Fix issues with --gpu-bind while using cgroups
CUDA_VISIBLE_DEVICES was not being set to the correct GPU indexes when cgroups were being used. These issues were exhibited with at least the map_gpu and mask_gpu binding options. The issue was that usable_gres is a bitmask of GRESs in the step's cgroup, but bit_test() was looking at bit i, which is the index of the global gres_list (not constrained by cgroups). Bug 7509
Please register or sign in to comment