2021-01-26 17:01:03 +00:00
|
|
|
# This is the PyTorch mypy-strict.ini file (note: don't change this line! -
|
|
|
|
|
# test_run_mypy in test/test_type_hints.py uses this string)
|
|
|
|
|
|
|
|
|
|
# Unlike mypy.ini, it enforces very strict typing rules. The intention is for
|
|
|
|
|
# this config file to be used to ENFORCE that people are using mypy on codegen
|
|
|
|
|
# files.
|
|
|
|
|
|
More Timer refinement (#46023)
Summary:
This PR just adds more polish to the benchmark utils:
1) `common.py`, `timer.py`, and `valgrind_wrapper/timer_interface.py` are now MyPy strict compliant. (except for three violations due to external deps.) Compare and Fuzzer will be covered in a future PR.
2) `CallgrindStats` now uses `TaskSpec` rather than accepting the individual fields which brings it closer to `Measurement`.
3) Some `__repr__` logic has been moved into `TaskSpec` (which `Measurement` and `CallgrindStats` use in their own `__repr__`s) for a more unified feel and less horrible f-string hacking, and the repr's have been given a cleanup pass.
4) `Tuple[FunctionCount, ...]` has been formalized as the `FunctionCounts` class, which has a much nicer `__repr__` than just the raw tuple, as well as some convenience methods (`__add__`, `__sub__`, `filter`, `transform`) for easier DIY stat exploration. (I find myself using the latter two a lot now.) My personal experience is that manipulating `FunctionCounts` is massively more pleasant than the raw tuples of `FunctionCount`. (Though it's still possible to get at the raw data if you want.)
5) Better support for multi-line `stmt` and `setup`.
6) Compare now also supports rowwise coloring, which is often the more natural layout for A/B testing.
7) Limited support for `globals` in `collect_callgrind`. This should make it easier to benchmark JIT models. (CC ZolotukhinM)
8) More unit tests, including extensive tests for the Callgrind stats manipulation APIs.
9) Mitigate issue with `MKL_THREADING_LAYER` when run in Jupyter. (https://github.com/pytorch/pytorch/issues/37377)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46023
Test Plan: changes should be covered by existing and new unit tests.
Reviewed By: navahgar, malfet
Differential Revision: D24313911
Pulled By: robieta
fbshipit-source-id: 835d4b5cde336fb7ff0adef3c0fd614d64df0f77
2020-10-15 23:30:49 +00:00
|
|
|
# For now, only code_template.py and benchmark utils Timer are covered this way
|
2020-08-05 19:25:10 +00:00
|
|
|
|
|
|
|
|
[mypy]
|
|
|
|
|
python_version = 3.6
|
2021-02-08 23:34:53 +00:00
|
|
|
plugins = mypy_plugins/check_mypy_version.py
|
2020-08-05 19:25:10 +00:00
|
|
|
|
2021-01-19 18:03:04 +00:00
|
|
|
cache_dir = .mypy_cache/strict
|
2020-08-05 19:25:10 +00:00
|
|
|
strict_optional = True
|
|
|
|
|
show_column_numbers = True
|
|
|
|
|
warn_no_return = True
|
|
|
|
|
disallow_any_unimported = True
|
|
|
|
|
|
|
|
|
|
# Across versions of mypy, the flags toggled by --strict vary. To ensure
|
|
|
|
|
# we have reproducible type check, we instead manually specify the flags
|
|
|
|
|
warn_unused_configs = True
|
|
|
|
|
disallow_any_generics = True
|
|
|
|
|
disallow_subclassing_any = True
|
|
|
|
|
disallow_untyped_calls = True
|
|
|
|
|
disallow_untyped_defs = True
|
|
|
|
|
disallow_incomplete_defs = True
|
|
|
|
|
check_untyped_defs = True
|
|
|
|
|
disallow_untyped_decorators = True
|
|
|
|
|
no_implicit_optional = True
|
|
|
|
|
warn_redundant_casts = True
|
|
|
|
|
warn_unused_ignores = True
|
|
|
|
|
warn_return_any = True
|
|
|
|
|
implicit_reexport = False
|
|
|
|
|
strict_equality = True
|
|
|
|
|
|
More Timer refinement (#46023)
Summary:
This PR just adds more polish to the benchmark utils:
1) `common.py`, `timer.py`, and `valgrind_wrapper/timer_interface.py` are now MyPy strict compliant. (except for three violations due to external deps.) Compare and Fuzzer will be covered in a future PR.
