I'm trying to use the device partition to evaluate OpenCL as an alternative to OpenMP with vectorization on NUMA architectures.
However I'm unable to use partitioning by affinity with NUMA affinity.
I'm working mainly on two types of cluster nodes:
- 4P Magny-Cours with AMD APP 2.8 (OpenCL 1.2)
- 1P Interlagos (Cray XK7 node) with AMD APP 2.5 (OpenCL 1.1 - device fission extension)
the query for affinity domains available only gives me L1, L2, L3 and next, and no NUMA affinity (that I would require).
Is there some special requirement to have the partitioning by NUMA affinity or is it just not supported yet?