Differences

This shows you the differences between two versions of the page.

--- doku:vasp-benchmarks [2015/01/08 13:37] – [VSC 2] ir
+++ doku:vasp-benchmarks [2015/02/19 14:34] – ir
@@ Line 61: / Line 61: @@
 **Figure 5:** real running time depending on the selected mpich environment and the number of processes. Here the number of threads is always 1.
-===== VSC 2 =====
+===== VSC 3 =====
 The code was compiled with the intel compiler, intel MKL (BLACS, SCALAPACK), and intel mpi (5.0.0.028).
@@ Line 67: / Line 67: @@
 Figure 6 shows that the running time of this benchmark substantially decreases with the number of MPI-processes. The decrease in running time with the number of threads is less dominant. However, other applications may exhibit a different behavior.
+{{:doku:vasp:nn08_vsc3_vasp.png?400|}}
+{{:doku:vasp:nn32_vsc3_vasp.png?400|}}
-**Figure 6:** real running time on eight nodes depending on the number of MPI processes and the number of threads.
+**Figure 6:** real running time on eight and 32 nodes depending on the number of MPI processes and the number of threads.
+{{ :doku:vasp:nn1-64_tn16_th01_time.png?600 |}}
+**Figure 7:** real running time for 16 tasks (MPI processes) per node and one thread depending on the number of nodes.