2) `CallgrindStats` now uses `TaskSpec` rather than accepting the individual fields which brings it closer to `Measurement`.
3) Some `__repr__` logic has been moved into `TaskSpec` (which `Measurement` and `CallgrindStats` use in their own `__repr__`s) for a more unified feel and less horrible f-string hacking, and the repr's have been given a cleanup pass.
4) `Tuple[FunctionCount, ...]` has been formalized as the `FunctionCounts` class, which has a much nicer `__repr__` than just the raw tuple, as well as some convenience methods (`__add__`, `__sub__`, `filter`, `transform`) for easier DIY stat exploration. (I find myself using the latter two a lot now.) My personal experience is that manipulating `FunctionCounts` is massively more pleasant than the raw tuples of `FunctionCount`. (Though it's still possible to get at the raw data if you want.)
5) Better support for multi-line `stmt` and `setup`.
6) Compare now also supports rowwise coloring, which is often the more natural layout for A/B testing.
7) Limited support for `globals` in `collect_callgrind`. This should make it easier to benchmark JIT models. (CC ZolotukhinM)
8) More unit tests, including extensive tests for the Callgrind stats manipulation APIs.
9) Mitigate issue with `MKL_THREADING_LAYER` when run in Jupyter. (https://github.com/pytorch/pytorch/issues/37377)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46023
Test Plan: changes should be covered by existing and new unit tests.
Reviewed By: navahgar, malfet
Differential Revision: D24313911
Pulled By: robieta
fbshipit-source-id: 835d4b5cde336fb7ff0adef3c0fd614d64df0f77
2020-10-15 23:30:49 +00:00
|
|
|
files = tools/codegen/gen.py,
|
2021-01-19 07:51:50 +00:00
|
|
|
tools/autograd/*.py,
|
|
|
|
|
tools/pyi/*.py,
|
2021-02-11 21:11:32 +00:00
|
|
|
tools/test_history.py,
|
2021-03-15 23:31:47 +00:00
|
|
|
torch/testing/_internal/framework_utils.py,
|
2021-01-26 17:01:03 +00:00
|
|
|
torch/testing/_internal/mypy_wrapper.py,
|
[reland] Report test time regressions (#50171)
Summary:
This is a followup to https://github.com/pytorch/pytorch/issues/49190. Vaguely speaking, the goals are to make it easy to identify test time regressions introduced by PRs. Eventually the hope is to use this information to edit Dr CI comments, but this particular PR just does the analysis and prints it to stdout, so a followup PR would be needed to edit the actual comments on GitHub.
**Important:** for uninteresting reasons, this PR moves the `print_test_stats.py` file.
- *Before:* `test/print_test_stats.py`
- *After:* `torch/testing/_internal/print_test_stats.py`
Notes on the approach:
- Just getting the mean and stdev for the total job time of the last _N_ commits isn't sufficient, because e.g. if `master` was broken 5 commits ago, then a lot of those job times will be much shorter, breaking the statistics.
- We use the commit history to make better estimates for the mean and stdev of individual test (and suite) times, but only when the test in that historical commit is present and its status matches that of the base commit.
- We list all the tests that were removed or added, or whose status changed (e.g. skipped to not skipped, or vice versa), along with time (estimate) info for that test case and its containing suite.
- We don't list tests whose time changed a lot if their status didn't change, because there's a lot of noise and it's unclear how to do that well without too many false positives.
