pytorch / pytorch/pytorch

DISABLED test_perf_atomic_contention (__main__.TestPartitionedScatterOpt)

Open
#193,150 1 comment 0 reactions 0 assignees View on GitHub
module: flaky-tests module: inductor oncall: pt2 skipped triaged
Dominant language
Python
Stars
103k
Forks
29.6k
PR merge metrics
PR metrics pending

Description

Platforms: linux

This test was disabled because it is failing in CI. See [recent examples](https://hud.pytorch.org/flakytest?name=test_perf_atomic_contention&suite=TestPartitionedScatterOpt&limit=100) and the most recent trunk [workflow logs](https://github.com/pytorch/pytorch/runs/94058989777).

Over the past 6 hours, it has been determined flaky in 3 workflow(s) with 3 failures and 3 successes.

**Debugging instructions (after clicking on the recent samples link):**
DO NOT ASSUME THINGS ARE OKAY IF THE CI IS GREEN. We now shield flaky tests from developers so CI will thus be green but it will be harder to parse the logs.
To find relevant log snippets:
1. Click on the workflow logs linked above
2. Click on the Test step of the job so that it is expanded. Otherwise, the grepping will not work.
3. Grep for `test_perf_atomic_contention`
4. There should be several instances run (as flaky tests are rerun in CI) from which you can study the logs.

Sample error message

```
Traceback (most recent call last):
File "/__w/pytorch/pytorch/test/inductor/test_scatter_optimization.py", line 750, in test_perf_atomic_contention
self.assertGreater(
File "/usr/lib/python3.10/unittest/case.py", line 1244, in assertGreater
self.fail(self._formatMessage(msg, standardMsg))
File "/usr/lib/python3.10/unittest/case.py", line 675, in fail
raise self.failureException(msg)
AssertionError: 1.0344550786742435 not greater than 1.5 : expected ≥1.5× speedup (moderate contention, 8 slots), got 1.03× (baseline=3.966 ms, partitioned=3.834 ms)

To execute this test, run the following from the base repo dir:
python test/inductor/test_scatter_optimization.py TestPartitionedScatterOpt.test_perf_atomic_contention

This message can be suppressed by setting PYTORCH_PRINT_REPRO_ON_FAILURE=0
```

Test file path: `inductor/test_scatter_optimization.py`

For all disabled tests (by GitHub issue), see https://hud.pytorch.org/disabled.

cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @kadeng @muchulee8 @amjames @chauhang @aakhundov @coconutruben @jataylo

Contributor guide

Open the contributing guide

Research direction

Start with test/inductor/test_scatter_optimization.py and inspect the linked recent samples and workflow logs for test_perf_atomic_contention. Run python test/inductor/test_scatter_optimization.py TestPartitionedScatterOpt.test_perf_atomic_contention to reproduce the failure and compare the repeated runs. Done means the test is no longer flaky, meets its expected speedup, and can be re-enabled.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
compilers, performance, testing-qa
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.