[PATCH] D26476: [AMDGPU] Add support for f16 builtin functions for VI+
Yaxun Liu via cfe-commits
cfe-commits at lists.llvm.org
Fri Nov 11 10:24:03 PST 2016
yaxunl added inline comments.
================
Comment at: test/CodeGenOpenCL/builtins-amdgcn-error-f16-div-fixup.cl:8
+{
+ *out = __builtin_amdgcn_div_fixuph(a, b, c); // expected-error {{'__builtin_amdgcn_div_fixuph' needs target feature 16-bit-insts}}
+}
----------------
The tests for checking error messages are usually put in SemaOpenCL.
https://reviews.llvm.org/D26476
More information about the cfe-commits
mailing list