wip before meeting

docs/source/API/core/Graph.axpby.kokkos.graph.cpp

@@ -0,0 +1,12 @@
+auto graph = Kokkos::Experimental::create_graph(exec_A, [&](auto root){
+    auto node_xpy = root.then_parallel_for(N, MyAxpby{x, y, alpha, beta});
+    auto node_zpy = root.then_parallel_for(N, MyAxpby{z, y, gamma, beta});
+
+    auto node_dotp = Kokkos::Experimental::when_all(node_xpy, node_zpy).then_parallel_reduce(
+        N, MyDotp{x, z}, dotp
+    )
+});
+
+graph.submit(exec_A);
+
+exec_A.fence();

docs/source/API/core/Graph.axpby.kokkos.graph.p2300.cpp

@@ -0,0 +1,15 @@
+auto graph = Kokkos::construct_graph();
+
+auto node_xpy = Kokkos::then(graph, Kokkos::parallel_for(N, MyAxpby{x, y, alpha, beta}));
+auto node_zpy = Kokkos::then(graph, Kokkos::parallel_for(N, MyAxpby{z, y, gamma, beta}));
+
+auto node_dotp = Kokkos::then(
+    Kokkos::when_all(node_xpy, node_zpy),
+    Kokkos::parallel_reduce(N, MyDotp{x, z}, dotp)
+);
+
+graph.instantiate();
+
+graph.submit(exec_A);
+
+exec_A.fence();

docs/source/API/core/Graph.axpby.kokkos.vanilla.cpp

@@ -0,0 +1,8 @@
+Kokkos::parallel_for(policy_t(exec_A, 0, N), MyAxpby{x, y, alpha, beta});
+Kokkos::parallel_for(policy_t(exec_B, 0, N), MyAxpby{z, y, gamma, beta});
+
+exec_B.fence();
+
+Kokkos::parallel_reduce(policy_t(exec_A, 0, N), MyDotp{x, z}, dotp);
+
+exec_A.fence();