Yifan Sun
Yifan Sun
Here is some more detailed information about the environment we are trying. ROCm version: 5.0.0 GPUs: Radeon VII + RX5500XT, but we only care about the Radeon VII. Tensile Version:...
@eshcherb Any update on this thread? I recently noticed that even simply running `rocprof --list-basic` can cause the same problem.
This is the error I get when I simply run `--list-basic`.
I have been upgrading to ROCm 4.0 and the problem is not there anymore. So I guess @MathiasMagnus is right, it should be an installation issue.
@ghostplant No, still have exactly the same errors. What I eventually do is to write OpenCL kernel with inline assembly. But I think that is not a solution to this...
What is the error if `ocl-icd-opencl-dev` is not installed? I have never had this problem and have never installed this package before.
Are you checking the [file](https://github.com/NUCAR-DEV/Hetero-Mark/blob/Develop/run_all/benchmark.py) for the input sizes? For knn, you can simply use the command line option `-n` to specify the number of nodes to insert to the...
Are you running the CUDA version of the KNN benchmark? Let me try to recreate your problem.
May I know which GPU and which version of CUDA are you using?
@Yzgll Just want to make sure, this version runs your newly compiled AES without error right?