BF16 in CUDA builtins.hpp

[jinz2014]

Describe the bug

BF16 is not added in
https://github.com/intel/llvm/blob/sycl/sycl/include/sycl/ext/oneapi/experimental/cuda/builtins.hpp

To reproduce

The error message is "no matching function for call to 'ldg'"

Environment

No response

Additional context

No response

[JackAKirk]

Thanks, do you have an example cuda application that uses __ldg for bf16?

[jinz2014]

Please see https://github.com/zjin-lcf/HeCBench/blob/master/src/addBiasResidualLayerNorm-sycl/

[JackAKirk]

cc @npmiller