fix hipify docstring

docs/source/conf.py

@@ -1308,319 +1308,8 @@ coverage_ignore_functions = [
     # torch.onnx.symbolic_opset7
     "max",
     "min",
-    # torch.onnx.symbolic_opset8
-    "addmm",
-    "bmm",
-    "empty",
-    "empty_like",
-    "flatten",
-    "full",
-    "full_like",
-    "gt",
-    "lt",
-    "matmul",
-    "mm",
-    "ones",
-    "ones_like",
-    "prelu",
-    "repeat",
-    "zeros",
-    "zeros_like",
-    # torch.onnx.symbolic_opset9
-    "abs",
-    "acos",
-    "adaptive_avg_pool1d",
-    "adaptive_avg_pool2d",
-    "adaptive_avg_pool3d",
-    "adaptive_max_pool1d",
-    "adaptive_max_pool2d",
-    "adaptive_max_pool3d",
-    "add",
-    "addcmul",
-    "addmm",
-    "alias",
-    "amax",
-    "amin",
-    "aminmax",
-    "arange",
-    "argmax",
-    "argmin",
-    "as_strided",
-    "as_tensor",
-    "asin",
-    "atan",
-    "atan2",
-    "avg_pool1d",
-    "avg_pool2d",
-    "avg_pool3d",
-    "baddbmm",
-    "batch_norm",
-    "bernoulli",
-    "bitwise_not",
-    "bitwise_or",
-    "bmm",
-    "broadcast_tensors",
-    "broadcast_to",
-    "bucketize",
-    "cat",
-    "cdist",
-    "ceil",
-    "clamp",
-    "clamp_max",
-    "clamp_min",
-    "clone",
-    "constant_pad_nd",
-    "contiguous",
-    "conv1d",
-    "conv2d",
-    "conv3d",
-    "conv_tbc",
-    "conv_transpose1d",
-    "conv_transpose2d",
-    "conv_transpose3d",
-    "convert_element_type",
-    "convolution",
-    "cos",
-    "cosine_similarity",
-    "cross",
-    "cumsum",
-    "detach",
     "dim",
-    "div",
-    "dot",
-    "dropout",
-    "elu",
-    "embedding",
-    "embedding_bag",
-    "empty",
-    "empty_like",
-    "eq",
-    "erf",
-    "exp",
-    "expand",
-    "expand_as",
-    "eye",
-    "fill",
-    "flatten",
-    "floor",
-    "floor_divide",
-    "floordiv",
-    "frobenius_norm",
-    "full",
-    "full_like",
-    "gather",
-    "ge",
-    "gelu",
-    "get_pool_ceil_padding",
-    "glu",
-    "group_norm",
-    "gru",
-    "gt",
-    "hann_window",
-    "hardshrink",
-    "hardsigmoid",
-    "hardswish",
-    "hardtanh",
-    "index",
-    "index_add",
-    "index_copy",
-    "index_fill",
-    "index_put",
-    "index_select",
-    "instance_norm",
-    "is_floating_point",
-    "is_pinned",
-    "isnan",
-    "item",
-    "kl_div",
-    "layer_norm",
-    "le",
-    "leaky_relu",
-    "lerp",
-    "lift",
-    "linalg_cross",
-    "linalg_matrix_norm",
-    "linalg_norm",
-    "linalg_vector_norm",
-    "linear",
-    "linspace",
-    "log",
-    "log10",
-    "log1p",
-    "log2",
-    "log_sigmoid",
-    "log_softmax",
-    "logical_and",
-    "logical_not",
-    "logical_or",
-    "logical_xor",
-    "logit",
-    "logsumexp",
-    "lstm",
-    "lstm_cell",
-    "lt",
