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

↓ 4 callersMethodadd_param

(self, t: Union[str, Type], name: Optional[str] = None)

tools/api.py:256

↓ 4 callersMethodadd_params

src/module.cpp:1096

↓ 4 callersMethodadd_split_axis

src/shape_transform_descriptor.cpp:1967

↓ 4 callersFunctionadjacent_remove_if

src/include/migraphx/algorithm.hpp:144

↓ 4 callersFunctionany_arg

src/include/migraphx/matcher.hpp:1043

↓ 4 callersMethodapply

test/verify/verify_program.hpp:49

↓ 4 callersMethodapply

src/include/migraphx/matcher.hpp:661

↓ 4 callersFunctionarg_op

src/targets/gpu/include/migraphx/gpu/device/arg_op.hpp:131

↓ 4 callersFunctionargument

src/include/migraphx/argument.hpp:47

↓ 4 callersFunctionas_number

src/include/migraphx/as_number.hpp:34

↓ 4 callersFunctionatomic_assign

src/targets/gpu/kernels/include/migraphx/kernels/atomic.hpp:136

↓ 4 callersMethodbegin

src/include/migraphx/transform_view.hpp:110

↓ 4 callersFunctionbit_cast_and_handle_specials

test/fp8_ocp_to_fnuz_test.cpp:63

↓ 4 callersFunctioncast_fp8_helper

test/fp8_ocp_to_fnuz_test.cpp:97

↓ 4 callersFunctioncheck_padding_mode

src/onnx/padding.cpp:70

↓ 4 callersFunctioncheck_shapes

test/py/test_array.py:66

↓ 4 callersMethodclear

src/include/migraphx/bit_signal.hpp:84

↓ 4 callersMethodclear_arguments

src/instruction.cpp:115

↓ 4 callersFunctioncommon_average

src/program.cpp:867

↓ 4 callersFunctioncompile

src/targets/gpu/compiler.cpp:56

↓ 4 callersMethodcompile

src/targets/gpu/fuse_ops.cpp:140

↓ 4 callersMethodcompile

src/targets/gpu/include/migraphx/gpu/convolution.hpp:153

↓ 4 callersMethodcompute

src/common_dims.cpp:163

↓ 4 callersFunctioncompute_dominator

src/dom_info.cpp:94

↓ 4 callersFunctioncompute_op

src/include/migraphx/operation.hpp:201

↓ 4 callersMethodcompute_shape

src/targets/gpu/include/migraphx/gpu/hip.hpp:106

↓ 4 callersFunctioncompute_shape_op

src/include/migraphx/operation.hpp:133

↓ 4 callersMethodcompute_shapes

src/module.cpp:751

↓ 4 callersFunctionconv_const_weights

src/simplify_algebra.cpp:60

↓ 4 callersMethodcopy

src/argument.cpp:186

↓ 4 callersFunctioncpp_var_name

src/module.cpp:1306

↓ 4 callersFunctioncreate_broadcast_index

src/targets/gpu/device/include/migraphx/gpu/device/nary.hpp:67

↓ 4 callersFunctioncreate_gather

test/normalize_ops_test.cpp:69

↓ 4 callersFunctioncreate_gqa_program

test/onnx/include/onnx_test_utils.hpp:207

↓ 4 callersFunctioncreate_key

src/targets/gpu/problem_cache.cpp:60

↓ 4 callersFunctioncreate_program

test/run_loop_test.cpp:163

↓ 4 callersFunctioncreate_reduce_mean

test/normalize_ops_test.cpp:121

↓ 4 callersFunctioncreate_slice

test/normalize_ops_test.cpp:150

↓ 4 callersMethoddebug_print

src/value.cpp:590

↓ 4 callersFunctiondequantizelinear_op

* Find dequantizelinear (DQ) instruction with constant scale and zero point input * while skipping broadcast instructions between DQ and scale/zero p

src/include/migraphx/match/dq_helpers.hpp:40

↓ 4 callersFunctiondfor

Multidimensional for loop

src/targets/gpu/kernels/include/migraphx/kernels/dfor.hpp:30

↓ 4 callersFunctiondisabled

src/include/migraphx/env.hpp:58

↓ 4 callersFunctiondpp_row_shr

src/targets/gpu/kernels/include/migraphx/kernels/dpp.hpp:40

↓ 4 callersFunctiondpp_row_shr

src/targets/gpu/device/include/migraphx/gpu/device/reduce.hpp:76

↓ 4 callersMethodelements

src/targets/gpu/kernels/include/migraphx/kernels/reduce.hpp:443

↓ 4 callersFunctionemplace

src/include/migraphx/value.hpp:333

↓ 4 callersMethodempty

src/argument.cpp:146

↓ 4 callersMethodempty

src/targets/gpu/fuse_ops.cpp:75

↓ 4 callersMethodempty

src/api/include/migraphx/migraphx.hpp:224

↓ 4 callersMethodencoder

(self, inp, feature_length)

