e2e-model-learning icon indicating copy to clipboard operation
e2e-model-learning copied to clipboard

Published 20 hours ago • verified publisher icon locuslab

Low GPU utilization for sequential quadratic programming solver

Open ryanvolpi opened this issue 4 years ago • 0 comments

When I train the task_net from the power scheduling problem (modified to work with my data) the SQP solving process takes forevor. While it runs, my GPU (Tesla K80) utilization hovers at only ~3%. I'm not sure if that is normal or what the bottleneck may be. However, this step significantly impacts training time. Training the rmse nets is extremely quick, of course.

ryanvolpi avatar Jan 25 '21 17:01 ryanvolpi