Benchmarks: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
|||
| Line 6: | Line 6: | ||
Using 100 processors: basic = 5 s, auto = 152 s, test suite = 529 s | Using 100 processors: basic = 5 s, auto = 152 s, test suite = 529 s | ||
Using 50 processors: basic = 5 s, auto = 152 s, test suite = 529 s | Using 50 processors: basic = 5 s, auto = 152 s, test suite = 529 s | ||
Using 20 processors: basic = 5 s, auto = 152 s, test suite = 529 s | Using 20 processors: basic = 5 s, auto = 152 s, test suite = 529 s | ||
Using 10 processors: basic = 16 s, auto = 762 s, test suite = 2997 s | Using 10 processors: basic = 16 s, auto = 762 s, test suite = 2997 s | ||
Using 1 processor: basic = 5 s, auto = 152 s, test suite = 529 s | Using 1 processor: basic = 5 s, auto = 152 s, test suite = 529 s | ||
===== Benchmark calculations: ===== | |||
Revision as of 17:42, 3 December 2008
CYANA Benchmarks
Desktop: 1 Intel Core2 Quad CPU Q6600, 2.40 Ghz, 3.0 GB memory, Ubuntu 8.04 Linux, gfortran (-O3) Fortran compiler
Server: 20 nodes, each with 2 Intel Xeon Quad CPU E5462, 2.80 Ghz, 16 GB memory, Ubuntu 8.04 Linux, gfortran (-O3) Fortran compiler
Using 100 processors: basic = 5 s, auto = 152 s, test suite = 529 s
Using 50 processors: basic = 5 s, auto = 152 s, test suite = 529 s
Using 20 processors: basic = 5 s, auto = 152 s, test suite = 529 s
Using 10 processors: basic = 16 s, auto = 762 s, test suite = 2997 s
Using 1 processor: basic = 5 s, auto = 152 s, test suite = 529 s