM_COMPUTE_CREATE_ERROR(ErrorCode::RUNTIME_ERROR, "Failed to construct an auxiliary tensor");
+
+ if(tensor_object == nullptr)
+ {
+ return ARM_COMPUTE_CREATE_ERROR(ErrorCode::RUNTIME_ERROR, "Failed to construct an auxiliary tensor");
+ }
}
}
return Status{};