Open
Description
Is your feature request related to a problem? Please describe
joint_matrix with parameters matrix_type::fp16, use::a, Rows=16, Cols=16 is not supported on this device
Describe the solution you would like
Thank you for explaining that this is not supported.
Describe alternatives you have considered
No response
Additional context
Running the program on an Intel GPU shows the error.
https://github.com/zjin-lcf/HeCBench/tree/master/src/wmma-sycl
The CUDA and HIP programs run successfully on the NVIDIA and AMD GPUs, respectively.