check_error not handle CUDA_ERROR_DEINITIALIZED?
Open
bug
cuda
- Dominant language
- LLVM
- Stars
- 1.5k
- Forks
- 854
- Avg merge
- 3d 17h
- Merged PRs (30d)
- 137
Description
**Describe the bug**
The code in [pi_cuda.cpp](https://github.com/intel/llvm/blob/2022-09/sycl/plugins/cuda/pi_cuda.cpp) check_error
why the CUDA_ERROR_DEINITIALIZED return PI_SUCCESS ? Does it can correct free *ptr ? how to understand the CUDA_ERROR_DEINITIALIZED state to usm_free memory?

**To Reproduce**
**Environment (please complete the following information):**
- OS: Linux
- Target device and vendor: Nvidia GPU
- DPC++ version: 2022-09
- Dependencies version: cuda-11.2
**Additional context**
Add any other context about the problem here.
Contributor guide
Assessment
This issue has not been assessed yet.