[iOS][Metal] Add aten::hardswish

[xta0]

Stack from ghstack:

• -> [iOS][Metal] Add aten::hardswish #64588

Add aten::hardswish to run the mobilenetv3 model from torchvision.

Differential Revision: D30781008

NOTE FOR REVIEWERS: This PR has internal Facebook specific changes or comments, please review them on Phabricator!

[facebook-github-bot]

🔗 Helpful links

• 🧪 See artifacts and rendered test results at hud.pytorch.org/pr/64588

💊 CI failures summary and remediations

As of commit 6f0fd79 (more details on the Dr. CI page):

---

• 1/1 failures introduced in this PR

---

🕵️ 1 new failure recognized by patterns

The following CI failures do not appear to be due to upstream breakages:

win-vs2019-cpu-py3 / test (default, 1, 2, windows.4xlarge) (1/1)

Step: "Run test scripts" (full log | diagnosis details | 🔁 rerun)

2021-09-07T19:19:36.7797443Z ERROR [0.006s]: test_poisson_sample (__main__.TestDistributions)

2021-09-07T19:19:36.7788713Z   File "distributions/test_distributions.py", line 812, in _check_sampler_discrete
2021-09-07T19:19:36.7789839Z     chisq, p = scipy.stats.chisquare(counts[msk], pmf[msk] * num_samples)
2021-09-07T19:19:36.7790924Z   File "c:\jenkins\miniconda3\lib\site-packages\scipy\stats\stats.py", line 6852, in chisquare
2021-09-07T19:19:36.7791913Z     return power_divergence(f_obs, f_exp=f_exp, ddof=ddof, axis=axis,
2021-09-07T19:19:36.7792982Z   File "c:\jenkins\miniconda3\lib\site-packages\scipy\stats\stats.py", line 6694, in power_divergence
2021-09-07T19:19:36.7793854Z     raise ValueError(msg)
2021-09-07T19:19:36.7795071Z ValueError: For each axis slice, the sum of the observed frequencies must agree with the sum of the expected frequencies to a relative tolerance of 1e-08, but the percent differences are:
2021-09-07T19:19:36.7796156Z 0.008265582255680495
2021-09-07T19:19:36.7796415Z 
2021-09-07T19:19:36.7796801Z ======================================================================
2021-09-07T19:19:36.7797443Z ERROR [0.006s]: test_poisson_sample (__main__.TestDistributions)
2021-09-07T19:19:36.7798244Z ----------------------------------------------------------------------
2021-09-07T19:19:36.7798892Z Traceback (most recent call last):
2021-09-07T19:19:36.7799831Z   File "distributions/test_distributions.py", line 1352, in test_poisson_sample
2021-09-07T19:19:36.7800710Z     self._check_sampler_discrete(Poisson(rate),
2021-09-07T19:19:36.7801654Z   File "distributions/test_distributions.py", line 812, in _check_sampler_discrete
2021-09-07T19:19:36.7802673Z     chisq, p = scipy.stats.chisquare(counts[msk], pmf[msk] * num_samples)
2021-09-07T19:19:36.7803759Z   File "c:\jenkins\miniconda3\lib\site-packages\scipy\stats\stats.py", line 6852, in chisquare
2021-09-07T19:19:36.7804731Z     return power_divergence(f_obs, f_exp=f_exp, ddof=ddof, axis=axis,
2021-09-07T19:19:36.7805799Z   File "c:\jenkins\miniconda3\lib\site-packages\scipy\stats\stats.py", line 6694, in power_divergence
2021-09-07T19:19:36.7806670Z     raise ValueError(msg)

---

This comment was automatically generated by Dr. CI (expand for details).

Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

[facebook-github-bot]

This pull request has been merged in 52ff9bc.