Files
pytorch/tools/setup_helpers/generate_code.py
Dhruv Matani 0c5cd8c2b9 [RFC] Switch PyTorch Selective Build (Custom Build) to use the SelectiveBuilder abstraction (#45722)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/45722

This diff does a bunch of things:

1. Introduces some abstractions as detailed in https://fb.quip.com/2oEzAR5MKqbD to help with selective build related codegen in multiple files.
2. Adds helper methods to combine operators, debug info, operator lists, etc...
3. Currently, the selective build machinery querying `op_registration_whitelist` directly at various places in the code. `op_registration_whitelist` is a list of allowed operator names (without overload name). We want to move to a world where the overload names are also included so that we can be more selective about which operators we include. To that effect, it makes sense to hide the checking logic in a separate abstraction and have the build use that abstraction instead of putting all this selective build specific logic in the code-generator itself. This change is attempting to do just that.
4. Updates generate_code, unboxing-wrapper codegen, and autograd codegen to accept the operator selector paradigm as opposed to a selected operator list.
5. Update `tools/code_analyzer/gen_op_registration_allowlist.py` to expose providing an actual structured operator dependency graph in addition to a serialized string.

There are a bunch of structural changes as well:

1. `root_op_list.yaml` and `combined_op_list.yaml` are now actual YAML files (not a space separated list of operator names)
2. `generate_code.py` accepts only paths to operator list YAML files (both old style as well as new style) and not list of operator names on the command line as arguments
3. `gen.py` optionally also accepts a custom build related operators YAML path (this file has information about which operators to register in the generated library).

ghstack-source-id: 114578753

(Note: this ignores all push blocking failures!)

Test Plan:
`buck test caffe2/test:selective_build`

Generated YAML files after the change:

{P143981979}

{P143982025}

{P143982056}

Ensure that the generated files are same before and after the change:

```
[dhruvbird@devvm2490 /tmp/TypeDefault.cpp] find -name "*.cpp" | xargs md5sum
d72c3d125baa7b77e4c5581bbc7110d2  ./after_change/gen_aten/TypeDefault.cpp
42353036c83ebc7620a7159235b9647f  ./after_change/lite_predictor_lib_aten/TypeDefault.cpp
d72c3d125baa7b77e4c5581bbc7110d2  ./before_change/gen_aten/TypeDefault.cpp
42353036c83ebc7620a7159235b9647f  ./before_change/lite_predictor_lib_aten/TypeDefault.cpp
```

`VariableTypes_N.cpp` are generated the same both before and after the change:

```
[dhruvbird@devvm2490 /tmp/VariableType] find -name "*.cpp" | xargs -n 1 md5sum | sort
3be89f63fd098291f01935077a60b677  ./after/VariableType_2.cpp
3be89f63fd098291f01935077a60b677  ./before/VariableType_2.cpp
40a3e59d64e9dbe86024cf314f127fd6  ./after/VariableType_4.cpp
40a3e59d64e9dbe86024cf314f127fd6  ./before/VariableType_4.cpp
a4911699ceda3c3a430f08c64e8243fd  ./after/VariableType_1.cpp
a4911699ceda3c3a430f08c64e8243fd  ./before/VariableType_1.cpp
ca9aa611fcb2a573a8cba4e269468c99  ./after/VariableType_0.cpp
ca9aa611fcb2a573a8cba4e269468c99  ./before/VariableType_0.cpp
e18f639ed23d802dc4a31cdba40df570  ./after/VariableType_3.cpp
e18f639ed23d802dc4a31cdba40df570  ./before/VariableType_3.cpp
```

Reviewed By: ljk53

Differential Revision: D23837010

fbshipit-source-id: ad06b1756af5be25baa39fd801dfdf09bc565442
2020-10-18 15:10:42 -07:00

