Let's do the lowering of non-split into split barriers in a new IR pass, AMDGPULowerIntrinsics. That way, there is no code duplication between SelectionDAG and GlobalISel. This simplifies some upcoming extensions to the code.
Expand large or unknown size memory intrinsics into loops in the default lowering pipeline if the target doesn't have the corresponding libfunc. Previously AMDGPU had a custom pass which existed to call the expansion utilities. With a default no-libcall option, we can remove the libfunc checks in LoopIdiomRecognize for these, which never made any sense. This also provides a path to lifting the immarg restriction on llvm.memcpy.inline. There seems to be a bug where TLI reports functions as available if you use -march and not -mtriple.
With these dropped and memory intrinsic moved into a generic pass, we can drop the whole pass. No tests fail with this removed. The new amdgcn intrinsics are annotated in clang up front. Theoretically may regress r600, but that would need new testing and support work (r600 ideally would also follow the clang handling). The regression would be any IR passes making use of known bits between this point and codegen. The DAG computeKnownBits understand the intrinsics directly now. If we wanted to refine these values, a better place would be in AMDGPUAttributor.
Running iwyu-diff on LLVM codebase since fa5a4e1b95c8f37796 detected a few regressions, fixing them. Differential Revision: https://reviews.llvm.org/D124847
Currently metadata is inserted in a late pass which is lowered to an AssertZext. The metadata would be more useful if it was inserted earlier after inlining, but before codegen. Probably shouldn't change anything now. Just replacing the late metadata annotation needs more work, since we lose out on optimizations after these are lowered to CopyFromReg. Seems to be slightly better than relying on the AssertZext from the metadata. The test change in cvt_f32_ubyte.ll is a quirk from it using -start-before=amdgpu-isel instead of running the usual codegen pipeline.
... to reduce headers dependency. Reviewed By: rampitec, arsenm Differential Revision: https://reviews.llvm.org/D95036
Reviewed By: rampitec Differential Revision: https://reviews.llvm.org/D93813
Intrinsic declarations use the default subtarget, but this should be using the subtarget for the calling function. I haven't been able to come up with a case where it matters though.