MCPcopy Create free account

hub / github.com/MegEngine/MegCC / functions

Functions3,375 in github.com/MegEngine/MegCC

⨍ Functions 3,375◇ Types & classes 687
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/AutoBareMetal/ElemwiseKernel.cpp:27
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/AutoBareMetal/MatmulKernel.cpp:20
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/InternalKernel/DotInt8x8x32M8N6K4Matmul.cpp:683
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/InternalKernel/Fp32M4N12K4Matmul.cpp:538
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/InternalKernel/Fp32M4N12Matmul.cpp:938
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/InternalKernel/Int8x8x32MK4Matmul.cpp:416
↓ 1 callersMethodGetKernelSymbol
kernel gen
compiler/lib/KernelGen/Arm/Armv7/MatMulKernel/Fp32MatMulM4N12.cpp:28
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/ConvKernel/Int8Conv1x1Nchw44.cpp:54
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/ConvKernel/Fp32Conv1x1Mk4M4N12.cpp:37
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/ConvKernel/DotInt8Conv1x1NchwM6N8K4.cpp:53
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Armv7/ConvKernel/Fp32WinogradNchw44.cpp:80
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/ArmCommon/Elemwise/Elemwise.cpp:35
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/ArmCommon/ConvKernel/Int8/Int8DirectNchw44.cpp:1546
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/ArmCommon/ConvKernel/Int8/Int8WinogradF23Nchw44MK8.cpp:85
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/BatchedMatmul/Fp32BatchedMatmul.cpp:66
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/InternalKernel/Fp32M8N12Matmul.cpp:1665
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/InternalKernel/Int8I8mmM8K8N12MK4GEMM.cpp:1342
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/InternalKernel/Int8DotM8N12MK4GEMM.cpp:1484
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/InternalKernel/Fp32M8N12K4Matmul.cpp:1174
↓ 1 callersMethodGetKernelSymbol
kernel gen
compiler/lib/KernelGen/Arm/Arm64/MatMulKernel/Fp32MatMulM8N12.cpp:28
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/Elemwise/Elemwise.cpp:24
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/ConvKernel/Fp32/Fp32Conv1x1Mk4M8N12.cpp:43
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/ConvKernel/Fp32/Fp32WinogradNchw44.cpp:81
↓ 1 callersMethodGetKernelSymbol
namespace
compiler/lib/KernelGen/Arm/Arm64/ConvKernel/Int8/Int8DotIm2col.cpp:58
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/ConvKernel/Int8/Int8I8mmIm2colS1NCHW44M8N12K8.cpp:1416
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/Arm/Arm64/ConvKernel/Int8/Int8DotConv1x1Mk4M8N12.cpp:41
↓ 1 callersMethodGetKernelSymbol
kernel gen
compiler/lib/KernelGen/GeneralIntrinsic/Resize.cpp:22
↓ 1 callersMethodGetKernelSymbol
kernel gen
compiler/lib/KernelGen/GeneralIntrinsic/WarpAffine.cpp:33
↓ 1 callersMethodGetKernelSymbol
kernel gen
compiler/lib/KernelGen/GeneralIntrinsic/Relayout.cpp:43
↓ 1 callersMethodGetKernelSymbol
kernel gen
compiler/lib/KernelGen/GeneralIntrinsic/MatMulKernel/Fp32MatMulM4N12.cpp:18
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Fp32NchwBackwardConv.cpp:33
↓ 1 callersMethodGetKernelSymbol
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Fp32Conv1x1Mk4M4N12.cpp:38
