Branch: refs/heads/main
Revision: 372666d
Author: stonea
Link: Unavailable
Log Message:
Merge pull request #20024 from stonea/allow_gpu_ugni_ofi
Remove check disallowing CHPL_LOCALE_MODEL=gpu to be used with CHPL_COMM=ugni and CHPL_COMM=ofi
I've manually verified that CHPL_COMM=ugni works fine (by running all the test under gpu/native/) on a Cray XC system and that CHPL_COMM=ofi works on a Cray CS system.
[Reviewed by @e-kayrakli]
Modified Files:
M util/chplenv/chpl_gpu.py
Compare: https://github.com/chapel-lang/chapel/compare/dce102cb96c5...372666dfa47f