Skip to navigation Skip to content
Careers | Phone Book | A - Z Index
Performance and Algorithms Research

November 2015 Results

Here are the results for the fourth order (operators.fv4.c) HPGMG-FV implementation (v0.3). Each machine was allowed to use any amount of memory per node, but three problem sizes were benchmarked: h(max), 2h(max/8), and 4h(max/64). Unfortuantely, due to scheduling and allocation limitations, some machines only evaluated at limited concurrency (%'s). Currently, these machines are ranked based on peak DOF/s (almost invariably h). Nevertheless, we are considering alternate metrics such as the sum, mean, geometric mean, and median. Feedback from the community is welcome.

  System HPGMG DOF/s Parallelization DOF per Top500
Rank Name Site h 2h 4h MPI OMP ACC Process Rank
1 Mira ALCF 5.00e11 3.13e11 1.07e11 49152 64   36M 5
      3.95e11 2.86e11 1.07e11 49152 64   36M  
2 Edison NERSC 2.96e11 2.46e11 1.27e11 10648 12   128M 34
3 Titan (CPU-only) OLCF 1.61e11 8.25e10 2.37e10 36864 8   48M 2
4 Hopper NERSC 7.26e10 5.45e10 2.74e10 21952 6   16M 62
5 SuperMUC (22%) LRZ 7.25e10 5.25e10 2.80e10 4096 8   54M 20
6 Hazel Hen (7%) HLRS 1.82e10 8.73e09 2.02e09 1024 12   16M -
7 SX-ACE (vector) HLRS 3.24e09 1.77e09 7.51e08 256 1   32M -
8 Babbage (MIC-only) NERSC 7.62e08 3.16e08 9.93e07 256 45   8M -