Demo of aggregating results of all executions of slambench across all platforms (different CPU, GPU, frequency, compiler, etc). 
It can help build a realistic training set for further machine learning based autotuning and run-time adaptation as described in our papers 
[<a href="http://hal.inria.fr/hal-01054763">1</a>, <a href="https://hal.inria.fr/inria-00436029">2</a>, <a href="http://arxiv.org/abs/1406.4020">3</a>].
We can use it to find an optimal platform for a given data set (balancing execution time, energy/frequency, accuracy, price, cost, etc - 
particularly useful for cloud computing or mobile devices).

<hr>

<a href="http://cknowledge.org/repo/web.php?subview=17f4334bf785af5b&wcid=bc0409fb61f0aa82:fb8db7bfa6a1a11d&reverse_table_sort=14">CK report at cknowledge.org/repo</a> with ranking of all devices/kernel vs FPS, energy, accuracy, etc.

<hr>

<center>
<img src="$#ck_root_url#$action=pull&common_func=yes&cid=2d41f89bcf32d4d4:4028b74e6084d9c6&filename=time_vs_freq.png" width="700" height="400" ><br>
<br>
<a href="$#ck_root_url#$wcid=2d41f89bcf32d4d4:4028b74e6084d9c6">Reproduce/reuse/replay/discuss via CK (interactive graphs)</a>
</center>




<br>
<br>