Differences

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

--- cluster:164 [2017/10/27 19:38]
hmeij07
+++ cluster:164 [2017/11/16 17:41]
hmeij07 [PPMA Bench]
@@ Line 569: / Line 569: @@
   * Adding mpi threads or more gpus reduces ns/day performance
   * No idea if adding omp threads shows a different picture
+  * No idea how it compares to K20 gpus
 <code>
 nvidia-smi -pm 0; nvidia-smi -c 0
 # gpu_id is done via CUDA_VISIBLE_DEVICES
@@ Line 634: / Line 636: @@
 -n 4, -gpuid 0123
+# comparison of binaries running PMMA
+# 1 gpu 4 mpi threads each run
+# lmp_mpi-double-double-with-gpu.log
+Performance: 49.833 ns/day, 0.482 hours/ns, 576.769 timesteps/s
+# lmp_mpi-single-double-with-gpu.log
+Performance: 58.484 ns/day, 0.410 hours/ns, 676.899 timesteps/s
+# lmp_mpi-single-single-with-gpu.log
+Performance: 56.660 ns/day, 0.424 hours/ns, 655.793 timesteps/s
 </code>
+==== FSL ====
+**User Time Reported** from time command
+  * mwgpu cpu run
+  * 2013 model name      : Intel(R) Xeon(R) CPU E5-2660 0 @ 2.20GHz
+    * All tests 45m
+    * Bft test 16m28s (bedpostx)
+  * amber128 cpu run
+  * 2017 model name      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
+    * All tests 17m - 2.5x faster
+    * Bft test 3m39s - 6x faster (bedpostx)
+  * amber128 gpu run
+  * 2017 CUDA Device Name: GeForce GTX 1080 Ti
+    * Bft gpu test 0m1.881s (what!? from command line) - 116x faster (bedpostx_gpu)
+    * Bft gpu test 0m1.850s (what!? via scheduler) - 118x faster (bedpostx_gpu)
 \\
 **[[cluster:0|Back]]**

DokuWiki