Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/alibaba/BladeDISC
/ functions
Functions
6,088 in github.com/alibaba/BladeDISC
⨍
Functions
6,088
◇
Types & classes
1,279
↳
Endpoints
6
↓ 1 callers
Method
getStrategyMap
tao_compiler/mlir/disc/transforms/fusion_utils.h:531
↓ 1 callers
Method
getStride
Returns the `Stride` for `axis`.
tao_compiler/mlir/disc/transforms/disc_shape_optimization_utils.h:160
↓ 1 callers
Method
getSymbolicDimSSAValueInstance
tao_compiler/mlir/disc/transforms/disc_shape_optimization.cc:1405
↓ 1 callers
Method
getTiledImplementation
Instantiate the tiled implementation of the operation.
tao_compiler/mlir/disc/tools/disc-transform/LinalgExt/LinalgExtOps.cc:743
↓ 1 callers
Function
getTorchPredefinedPDLPatterns
add pre-defined pdll patterns here.
pytorch_blade/pytorch_blade/torch-mlir/include/torch-mlir/Dialect/TorchConversion/Transforms/DiscPdlPredefinedPatterns.h:22
↓ 1 callers
Function
get_DISC_MIN_NUM_UNIT_PER_CORE
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:766
↓ 1 callers
Function
get_OMP_NUM_THREADS
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:750
↓ 1 callers
Function
get_calib_file_for_each_group
(c_module)
pytorch_blade/torch_blade/quantization/prepare_data.py:222
↓ 1 callers
Function
get_canonical_tensor_name
Legal tensor names are like: name, ^name, or name:digits. Please refert to: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/c
tensorflow_blade/tf_blade/util/tf_util.py:65
↓ 1 callers
Function
get_cudnn_version
(cuda_home)
pytorch_blade/common_setup.py:491
↓ 1 callers
Function
get_device
(backend)
examples/PyTorch/Train/Lazy/Bert/bert_train_ltc.py:115
↓ 1 callers
Function
get_dummy_input
()
examples/PyTorch/Quantization/bert_ptq.py:99
↓ 1 callers
Function
get_dynamic_settings
(c_module, trt_unsupported)
pytorch_blade/torch_blade/tensorrt/dynamic_shapes.py:248
↓ 1 callers
Function
get_dynamic_shape
Determine which dimension should be set to -1 according to min/max shape
pytorch_blade/torch_blade/tensorrt/dynamic_shapes.py:115
↓ 1 callers
Function
get_fallback_names
(root: nn.Module, num: int)
tools/torch_quant/torch_quant/amp_module.py:52
↓ 1 callers
Method
get_git_version
(self)
pytorch_blade/torch_blade_build.py:85
↓ 1 callers
Method
get_groups
(self)
pytorch_blade/torch_blade/algorithm/union_set.py:51
↓ 1 callers
Function
get_install_requires
()
tensorflow_blade/setup.py:49
↓ 1 callers
Function
get_libstdcxx
Get full path of linked libstdc++.so and a normalized name in format libstdc++.so.[0-9] .
scripts/python/tao_build.py:611
↓ 1 callers
Function
get_matched_pattern
( simple_graph: SimpleGraph, pattern_nodes: Dict[str, SimpleNode], first_node_key: str, init_n
tensorflow_blade/tf_blade/util/tf_graph_transform_util.py:807
↓ 1 callers
Method
get_ndims
public ndims
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/tensor.hpp:83
↓ 1 callers
Function
get_node_attr_value
(node: tf.NodeDef, attr: str, vname: str)
tensorflow_blade/tf_blade/util/tf_graph_transform_util.py:644
↓ 1 callers
Function
get_node_attr_value_ex
(node: tf.NodeDef, attr: str, vname: str)
tensorflow_blade/tf_blade/util/tf_graph_transform_util.py:656
↓ 1 callers
Function
get_node_type
(node: tf.NodeDef, attr: str)
tensorflow_blade/tf_blade/util/tf_graph_transform_util.py:664
↓ 1 callers
Method
get_patterh_node_by_name
(self, inp_name: str)
tensorflow_blade/tf_blade/util/tf_hierarchy_pattern_match.py:78
↓ 1 callers
Method
get_pattern
Overrides in Derived Class Returns a list of the pattern, where element of the list is a SimpleNode object. NOTE: now we only support
tensorflow_blade/tf_blade/util/tf_hierarchy_pattern_match.py:55
↓ 1 callers
Method
get_size
tao_compiler/mlir/xla/ral/context/mkldnn/ideep/ideep/tensor.hpp:611
↓ 1 callers
Function
get_subgraph_test_inputs_shapes
( graph_def: tf.GraphDef, test_data: List[Any], num_test_data: int, subgraph_ori_input_names:
tensorflow_blade/tf_blade/util/tf_conversion_util.py:120
↓ 1 callers
Function
get_tensor_output_idx
(tensor_name: str)
tensorflow_blade/tf_blade/util/tf_util.py:85
↓ 1 callers
Function
get_test_data
(batch=1, seq_len=12)
examples/PyTorch/Inference/CPU/albert/main.py:145
↓ 1 callers
Function
get_tf_bert_model
()
tensorflow_blade/examples/Inference/CUDA/BERT/bert_inference_opt.py:31
