[SOLVED] ROCM and crashes

[James3]

Hi,

This is just a small email that might help anyone using ROCM on AMD FW13/16 laptops.
I have been having crash problems for a while, and I have finally found a work around.
It does not cover some edge cases, but for me, it is a workable solution.

To help reduce ROCM crashes. You might still get one crash after a reboot, but then after that it is fine.

There are more details here:

Experiments with using ROCM on the FW16 AMD

Hi, I have been playing with rocm 6.3.1 on the FW16 without the dGPU, on Ubuntu 24.04 If anyone sees this message: rocBLAS error: Cannot read /opt/rocm-6.3.1/lib/rocblas/library/TensileLibrary.dat: No such file or directory for GPU arch : gfx1103 List of available TensileLibrary Files : "/opt/rocm-6.3.1/lib/rocblas/library/TensileLibrary_lazy_gfx1010.dat" "/opt/rocm-6.3.1/lib/rocblas/library/TensileLibrary_lazy_gfx1012.dat" "/opt/rocm-6.3.1/lib/rocblas/library/TensileLibrary_lazy_gfx1030.da…

Specifically, with:
amdgpu.cwsr_enable=0
or a file in /etc/modprobe.d:
options amdgpu cwsr_enable=0

It seems to fix the ROCM gpu crash problems that I have observed in ROCM 6.x ans 7.x.
LLMs/AI/ML seems quite reliable now on my FW16 7840HS.

AMD will need to fix the cwsr bug, but at least we have a work around in the short term.