Skip to main content
Ctrl+K
onnx-light 0.1.21 documentation - Home onnx-light 0.1.21 documentation - Home
  • Quick tour
  • Start
  • Design
  • API
  • Ops
  • How-To
  • Next Steps
  • Miscellaneous
  • GitHub
  • Quick tour
  • Start
  • Design
  • API
  • Ops
  • How-To
  • Next Steps
  • Miscellaneous
  • GitHub

Section Navigation

  • protos
    • AttributeProto
    • DeviceConfigurationProto
    • FunctionProto
    • GraphProto
    • IntIntListEntryProto
    • MapProto
    • Message
    • ModelProto
    • NodeDeviceConfigurationProto
    • NodeProto
    • OperatorSetIdProto
    • OperatorStatus
    • OptionalProto
    • SequenceProto
    • ShardedDimProto
    • ShardingSpecProto
    • SimpleShardedDimProto
    • SparseTensorProto
    • StringStringEntryProto
    • TensorAnnotation
    • TensorProto
    • TensorShapeProto
    • TypeProto
    • ValueInfoProto
  • Python API
    • onnx_light.onnx
      • onnx_light.onnx.backend
      • onnx_light.onnx.checker
      • onnx_light.onnx.compose
      • onnx_light.onnx.defs
      • onnx_light.onnx.external_data_helper
      • onnx_light.onnx.helper
      • onnx_light.onnx.inliner
      • onnx_light.onnx.mapping
      • onnx_light.onnx.numpy_helper
      • onnx_light.onnx.onnx_pb
      • onnx_light.onnx.parser
      • onnx_light.onnx.printer
      • onnx_light.onnx.reference
      • onnx_light.onnx.shape_inference
      • onnx_light.onnx.tools
      • onnx_light.onnx.version_converter
    • onnx_light.onnx_core
      • onnx_light.onnx_core.expressions
      • onnx_light.onnx_core.gradient
      • onnx_light.onnx_core.graph_builder
      • onnx_light.onnx_core.optimization
      • onnx_light.onnx_core.shape_inference
    • onnx_light.onnx_op
    • onnx_light.cpp_build
    • onnx_light.doc
    • Kernel tuning
    • onnx_light.tools
      • onnx_light.tools.dot
      • onnx_light.tools.mermaid
      • onnx_light.tools.pretty_print
      • onnx_light.tools.schema_comparison
      • onnx_light.tools.schema_diff
      • onnx_light.tools.svg
      • onnx_light.tools.translate
    • onnx_light.ext_test_case
  • C++ API
    • common
      • Helpers
      • simple_span
    • onnx
      • checker.h
      • string_utils.h
      • common
        • array_ref.h
        • assertions.h
        • common.h
        • constants.h
        • file_utils.h
        • graph_node_list.h
        • ir.h
        • ir_pb_converter.h
        • narrow.h
        • onnx_pb.h
        • path.h
        • platform_helpers.h
        • proto_util.h
        • proto_utils.h
        • safe_math.h
        • scoped_resource.h
        • status.h
        • string_utils.h
        • tensor.h
        • visitor.h
      • inliner
        • inliner.h
      • shape_inference
        • attribute_binder.h
        • implementation.h
      • version_converter
        • BaseConverter.h
        • convert.h
        • errors.h
        • helper.h
        • internal_symbol.h
        • adapters
    • onnx_defs
      • controlflow/utils.h
      • data_propagators.h
      • doc_strings.h
      • function.h
      • generator/utils.h
      • math/utils.h
      • nn/utils.h
      • reduction/utils.h
      • schema.h
      • sequence/utils.h
      • shape_inference.h
      • tensor/utils.h
      • traditionalml/utils.h
    • onnx_manipulations
      • attr_proto_util.h
      • compose.h
      • data_type_utils.h
      • parser.h
      • printer.h
      • tensor_proto_util.h
      • tensor_util.h
    • onnx_core
      • expressions.h
      • dim_sum.h
      • graph_manipulations.h
      • light_op_schema.h
      • sym_tensor.h
      • sym_sequence.h
      • sym_map.h
      • symbolic_helper.h
      • builder
        • graph_builder.h
        • graph_graph.h
        • pattern_optimization.h
        • pattern_registry.h
      • gradient
        • gradient.h
        • grad_common.h
        • grad_dispatcher.h
      • platform
        • cpu_descriptor.h
      • shapes
        • shapes_context.h
        • shape_broadcast.h
        • shape_check.h
        • shape_inference.h
        • dispatch_table.h
      • runtime
        • simple_tensor.h
        • simple_sequence.h
        • simple_map.h
        • runtime_context.h
        • kernel_context.h
        • runtime_parameters.h
        • run_nodes.h
        • runtime_session.h
        • kernel_dispatch_table.h
        • cpu_executor.h
        • cpu_execution_policy.h
        • parallel_region_collector.h
        • kernel_tuning.h
        • kernel_tuning_cache.h
        • parallel_for.h
        • tensor_compare.h
        • node_helpers.h
        • temporary_buffer.h
        • random.h
        • cast_float8.h
        • cast_helper.h
        • cast_sub_byte.h
