================
@@ -0,0 +1,3 @@
+_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE __clc_native_exp(__CLC_GENTYPE val) {
+ return __clc_native_exp2(val * M_LOG2E_F);
----------------
frasercrmck wrote:
With #133696 merged, I think this is resolved. AMDGPU still has a custom
definition of `__clc_native_exp`, which forwards on to `__clc_native_exp2`,
which AMDGPU also (continues to) define as a call to `__builtin_amdgcn_exp2f`.
There's no codegen change with this PR.
https://github.com/llvm/llvm-project/pull/129679
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