↓ 1 callers
Function
get_tf_gpu_version
Get proper value of env var TF_GPU_VERSION, which is used to choose env.conf file: ${TF_PLATFORMS_DIR}/${TF_PLATFORM}/${TF_DEVICE}/env.conf.$
scripts/python/tao_common.py:91
↓ 1 callers
Function
get_tf_graph_def
()
tensorflow_blade/examples/Inference/CUDA/BERT/bert_inference_opt.py:36
↓ 1 callers
Function
get_tf_info
(python_executable)
scripts/python/common_setup.py:389
↓ 1 callers
Function
get_tf_major_version
()
tensorflow_blade/tf_blade/util/tf_util.py:37
↓ 1 callers
Function
get_tf_version
()
tensorflow_blade/tf_blade/util/tf_util.py:33
↓ 1 callers
Function
get_torch_bert_model
(num_hidden_layers: int = 12, num_attention_heads: int = 12,
examples/PyTorch/Inference/CUDA/BERT/main.py:89
↓ 1 callers
Function
get_torch_test_data
(batch: int = 1, seq_len: int = 128, cuda: bool = False)
examples/PyTorch/Inference/CUDA/BERT/main.py:77
↓ 1 callers
Function
get_trt_version
(trt_home)
tensorflow_blade/common_internal.py:79
↓ 1 callers
Method
get_unsupported
(self)
pytorch_blade/torch_blade/onnx_backends/backend_testbed.py:316
↓ 1 callers
Function
get_unsupported_nodes
(graph, ignore_device=False)
pytorch_blade/torch_blade/tensorrt/tensorrt_optimization.py:41
↓ 1 callers
Method
get_version
(self)
pytorch_blade/torch_blade_build.py:97
↓ 1 callers
Function
get_version_file
()
scripts/python/common_setup.py:680
↓ 1 callers
Function
get_version_file
()
pytorch_blade/common_setup.py:680
↓ 1 callers
Function
glorot_uniform_init_
(weights)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/model/modules/ops.py:68
↓ 1 callers
Function
gpu_dealloc
tao_compiler/mlir/disc/tests/mlir_test.cc:172
↓ 1 callers
Function
graph_in_topology_order
(graph)
pytorch_blade/torch_blade/utils.py:58
↓ 1 callers
Function
graph_node_topolist
(graph: torch._C.Graph)
pytorch_blade/torch_blade/utils.py:128
↓ 1 callers
Function
group_node_to_engine
( module, node, try_cvt_to_engine_func, adapt_number_ios, idxes,
pytorch_blade/torch_blade/clustering/support_group_conversion.py:141
↓ 1 callers
Function
group_supported_clusters
(block, trt_unsupported, support_number_inpts_outs=False)
pytorch_blade/torch_blade/clustering/support_fusion_algorithm.py:301
↓ 1 callers
Function
group_to_engine_conversion
( module, try_cvt_to_engine_func, adapt_number_ios=False, quantization_calib_f
pytorch_blade/torch_blade/clustering/support_group_conversion.py:201
↓ 1 callers
Method
hashCode
pytorch_blade/pytorch_blade/compiler/jit/shape_type_spec.h:43
↓ 1 callers
Function
he_normal_init_
(weights)
examples/PyTorch/Inference/CUDA/AlphaFold/FoldAcc/foldacc/model/modules/ops.py:64
↓ 1 callers
Function
helper
(mod, prefix='')
pytorch_blade/torch_blade/exporter.py:128
↓ 1 callers
Function
inSameFusionFamily
tao_compiler/mlir/disc/transforms/fusion_utils.cc:361
↓ 1 callers
Function
inSameFusionOp
tao_compiler/mlir/disc/transforms/fusion_utils.cc:352
↓ 1 callers
Method
inTargetBlock
tao_compiler/mlir/disc/transforms/disc_transpose_simplifier.cc:294
↓ 1 callers
Method
in_edges
(self, node: int)
pytorch_blade/torch_blade/clustering/support_fusion_algorithm.py:40
↓ 1 callers
Function
initCustomCallShapeCalcOperandMap
tao_compiler/mlir/disc/transforms/placement_utils.cc:107
↓ 1 callers
Function
initDebugMode
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:52
↓ 1 callers
Function
initDiscCpuMathKernelMode
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:32
↓ 1 callers
Function
initEnableGlobalConstantStore
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:57
↓ 1 callers
Function
initEnableWeightPrePacking
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:78
↓ 1 callers
Function
initFlushDenormalMode
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:75
↓ 1 callers
Function
initInOutLayoutTuningFlag
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:69
↓ 1 callers
Function
initMLIRBindings
pytorch_blade/pytorch_blade/compiler/mlir/pybind_functions.cpp:23
↓ 1 callers
Function
initNeuralEngineBindings
pytorch_blade/pytorch_blade/compiler/neural_engine/pybind_functions.cpp:20
↓ 1 callers
Function
initProfileMode
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:66
↓ 1 callers
Function
initPromoteConv1DToConv2D
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:57
