Distributed-Model.md

@@ -148,3 +148,10 @@ With B=16, T=1024, 1 rank/socket
 | 16 | 4 | 15084 ms | 1086 | 4.9 |
 | 32 | 8 | 31649 ms | 1035 | 4.6 |
 | 64 | 16 | 68551 | 956 | 4.3 |
+
+
+## Trace
+
+Here we are using B08, T=1024, 4 ranks, 1 rank/socket
+
+![oss-mpi](uploads/e5dfb6f721eddbd936c04349d50017bb/oss-mpi.png)![oss-mpi.code_legend](uploads/5255e10205e11138e63a9d6ee1ca0908/oss-mpi.code_legend.png)