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>

1 files changed, 5 insertions, 1 deletions

diff --git a/tests/validation/fixtures/dynamic_fusion/operators/CastFixture.h b/tests/validation/fixtures/dynamic_fusion/operators/CastFixture.h
index 8553472fb9..418cf4fe04 100644
--- a/tests/validation/fixtures/dynamic_fusion/operators/CastFixture.h
+++ b/tests/validation/fixtures/dynamic_fusion/operators/CastFixture.h
@@ -30,6 +30,7 @@
 #include "arm_compute/dynamic_fusion/runtime/gpu/cl/ClWorkloadRuntime.h"
 #include "arm_compute/dynamic_fusion/sketch/attributes/CastAttributes.h"
 #include "arm_compute/dynamic_fusion/sketch/gpu/GpuWorkloadSketch.h"
+#include "arm_compute/dynamic_fusion/sketch/gpu/operators/GpuOutput.h"
 
 #include "tests/framework/Fixture.h"
 #include "tests/validation/reference/DepthConvertLayer.h"
@@ -121,7 +122,10 @@ protected:
         CastAttributes attributes;
         attributes.convert_policy(policy).data_type(dt_out);
 
-        FunctionType::create_op(sketch, &src_info, &dst_info, attributes);
+        auto ans_info = sketch.create_tensor_info();
+
+        FunctionType::create_op(sketch, &src_info, &ans_info, attributes);
+        GpuOutput::create_op(sketch, &ans_info, &dst_info);
 
         // Configure runtime
         ClWorkloadRuntime runtime;