Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

asarray() function returns RuntimeError: Native API failed. #1089

Closed
npolina4 opened this issue Feb 28, 2023 · 0 comments · Fixed by #1117
Closed

asarray() function returns RuntimeError: Native API failed. #1089

npolina4 opened this issue Feb 28, 2023 · 0 comments · Fixed by #1117

Comments

@npolina4
Copy link
Collaborator 

import dpctl.tensor as dpt
x = dpt.asarray([1, 2, 3], device='level_zero:gpu')
dpt.asarray(x, dtype='i4', device='opencl:gpu')
dpt.asarray(x, dtype='i4', device='opencl:gpu')
x = dpt.asarray([1, 2, 3], device='level_zero:gpu')
RuntimeError: Native API failed. Native API returns: -997 (The plugin has emitted a backend specific error) -997 (The plugin has emitted a backend specific error)

OS: Windows
Driver version: 30.0.101.1660
oleksandr-pavlyk added a commit that referenced this issue Mar 13, 2023
@oleksandr-pavlyk
Hardened _copy_from_numpy_into to handle ndarray with USMMemory buffe…
b1355d4 
…r underneath

Copy-with-casting kernel to transfer content of numpy.ndarray to usm_ndarray is
implemented using sycl::buffer used on ndarray's data-pointer. The pointer can
not be a host-accessible USM pointer for the behavior to be well-defined.

This change should fix issue gh-1089
@oleksandr-pavlyk oleksandr-pavlyk mentioned this issue Mar 13, 2023
Merged
5 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Handle numpy arrays with usm memory underneath in dpctl.tensor.asarray IntelPython/dpctl
1 participant
@npolina4