        • elementwise_helpers.h
        • float16_promote.h
        • controlflow
      • compute
        • compute_context.h
        • constant_info.h
        • result_lifetime.h
        • inplace_reuse.h
        • inplace_reuse_types.h
        • peak_memory.h
        • value_tags.h
        • raw_buffer_allocator.h
        • execute_action.h
        • execution_plan.h
        • prepared_task.h
        • resolved_model_fixture.h
      • backend_test
        • test_case.h
        • test_case_registry.h
        • expect.h
        • io_data.h
    • onnx_op
      • operator_sets.h
      • operator_sets_controlflow.h
      • operator_sets_controlflow_doc.h
      • operator_sets_generator.h
      • operator_sets_generator_doc.h
      • operator_sets_image.h
      • operator_sets_image_doc.h
      • operator_sets_logical.h
      • operator_sets_logical_doc.h
      • operator_sets_math.h
      • operator_sets_math_doc.h
      • operator_sets_nn.h
      • operator_sets_nn_doc.h
      • operator_sets_object_detection.h
      • operator_sets_object_detection_doc.h
      • operator_sets_optional.h
      • operator_sets_optional_doc.h
      • operator_sets_preview.h
      • operator_sets_preview_doc.h
      • operator_sets_quantization.h
      • operator_sets_quantization_doc.h
      • operator_sets_reduction.h
      • operator_sets_reduction_doc.h
      • operator_sets_rt.h
      • operator_sets_rt_doc.h
      • operator_sets_sequence.h
      • operator_sets_sequence_doc.h
      • operator_sets_tensor.h
      • operator_sets_tensor_doc.h
      • operator_sets_text.h
      • operator_sets_text_doc.h
      • operator_sets_traditionalml.h
      • operator_sets_traditionalml_doc.h
      • operator_sets_training.h
      • operator_sets_training_doc.h
    • onnx_shapes
      • dispatch_table.h
      • shapes
        • controlflow
        • generator
        • image
        • logical
        • math
        • nn
        • optional
        • preview
        • quantization
        • reduction
        • rt
        • sequence
        • tensor
        • text
        • traditionalml
        • training
    • onnx_gradient
    • onnx_kernels
      • kernel_dispatch_table.h
      • kernel_run_helpers.h
      • kernels
        • include_generator_kernels.h
        • include_image_kernels.h
        • include_logical_kernels.h
        • include_math_kernels.h
        • include_nn_kernels.h
        • include_object_detection_kernels.h
        • include_optional_kernels.h
        • include_preview_kernels.h
        • include_quantization_kernels.h
        • include_reduction_kernels.h
        • include_rt_kernels.h
        • include_sequence_kernels.h
        • include_tensor_kernels.h
        • include_text_kernels.h
        • include_traditionalml_kernels.h
        • include_training_kernels.h
        • auto_pad.h
        • matmul_shape_utils.h
        • pool_attrs.h
        • recurrent_common.h
        • kernel_svm_common.h
        • kernel_tree_ensemble_common.h
      • tuning
        • portable_gemm_tuning.h
        • portable_parallel_tuning.h
    • onnx_backend_test
      • cases
        • include_controlflow_cases.h
        • include_generator_cases.h
        • include_image_cases.h
        • include_logical_cases.h
        • include_math_cases.h
        • include_nn_cases.h
        • include_object_detection_cases.h
        • include_optional_cases.h
        • include_preview_cases.h
        • include_quantization_cases.h
        • include_reduction_cases.h
        • include_sequence_cases.h
        • include_tensor_cases.h
        • include_text_cases.h
        • include_traditionalml_cases.h
        • include_training_cases.h
      • cases_for_shapes
        • empty_shape
        • inference
        • constant
        • inplace
        • peak_memory
        • release
        • shape_tag
      • cases_numerical
        • nan_inf
      • cases_runtime
        • local_function
    • onnx_proto
      • onnx.h
      • onnx_helper.h
      • onnx_alias.h
      • onnx_crypt.h
      • stream_class.h
      • stream.h
      • simple_string.h
      • simple_span.h
      • thread_pool.h
      • worker_pool.h
      • fields.h
      • onnx_verify.h
      • serialize_options.h
      • tml.h
      • type_helper.h
      • visibility.h
      • google_protobuf_compat.h
  • API
  • C++ API
  • onnx_kernels
  • tuning

tuning#

Portable auto-tuning helpers for the GEMM and parallel-for kernels (PortableGemmTuning, PortableParallelTuning).

  • portable_gemm_tuning.h
  • portable_parallel_tuning.h

previous

kernel_tree_ensemble_common.h

next

portable_gemm_tuning.h
Show Source

Created using Sphinx 9.1.0.

Built with the PyData Sphinx Theme 0.20.0.