Is it possible to specify a stream for a kernel launch in Quadrants?
I have a bunch of mixed taichi-pytorch-cuda code, which would benefit from being able to specify a consistent stream to avoid race conditions through it. It mostly seems to work at the moment, but it seems like perhaps I'm just relying on luck that there aren't problems.
Maybe I just misunderstood how the Taichi/(now Quadrants) runtime is operating.
Cheers,
Oliver
Concisely describe the proposed feature
A clear and concise description of what you want. For example,
I would like to add an Apple Metal backend to the compiler so that my Macbook GPU can be utilized.
Describe the solution you'd like (if any)
A clear and concise description of what you want to achieve and implement.
Additional comments
Add any other context or screenshots about the feature request here.
Is it possible to specify a stream for a kernel launch in Quadrants?
I have a bunch of mixed taichi-pytorch-cuda code, which would benefit from being able to specify a consistent stream to avoid race conditions through it. It mostly seems to work at the moment, but it seems like perhaps I'm just relying on luck that there aren't problems.
Maybe I just misunderstood how the Taichi/(now Quadrants) runtime is operating.
Cheers,
Oliver
Concisely describe the proposed feature
A clear and concise description of what you want. For example,
Describe the solution you'd like (if any)
A clear and concise description of what you want to achieve and implement.
Additional comments
Add any other context or screenshots about the feature request here.