llvm-project

72572617 - [NVPTX] Fix generic address in st.bulk intrinsic (#130740)

[NVPTX] Fix generic address in st.bulk intrinsic (#130740) This PR fixes an oversight from the previous change (PR #128856) that introduced the `st.bulk` intrinsic where `llvm_global_ptr_ty` was used instead of `llvm_ptr_ty` for generic addressing. PTX Spec Reference: https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-st-bulk