Functions — github.com/ROCm/AMDMIGraphX

CodeHub MCPcopy Create free account

hub / github.com/ROCm/AMDMIGraphX / functions

Functions10,303 in github.com/ROCm/AMDMIGraphX

⨍ Functions 10,303◇ Types & classes 3,400

↓ 23 callersFunctionconvert_to_json

src/convert_to_json.cpp:80

↓ 23 callersFunctiondestroy

src/api/api.cpp:419

↓ 23 callersFunctiondevice_cast

src/targets/gpu/device/include/migraphx/gpu/device/types.hpp:137

↓ 23 callersMethodrun_pass

test/schedule_test.cpp:197

↓ 23 callersMethodsize

src/program.cpp:163

↓ 23 callersMethodsubstitute

(self, s: str, **kwargs)

tools/api.py:1033

↓ 23 callersFunctionto_json_string

src/json.cpp:153

↓ 22 callersFunctionadd_scale_mul

test/include/quantize_helpers.hpp:60

↓ 22 callersFunctionauto_any_cast

src/include/migraphx/auto_any_cast.hpp:59

↓ 22 callersFunctionbit_equal

test/bf16.cpp:35

↓ 22 callersFunctionbit_equal

test/half.cpp:35

↓ 22 callersMethodfind

src/include/migraphx/target_assignments.hpp:47

↓ 22 callersMethodget_parameter

src/module.cpp:657

↓ 22 callersMethodparse

test/include/test.hpp:660

↓ 22 callersFunctionsplit_string

src/include/migraphx/stringutils.hpp:86

↓ 22 callersMethodto_value

src/targets/cpu/lowering.cpp:149

↓ 22 callersFunctionupper_bound

src/targets/gpu/device/multinomial.cpp:38

↓ 21 callersMethodadd_broadcastable_binary_op

src/onnx/onnx_parser.cpp:149

↓ 21 callersFunctionarg

src/targets/gpu/kernels/include/migraphx/kernels/functional.hpp:351

↓ 21 callersFunctionargument

src/api/migraphx.py:132

↓ 21 callersFunctionbase64_encode

src/base64.cpp:75

↓ 21 callersFunctionchain

test/schedule_test.cpp:263

↓ 21 callersFunctioncompare

src/value.cpp:489

↓ 21 callersMethodemplace_param

src/targets/gpu/include/migraphx/gpu/compile_hip_code_object.hpp:69

↓ 21 callersFunctionend

src/targets/gpu/device/include/migraphx/gpu/device/array.hpp:83

↓ 21 callersMethodend

src/include/migraphx/matcher.hpp:334

↓ 21 callersMethodis_null

src/value.cpp:235

↓ 21 callersFunctionmake_index

src/targets/gpu/kernels/include/migraphx/kernels/index.hpp:307

↓ 21 callersFunctionmake_shape

src/targets/gpu/kernels/include/migraphx/kernels/shape.hpp:209

↓ 21 callersFunctionmake_tensor

src/targets/gpu/include/migraphx/gpu/miopen.hpp:130

↓ 21 callersFunctionquantize_fp16

This function is to convert any instructions specified in the input from double or float to float16 by inserting a convert operator. For the conversio

src/quantization.cpp:68

↓ 21 callersFunctionrun_pass

test/propagate_constant_test.cpp:33

↓ 21 callersMethodsave

src/driver/main.cpp:433

↓ 21 callersFunctionskip

src/include/migraphx/matcher.hpp:915

↓ 21 callersMethodto_common_from_dst

src/shape_transform_descriptor.cpp:1742

↓ 20 callersMethodanalyze

test/analyze_streams.cpp:143

↓ 20 callersMethodas_standard

src/shape.cpp:575

↓ 20 callersFunctioncalculate_padding

src/pad_calc.cpp:55

↓ 20 callersMethodcommon_dims

src/shape_transform_descriptor.cpp:1932

↓ 20 callersMethoddata

src/targets/gpu/kernels/include/migraphx/kernels/array.hpp:159

↓ 20 callersMethodempty

src/targets/gpu/kernels/include/migraphx/kernels/array.hpp:163

↓ 20 callersFunctionfind_if

src/targets/gpu/kernels/include/migraphx/kernels/algorithm.hpp:149

↓ 20 callersMethodfrom_value

src/program.cpp:816

↓ 20 callersMethodget

src/targets/gpu/fuse_ops.cpp:87

↓ 20 callersMethodget_arg

src/targets/gpu/include/migraphx/gpu/oper.hpp:57

↓ 20 callersMethodis_array

src/value.cpp:211

↓ 20 callersMethodis_nan

src/include/migraphx/float8.hpp:135

↓ 20 callersMethodlocal_stride

src/targets/gpu/kernels/include/migraphx/kernels/index.hpp:277

↓ 20 callersFunctionmake_basic_pred_matcher

src/include/migraphx/matcher.hpp:288

↓ 20 callersFunctionmerge

src/targets/gpu/kernels/include/migraphx/kernels/algorithm.hpp:351

↓ 20 callersFunctionread_onnx

test/api/include/read_onnx.hpp:31

↓ 20 callersFunctionreplace

src/include/migraphx/ranges.hpp:226

↓ 20 callersFunctionshape_for_each

src/include/migraphx/shape_for_each.hpp:38

↓ 20 callersMethodto_common_from_src

src/shape_transform_descriptor.cpp:1730

↓ 20 callersFunctionto_msgpack

src/msgpack.cpp:234

↓ 20 callersFunctiontrim

src/include/migraphx/stringutils.hpp:99

↓ 20 callersFunctionunfold

src/include/migraphx/unfold.hpp:121

↓ 19 callersMethod__init__

(self, config_dict, dtype, device)

