You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the bug
When fixing #4741, I found that SPIR-V does not support float immediate number of f16 type, and test_f16.py::test_fractal_f16 fails.
Note: remember to add dtype=ti.f16 to the test after fixing this issue. To Reproduce
This is an altered version of test_f16.py::test_fractal_f16 that all vectors store f16 values.
Log/Screenshots
Please post the full log of the program (instead of just a few lines around the error message, unless the log is > 1000 lines). This will help us diagnose what's happening. For example:
lin-hitonami
changed the title
SPIR-V does not support float immediate number of f16 type
SPIR-V backend does not support float immediate number of f16 type
Apr 11, 2022
Describe the bug
When fixing #4741, I found that SPIR-V does not support float immediate number of f16 type, and test_f16.py::test_fractal_f16 fails.
Note: remember to add
dtype=ti.f16
to the test after fixing this issue.To Reproduce
This is an altered version of test_f16.py::test_fractal_f16 that all vectors store f16 values.
Log/Screenshots
Please post the full log of the program (instead of just a few lines around the error message, unless the log is > 1000 lines). This will help us diagnose what's happening. For example:
The text was updated successfully, but these errors were encountered: