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
A couple of years have passed since the inception of the code. The current state of affairs is, that the code uses OpenMP to accelerate computation, which brings down the time required significantly. However, the 3D computation for the 14.1 million vertices in the 3D Oase composite data set still takes up to 20 minutes, depending on how much is going on.
There is a new library out, which strifes to provide access to all accelerator components, like Graphics cards, eGPUs and multiple CPU cores. It's called OneAPI (https://www.oneapi.com).
The scope of this ticket would be to make an experiment with OneAPI and measure what it can do for our performance when an eGpu is present etc.
The text was updated successfully, but these errors were encountered:
A couple of years have passed since the inception of the code. The current state of affairs is, that the code uses OpenMP to accelerate computation, which brings down the time required significantly. However, the 3D computation for the 14.1 million vertices in the 3D Oase composite data set still takes up to 20 minutes, depending on how much is going on.
There is a new library out, which strifes to provide access to all accelerator components, like Graphics cards, eGPUs and multiple CPU cores. It's called OneAPI (https://www.oneapi.com).
The scope of this ticket would be to make an experiment with OneAPI and measure what it can do for our performance when an eGpu is present etc.
The text was updated successfully, but these errors were encountered: