CUDA applications hanging

This may be related to the pinned ‘Known Limitations’ thread, but I just wanted to report that CUDA applications appear to be hanging on my machine with an Intel Core i7-8850H CPU @ 2.60GHz with an NVIDIA GeForce MX130.

CUDA Applications in WSL 2 seem to detect the GPU properly, but hang, maxing out one of the logical processors in htop and showing nothing on the GPU in windows except for sometimes a small blip in Compute_0 at the start and a big spike when I kill it.

$ ./deviceQuery
./deviceQuery Starting…

CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: “GeForce MX130”
CUDA Driver Version / Runtime Version 11.1 / 10.2
CUDA Capability Major/Minor version number: 5.0
Total amount of global memory: 2048 MBytes (2147483648 bytes)
( 3) Multiprocessors, (128) CUDA Cores/MP: 384 CUDA Cores
GPU Max Clock rate: 1189 MHz (1.19 GHz)
Memory Clock rate: 2505 Mhz
Memory Bus Width: 64-bit
L2 Cache Size: 1048576 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
Maximum Layered 1D Texture Size, (num) layers 1D=(16384), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(16384, 16384), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 4 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device supports Compute Preemption: No
Supports Cooperative Kernel Launch: No
Supports MultiDevice Co-op Kernel Launch: No
Device PCI Domain ID / Bus ID / location ID: 0 / 2 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.1, CUDA Runtime Version = 10.2, NumDevs = 1
Result = PASS

Thanks a lot for reaching out !

Your hang seems related to the initialization issue we have just fixed in this driver: https://developer.nvidia.com/cuda/wsl/download (455.41)

Also most of the impacted systems were AMD Ryzen, we found that you could run into the same issue elsewhere (also these platforms are less common).

Let us know how it goes with the new driver. Thanks!

Hi,
Thanks for reporting the issue with good details.
We just posted another driver with a good set of fixes. Would you mind to give it a try?

It works! Thanks for the prompt response and active development! Exciting stuff!