examples/diffusion/python_stable_diffusion_3/other_impls.py:502

↓ 19 callersFunctionfill

src/targets/gpu/device/fill.cpp:32

↓ 19 callersFunctionfp4_to_fp8

converts 4 LSB to fp8e4m3fn_type

src/include/migraphx/fp4_casts.hpp:72

↓ 19 callersMethodget_context

test/eval_test.cpp:48

↓ 19 callersFunctiongs_launch

src/targets/gpu/device/include/migraphx/gpu/device/launch.hpp:122

↓ 19 callersMethodvalid

src/instruction.cpp:130

↓ 19 callersMethodwithout_key

src/value.cpp:433

↓ 18 callersMethodattributes

src/api/api.cpp:360

↓ 18 callersFunctionfrom_gpu

src/targets/gpu/hip.cpp:197

↓ 18 callersFunctionfrom_msgpack

src/msgpack.cpp:246

↓ 18 callersMethodlen

src/shape_transform_descriptor.cpp:1915

↓ 18 callersFunctionmake_layer_norm

(shape, axis=-1, dtype=TensorProto.FLOAT, scale_sh

test/onnx/gen_onnx.py:7991

↓ 18 callersMethodmove_instruction

src/module.cpp:416

↓ 18 callersMethodmulti

src/targets/gpu/device/include/migraphx/gpu/device/shape.hpp:92

↓ 18 callersMethodname

test/include/basic_ops.hpp:235

↓ 18 callersMethodnormalize_compute_shape

src/include/migraphx/op/topk.hpp:61

↓ 18 callersFunctionopt_pooling

test/rewrite_pooling_test.cpp:40

↓ 18 callersMethodpush_back

src/targets/gpu/device/include/migraphx/gpu/device/vector.hpp:75

↓ 18 callersMethodreplace

src/module.cpp:1165

↓ 17 callersMethodadd_literal

src/tf/tf_parser.cpp:138

↓ 17 callersMethodapply

test/eval_test.cpp:116

↓ 17 callersMethodcompile

src/program.cpp:228

↓ 17 callersFunctioncreate_literal

src/onnx/onnx_parser.cpp:72

↓ 17 callersFunctioncreate_pointwise_module

test/include/pointwise.hpp:34

↓ 17 callersFunctiondump_mlir

src/targets/gpu/mlir.cpp:1169

↓ 17 callersFunctionfind_permutation

src/targets/gpu/kernels/include/migraphx/kernels/permutation.hpp:92

↓ 17 callersFunctionfp4_to_float

converts 4 LSB to float

src/include/migraphx/fp4_casts.hpp:66

↓ 17 callersMethodget_modules

src/program.cpp:1248

↓ 17 callersFunctioninner_product

src/targets/gpu/kernels/include/migraphx/kernels/algorithm.hpp:210

↓ 17 callersFunctioninsert

src/op/builder/op_builder.cpp:46

↓ 17 callersMethodmax

src/include/migraphx/shape.hpp:367

↓ 17 callersFunctionreorder_shape

src/permutation.cpp:34

↓ 17 callersMethodsize

src/targets/gpu/device/include/migraphx/gpu/device/vector.hpp:66

↓ 17 callersFunctiontune_axis

src/include/migraphx/tune_axis.hpp:33

↓ 16 callersMethodadd_instruction

src/module.cpp:291

↓ 16 callersFunctionbcast_qdq_instr

This method is to prep for quantizelinear or dequantizelinear operation for either the broadcasting of weight-scale or zero-points of qlinearadd opera

src/onnx/broadcast_qdq.cpp:34

↓ 16 callersMethodcompute_shape

src/include/migraphx/operation.hpp:1050

↓ 16 callersFunctionenclose_name

src/module.cpp:1273

↓ 16 callersFunctionfind_permutation

src/permutation.cpp:44

↓ 16 callersFunctiongenerate_for

test/shape_transform_descriptor.cpp:137

↓ 16 callersFunctionget_attrs

test/gpu/mlir.cpp:160

↓ 16 callersFunctionget_device_name

src/targets/gpu/device_name.cpp:49

↓ 16 callersMethodglobal_stride

src/targets/gpu/kernels/include/migraphx/kernels/index.hpp:271

← previous next →301–400 of 10,303, ranked by callers