Description
I install accelerate on WLS2, and run some code very well with accelerate-llvm-native backend. But if I use accelerate-llvm-ptx backend, it throws an error.thread blocked indefinitely in an MVar operation. I don't use stm package and any MVar operation.
Steps to reproduce
if can download this code https://gitee.com/wujilingfeng/haskell-sift.
Your environment
If the bug is with the accelerate-llvm-ptx GPU backend, include the output of nvidia-device-query
- Accelerate: 1.3.0.0
- Accelerate backend(s): accelerate-llvm-ptx
- GHC: 8.10.7
- OS: windows 10 wsl2
- nvidia GTX 1660 Ti cuda-11.4