You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We are using MAP to solve a data analysis problem in plasma physics. For the MAP problem we usually only have a single point at which we want to differentiate the our function. Hence, so far we parallelized across stencil points rather than over multiple x values.
We would very much like to try this library but without vectorization across stencil points we can only test it for our simplest cases.
Taking a brief look at the code indicates to me that adding vectorization across stencil points might be quite time consuming, so I understand if this is too tall an ask.
Hope you have a nice day!
The text was updated successfully, but these errors were encountered:
We are using MAP to solve a data analysis problem in plasma physics. For the MAP problem we usually only have a single point at which we want to differentiate the our function. Hence, so far we parallelized across stencil points rather than over multiple
x
values.We would very much like to try this library but without vectorization across stencil points we can only test it for our simplest cases.
Taking a brief look at the code indicates to me that adding vectorization across stencil points might be quite time consuming, so I understand if this is too tall an ask.
Hope you have a nice day!
The text was updated successfully, but these errors were encountered: