Parallel solves
I wanted to know whether it is possible to run several solves in parallel, if they will all fit in GPU memory.
The use case is as follows - there are around 40 solves, each one of them takes around 10 seconds. I have been using a custom CG solver written in CUDA, where I could run e.g. 10 such solves in parallel.
After switching to AMGX, I am receiving a lot of exceptions, when several solves are trying to be run from different threads. I tried to perform the initialisation on single thread, but the result is the same.
Are you trying to solve multiple different systems or a system with multiple right hand sides? Are you using same solver (config) or different ones?
I am trying to solve multiple systems, with different both left and right hand sides. The config files may be the same.