-    "masked_fill",
-    "masked_fill_",
-    "matmul",
-    "max",
-    "max_pool1d",
-    "max_pool1d_with_indices",
-    "max_pool2d",
-    "max_pool2d_with_indices",
-    "max_pool3d",
-    "max_pool3d_with_indices",
-    "maximum",
-    "meshgrid",
-    "min",
-    "minimum",
-    "mish",
-    "mm",
-    "movedim",
-    "mse_loss",
-    "mul",
-    "multinomial",
-    "mv",
-    "narrow",
-    "native_layer_norm",
-    "ne",
-    "neg",
-    "new_empty",
-    "new_full",
-    "new_ones",
-    "new_zeros",
-    "nonzero",
-    "nonzero_numpy",
-    "noop_complex_operators",
-    "norm",
-    "numel",
-    "numpy_T",
-    "one_hot",
-    "ones",
-    "ones_like",
-    "onnx_placeholder",
-    "overload_by_arg_count",
-    "pad",
-    "pairwise_distance",
-    "permute",
-    "pixel_shuffle",
-    "pixel_unshuffle",
-    "pow",
-    "prelu",
-    "prim_constant",
-    "prim_constant_chunk",
-    "prim_constant_split",
-    "prim_data",
-    "prim_device",
-    "prim_dtype",
-    "prim_if",
-    "prim_layout",
-    "prim_list_construct",
-    "prim_list_unpack",
-    "prim_loop",
-    "prim_max",
-    "prim_min",
-    "prim_shape",
-    "prim_tolist",
-    "prim_tuple_construct",
-    "prim_type",
-    "prim_unchecked_cast",
-    "prim_uninitialized",
-    "rand",
-    "rand_like",
-    "randint",
-    "randint_like",
-    "randn",
-    "randn_like",
-    "reciprocal",
-    "reflection_pad",
-    "relu",
-    "relu6",
-    "remainder",
-    "repeat",
-    "repeat_interleave",
-    "replication_pad",
-    "reshape",
-    "reshape_as",
-    "rnn_relu",
-    "rnn_tanh",
-    "roll",
-    "rrelu",
-    "rsqrt",
-    "rsub",
-    "scalar_tensor",
-    "scatter",
-    "scatter_add",
-    "select",
-    "selu",
-    "sigmoid",
-    "sign",
-    "silu",
-    "sin",
-    "size",
-    "slice",
-    "softmax",
-    "softplus",
-    "softshrink",
-    "sort",
-    "split",
-    "split_with_sizes",
-    "sqrt",
-    "square",
-    "squeeze",
-    "stack",
-    "std",
-    "std_mean",
-    "sub",
-    "t",
-    "take",
-    "tan",
-    "tanh",
-    "tanhshrink",
-    "tensor",
-    "threshold",
-    "to",
-    "topk",
-    "transpose",
-    "true_divide",
-    "type_as",
-    "unbind",
-    "unfold",
-    "unsafe_chunk",
-    "unsafe_split",
-    "unsafe_split_with_sizes",
-    "unsqueeze",
-    "unsupported_complex_operators",
-    "unused",
-    "upsample_bilinear2d",
-    "upsample_linear1d",
-    "upsample_nearest1d",
-    "upsample_nearest2d",
-    "upsample_nearest3d",
-    "upsample_trilinear3d",
-    "var",
-    "var_mean",
-    "view",
-    "view_as",
-    "where",
-    "wrap_logical_op_with_cast_to",
-    "wrap_logical_op_with_negation",
-    "zero",
-    "zeros",
-    "zeros_like",
-    # torch.onnx.utils
