The most common symptom of patients with alcohol use disorders (AUD) is cognitive impairment that negatively affects abstinence. Presently, there is a lack of indicators for early diagnosis of alcohol-related cognitive impairment (ARCI). We aimed to assess the cognitive deficits in AUD patients with the help of a specific imaging marker for ARCI. Data-driven dynamic and static global signal topography (GST) methods were applied to explore the cross-talks between local and global neuronal activities in the AUD brain. Twenty-six ARCI, 54 AUD without cognitive impairment (AUD-NCI), and gender/age-matched 40 healthy control (HC) subjects were recruited for this study. We found that there was no significant difference with respect to voxel-based morphometry (VBM) and static GST between AUD-NCI and ARCI groups. And in dynamic GST measurements, the AUD-NCI patients had the highest coefficient of variation (CV) at the right insula, followed by ARCI and the HC subjects. In precuneus, the order was reversed. There was no significant correlation between the dynamic GST and behavioral scores or alcohol consumption. These results suggested that dynamic GST might have potential implications in understanding AUD pathogenesis and disease management.