↓ 1 callersMethodGetPackASignature
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2col/F32StrategyM4N12.h:38
↓ 1 callersMethodGetPackAWorkspaceBody
compiler/lib/KernelGen/GeneralIntrinsic/InternalKernel/Fp32M4N12Matmul.cpp:950
↓ 1 callersMethodGetPackAWorkspaceSignature
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2col/F32StrategyM4N12.h:42
↓ 1 callersMethodGetPackAWorkspaceSym
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2colCommon.h:47
↓ 1 callersMethodGetPackBSignature
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2col/F32StrategyM4N12.h:46
↓ 1 callersMethodGetPackBWorkspaceSignature
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2col/F32StrategyM4N12.h:50
↓ 1 callersMethodGetPackBWorkspaceSym
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2colCommon.h:51
↓ 1 callersMethodGetWorkspaceBody
compiler/lib/KernelGen/BareMetal/Topk.cpp:43
↓ 1 callersMethodGetWorkspaceBodyAndJitExec
compiler/lib/KernelGen/BareMetal/Topk.h:16
↓ 1 callersMethodGiMultiplyAddFloat16
compiler/lib/KernelGen/GeneralIntrinsic/GIMathHelper.h:514
↓ 1 callersFunctionGiMultiplyInt8
in x86, there is no int multiply, so implement it naive
immigration/include/gi_int.h:519
↓ 1 callersMethodGiReduceMaxNanFloat16
compiler/lib/KernelGen/GeneralIntrinsic/GIMathHelper.h:464
↓ 1 callersMethodGiReduceMinNanFloat16
compiler/lib/KernelGen/GeneralIntrinsic/GIMathHelper.h:447
↓ 1 callersMethodGiReduceMultiplyFloat16
compiler/lib/KernelGen/GeneralIntrinsic/GIMathHelper.h:497
↓ 1 callersMethodInputFeatureTrans
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/fp16/WinogradF43Strategy8x8MK8.cpp:113
↓ 1 callersFunctionIsHeaderFile
(filename)
compiler/.ycm_extra_conf.py:105
↓ 1 callersFunctionIsHeaderFile
(filename)
runtime/.ycm_extra_conf.py:101
↓ 1 callersFunctionIsHeaderFile
(filename)
runtime/test/.ycm_extra_conf.py:99
↓ 1 callersFunctionLITE_set_tensor_layout
runtime/src/lite/tensor.c:78
↓ 1 callersFunctionMGBTensor2Tensor
runtime/src/vm/extern_opr.c:133
↓ 1 callersFunctionMakeConcatArrayAttr
compiler/lib/Conversion/MGBToKernel/MGBToKernelHelper.h:419
↓ 1 callersMethodOutputFeatureTrans
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/fp16/WinogradF43Strategy8x8MK8.cpp:564
↓ 1 callersFunctionPREALLOC_MEM
compiler/lib/Dialect/Kernel/Transforms/migrate/static_mem_alloc/pushdown.cpp:239
↓ 1 callersMethodPackASym
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2colCommon.h:45
↓ 1 callersMethodPackBSym
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/Im2colCommon.h:43
↓ 1 callersFunctionTensor2MGBTensor
Convert Tensor to MGBTensor, except MGBTensor.data.
runtime/src/vm/extern_opr.c:107
↓ 1 callersMethodWeightTrans
compiler/lib/KernelGen/GeneralIntrinsic/ConvKernel/fp16/WinogradF43Strategy8x8MK8.cpp:11
↓ 1 callersFunction_MM_EXTRACT_PS
immigration/include/gi_float.h:468
↓ 1 callersMethodaddCVKernel
compiler/include/compiler/Target/TinyNN/export.h:46
↓ 1 callersMethodaddDeduceShapeKernel
compiler/include/compiler/Target/TinyNN/export.h:63
↓ 1 callersMethodaddInitFunc
compiler/include/compiler/Target/TinyNN/export.h:51
↓ 1 callersMethodaddKernel
compiler/include/compiler/Target/TinyNN/export.h:35
↓ 1 callersMethodadd_binary
compiler/test/kernel/common/src/target_module.cpp:71
↓ 1 callersMethodadd_cv
compiler/test/kernel/common/src/target_module.cpp:77
