We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Allowing execution agent types to convert to their indices might simplify very simple loops where the execution category of the agent is irrelevant:
A saxpy loop
bulk_invoke(par(n), [=](parallel_agent& self) { auto i = self.index(); z[i] = a * x[i] + y[i]; });
would become
bulk_invoke(par(n), [=](size_t idx) { z[i] = a * x[i] + y[i]; });
The size of the agent's group would be lost, as well as functionality such as concurrent_agent::wait().
concurrent_agent::wait()
This also seems like it would be a little redundant with Intel's proposed for_loop control structure.
for_loop
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Allowing execution agent types to convert to their indices might simplify very simple loops where the execution category of the agent is irrelevant:
A saxpy loop
would become
The size of the agent's group would be lost, as well as functionality such as
concurrent_agent::wait()
.This also seems like it would be a little redundant with Intel's proposed
for_loop
control structure.The text was updated successfully, but these errors were encountered: