23 Jun
2016
23 Jun
'16
4:39 p.m.
Hi All,
Following is the profiling results comparison of the decoding algorithms (unit in
micro-seconds). Each of the 4 test inputs is decoded 10000 times for getting below data.
Input test In target
In host
Vector id Tree based Existing
Tree based Existing
Min Avg Min Avg
Min Avg Min Avg
1 66 69.6 164 173.4
2 6.8 5 13.3
2 59 62.3 118 124.8
2 5.5 3 11.5
3 12 13.1 20 22
0 0.5 0 1.3
4 96 102.4 251 264
3 9.2 7 19.8
Important summary:
1. For few other identified test vectors existing algorithm fails functionally to decode
whereas tree based decoding algorithm succeeds.
2. Details of these test vectors are in the latest patch available in
users/pravin/epdan_profiling at http://git.osmocom.org/radisys/osmo-pcu/
3. From the above results it shows that Tree based decoding algorithm is better than
existing algorithm for the decoding time consumed.
4. The max value is not included because it is abnormally high which occurs at very low
frequency like once in 10000 iterations.
The detailed Profiling data follows,
In target:
Tree based decoding algorithm:
Input test Min Avg Max
vector Id
1 66 69.6 651
2 59 62.3 1125
3 12 13.1 259
4 96 102.4 1418
Existing Algorithm:
Input test Min Avg Max
vector Id
1 164 173.4 1372
2 118 124.8 691
3 20 22 1376
4 251 264 1229
In host:
Tree based decoding algorithm:
Input test Min Avg Max
Vector id
1 2 6.8 16065
2 2 5.5 20063
3 0 0.5 67
4 3 9.2 16219
Existing Algorithm:
Input test Min Avg Max
Vector id
1 5 13.3 12042
2 3 11.5 10816
3 0 1.3 5227
4 7 19.8 12078
Regards,
Pravin