↓ 1 callers
Function
initQuantizationBindings
pytorch_blade/pytorch_blade/quantization/pybind_functions.cpp:349
↓ 1 callers
Function
initReductionTileSizeOnCPU
tao_compiler/mlir/disc/transforms/codegen_utils.cc:342
↓ 1 callers
Function
initShapeCalcOperandMap
tao_compiler/mlir/disc/transforms/placement_utils.cc:81
↓ 1 callers
Function
initSupportedLayouts
tao_compiler/mlir/xla/ral/context/stream_executor_based_impl.cc:990
↓ 1 callers
Function
initTensorRTBindings
Some pybind functions specific for pytorch are removed, such as TrtEngineClass's register func
tensorflow_blade/src/tensorrt/pybind_functions.cpp:101
↓ 1 callers
Function
initTensorRTBindings
pytorch_blade/pytorch_blade/compiler/tensorrt/pybind_functions.cpp:48
↓ 1 callers
Function
initToolsBindings
namespace
pytorch_blade/pytorch_blade/compiler/jit/pybind_functions.cpp:57
↓ 1 callers
Function
initWeightPrePackingCacheCapacity
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:89
↓ 1 callers
Method
initialized
tao/tao_bridge/kernels/tao_compilation_info_collector.h:91
↓ 1 callers
Function
injectStaticKnownInfo
tao_compiler/mlir/disc/transforms/disc_shape_optimization.cc:1652
↓ 1 callers
Function
inlineBody
XXX: This function can only be called with a loop that is guaranteed to execute EXACTLY ONCE.
pytorch_blade/pytorch_blade/compiler/jit/torch/const_loop_unroll.cpp:35
↓ 1 callers
Function
inlinePayload
Method to inline the payload of a `linalgOp` given the iteration space point and values for the arguments of the payload.
tao_compiler/mlir/disc/tools/disc-transform/LinalgExt/LinalgExtOps.cc:677
↓ 1 callers
Function
insertBlockCopy
inserts a copy of body, passing inputs to the inputs of the block it returns the a list of the Values for the output of the block
pytorch_blade/pytorch_blade/compiler/jit/torch/const_loop_unroll.cpp:68
↓ 1 callers
Function
insertDeallocOp
tao_compiler/mlir/disc/transforms/disc_buffer_deallocation.cc:46
↓ 1 callers
Function
insertTieShapeOnBlock
tao_compiler/mlir/disc/transforms/disc_shape_optimization.cc:118
↓ 1 callers
Function
insertTieShapeOnOperation
tao_compiler/mlir/disc/transforms/disc_shape_optimization.cc:99
↓ 1 callers
Function
internal_tao_bridge_dir
()
scripts/python/common_setup.py:547
↓ 1 callers
Function
internal_tao_bridge_dir
()
pytorch_blade/common_setup.py:547
↓ 1 callers
Function
isAclSupportedConv
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:336
↓ 1 callers
Function
isAclSupportedDepthwiseConv
tao_compiler/mlir/xla/ral/context/common_context_impl_mkldnn.cc:207
↓ 1 callers
Function
isCheapComputation
Returns true if the value produced by a cheap computation. Here "cheap" means duplication of such computation would not hurt performance.
tao_compiler/mlir/disc/transforms/disc_duplicate_computation_for_fusion.cc:224
↓ 1 callers
Function
isColOrRowReduction
Returns true if this op is a col or reduction.
tao_compiler/mlir/disc/transforms/reduction_rewriters.cc:31
↓ 1 callers
Function
isConstantZeroTensor
tao_compiler/mlir/disc/transforms/lower_tf.cc:776
↓ 1 callers
Function
isDeadBuffer
tao_compiler/mlir/disc/transforms/disc_remove_dead_buffer.cc:47
↓ 1 callers
Function
isDebugMode
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:111
↓ 1 callers
Method
isEdgePaddingLowUnknown
Returns true if the `EdgePaddingLow` of the `axis` is unknown.
tao_compiler/mlir/disc/transforms/disc_shape_optimization_utils.h:210
↓ 1 callers
Function
isElementWiseBinary
Returns true if the op is an elementwise binary lmhlo op. TODO(disc): use fusibility interface
tao_compiler/mlir/disc/transforms/fusion_utils.cc:406
↓ 1 callers
Function
isElementWiseTernary
Returns true if the op is an elementwise ternary lmhlo op.
tao_compiler/mlir/disc/transforms/fusion_utils.cc:425
↓ 1 callers
Function
isElementWiseUnary
Returns true if the op is an elementwise unary lmhlo op. TODO(disc): use fusibility interface TODO(disc): Unify with disc_supported_list.h and Element
tao_compiler/mlir/disc/transforms/fusion_utils.cc:377
↓ 1 callers
Function
isFlushDenormalEnabled
tao_compiler/mlir/xla/ral/context/common_context_impl.cc:85
↓ 1 callers
Function
isForLoop
pytorch_blade/pytorch_blade/compiler/jit/torch/const_loop_unroll.cpp:26
← previous
next →
2,201–2,300 of 6,088, ranked by callers