-    "disable_apex_o2_state_dict_hook",
     "export",
-    "export_to_pretty_string",
-    "exporter_context",
-    "is_in_onnx_export",
-    "model_signature",
-    "register_custom_op_symbolic",
-    "select_model_mode_for_export",
-    "setup_onnx_logging",
-    "unconvertible_ops",
-    "unpack_quantized_tensor",
-    "warn_on_static_input_change",
-    # torch.onnx.verification
     "check_export_model_diff",
     "verify",
     "verify_aten_graph",
@@ -1711,32 +1400,6 @@ coverage_ignore_functions = [
     "noop_context_fn",
     "set_checkpoint_early_stop",
     "set_device_states",
-    # torch.utils.collect_env
-    "check_release_file",
-    "get_cachingallocator_config",
-    "get_clang_version",
-    "get_cmake_version",
-    "get_conda_packages",
-    "get_cpu_info",
-    "get_cuda_module_loading_config",
-    "get_cudnn_version",
-    "get_env_info",
-    "get_gcc_version",
-    "get_gpu_info",
-    "get_libc_version",
-    "get_lsb_version",
-    "get_mac_version",
-    "get_nvidia_driver_version",
-    "get_nvidia_smi",
-    "get_os",
-    "get_pip_packages",
-    "get_platform",
-    "get_pretty_env_info",
-    "get_python_platform",
-    "get_running_cuda_version",
-    "get_windows_version",
-    "is_xnnpack_available",
-    "pretty_str",
     # torch.utils.cpp_backtrace
     "get_cpp_backtrace",
     # torch.utils.cpp_extension
@@ -1800,52 +1463,6 @@ coverage_ignore_functions = [
     "apply_shuffle_seed",
     "apply_shuffle_settings",
     "get_all_graph_pipes",
-    # torch.utils.flop_counter
-    "addmm_flop",
-    "baddbmm_flop",
-    "bmm_flop",
-    "conv_backward_flop",
-    "conv_flop",
-    "conv_flop_count",
-    "convert_num_with_suffix",
-    "get_shape",
-    "get_suffix_str",
-    "mm_flop",
-    "normalize_tuple",
-    "register_flop_formula",
-    "sdpa_backward_flop",
-    "sdpa_backward_flop_count",
-    "sdpa_flop",
-    "sdpa_flop_count",
-    "shape_wrapper",
-    "transpose_shape",
-    # torch.utils.hipify.hipify_python
-    "add_dim3",
-    "compute_stats",
-    "extract_arguments",
-    "file_add_header",
-    "file_specific_replacement",
-    "find_bracket_group",
-    "find_closure_group",
-    "find_parentheses_group",
-    "fix_static_global_kernels",
-    "get_hip_file_path",
-    "hip_header_magic",
-    "hipify",
-    "is_caffe2_gpu_file",
-    "is_cusparse_file",
-    "is_out_of_place",
-    "is_pytorch_file",
-    "is_special_file",
-    "match_extensions",
-    "matched_files_iter",
-    "openf",
-    "preprocess_file_and_save_result",
-    "preprocessor",
-    "processKernelLaunches",
-    "replace_extern_shared",
-    "replace_math_functions",
-    "str2bool",
     # torch.utils.hooks
     "unserializable_hook",
     "warn_if_has_hooks",

