Add host APIs for querying device ctx and remote heap pointer (#200)

* Add host APIs for querying device ctx and remote heap pointer

* Host API to query device pointer for ROCSHMEM_DEFAULT_CONTEXT,
  this is needed to support dynamic module initialization via device kernel
  library bitcode.
* Host API to query remote symmetric heap pointer that can be used in
  custom device kernel for RMA operations.

* Added rocshmem_ptr implementation within the Host Context class
* Enables pointer retrieval functionality for symmetric data objects
* Copy IPC pointers to host memory in RO host context

---------

Co-authored-by: avinashkethineedi <avinash.kethineedi@amd.com>

include/rocshmem/rocshmem.hpp

@@ -65,6 +65,29 @@ constexpr char VERSION[] = "3.0.0";
  */
 __host__ void rocshmem_init(MPI_Comm comm = MPI_COMM_WORLD);
 
+/**
+ * @brief Query rocSHMEM context from host API
+ *
+ * @param[out] ctx      Returns ROCSHMEM_CTX_DEFAULT device pointer that users 
+ *                      can query from one instance of rocshmem host library and
+ *                      use use later for dynamic module initialization in 
+ *                      kernel bitcode device library in the same application
+ */
+__host__ void * rocshmem_get_device_ctx();
+
+/**
+ * @brief Query rocSHMEM remote symmetric heap pointer
+ *
+ * @param[in]  dest     local symmetric heap allocation pointer for current pe/device
+ * 
+ * @param[in]  pe       remote PE
+ * 
+ * @param[out] ptr      Returns remote symmetric heap device pointer from host-side API.
+ *                      This can be used to issue load/store from custom kernels
+ *                      instead of using rocshmem device side get/put APIs for RMA operations.
+ */
+__host__ void *rocshmem_ptr(void *dest, int pe);
+
 /**
  * @brief Initialize the rocSHMEM runtime and underlying transport layer
  *        with an attempt to enable the requested thread support.