examples/nlp/python_rnnt/rnnt.py:160

↓ 4 callersMethodend

src/api/include/migraphx/migraphx.hpp:245

↓ 4 callersMethodend

src/include/migraphx/transform_view.hpp:111

↓ 4 callersFunctionerase_iterator

test/algorithm.cpp:42

↓ 4 callersFunctionexec

src/process.cpp:57

↓ 4 callersFunctionfast_div

src/targets/gpu/device/include/migraphx/gpu/device/fast_div.hpp:48

↓ 4 callersMethodfill

src/include/migraphx/literal.hpp:113

↓ 4 callersMethodfind_broadcasted_axes

src/shape_transform_descriptor.cpp:1706

↓ 4 callersFunctionfind_idx

src/include/migraphx/verify.hpp:150

↓ 4 callersFunctionfind_vectorize_size

src/targets/gpu/kernels/include/migraphx/kernels/vectorize.hpp:167

↓ 4 callersMethodfinish

src/include/migraphx/context.hpp:304

↓ 4 callersMethodfloat

upcast using device specific intrinsic

src/targets/gpu/kernels/include/migraphx/kernels/float8.hpp:250

↓ 4 callersMethodfor_stride

src/targets/gpu/device/include/migraphx/gpu/device/multi_index.hpp:44

↓ 4 callersMethodfrom_value

src/targets/gpu/include/migraphx/gpu/context.hpp:349

↓ 4 callersFunctiongeneric_get_modules

src/program.cpp:1224

↓ 4 callersFunctiongeneric_get_unused_modules

src/program.cpp:1234

↓ 4 callersMethodget

src/targets/gpu/driver/include/migraphx/gpu/driver/parser.hpp:47

↓ 4 callersFunctionget_batch_stride

src/targets/gpu/gemm_impl.cpp:155

↓ 4 callersFunctionget_between_ins

src/simplify_qdq.cpp:52

↓ 4 callersFunctionget_bit

src/targets/gpu/kernels/include/migraphx/kernels/bit.hpp:33

↓ 4 callersFunctionget_changed_files

Return a list of files that are staged for commit and have changed compared to the merge base with the given branch. Only includes modifi

tools/git_tools.py:76

↓ 4 callersMethodget_coord_trans_mode

src/onnx/parse_resize.cpp:158

↓ 4 callersFunctionget_device_name

src/targets/gpu/device/targets.cpp:54

↓ 4 callersMethodget_event_id

src/include/migraphx/stream_model.hpp:200

↓ 4 callersMethodget_exhaustive_tune_flag

src/targets/gpu/include/migraphx/gpu/context.hpp:296

↓ 4 callersFunctionget_hash

src/driver/perf.cpp:43

↓ 4 callersFunctionget_name

src/tf/tf_parser.cpp:165

↓ 4 callersFunctionget_output_name

examples/diffusion/python_stable_diffusion_3/txt2img.py:193

↓ 4 callersFunctionget_splits

Search for multiple "slice" instructions in an instruction's outputs * which are contiguous slices of the same tensor. */

src/simplify_algebra.cpp:1119

↓ 4 callersFunctionget_version

src/driver/main.cpp:103

↓ 4 callersMethodget_workspace

src/targets/gpu/fuse_ops.cpp:127

↓ 4 callersFunctiongfx_has_fp8fnuz_intrinsics

src/targets/gpu/device_name.cpp:58

↓ 4 callersFunctiongfx_has_fp8ocp_intrinsics

src/targets/gpu/device_name.cpp:64

↓ 4 callersFunctiongpu_sync

src/targets/gpu/hip.cpp:225

↓ 4 callersMethodgroup

src/targets/cpu/binary.cpp:40

↓ 4 callersMethodgroup_stride

src/targets/gpu/kernels/include/migraphx/kernels/index.hpp:283

↓ 4 callersMethodhas_finalize

src/include/migraphx/operation.hpp:1020

↓ 4 callersFunctionhas_target_attr

check if it is custom_op or run_on_module operator

test/multi_target/multitarget_test.cpp:46

↓ 4 callersFunctionhip_visit_views

src/targets/gpu/device/include/migraphx/gpu/device/visit.hpp:229

↓ 4 callersMethodif_array

src/value.cpp:218

↓ 4 callersFunctioninit_zero_point

test/simplify_qdq_test.cpp:57

↓ 4 callersMethodinsert_literal

src/module.cpp:584

↓ 4 callersFunctioninsert_mlir

src/targets/gpu/mlir.cpp:1319

↓ 4 callersFunctioninsert_module_in_submodule

src/fuse_reduce.cpp:95

↓ 4 callersMethodinsert_parameter

src/module.cpp:590

↓ 4 callersFunctioninsert_quantizelinear_clip

test/onnx/include/onnx_test_utils.hpp:702

↓ 4 callersFunctionis_ck_gemm

src/targets/gpu/prefuse_ops.cpp:139

↓ 4 callersMethodis_compiled

src/program.cpp:226

↓ 4 callersMethodis_const

tools/api.py:65

↓ 4 callersFunctionis_dead

src/fuse_pointwise.cpp:70

↓ 4 callersFunctionis_device_ptr

src/targets/gpu/hip.cpp:55

← previous next →901–1,000 of 10,303, ranked by callers