- We show a human-readable commit graph that indicates exactly how many commits are in the pool of commits that could be causing regressions (e.g. if a PR has multiple commits in it, or if the base commit on `master` doesn't have a report in S3).
- We don't show an overall estimate of whether the PR increased or decreased the total test job time, because it's noisy and it's a bit tricky to aggregate stdevs up from individual tests to the whole job level. This might change in a followup PR.
- Instead, we simply show a summary at the bottom which says how many tests were removed/added/modified (where "modified" means that the status changed), and our best estimates of the mean times (and stdevs) of those changes.
- Importantly, the summary at the bottom is only for the test cases that were already shown in the more verbose diff report, and does not include any information about tests whose status didn't change but whose running time got much longer.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/50171
Test Plan:
To run the unit tests:
```
$ python test/test_testing.py
$ python test/print_test_stats.py
```
To verify that this works, check the [CircleCI logs](https://app.circleci.com/pipelines/github/pytorch/pytorch/258628/workflows/9cfadc34-e042-485e-b3b3-dc251f160307) for a test job run on this PR; for example:
- pytorch_linux_bionic_py3_6_clang9_test
To test locally, use the following steps.
First run an arbitrary test suite (you need to have some XML reports so that `test/print_test_stats.py` runs, but we'll be ignoring them here via the `--use-json` CLI option):
```
$ DATA_DIR=/tmp
$ ARBITRARY_TEST=testing
$ python test/test_$ARBITRARY_TEST.py --save-xml=$DATA_DIR/test/test_$ARBITRARY_TEST
```
Now choose a commit and a test job (it has to be on `master` since we're going to grab the test time data from S3, and [we only upload test times to S3 on the `master`, `nightly`, and `release` branches](https://github.com/pytorch/pytorch/pull/49645)):
```
$ export CIRCLE_SHA1=c39fb9771d89632c5c3a163d3c00af3bef1bd489
$ export CIRCLE_JOB=pytorch_linux_bionic_py3_6_clang9_test
```
Download the `*.json.bz2` file(s) for that commit/job pair:
```
$ aws s3 cp s3://ossci-metrics/test_time/$CIRCLE_SHA1/$CIRCLE_JOB/ $DATA_DIR/ossci-metrics/test_time/$CIRCLE_SHA1/$CIRCLE_JOB --recursive
```
And feed everything into `test/print_test_stats.py`:
```
$ bzip2 -kdc $DATA_DIR/ossci-metrics/test_time/$CIRCLE_SHA1/$CIRCLE_JOB/*Z.json.bz2 | torch/testing/_internal/print_test_stats.py --compare-with-s3 --use-json=/dev/stdin $DATA_DIR/test/test_$ARBITRARY_TEST
```
The first part of the output should be the same as before this PR; here is the new part, at the end of the output:
- https://pastebin.com/Jj1svhAn
Reviewed By: malfet, izdeby
Differential Revision: D26317769
Pulled By: samestep
fbshipit-source-id: 1ba06cec0fafac77f9e7341d57079543052d73db
2021-02-08 23:27:11 +00:00
|
|
|
torch/testing/_internal/print_test_stats.py,
|
More Timer refinement (#46023)
Summary:
This PR just adds more polish to the benchmark utils:
1) `common.py`, `timer.py`, and `valgrind_wrapper/timer_interface.py` are now MyPy strict compliant. (except for three violations due to external deps.) Compare and Fuzzer will be covered in a future PR.
2) `CallgrindStats` now uses `TaskSpec` rather than accepting the individual fields which brings it closer to `Measurement`.
3) Some `__repr__` logic has been moved into `TaskSpec` (which `Measurement` and `CallgrindStats` use in their own `__repr__`s) for a more unified feel and less horrible f-string hacking, and the repr's have been given a cleanup pass.
