[PATCH] D80804: [AMDGPU] Introduce Clang builtins to be mapped to AMDGCN atomic inc/dec intrinsics
Matt Arsenault via Phabricator via cfe-commits
cfe-commits at lists.llvm.org
Mon Jun 8 12:42:12 PDT 2020
arsenm added inline comments.
================
Comment at: clang/lib/CodeGen/CGBuiltin.cpp:14553
+ case AMDGPU::BI__builtin_amdgcn_atomic_inc32:
+ IntType = Int32Ty;
+ BuiltinAtomicOp = Intrinsic::amdgcn_atomic_inc;
----------------
This should be implied by the return type of the builtin? You shouldn't need to switch over it, and you just need to switch between inc/dec intrinsics
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D80804/new/
https://reviews.llvm.org/D80804
More information about the cfe-commits
mailing list