Merge pull request #7329 from janjust/v4.0.x-oshmem-perf-multi-worker

V4.0.x: oshmem/ucx: improves spml ucx performance for multi-threaded applications.

Author: gpaulsen

oshmem/mca/atomic/ucx/atomic_ucx_cswap.c

@@ -50,6 +50,6 @@ int mca_atomic_ucx_cswap(shmem_ctx_t ctx,
         mca_spml_ucx_remote_op_posted(ucx_ctx, pe);
     }
 
-    return opal_common_ucx_wait_request(status_ptr, ucx_ctx->ucp_worker,
+    return opal_common_ucx_wait_request(status_ptr, ucx_ctx->ucp_worker[0],
                                         "ucp_atomic_fetch_nb");
 }

oshmem/mca/atomic/ucx/atomic_ucx_module.c

@@ -80,7 +80,7 @@ int mca_atomic_ucx_fop(shmem_ctx_t ctx,
                                      op, value, prev, size,
                                      rva, ucx_mkey->rkey,
                                      opal_common_ucx_empty_complete_cb);
-    return opal_common_ucx_wait_request(status_ptr, ucx_ctx->ucp_worker,
+    return opal_common_ucx_wait_request(status_ptr, ucx_ctx->ucp_worker[0],
                                         "ucp_atomic_fetch_nb");
 }