Depends on what you need. Does your sample frame have identified subpopulations that you want to sample from, such as might be indicated with a geography, product purchased, age or similar subpopulation definition?
If so then most likely you need 1) a single variable to identify which group the observation in your sample frame belongs to, 2) sort the data by that variable, 3) use a STRATA statement to indicate that variable defines groups in Proc Surveyselect.
Yes the referenced approach simulates an SRS and adds a variable they use called SampleId to indicate which group the selected observations belong in. Following the example logic it is a single pass. The key elements are specifying how many records you need at the first step (number of groups X number of records in each group) as the sample size in the Surveyselect SAMPSIZE option and then using the same number of records in the last data step in the
SampleID=ceil(_n_/10);