[quant] Fix applying non-zero offset 1 to null pointer in quantized interpolation

[z-a-f]

Summary: Although this is not an issue that could pop-up in practice, LLVM-12 throws an error about this issue if not checked.

Test Plan: buck test mode/dev //caffe2/test:quantization -- --exact 'caffe2/test:quantization - test_empty_batch (quantization.core.test_quantized_op.TestQuantizedOps)'

Reviewed By: r-barnes

Differential Revision: D31151681

[facebook-github-bot]

🔗 Helpful links

• 🧪  See artifacts and rendered test results at hud.pytorch.org/pr/65570
• 📄  Preview docs built from this PR
• 📄  Preview C++ docs built from this PR
• ↩️  [fb-only] Re-run with SSH instructions
• 🔧  Opt-in to CIFlow to control what jobs run on your PRs

💊 CI failures summary and remediations

As of commit f04376a (more details on the Dr. CI page):

---

• 1/2 failures introduced in this PR
• 1/2 tentatively recognized as flaky ❄️
  • Click here to rerun these jobs

---

1 failure not recognized by patterns:

Job	Step	Action
linux-xenial-cuda11.3-py3.6-gcc7 / test (default, 2, 2, linux.8xlarge.nvidia.gpu)	Unknown	🔁 rerun

---

❄️ 1 failure tentatively classified as flaky

but reruns have not yet been triggered to confirm:

pytorch_xla_linux_bionic_py3_6_clang9_test (1/1)

Step: "Test" (full log | diagnosis details | 🔁 rerun) ❄️

Sep 23 22:01:44 RuntimeError: tensorflow/compil...OK() (Unknown: Could not start gRPC server vs. OK)

Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch_xla-1.10-py3.6-linux-x86_64.egg/torch_xla/distributed/xla_multiprocessing.py", line 314, in _setup_replication
Sep 23 22:01:44     device = xm.xla_device()
Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch_xla-1.10-py3.6-linux-x86_64.egg/torch_xla/core/xla_model.py", line 232, in xla_device
Sep 23 22:01:44     devkind=devkind if devkind is not None else None)
Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch_xla-1.10-py3.6-linux-x86_64.egg/torch_xla/core/xla_model.py", line 137, in get_xla_supported_devices
Sep 23 22:01:44     xla_devices = _DEVICES.value
Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch_xla-1.10-py3.6-linux-x86_64.egg/torch_xla/utils/utils.py", line 32, in value
Sep 23 22:01:44     self._value = self._gen_fn()
Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch_xla-1.10-py3.6-linux-x86_64.egg/torch_xla/core/xla_model.py", line 19, in <lambda>
Sep 23 22:01:44     _DEVICES = xu.LazyProperty(lambda: torch_xla._XLAC._xla_get_devices())
Sep 23 22:01:44 RuntimeError: tensorflow/compiler/xla/xla_client/xrt_local_service.cc:56 : Check failed: tensorflow::NewServer(server_def, &server_) == ::tensorflow::Status::OK() (Unknown: Could not start gRPC server vs. OK)
Sep 23 22:01:44 Traceback (most recent call last):
Sep 23 22:01:44   File "/var/lib/jenkins/workspace/xla/test/test_mp_save.py", line 63, in <module>
Sep 23 22:01:44     xmp.spawn(_mp_fn, args=(temp_file,))
Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch_xla-1.10-py3.6-linux-x86_64.egg/torch_xla/distributed/xla_multiprocessing.py", line 394, in spawn
Sep 23 22:01:44     start_method=start_method)
Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes
Sep 23 22:01:44     while not context.join():
Sep 23 22:01:44   File "/opt/conda/lib/python3.6/site-packages/torch/multiprocessing/spawn.py", line 144, in join
Sep 23 22:01:44     exit_code=exitcode
Sep 23 22:01:44 torch.multiprocessing.spawn.ProcessExitedException: process 2 terminated with exit code 17

---

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 was exported from Phabricator. Differential Revision: D31151681