Displaying 1 result from an estimated 1 matches for "ptx_read_sreg_r32".
2020 Apr 13
3
Are AMDGPU intrinsics available in LLVM IR ?
...UReadPreloadRegisterIntrinsic_xyz_named
<"__builtin_amdgcn_workgroup_id">;
There is no new definition of any intrinsics within the target
AMDGPU. I was working before with the NVPTX backend and that target
has the special registers are associated with strings for the LLVM IR,
e.g., PTX_READ_SREG_R32<"tid.x", int_nvvm_read_ptx_sreg_tid_x>;
Maybe I'm missing something but does this mean at the moment it is not
possible to write a function in the LLVM IR language which accesses
the workgroup id?
Frank