Techniques are disclosed for performing dump collection on a computing system. One technique includes detecting an error event on the computing system. After detecting the error event, a subset of hardware registers associated with the error event are determined. One or more hardware units within the computing system to capture data from are determined from a set of rules that specify an association between the one or more hardware units and the subset of hardware registers associated with the error event. Data is captured from each of the one or more hardware units.