OpenMP/Benchmarks: Difference between revisions
< OpenMP
Line 7: | Line 7: | ||
Example usage: | Example usage: | ||
<source lang="bash"> | |||
unset OMP_NUM_THREADS | unset OMP_NUM_THREADS | ||
time ./neighbor 5000 5000 23 | time ./neighbor 5000 5000 23 | ||
Line 17: | Line 18: | ||
export OMP_NUM_THREADS=6 | export OMP_NUM_THREADS=6 | ||
time ./neighbor 5000 5000 23 | time ./neighbor 5000 5000 23 | ||
</source> | |||
results table: | results table: | ||
Line 29: | Line 30: | ||
!Compiler | !Compiler | ||
!Compiler version | !Compiler version | ||
!Compiler flags | |||
!OS | !OS | ||
!System RAM | !System RAM | ||
|- | |- | ||
| | |||
| | | | ||
| | | | ||
Line 42: | Line 45: | ||
| | | | ||
|- | |- | ||
| | |||
| | | | ||
| | | | ||
Line 60: | Line 64: | ||
| ''gcc'' | | ''gcc'' | ||
| ''4.4.8'' | | ''4.4.8'' | ||
| ''-O3'' | |||
| ''Ubuntu 12.04'' | | ''Ubuntu 12.04'' | ||
| ''8 gb'' | | ''8 gb'' | ||
|} | |} |
Revision as of 07:06, 24 July 2013
Neighborhood analysis
Performance using OpenMP and different compilers:
source|svn/sandbox/soeren/benchmarks/neighborhood_openmp/
Best to run it 4 times for each case, discard the first and average the next 3.
Example usage:
unset OMP_NUM_THREADS
time ./neighbor 5000 5000 23
export OMP_NUM_THREADS=1
time ./neighbor 5000 5000 23
...
export OMP_NUM_THREADS=6
time ./neighbor 5000 5000 23
results table:
CPU | Number of cores | OMP NUM THREADS | Time "real" | Time "user" | Time "sys" | Compiler | Compiler version | Compiler flags | OS | System RAM |
---|---|---|---|---|---|---|---|---|---|---|
Intel i7 3770 | 4 real (8 w/ hyperthread) | unset (all) | example entry | gcc | 4.4.8 | -O3 | Ubuntu 12.04 | 8 gb |