Open WardBrian opened 7 months ago
Does it also break if you specify the device id explicitly in the kwargs? e.g.
cufinufft.nufft2d1(
*omega.to("cuda:1"),
data.reshape(-1, 12000).to("cuda:1"),
(320,320),
isign=-1,
gpu_device_id=1
)
@lu1and10 no, that seems to have fixed it (sorry for not chasing through enough **kwarg
doc to find that option).
So this issue can be re-worded as a feature request: can _compat.py
pick up a reasonable default for gpu_device_id
?
@lu1and10 no, that seems to have fixed it (sorry for not chasing through enough
**kwarg
doc to find that option).So this issue can be re-worded as a feature request: can
_compat.py
pick up a reasonable default forgpu_device_id
?
Yes, I guess so. It will be a nice feature that device can be inferred from inputs.
Originally reported downstream: https://github.com/flatironinstitute/pytorch-finufft/issues/103
The following will segfault with either a
Fatal Python error: aborted
orFatal Python error: PyThreadState_Get: the function must be called with the GIL held, but the GIL is released (the current Python thread state is NULL)
If you change to
cuda:0
for both arrays it seems to work fine.The full error I get is