4) `Tuple[FunctionCount, ...]` has been formalized as the `FunctionCounts` class, which has a much nicer `__repr__` than just the raw tuple, as well as some convenience methods (`__add__`, `__sub__`, `filter`, `transform`) for easier DIY stat exploration. (I find myself using the latter two a lot now.) My personal experience is that manipulating `FunctionCounts` is massively more pleasant than the raw tuples of `FunctionCount`. (Though it's still possible to get at the raw data if you want.)
5) Better support for multi-line `stmt` and `setup`.
6) Compare now also supports rowwise coloring, which is often the more natural layout for A/B testing.
7) Limited support for `globals` in `collect_callgrind`. This should make it easier to benchmark JIT models. (CC ZolotukhinM)
8) More unit tests, including extensive tests for the Callgrind stats manipulation APIs.
9) Mitigate issue with `MKL_THREADING_LAYER` when run in Jupyter. (https://github.com/pytorch/pytorch/issues/37377)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46023
Test Plan: changes should be covered by existing and new unit tests.
Reviewed By: navahgar, malfet
Differential Revision: D24313911
Pulled By: robieta
fbshipit-source-id: 835d4b5cde336fb7ff0adef3c0fd614d64df0f77
2020-10-15 23:30:49 +00:00
|
|
|
torch/utils/benchmark/utils/common.py,
|
|
|
|
|
torch/utils/benchmark/utils/timer.py,
|
Add utilities to support handling of nested python data structures (#46287)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46287
This adds a lightweight `pytree` implementation that is similar to and
inspired by JAX pytrees, tensorflow.nest, deepmind/tree,
TorchBeast's TensorNest, etc.
A *pytree* is Python nested data structure. It is a tree in the sense
that nodes are Python collections (e.g., list, tuple, dict) and the leaves
are Python values. Furthermore, a pytree should not contain reference
cycles.
This PR:
- adds support for flattening and unflattening nested Python list/dict/tuples
Context: nested Tensor inputs for vmap
--------------------------------------
Right now, vmap is restricted to taking in flat lists of tensors. This
is because vmap needs to be able to convert every tensor in the input
that is being vmapped over into a BatchedTensor.
With a pytree library, we can simply flatten the input data structure
(returning the leaves), map all of the Tensors in the flat input to
BatchedTensors, and unflatten the flat list of BatchedTensors into a new
input. Or equivalently, with a `tree_map` function, we can map a nested
python data structure containing Tensors into one containing
BatchedTensors.
Future work
-----------
In some future PRs, we'll add nested input support for vmap. The
prerequisites for that are:
- a `broadcast_to(small, big)` that broadcasts `small` up to `big`.
This is for handling the in_dims to vmap: the in_dims structure must
be compatible with the structure of the inputs.
Test Plan
---------
- New tests in test/test_pytree.py
Test Plan: Imported from OSS
Reviewed By: heitorschueroff
Differential Revision: D24392890
Pulled By: zou3519
fbshipit-source-id: 7daf7430c5a38354e7d203a72882bd7a9b24cfb1
2020-10-20 14:42:20 +00:00
|
|
|
torch/utils/benchmark/utils/valgrind_wrapper/*.py,
|
|
|
|
|
torch/utils/_pytree.py
|
More Timer refinement (#46023)
Summary:
This PR just adds more polish to the benchmark utils:
1) `common.py`, `timer.py`, and `valgrind_wrapper/timer_interface.py` are now MyPy strict compliant. (except for three violations due to external deps.) Compare and Fuzzer will be covered in a future PR.
2) `CallgrindStats` now uses `TaskSpec` rather than accepting the individual fields which brings it closer to `Measurement`.
3) Some `__repr__` logic has been moved into `TaskSpec` (which `Measurement` and `CallgrindStats` use in their own `__repr__`s) for a more unified feel and less horrible f-string hacking, and the repr's have been given a cleanup pass.
4) `Tuple[FunctionCount, ...]` has been formalized as the `FunctionCounts` class, which has a much nicer `__repr__` than just the raw tuple, as well as some convenience methods (`__add__`, `__sub__`, `filter`, `transform`) for easier DIY stat exploration. (I find myself using the latter two a lot now.) My personal experience is that manipulating `FunctionCounts` is massively more pleasant than the raw tuples of `FunctionCount`. (Though it's still possible to get at the raw data if you want.)
