24.04
|
#include <GpuDepthwiseConv2d.h>
Public Types | |
using | Attributes = DepthwiseConv2dAttributes |
Attributes are a set of backend-agnostic parameters that define what an operator does. More... | |
Static Public Member Functions | |
static ITensorInfo * | create_op (GpuWorkloadSketch &sketch, ITensorInfo *src, ITensorInfo *wei, ITensorInfo *bia, const Attributes &attributes) |
Create an operator and fuse it into the workload sketch. More... | |
static Status | is_supported_op (const GpuWorkloadContext &context, const ITensorInfo *src, const ITensorInfo *wei, const ITensorInfo *bia, const Attributes &attributes) |
Check if the operator configuration is supported, irrespective of fusion. More... | |
static Status | validate_op (const GpuWorkloadSketch &sketch, const ITensorInfo *src, const ITensorInfo *wei, const ITensorInfo *bia, const Attributes &attributes) |
Check if the operator configuration is supported and if it can be fused into the workload sketch. More... | |
Operator interface.
Definition at line 40 of file GpuDepthwiseConv2d.h.
using Attributes = DepthwiseConv2dAttributes |
Attributes are a set of backend-agnostic parameters that define what an operator does.
Definition at line 44 of file GpuDepthwiseConv2d.h.
|
static |
Create an operator and fuse it into the workload sketch.
sketch
remains unchanged and valid.Valid data type configurations:
src | wei | bia | dst |
---|---|---|---|
F16 | F16 | F16 | F16 |
F32 | F32 | F32 | F32 |
Valid data layouts:
[in,out] | sketch | Workload sketch into which the operator will be fused |
[in] | src | Source tensor |
[in] | wei | Weight tensor |
[in] | bia | (Optional) Bias tensor |
[in] | attributes | Operator attributes |
Definition at line 192 of file GpuDepthwiseConv2d.cpp.
References arm_compute::ACL_DST_0, arm_compute::ACL_SRC_0, arm_compute::ACL_SRC_1, arm_compute::ACL_SRC_2, ArgumentPack< T >::add_const_tensor(), GpuKernelComponentGraph::add_new_component(), GpuOperatorGroup::add_operator(), ARM_COMPUTE_ERROR, ARM_COMPUTE_ERROR_ON_NULLPTR, ARM_COMPUTE_ERROR_THROW_ON, ARM_COMPUTE_LOG_PARAMS, GpuWorkloadSketch::Implementation::component_graph(), GpuWorkloadSketch::Implementation::context(), ClDWCNativeKernelConfigurationFactory::create(), GpuWorkloadSketch::Implementation::create_virtual_tensor(), DepthwiseConv2dAttributes::depth_multiplier(), DepthwiseConv2dAttributes::dilation(), arm_compute::test::validation::dst, DWCComputeKernelInfo::export_input_to_cl_image, DWCComputeKernelInfo::export_weights_to_cl_image, arm_compute::FLOOR, arm_compute::get_arch_from_target(), GpuWorkloadContext::gpu_target(), GpuWorkloadSketch::implementation(), DWCComputeKernelInfo::m0, arm_compute::MIDGARD, DWCComputeKernelInfo::n0, GpuOperatorGroup::new_operator(), arm_compute::experimental::dynamic_fusion::OpenCL, GpuWorkloadSketch::Implementation::operator_group(), DepthwiseConv2dAttributes::pad(), UnitWorkloadStage::Run, arm_compute::test::validation::sketch, arm_compute::test::validation::src, KernelProperties::stage(), DepthwiseConv2dAttributes::stride(), tf_frozen_model_extractor::t, arm_compute::opencl::kernels::gemm::update_padding_for_cl_image(), and GpuDepthwiseConv2d::validate_op().
Referenced by arm_compute::test::validation::TEST_CASE().
|
static |
Check if the operator configuration is supported, irrespective of fusion.
[in] | context | Workload context within which the operator is running |
[in] | src | Source tensor |
[in] | wei | Weight tensor |
[in] | bia | (Optional) Bias tensor |
[in] | attributes | Operator attributes |
Definition at line 145 of file GpuDepthwiseConv2d.cpp.
References arm_compute::test::validation::context, and arm_compute::test::validation::src.
|
static |
Check if the operator configuration is supported and if it can be fused into the workload sketch.
Parameters are similar to GpuDepthwiseConv2d::create_op()
Definition at line 154 of file GpuDepthwiseConv2d.cpp.
References arm_compute::ACL_DST_0, arm_compute::ACL_SRC_0, arm_compute::ACL_SRC_1, arm_compute::ACL_SRC_2, ArgumentPack< T >::add_const_tensor(), ITensorInfo::are_values_constant(), ARM_COMPUTE_RETURN_ERROR_ON, ARM_COMPUTE_RETURN_ERROR_ON_MSG, ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR, GpuWorkloadSketch::gpu_context(), ITensorInfo::has_valid_id(), GpuWorkloadSketch::implementation(), GpuOperatorGroup::new_operator(), GpuWorkloadSketch::Implementation::operator_group(), arm_compute::test::validation::sketch, arm_compute::test::validation::src, and GpuOperatorGroup::try_add_operator().
Referenced by GpuDepthwiseConv2d::create_op(), and arm_compute::test::validation::TEST_CASE().