Add multiple output support for dynamic fusion

* The dependency graph now can schedule any acyclic graph into
  a sequential list of operators. This is needed as the output
  operators now form branches in the graph.
* Fix the definition of input, output and intermediate tensors
  in GpuKernelComponentGroup to support non-linear but sequential
  list of operators.
* Add constraint on GpuOperatorGroup to enforce strictly linear
  fusion style, but allow output operator as the only form of
  branch.

Resolves: COMPMID-5771
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I68de3a31a2456145081f0a397e4e61dd66327682
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8823
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 2 insertions, 2 deletions

diff --git a/src/dynamic_fusion/sketch/gpu/operators/GpuOutput.cpp b/src/dynamic_fusion/sketch/gpu/operators/GpuOutput.cpp
index 017536df6c..60c2281433 100644
--- a/src/dynamic_fusion/sketch/gpu/operators/GpuOutput.cpp
+++ b/src/dynamic_fusion/sketch/gpu/operators/GpuOutput.cpp
@@ -81,7 +81,7 @@ Status GpuOutput::validate_op(const GpuWorkloadSketch &sketch,
 
     const auto group = sketch.implementation().operator_group();
     const auto op = group.new_operator(operator_type, tensors);
-    const auto success = group.try_add_operator(op);
+    const auto success = group.try_add_operator(op, true);
 
     ARM_COMPUTE_RETURN_ERROR_ON_MSG(!success, "This operator cannot be fused into the workload.");
     ARM_COMPUTE_UNUSED(success);
@@ -133,7 +133,7 @@ void GpuOutput::create_op(GpuWorkloadSketch &sketch,
     tensors.add_const_tensor(ACL_DST_0, dst);
 
     const Operator op = sketch.implementation().operator_group().new_operator(operator_type, tensors);
-    sketch.implementation().operator_group().add_operator(op);
+    sketch.implementation().operator_group().add_operator(op, true);
 }
 
 } // namespace dynamic_fusion