docs/source/utils.md

@@ -19,6 +19,91 @@
     swap_tensors
 ```
 
+# torch.utils.collect_env
+```{eval-rst}
+.. automodule:: torch.utils.collect_env
+```
+
+```{eval-rst}
+.. currentmodule:: torch.utils.collect_env
+```
+
+```{eval-rst}
+.. autosummary::
+    :toctree: generated
+    :nosignatures:
+
+    check_release_file
+    is_xnnpack_available
+    pretty_str
+```
+
+# torch.utils.flop_counter
+```{eval-rst}
+.. automodule:: torch.utils.flop_counter
+```
+
+```{eval-rst}
+.. currentmodule:: torch.utils.flop_counter
+```
+
+```{eval-rst}
+.. autosummary::
+    :toctree: generated
+    :nosignatures:
+
+    baddbmm_flop
+    bmm_flop
+    conv_backward_flop
+    conv_flop
+    conv_flop_count
+    register_flop_formula
+    sdpa_backward_flop
+    sdpa_backward_flop_count
+    sdpa_flop
+    sdpa_flop_count
+    shape_wrapper
+```
+
+# torch.utils.hipify.hipify_python
+```{eval-rst}
+.. automodule:: torch.utils.hipify.hipify_python
+```
+
+```{eval-rst}
+.. currentmodule:: torch.utils.hipify.hipify_python
+```
+
+```{eval-rst}
+.. autosummary::
+    :toctree: generated
+    :nosignatures:
+
+    compute_stats
+    extract_arguments
+    file_add_header
+    file_specific_replacement
+    find_bracket_group
+    find_closure_group
+    find_parentheses_group
+    fix_static_global_kernels
+    hip_header_magic
+    hipify
+    is_caffe2_gpu_file
+    is_cusparse_file
+    is_out_of_place
+    is_pytorch_file
+    is_special_file
+    openf
+    preprocess_file_and_save_result
+    preprocessor
+    processKernelLaunches
+    replace_extern_shared
+    replace_math_functions
+    str2bool
+```
+
+
 <!-- This module needs to be documented. Adding here in the meantime
 for tracking purposes -->
 ```{eval-rst}
@@ -43,7 +128,6 @@ for tracking purposes -->
 .. py:module:: torch.utils.benchmark.utils.valgrind_wrapper.timer_interface
 .. py:module:: torch.utils.bundled_inputs
 .. py:module:: torch.utils.checkpoint
-.. py:module:: torch.utils.collect_env
 .. py:module:: torch.utils.cpp_backtrace
 .. py:module:: torch.utils.cpp_extension
 .. py:module:: torch.utils.data.backward_compatibility
@@ -80,10 +164,8 @@ for tracking purposes -->
 .. py:module:: torch.utils.data.sampler
 .. py:module:: torch.utils.dlpack
 .. py:module:: torch.utils.file_baton
-.. py:module:: torch.utils.flop_counter
 .. py:module:: torch.utils.hipify.constants
 .. py:module:: torch.utils.hipify.cuda_to_hip_mappings
-.. py:module:: torch.utils.hipify.hipify_python
 .. py:module:: torch.utils.hipify.version
 .. py:module:: torch.utils.hooks
 .. py:module:: torch.utils.jit.log_extract

torch/utils/hipify/hipify_python.py

@@ -529,11 +529,14 @@ RE_EXTERN_SHARED = re.compile(r"extern\s+([\w\(\)]+)?\s*__shared__\s+([\w:<>\s]+
 
 
 def replace_extern_shared(input_string):
-    """Match extern __shared__ type foo[]; syntax and use HIP_DYNAMIC_SHARED() MACRO instead.
-       https://github.com/ROCm/hip/blob/master/docs/markdown/hip_kernel_language.md#__shared__
-    Example:
-        "extern __shared__ char smemChar[];" => "HIP_DYNAMIC_SHARED( char, smemChar)"
-        "extern __shared__ unsigned char smem[];" => "HIP_DYNAMIC_SHARED( unsigned char, my_smem)"
+    """
+    Match 'extern __shared__ type foo[];' syntax and use HIP_DYNAMIC_SHARED() MACRO instead.
+    See: https://github.com/ROCm/hip/blob/master/docs/markdown/hip_kernel_language.md#__shared__
+    Examples:
+        "extern __shared__ char smemChar[];"
+            => "HIP_DYNAMIC_SHARED( char, smemChar)"
+        "extern __shared__ unsigned char smem[];"
+            => "HIP_DYNAMIC_SHARED( unsigned char, my_smem)"
     """
     output_string = input_string
     output_string = RE_EXTERN_SHARED.sub(
@@ -1043,14 +1046,17 @@ RE_INCLUDE = re.compile(r"#include .*\n")
 
 
 def extract_arguments(start, string):
-    """ Return the list of arguments in the upcoming function parameter closure.
-        Example:
+    """
+    Return the list of arguments in the upcoming function parameter closure.
+    Example:
         string (input): '(blocks, threads, 0, THCState_getCurrentStream(state))'
         arguments (output):
-            '[{'start': 1, 'end': 7},
-            {'start': 8, 'end': 16},
-            {'start': 17, 'end': 19},
-            {'start': 20, 'end': 53}]'
+            [
+                {'start': 1, 'end': 7},
+                {'start': 8, 'end': 16},
+                {'start': 17, 'end': 19},
+                {'start': 20, 'end': 53}
+            ]
     """
 
     arguments = []