5) Better support for multi-line `stmt` and `setup`.
6) Compare now also supports rowwise coloring, which is often the more natural layout for A/B testing.
7) Limited support for `globals` in `collect_callgrind`. This should make it easier to benchmark JIT models. (CC ZolotukhinM)
8) More unit tests, including extensive tests for the Callgrind stats manipulation APIs.
9) Mitigate issue with `MKL_THREADING_LAYER` when run in Jupyter. (https://github.com/pytorch/pytorch/issues/37377)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46023
Test Plan: changes should be covered by existing and new unit tests.
Reviewed By: navahgar, malfet
Differential Revision: D24313911
Pulled By: robieta
fbshipit-source-id: 835d4b5cde336fb7ff0adef3c0fd614d64df0f77
2020-10-15 23:30:49 +00:00
|
|
|
|
|
|
|
|
# Specifically enable imports of benchmark utils. As more of `torch` becomes
|
|
|
|
|
# strict compliant, those modules can be enabled as well.
|
|
|
|
|
[mypy-torch.utils.benchmark.utils.*]
|
|
|
|
|
follow_imports = normal
|
|
|
|
|
|
|
|
|
|
# Don't follow imports as much of `torch` is not strict compliant.
|
|
|
|
|
[mypy-torch]
|
|
|
|
|
follow_imports = skip
|
|
|
|
|
|
|
|
|
|
[mypy-torch.*]
|
|
|
|
|
follow_imports = skip
|
|
|
|
|
|
2021-01-26 17:01:03 +00:00
|
|
|
# Missing stubs.
|
|
|
|
|
|
More Timer refinement (#46023)
Summary:
This PR just adds more polish to the benchmark utils:
1) `common.py`, `timer.py`, and `valgrind_wrapper/timer_interface.py` are now MyPy strict compliant. (except for three violations due to external deps.) Compare and Fuzzer will be covered in a future PR.
2) `CallgrindStats` now uses `TaskSpec` rather than accepting the individual fields which brings it closer to `Measurement`.
3) Some `__repr__` logic has been moved into `TaskSpec` (which `Measurement` and `CallgrindStats` use in their own `__repr__`s) for a more unified feel and less horrible f-string hacking, and the repr's have been given a cleanup pass.
4) `Tuple[FunctionCount, ...]` has been formalized as the `FunctionCounts` class, which has a much nicer `__repr__` than just the raw tuple, as well as some convenience methods (`__add__`, `__sub__`, `filter`, `transform`) for easier DIY stat exploration. (I find myself using the latter two a lot now.) My personal experience is that manipulating `FunctionCounts` is massively more pleasant than the raw tuples of `FunctionCount`. (Though it's still possible to get at the raw data if you want.)
5) Better support for multi-line `stmt` and `setup`.
6) Compare now also supports rowwise coloring, which is often the more natural layout for A/B testing.
7) Limited support for `globals` in `collect_callgrind`. This should make it easier to benchmark JIT models. (CC ZolotukhinM)
8) More unit tests, including extensive tests for the Callgrind stats manipulation APIs.
9) Mitigate issue with `MKL_THREADING_LAYER` when run in Jupyter. (https://github.com/pytorch/pytorch/issues/37377)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/46023
Test Plan: changes should be covered by existing and new unit tests.
Reviewed By: navahgar, malfet
Differential Revision: D24313911
Pulled By: robieta
fbshipit-source-id: 835d4b5cde336fb7ff0adef3c0fd614d64df0f77
2020-10-15 23:30:49 +00:00
|
|
|
[mypy-numpy]
|
|
|
|
|
ignore_missing_imports = True
|
2021-01-26 17:01:03 +00:00
|
|
|
|
|
|
|
|
[mypy-mypy.*]
|
|
|
|
|
ignore_missing_imports = True
|