... | @@ -64,6 +64,8 @@ However, something else stands out. On another test, which runtime is shown just |
... | @@ -64,6 +64,8 @@ However, something else stands out. On another test, which runtime is shown just |
|
|
|
|
|
## General comparison
|
|
## General comparison
|
|
|
|
|
|
|
|
### Between versions
|
|
|
|
|
|
This board shows the mean runtime taken for one iteration. The sequential versions are using one thread, the parallels ones are using 2 threads.
|
|
This board shows the mean runtime taken for one iteration. The sequential versions are using one thread, the parallels ones are using 2 threads.
|
|
|
|
|
|
| setup \\ version | seq. without -fopenmp | seq with -fopenmp | openMP | openmp/nOS-V |
|
|
| setup \\ version | seq. without -fopenmp | seq with -fopenmp | openMP | openmp/nOS-V |
|
... | @@ -76,4 +78,10 @@ The tests run with numactl can sometimes output the following error : |
... | @@ -76,4 +78,10 @@ The tests run with numactl can sometimes output the following error : |
|
`ERROR numa_sched_setaffinity_v2_int() failed: Invalid argument` \
|
|
`ERROR numa_sched_setaffinity_v2_int() failed: Invalid argument` \
|
|
`sched_setaffinity: Invalid argument`
|
|
`sched_setaffinity: Invalid argument`
|
|
|
|
|
|
However, this error is not occurring systematically. |
|
However, this error is not occurring systematically.
|
|
\ No newline at end of file |
|
|
|
|
|
### With number of threads
|
|
|
|
|
|
|
|
![model-perf-base](uploads/9aa5c941abc636bfc7fa05219b2c7488/model-perf-base.png)
|
|
|
|
|
|
|
|
Here are the performances of the original given model, compiled with OpenMP. As shown be the graph, the performances of the model stop increasing over 15/20 threads. |
|
|
|
\ No newline at end of file |