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, 6 insertions, 2 deletions

diff --git a/tests/validation/dynamic_fusion/gpu/Integration.cpp b/tests/validation/dynamic_fusion/gpu/Integration.cpp
index 0b81dac1f0..58d2215e64 100644
--- a/tests/validation/dynamic_fusion/gpu/Integration.cpp
+++ b/tests/validation/dynamic_fusion/gpu/Integration.cpp
@@ -28,6 +28,7 @@
 #include "arm_compute/dynamic_fusion/sketch/OperatorAttributes.h"
 #include "arm_compute/dynamic_fusion/sketch/gpu/GpuWorkloadSketch.h"
 #include "arm_compute/dynamic_fusion/sketch/gpu/operators/GpuConv2d.h"
+#include "arm_compute/dynamic_fusion/sketch/gpu/operators/GpuOutput.h"
 
 #include "tests/CL/CLAccessor.h"
 #include "tests/framework/Macros.h"
@@ -70,8 +71,11 @@ TEST_CASE(Conv2d, framework::DatasetMode::ALL)
     Conv2dAttributes conv2d_attr{};
     auto             input_info  = sketch.create_tensor_info(t_input_shape, 1, data_type, data_layout);
     auto             weight_info = sketch.create_tensor_info(TensorInfo(t_weight_shape, 1, data_type, data_layout));
-    auto             dst_info    = sketch.create_tensor_info();
-    GpuConv2d::create_op(sketch, &input_info, &weight_info, nullptr, &dst_info, conv2d_attr);
+    auto             ans_info    = sketch.create_tensor_info();
+    GpuConv2d::create_op(sketch, &input_info, &weight_info, nullptr, &ans_info, conv2d_attr);
+
+    auto dst_info = sketch.create_tensor_info();
+    GpuOutput::create_op(sketch, &ans_info, &dst_info);
 
     // Configure runtime
     ClWorkloadRuntime runtime;