search

SpineML / SpineML_2_BRAHMS

Code generation scripts to run a SpineML neural model using BRAHMS on standard CPUs
http://spineml.github.io/simulators/BRAHMS/
4 stars 3 forks source link

Optimize AllToAll connections #22

Closed sebjameswml closed 8 years ago

sebjameswml commented 8 years ago

If alltoall connection has fixed delay and fixed weight, then the full MxN computation matrix does not need to be evaluated. Implement some runtime tests in SpineML_2_BRAHMS_CL_weight.xsl to optimise models containing these kinds of AllToAll connections.

sebjameswml commented 8 years ago

I've merged this into master now (a few days ago)

sebjameswml commented 8 years ago

Closing as it's merged now (but look out for a big bug issue!)