================
@@ -27,12 +27,24 @@ atomic_fetch_add(volatile __local atomic_uintptr_t *p,
ptrdiff_t v) {
__ATOMIC_SEQ_CST, __MEMORY_SCOPE_DEVICE);
}
+_CLC_OVERLOAD _CLC_DEF uintptr_t atomic_fetch_add(
+ volatile __local atomic_uintptr_t *p, ptrdiff_t v, memory_order order) {
----------------
wenju-he wrote:
this variant don't need __opencl_c_atomic_order_seq_cst guard at line 21
https://github.com/llvm/llvm-project/pull/188478
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
