| 1 |
On 01:34 Mon 11 Jul , Andrea Arteaga wrote: |
| 2 |
> FFTW can perform a wide number of tasks, and a survey has been taken |
| 3 |
> [1] asking the community about the most wanted tests. Following the |
| 4 |
> results, the following tests have been implemented: |
| 5 |
> * Forward Discrete Fourier Transormation |
| 6 |
> * Backward Discrete Fourier Transormation |
| 7 |
|
| 8 |
How about FFTs rather than DFTs? |
| 9 |
|
| 10 |
> The mid-term evaluation will come soon. For this, I'm performing many |
| 11 |
> tests in order to present, as mid-term result, a general comprehensive |
| 12 |
> report which makes clear that the project is already usable. My mentor |
| 13 |
> reported that my script already allowed him to find some bugs in a |
| 14 |
> package, which already is a good results for me -- even if the purpose |
| 15 |
> of the script is not (only) finding bugs --. My mid-term report will |
| 16 |
> hopefully persuade many people to run some benchmarks on their |
| 17 |
> computers. |
| 18 |
|
| 19 |
Is there any intent that it be able to automatically select the best |
| 20 |
parameters in addition to just graphing the results? From looking at |
| 21 |
some of those graphs, it seems like if you applied some smoothing, you |
| 22 |
could pick the peaks out fairly easily. |
| 23 |
|
| 24 |
-- |
| 25 |
Thanks, |
| 26 |
Donnie |
| 27 |
|
| 28 |
Donnie Berkholz |
| 29 |
Admin, Summer of Code |
| 30 |
Gentoo Linux and X.Org |
| 31 |
Blog: http://dberkholz.com |
Archives