Segmentation fault in Beanmachine-vectorized implementation of Robust Regresssion

Issue Description

When running PPLBench, the Beanmachine-vectorized implementation of Robust Regresssion causes segmentation fault. This occurs in Amazon EC2 Instances

Steps to Reproduce

Linux ip-172-31-10-135 4.15.0-1056-aws #58-Ubuntu SMP Tue Nov 26 15:14:34 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux

pip3 list
alabaster (0.7.12)
appdirs (1.4.3)
arviz (0.5.1)
asn1crypto (0.24.0)
attrs (19.3.0)
Automat (0.6.0)
Babel (2.7.0)
BeanMachine (0.0.1a1, /home/ubuntu/BeanMachine)
black (19.3b0)
blinker (1.4)
certifi (2019.11.28)
cftime (1.0.4.2)
chardet (3.0.4)
Click (7.0)
cloud-init (19.3)
colorama (0.3.7)
command-not-found (0.3)
configobj (5.0.6)
constantly (15.1.0)
coverage (5.0)
cryptography (2.1.4)
cycler (0.10.0)
Cython (0.29.14)
dataclasses (0.7)
distro-info (0.18ubuntu0.18.04.1)
docutils (0.15.2)
ec2-hibinit-agent (1.0.0)
entrypoints (0.3)
flake8 (3.7.9)
h5py (2.10.0)
hibagent (1.0.1)
httplib2 (0.9.2)
hyperlink (17.3.1)
idna (2.8)
imagesize (1.1.0)
importlib-metadata (1.3.0)
incremental (16.10.1)
isort (4.3.21)
Jinja2 (2.10.3)
jsonpatch (1.16)
jsonpointer (1.10)
jsonschema (2.6.0)
keyring (10.6.0)
keyrings.alt (3.0)
kiwisolver (1.1.0)
language-selector (0.1)
MarkupSafe (1.1.1)
matplotlib (3.1.2)
mccabe (0.6.1)
more-itertools (8.0.2)
netCDF4 (1.5.3)
netifaces (0.10.4)
numpy (1.17.4)
oauthlib (2.0.6)
packaging (19.2)
PAM (0.4.2)
pandas (0.25.3)
patsy (0.5.1)
pip (9.0.1)
plotly (4.4.1)
pluggy (0.13.1)
py (1.8.0)
pyasn1 (0.4.2)
pyasn1-modules (0.2.1)
pycodestyle (2.5.0)
pycrypto (2.6.1)
pyflakes (2.1.1)
Pygments (2.5.2)
pygobject (3.26.1)
pyjags (1.2.2)
PyJWT (1.5.3)
pymc3 (3.8)
pyOpenSSL (17.5.0)
pyparsing (2.4.5)
pyserial (3.4)
pystan (2.19.1.1)
pytest (5.3.2)
pytest-cov (2.8.1)
python-apt (1.6.4)
python-dateutil (2.8.1)
python-debian (0.1.32)
pytz (2019.3)
pyxdg (0.25)
PyYAML (3.12)
requests (2.22.0)
requests-unixsocket (0.1.5)
retrying (1.3.3)
scipy (1.4.0)
SecretStorage (2.3.1)
service-identity (16.0.0)
setuptools (42.0.2)
six (1.13.0)
snowballstemmer (2.0.0)
Sphinx (2.3.0)
sphinx-autodoc-typehints (1.10.3)
sphinxcontrib-applehelp (1.0.1)
sphinxcontrib-devhelp (1.0.1)
sphinxcontrib-htmlhelp (1.0.2)
sphinxcontrib-jsmath (1.0.1)
sphinxcontrib-qthelp (1.0.2)
sphinxcontrib-serializinghtml (1.1.3)
ssh-import-id (5.7)
statsmodels (0.10.2)
systemd-python (234)
Theano (1.0.4)
toml (0.10.0)
torch (1.2.0)
tqdm (4.40.2)
Twisted (17.9.0)
ufw (0.36)
unattended-upgrades (0.1)
urllib3 (1.25.7)
wcwidth (0.1.7)
wheel (0.30.0)
xarray (0.14.1)
zipp (0.6.0)
zope.interface (4.3.2)

Expected Behavior

What did you expect to happen?

run this command from pplbench dir: python3 PPLBench.py -m robustRegression -l beanmachine-vectorized -s 500 --trials 1

Expected outcome:

Generating data
Starting benchmark; estimated time is 0 hour(s),3 minutes
Outputs will be saved in : ./outputs/19-12-2019_19:21:56
Segmentation fault (core dumped)

System Info

Please provide information about your setup

PyTorch Version (run print(torch.__version__) : 1.2.0
Python version 3.6.9

Additional Context

For the following system (local server) this segfault does not happen.

