[PATCH] D20691: AMDGPU: Remove gcc builtin names from workitem intrinsics

[Jan Vesely via llvm-commits]

jvesely marked an inline comment as done.

================
Comment at: include/llvm/IR/IntrinsicsAMDGPU.td:41
@@ +40,3 @@
+
+// Range limited
+defm int_r600_read_local_size : AMDGPUReadPreloadRegisterIntrinsic_xyz;
----------------
arsenm wrote:
> This comment isn't needed / is misleading since the intrinsic itself has no indication of the range limit
Removed locally. IMO it would be preferable if the range metadata were tied to the intrinsic rather than added by clang.


Repository:
  rL LLVM

http://reviews.llvm.org/D20691