↓ 1 callersMethodadd_internal_func
compiler/test/kernel/common/src/target_module.cpp:89
↓ 1 callersMethodadd_workspace_size
compiler/test/kernel/common/src/target_module.cpp:64
↓ 1 callersMethodaddr_end
compiler/lib/Dialect/Kernel/Transforms/migrate/static_mem_alloc/impl.h:158
↓ 1 callersFunctionalignment_or_alloc_weights
runtime/src/parse.c:223
↓ 1 callersMethodalloc_aligned_addr
compiler/lib/Dialect/Kernel/Transforms/migrate/static_mem_alloc/best_fit.cpp:21
↓ 1 callersMethodalloc_placement
compiler/lib/Dialect/Kernel/Transforms/migrate/static_mem_alloc/best_fit.cpp:43
↓ 1 callersMethodarray
compiler/test/kernel/common/src/checker.cpp:21
↓ 1 callersFunctionas_float
runtime/src/parse.c:13
↓ 1 callersFunctionas_uint
compiler/lib/Target/TinyNN/exporter.cpp:19
↓ 1 callersFunctionas_uint
runtime/src/parse.c:10
↓ 1 callersFunctionauto_check
(model_name_2_all, eps, target_arch, target_host, env, mdl_str, user_input_dir, enable_fp16, enable_aarch32_do
script/test_model.py:213
↓ 1 callersFunctionbroadcast_postprocess_weight_memory
runtime/src/init.c:184
↓ 1 callersMethodbuild
(self, x86_target="fallback", build_options="")
benchmark/python/src/benchmark.py:49
↓ 1 callersMethodbuild
(self)
runtime/scripts/runtime_build.py:60
↓ 1 callersFunctionbuild_benchmarker
(x86_target="fallback", arch_str=None, benchmarkers=None)
benchmark/python/common.py:104
↓ 1 callersFunctionbuild_megcc_lib
(arch_desc="x86", model_config_json="", kernel_build_dir="",
benchmark/python/common.py:20
↓ 1 callersFunctionbuild_model_and_megcc_lib
(models, models_dir, arch_str)
benchmark/python/common.py:86
↓ 1 callersFunctionca_free_megcc_deamo
runtime/example/Nonstandard_OS/tee/host/main.c:21
↓ 1 callersFunctionca_init_megcc_deamo
runtime/example/Nonstandard_OS/tee/host/main.c:15
↓ 1 callersFunctionca_run_megcc_deamo
runtime/example/Nonstandard_OS/tee/host/main.c:25
↓ 1 callersMethodcheckInputLayout
compiler/lib/Dialect/Kernel/IR/KernelDialect.cpp:269
↓ 1 callersFunctioncheck_layout_equal
compiler/test/kernel/common/src/cc_proxy.cpp:112
↓ 1 callersMethodcheck_tensors
compiler/test/kernel/common/src/checker.cpp:277
↓ 1 callersFunctioncommon_define
compiler/lib/KernelGen/Arm/ArmCommon/MatMulKernel/Fp32Gevm.cpp:21
↓ 1 callersFunctioncommon_define
compiler/lib/KernelGen/GeneralIntrinsic/MatMulKernel/Fp32Gevm.cpp:7
↓ 1 callersFunctioncommon_define
compiler/lib/KernelGen/GeneralIntrinsic/MatMulKernel/fp16/Fp16Gevm.cpp:7
↓ 1 callersFunctioncommon_undef
compiler/lib/KernelGen/Arm/ArmCommon/MatMulKernel/Fp32Gevm.cpp:43
↓ 1 callersFunctioncommon_undef
compiler/lib/KernelGen/GeneralIntrinsic/MatMulKernel/Fp32Gevm.cpp:29
↓ 1 callersFunctioncommon_undef
compiler/lib/KernelGen/GeneralIntrinsic/MatMulKernel/fp16/Fp16Gevm.cpp:29
↓ 1 callersFunctioncompare_file_or_dir
(path_0, path_1, eps, output_name_2_dtype)
script/test_model.py:124
↓ 1 callersFunctioncompare_layout
runtime/src/lite/tensor.c:42
↓ 1 callersFunctioncompute_quater_body
compiler/lib/KernelGen/BareMetal/ElemwiseKernel.cpp:279
↓ 1 callersFunctioncompute_tenary_body
kernel format: for(int idx_out = 0; idx_out< nr_elem_out;idx+=block_1){ base_offset = get_all_offset_of_inputs_in_every_block_1();
compiler/lib/KernelGen/BareMetal/ElemwiseKernel.cpp:163
↓ 1 callersFunctionconfig_attr
compiler/tools/kernel_exporter/config_attr.cpp:147
← previousnext →601–700 of 3,375, ranked by callers