178 lines
6.3 KiB
Python

import argparse
import os
import sys
source_files = {'.py', '.cpp', '.h'}
DECLARATIONS_PATH = 'torch/share/ATen/Declarations.yaml'
# TODO: This is a little inaccurate, because it will also pick
# up setup_helper scripts which don't affect code generation
def all_generator_source():
r = []
for directory, _, filenames in os.walk('tools'):
for f in filenames:
if os.path.splitext(f)[1] in source_files:
full = os.path.join(directory, f)
r.append(full)
return sorted(r)
def generate_code(ninja_global=None,
declarations_path=None,
nn_path=None,
install_dir=None,
subset=None,
disable_autograd=False,
force_schema_registration=False,
operator_selector=None):
from tools.autograd.gen_autograd import gen_autograd, gen_autograd_python
from tools.autograd.gen_annotated_fn_args import gen_annotated
from tools.jit.gen_unboxing_wrappers import gen_unboxing_wrappers
from tools.codegen.selective_build.selector import SelectiveBuilder
# Build ATen based Variable classes
if install_dir is None:
install_dir = 'torch/csrc'
python_install_dir = 'torch/testing/_internal/generated'
else:
python_install_dir = install_dir
autograd_gen_dir = os.path.join(install_dir, 'autograd', 'generated')
jit_gen_dir = os.path.join(install_dir, 'jit', 'generated')
for d in (autograd_gen_dir, jit_gen_dir, python_install_dir):
if not os.path.exists(d):
os.makedirs(d)
runfiles_dir = os.environ.get("RUNFILES_DIR", None)
data_dir = os.path.join(runfiles_dir, 'pytorch') if runfiles_dir else ''
autograd_dir = os.path.join(data_dir, 'tools', 'autograd')
tools_jit_templates = os.path.join(data_dir, 'tools', 'jit', 'templates')
if subset == "pybindings" or not subset:
gen_autograd_python(declarations_path or DECLARATIONS_PATH, autograd_gen_dir, autograd_dir)
if operator_selector is None:
operator_selector = SelectiveBuilder.get_nop_selector()
if subset == "libtorch" or not subset:
gen_autograd(
declarations_path or DECLARATIONS_PATH,
autograd_gen_dir,
autograd_dir,
disable_autograd=disable_autograd,
operator_selector=operator_selector,
)
gen_unboxing_wrappers(
declarations_path or DECLARATIONS_PATH,
jit_gen_dir,
tools_jit_templates,
disable_autograd=disable_autograd,
operator_selector=operator_selector,
force_schema_registration=force_schema_registration)
if subset == "python" or not subset:
gen_annotated(
declarations_path or DECLARATIONS_PATH,
python_install_dir,
autograd_dir)
def get_selector_from_legacy_operator_selection_list(
selected_op_list_path: str,
):
from tools.autograd.utils import load_op_list_and_strip_overload
selected_op_list = load_op_list_and_strip_overload(
None,
selected_op_list_path,
)
# Internal build doesn't use this flag any more. Only used by OSS
# build now. Every operator should be considered a root operator
# (hence generating unboxing code for it, which is consistent with
# the current behaviour), and also be considered as used for
# training, since OSS doesn't support training on mobile for now.
#
is_root_operator = True
is_used_for_training = True
from tools.codegen.selective_build.selector import SelectiveBuilder
selector: SelectiveBuilder = SelectiveBuilder.get_nop_selector()
if selected_op_list is not None:
selector = SelectiveBuilder.from_legacy_op_registration_allow_list(
selected_op_list,
is_root_operator,
is_used_for_training,
)
return selector
def get_selector(selected_op_list_path, operators_yaml_path):
# cwrap depends on pyyaml, so we can't import it earlier
root = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
sys.path.insert(0, root)
from tools.codegen.selective_build.selector import SelectiveBuilder
assert not (selected_op_list_path is not None and
operators_yaml_path is not None), \
("Expected at most one of selected_op_list_path and " +
"operators_yaml_path to be set.")
if selected_op_list_path is None and operators_yaml_path is None:
return SelectiveBuilder.get_nop_selector()
elif selected_op_list_path is not None:
return get_selector_from_legacy_operator_selection_list(selected_op_list_path)
else:
return SelectiveBuilder.from_yaml_path(operators_yaml_path)
def main():
parser = argparse.ArgumentParser(description='Autogenerate code')
parser.add_argument('--declarations-path')
parser.add_argument('--nn-path')
parser.add_argument('--ninja-global')
parser.add_argument('--install_dir')
parser.add_argument(
'--subset',
help='Subset of source files to generate. Can be "libtorch" or "pybindings". Generates both when omitted.'
)
parser.add_argument(
'--disable-autograd',
default=False,
action='store_true',
help='It can skip generating autograd related code when the flag is set',
)
parser.add_argument(
'--selected-op-list-path',
help='Path to the yaml file that contains the list of operators to include for custom build.',
)
parser.add_argument(
'--operators_yaml_path',
help='Path to the model YAML file that contains the list of operators to include for custom build.',
)
parser.add_argument(
'--force_schema_registration',
action='store_true',
help='force it to generate schema-only registrations for ops that are not'
'listed on --selected-op-list'
)
options = parser.parse_args()
generate_code(
options.ninja_global,
options.declarations_path,
options.nn_path,
options.install_dir,
options.subset,
options.disable_autograd,
options.force_schema_registration,
# options.selected_op_list
operator_selector=get_selector(options.selected_op_list_path, options.operators_yaml_path),
)
if __name__ == "__main__":
main()