yaxunl added inline comments.

================
Comment at: clang/test/CodeGenCUDA/atomic-ops.cu:14
+// CHECK: load atomic i32, i32* {{%[0-9]+}} syncscope("singlethread-one-as") 
monotonic, align 4
+// CHECK: store i32 {{%[0-9]+}}, i32* %{{.*}}, align 4
+// CHECK: cmpxchg weak i32* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 {{%[0-9]+}} 
syncscope("singlethread-one-as") monotonic monotonic, align 4
----------------
should have atomic, syncscope and monotonic. same as below


================
Comment at: clang/test/CodeGenCUDA/atomic-ops.cu:31
+  __hip_atomic_store(ptr, val, __ATOMIC_RELAXED, 
__HIP_MEMORY_SCOPE_SINGLETHREAD);
+  flag = __hip_atomic_compare_exchange_weak(ptr, ptr2, val, desired, 
__ATOMIC_RELAXED, __HIP_MEMORY_SCOPE_SINGLETHREAD);
   return flag ? val : desired;
----------------
the signature of `__hip_atomic_compare_exchange_weak` is the same as 
`__hip_atomic_compare_exchange_strong` and should be called with the same 
arguments. It should end up with one atomic cmpxchg instruction in IR. same as 
below


================
Comment at: clang/test/SemaCUDA/atomic-ops.cu:10
+  val = __hip_atomic_load(pi32, 0, 0); // expected-error {{synchronization 
scope argument to atomic operation is invalid}}
+  val = __hip_atomic_load(pi32, 0, __HIP_MEMORY_SCOPE_SINGLETHREAD);
+  val = __hip_atomic_load(pi32, 0, __HIP_MEMORY_SCOPE_WAVEFRONT);
----------------
should use predefined macros for memory order, e.g. __ATOMIC_RELAXED. same as 
below


================
Comment at: clang/test/SemaCUDA/atomic-ops.cu:67
+  flag = __hip_atomic_compare_exchange_weak(ptr, 0, 0, 0, 0, 
__HIP_MEMORY_SCOPE_SYSTEM); // expected-warning {{null passed to a callee that 
requires a non-null argument}}
+  flag = __hip_atomic_compare_exchange_weak(ptr, ptr2, val, desired, 0, 
__HIP_MEMORY_SCOPE_SYSTEM);
+  flag = __hip_atomic_compare_exchange_weak(ptr, ptr2, val, desired, 1, 
__HIP_MEMORY_SCOPE_SINGLETHREAD);
----------------
signature is wrong. see above comments.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D114553/new/

https://reviews.llvm.org/D114553

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to