Dynamic scheduling across OpenMP thread teams on Xeon Phi

Dynamic scheduling across OpenMP thread teams on Xeon Phi

Hi,

I am curious why OpenMP (v4.5) specification does not provide dynamic scheduling across thread teams.

Is it possible to schedule loop iterations across OpenMP thread teams at runtime using Xeon Phi?

Any comments or suggestions are appreciated.

3 posts / 0 new
Last post
For more complete information about compiler optimizations, see our Optimization Notice.

You are asking this question in the wrong place. This forum is for discussions of the internals of the Intel OpenMp runtime implementation, whereas your question is about the design of the OpenMP standard.There is a discussion forum at http://openmp.org/ forum where you could ask this question (since that is the OpenMP ARB's site, and they own the standard it seems a good place to ask!)

Quote:

James C. (Intel) wrote:

You are asking this question in the wrong place. This forum is for discussions of the internals of the Intel OpenMp runtime implementation, whereas your question is about the design of the OpenMP standard.There is a discussion forum at http://openmp.org/ forum where you could ask this question (since that is the OpenMP ARB's site, and they own the standard it seems a good place to ask!)

Thank you James C.

Leave a Comment

Please sign in to add a comment. Not a member? Join today