[libclc] libclc: Use separate acquire and release fences in work_group_barrier (PR #185190)

[Matt Arsenault via cfe-commits]

================
@@ -10,8 +10,22 @@
 #include <clc/synchronization/clc_work_group_barrier.h>
 
 _CLC_OVERLOAD _CLC_DEF void
-__clc_work_group_barrier(int memory_scope, int memory_order,
+__clc_work_group_barrier(int memory_scope,
----------------
arsenm wrote:

That would add a lot of untested code, which I don't really want to do. I'd have to figure out how to interpret the parameter for the split barrier. Or silently ignore it, which is not very future friendly 

https://github.com/llvm/llvm-project/pull/185190