#1850: Severe performance problem on Stampede -------------------------+-------------------------------------------------- Reporter: hinder | Owner: Type: defect | Status: confirmed Priority: major | Milestone: Component: SimFactory | Version: development version Resolution: | Keywords: -------------------------+--------------------------------------------------
Comment (by knarf):
To summarize the current status: setting KMP_AFFINITY seems to be necessary for performance when using SystemTopology, but is harmful when not using it: either you have to use both, or none. Do I understand this correctly?
If so: - Is it understood why using SystemTopology results in poor performance when KMP_AFFINITY isn't set? - Is it understood why using KMP_AFFINITY results in poor performance when not using SystemTopology (but not using KMP_AFFINITY seems to be fine)?
My comments: It could be that 'using KMP_AFFINITY" isn't the right way to think about this. We set it specifically to "norespect,compact". Maybe we should set it to something different to work without SystemTopology.