Linux nanofabrics-server 5.0.0-37-generic #40~18.04.1-Ubuntu SMP Thu Nov 14 12:06:39 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux

pip3 list
alabaster (0.7.12)
appdirs (1.4.3)
apturl (0.5.2)
arviz (0.5.1)
asn1crypto (0.24.0)
astroid (2.3.3)
attrs (19.3.0)
Babel (2.7.0)
BeanMachine (0.0.1a1, /home/sourabh/BeanMachine)
black (19.3b0)
Brlapi (0.6.6)
certifi (2018.1.18)
cftime (1.0.4.2)
chardet (3.0.4)
Click (7.0)
command-not-found (0.3)
coverage (5.0)
cryptography (2.1.4)
cupshelpers (1.0)
cycler (0.10.0)
Cython (0.29.14)
dataclasses (0.7)
defer (1.0.6)
distro-info (0.18ubuntu0.18.04.1)
docutils (0.15.2)
flake8 (3.5.0)
h5py (2.10.0)
httplib2 (0.9.2)
idna (2.6)
imagesize (1.1.0)
importlib-metadata (1.3.0)
isort (4.3.21)
Jinja2 (2.10.3)
keyring (10.6.0)
keyrings.alt (3.0)
kiwisolver (1.1.0)
language-selector (0.1)
launchpadlib (1.10.6)
lazr.restfulclient (0.13.5)
lazr.uri (1.0.3)
lazy-object-proxy (1.4.3)
louis (3.5.0)
macaroonbakery (1.1.3)
Mako (1.0.7)
MarkupSafe (1.0)
matplotlib (3.1.2)
mccabe (0.6.1)
more-itertools (8.0.2)
netCDF4 (1.5.3)
netifaces (0.10.4)
numpy (1.17.4)
oauth (1.0.1)
olefile (0.45.1)
opt-einsum (3.1.0)
packaging (19.2)
pandas (0.25.3)
patsy (0.5.1)
pexpect (4.2.1)
Pillow (5.1.0)
pip (9.0.1)
pluggy (0.13.1)
protobuf (3.0.0)
py (1.8.0)
pycairo (1.16.2)
pycodestyle (2.3.1)
pycrypto (2.6.1)
pycups (1.9.73)
pyflakes (1.6.0)
Pygments (2.5.2)
pygobject (3.26.1)
pyjags (1.2.2)
pylint (2.4.4)
pymacaroons (0.13.0)
pymc3 (3.8)
PyNaCl (1.1.2)
pyparsing (2.4.5)
pyRFC3339 (1.0)
pyro-api (0.1.1)
pyro-ppl (1.1.0)
pystan (2.19.1.1)
pytest (5.3.2)
pytest-cov (2.8.1)
python-apt (1.6.4)
python-dateutil (2.8.1)
python-debian (0.1.32)
pytz (2019.3)
pyxdg (0.25)
PyYAML (3.12)
reportlab (3.4.0)
requests (2.18.4)
requests-unixsocket (0.1.5)
scipy (1.3.3)
SecretStorage (2.3.1)
setuptools (42.0.2)
simplejson (3.13.2)
six (1.13.0)
snowballstemmer (2.0.0)
Sphinx (2.3.0)
sphinx-autodoc-typehints (1.10.3)
sphinxcontrib-applehelp (1.0.1)
sphinxcontrib-devhelp (1.0.1)
sphinxcontrib-htmlhelp (1.0.2)
sphinxcontrib-jsmath (1.0.1)
sphinxcontrib-qthelp (1.0.2)
sphinxcontrib-serializinghtml (1.1.3)
ssh-import-id (5.7)
system-service (0.3)
systemd-python (234)
Theano (1.0.4)
toml (0.10.0)
torch (1.3.1)
tqdm (4.40.2)
typed-ast (1.4.0)
ubuntu-drivers-common (0.0.0)
ufw (0.36)
unattended-upgrades (0.1)
urllib3 (1.22)
usb-creator (0.3.3)
wadllib (1.3.2)
wcwidth (0.1.7)
wheel (0.30.0)
wrapt (1.11.2)
xarray (0.14.1)
xkit (0.0.0)
zipp (0.6.0)
zope.interface (4.3.2)

facebookresearch / beanmachine