Collective Knowledge Aggregator beta
Home Collaborative AI Interactive articles Graphs Programs Datasets Models Browse Get CK About
Join the community development of an open science SDK (CK) to automate, crowdsource and optimize machine learning and AI across diverse devices from IoT to supercomputers!
CK autotuning demo graphs: compiler flag tuning for susan on mingw
Demo of the multi-objective autotuning of compiler flags via CK with Pareto (can be any objective, i.e. execution time, energy, code size, cost, precision, reliability)
Discussion wiki (comments, reproducibility, etc.) ]
Select subgraph: 
Graph:
Graph params (to customize/reproduce):
   Auto-replot graph: , seconds:
Reproducing graph:
Experiment entries: demo-autotune-flags-susan-mingw-i10
demo-autotune-flags-susan-mingw-best
demo-autotune-flags-susan-mingw-i10-pareto
Scripts to rebuild: ck find demo:c292a04d8881888d
View in CK viewer
Replay graph from CMD: ck replay graph:be9fab019a546cef id=2d_points_time_vs_size_with_pareto
Obtain shared CK repo with all artifacts: ck pull repo:ck-autotuning
Original experiment table: Download in JSON;   Download in CSV
Embedd original image into interactive report/paper: <img src="http://cknowledge.org/repo/web.php?template=cknowledge&action=pull&common_func=yes&cid=2d41f89bcf32d4d4:be9fab019a546cef&filename=2d_points_time_vs_size_with_pareto.png" width="700" height="400" >
View entry in raw format

Developed by dividiti,
cTuning foundation,
and the community
          
Implemented as a CK workflow
                     
   
   
                      Hosted at