Started by user Gunther HueblerhueblerGunther Huebler4343abb325943da1a557e1213b2908ead3c828aff163abb325943da1a557e1213b2908ead3c828aff16refs/remotes/origin/master3abb325943da1a557e1213b2908ead3c828aff163abb325943da1a557e1213b2908ead3c828aff16refs/remotes/origin/master3abb325943da1a557e1213b2908ead3c828aff163abb325943da1a557e1213b2908ead3c828aff16refs/remotes/origin/masterhttps://github.com/larson-group/clubb.gitfalse#434237681419302clubb_release_diff_test #434434false4341287FAILURE1714598811797http://carson.math.uwm.edu/jenkins/view/all/job/clubb_release_diff_test/434/src/CLUBB_core/advance_clubb_core_module.F90src/CLUBB_core/advance_xm_wpxp_module.F90src/CLUBB_core/advance_wp2_wp3_module.F90src/CLUBB_core/clubb_api_module.F90src/Morrison_microphys/microphysics.F90src/CLUBB_core/fill_holes.F90src/CLUBB_core/advance_xp2_xpyp_module.F903abb325943da1a557e1213b2908ead3c828aff161714587276000http://carson.math.uwm.edu/jenkins/user/hueblerGunther Hueblerhuebler@uwm.eduMaking num_draw_points in fill_holes a constant. We were already using this value as a constant everywhere, but passing a constant by argument list makes it difficult/impossible for a compiler to optimize using that constant, unless it does inlining. Now, rather than passing the constant num_hf_draw_points (or sometimes a hardcoded 2) we just use num_hf_draw_points directly from constants_clubb. This massively improves the performance of a loop in fill holes when using nvhpc+omp, which was the motivation for this, but should also improve the performance on CPUs. Everything is BFB. 2024-05-01 13:14:36 -05003abb325943da1a557e1213b2908ead3c828aff16Making num_draw_points in fill_holes a constant. We were already using this value as a constant everywhere, but passing a constant by argument list makes it difficult/impossible for a compiler to optimize using that constant, unless it does inlining. Now, rather than passing the constant num_hf_draw_points (or sometimes a hardcoded 2) we just use num_hf_draw_points directly from constants_clubb. This massively improves the performance of a loop in fill holes when using nvhpc+omp, which was the motivation for this, but should also improve the performance on CPUs. Everything is BFB.editsrc/CLUBB_core/advance_clubb_core_module.F90editsrc/CLUBB_core/advance_wp2_wp3_module.F90editsrc/CLUBB_core/clubb_api_module.F90editsrc/CLUBB_core/advance_xp2_xpyp_module.F90editsrc/Morrison_microphys/microphysics.F90editsrc/CLUBB_core/advance_xm_wpxp_module.F90editsrc/CLUBB_core/fill_holes.F90githttp://carson.math.uwm.edu/jenkins/user/bmg2bmg2http://carson.math.uwm.edu/jenkins/user/noreplynoreplyhttp://carson.math.uwm.edu/jenkins/user/hueblerGunther Hueblerfalse435http://carson.math.uwm.edu/jenkins/view/all/job/clubb_release_diff_test/435/433http://carson.math.uwm.edu/jenkins/view/all/job/clubb_release_diff_test/433/