diff options
author | Viet-Hoa Do <viet-hoa.do@arm.com> | 2022-12-13 13:09:10 +0000 |
---|---|---|
committer | Viet-Hoa Do <viet-hoa.do@arm.com> | 2022-12-16 15:17:51 +0000 |
commit | b84e25313e5dc7acbc03623e1e071e845047c111 (patch) | |
tree | fbee083f1262017555c64c3280da45e2b638992e /tests/validation/fixtures/dynamic_fusion/gpu/cl/DepthwiseConv2dFixture.h | |
parent | a0ae8d2e6c57fd95c0edaf659b9df8b8c540d051 (diff) | |
download | ComputeLibrary-b84e25313e5dc7acbc03623e1e071e845047c111.tar.gz |
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>
Diffstat (limited to 'tests/validation/fixtures/dynamic_fusion/gpu/cl/DepthwiseConv2dFixture.h')
-rw-r--r-- | tests/validation/fixtures/dynamic_fusion/gpu/cl/DepthwiseConv2dFixture.h | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/tests/validation/fixtures/dynamic_fusion/gpu/cl/DepthwiseConv2dFixture.h b/tests/validation/fixtures/dynamic_fusion/gpu/cl/DepthwiseConv2dFixture.h index c7600e082e..630b664b78 100644 --- a/tests/validation/fixtures/dynamic_fusion/gpu/cl/DepthwiseConv2dFixture.h +++ b/tests/validation/fixtures/dynamic_fusion/gpu/cl/DepthwiseConv2dFixture.h @@ -33,6 +33,7 @@ #include "arm_compute/dynamic_fusion/sketch/attributes/DepthwiseConv2dAttributes.h" #include "arm_compute/dynamic_fusion/sketch/gpu/GpuWorkloadSketch.h" #include "arm_compute/dynamic_fusion/sketch/gpu/operators/GpuDepthwiseConv2d.h" +#include "arm_compute/dynamic_fusion/sketch/gpu/operators/GpuOutput.h" #include "tests/CL/CLAccessor.h" @@ -133,7 +134,11 @@ protected: auto weight_info = sketch.create_tensor_info(TensorInfo(weights_shape, 1, _data_type, _data_layout)); auto bias_info = sketch.create_tensor_info(TensorInfo(bias_shape, 1, _data_type, _data_layout)); auto dst_info = sketch.create_tensor_info(); - FunctionType::create_op(sketch, &input_info, &weight_info, &bias_info, &dst_info, dwc_conv2d_attr); + + auto ans_info = sketch.create_tensor_info(); + + FunctionType::create_op(sketch, &input_info, &weight_info, &bias_info, &ans_info, dwc_conv2d_attr); + GpuOutput::create_op(sketch, &ans_info, &dst_info); // Configure runtime ClWorkloadRuntime runtime; |