Add some notes in TESTS.

[loba.git] / TODO

diff --git a/TODO b/TODO
index 640fb9e7a4c08b070338f998b97cbee778cf6a80..a337bc4fc53de1c99b51bc28917889a8ab86adf4 100644 (file)
--- a/TODO
+++ b/TODO
@@ -1,26 +1,28 @@
-* faire un autre thread pour les envois d'infos
-  -> c'est stupide d'attendre la fin des calcules s'il y en a beaucoup
-     surtout en bookkeeping...
+* Change simulator to use discrete tasks.
+   Each task must then be iterated a minimum of times.
+   At least two strategies to balance the tasks:
+    (i) send the tasks that have the most count of iterations;
+   (ii) send the tasks that have the least count of iterations.

 
 

-* check if communications can fail !
-  (restart them)
+* Remove usage of opt::option_x in loba_besteffort.cpp and loba_2besteffort.cpp
+   Use -k instead (done).  Remove hack marked "FIXME" in opt::parse_args().

 
 

-* review receive with timeout.
+* Support heterogeneous platforms?
+   Not sure yet.
+   Should be doable if each process also sends its speed to its neighbors.

 
 

-* verify bookkeeping version.
+* Add options -j/-J: minimum number of iterations?

 
 

-* add several metrics
-  - message exchanges : number/volume of sent/received data/ctrl messages
+* Add options -f/-F: termination based on flops achieved?

 
 

-* add options -j/-J : minimum number of iterations?
+* Choose a license before making the code public.
+   CeCILL-B?

 
 

-* add a variant to (not) change neighbor load information at send?
+* Translate french parts in english (README, QUESTIONS, ALGORITHMS, ...)
+   Not urgent.

 
 

-* implement loba_* algorithms (start with some trivial one)
+* Add synchronized mode?
+   No.

 
 

-* for automatic process topology,
-   -> implement some random initial distribution of load
-
-* add synchronized mode
-
-* translate README file?
+* Add a variant to (not) change neighbor load information at send?
+   No.