[PATCH] D17019: [OpenMP] Code generation for teams - kernel launching
Carlo Bertolli via cfe-commits
cfe-commits at lists.llvm.org
Sun Feb 21 10:15:17 PST 2016
carlo.bertolli added a comment.
Just wanted to add that tgt_target_teams needs the values for num_teams and thread_limit because, for some accelerators, it is necessary to know those values in advance, before teams gets actually executed. For instance, on Nvidia GPUs we launch one CUDA block for each team. This can only be done at kernel launch time, which is performed in the implementation of tgt_target_teams.
http://reviews.llvm.org/D17019
More information about the cfe-commits
mailing list