Update atomic functional tests (#262)

* feat: implement function to return number of blocks in grid.

* test: update atomics functional tests
  - Standard atomic tests: `atomic_add`, `atomic_inc`, `fetch_atomic_add`, `fetch_atomic_inc`, and `fetch_compare_and_swap`
  - Bitwise atomic tests:    `atomic_and`, `atomic_or`, `atomic_xor`, fetch_atomic_and`, `fetch_atomic_or`, and `fetch_atomic_xor`
  - Extended atomic tests: `atomic_fetch`, `atomic_set`, and `atomic_swap`

* Added two different address modes for atomics.
* Added all supported data types for atomics tests.


[ROCm/rocshmem commit: 0a4f8a83b9]

projects/rocshmem/tests/functional_tests/amo_bitwise_tester.hpp

@@ -44,10 +44,19 @@ class AMOBitwiseTester : public Tester {
 
   virtual void verifyResults(size_t size) override;
 
-  dim3 _gridSize{};
-  char *_r_buf;
-  T *_ret_val;
-  T *_s_buf;
+  void verifyDestValues();
+  void verifyReturnValues();
+
+  int destIndex(int l, int elem_idx) const;
+  int numElems() const;
+  std::pair<T*, int> retChunk(int l, int elem_idx) const;
+
+  T* dest{nullptr};        // symmetric target buffer [loop][elem]
+  T* ret_val{nullptr};     // device returns [loop][thread]
+
+  size_t n_in{0};          // num_wgs * wg_size
+  size_t n_out{0};         // elements per loop: PerBlock->num_wgs, PerGrid->1
+  size_t n_loops{0};       // loop + skip
 };
 
 #endif