The HPDMDB Procedure
The HPDMDB procedure is a high-performance version of the DMDB procedure, which creates summaries of the input data source. PROC HPDMDB creates two output data sets: the VAROUT data set, which contains a summary of the numeric variables, and the CLASSOUT data set, which contains a summary of the classification variables.
PROC HPDMDB is high-performance in that it takes advantage of distributed and multicore computing environments when the input data are stored on the SAS appliance.
You can use PROC HPDMDB to create a data mining database (DMDB) that is compatible with the DMDB from PROC DMDB, although this feature of PROC HPDMDB might not be supported in future versions.
PROC HPDMDB runs in either single-machine mode or distributed mode.
Note: Distributed mode requires SAS High-Performance Server Distributed Mode .
Because the HPDMDB procedure is a high-performance analytical procedure, it also does the following:
-
enables you to run in distributed mode on a cluster of machines that distribute the data and the computations
-
enables you to run in single-machine mode on the server where SAS is installed
-
exploits all the available cores and concurrent threads, regardless of execution mode
For more information, see the section Processing Modes in Chapter 3: Shared Concepts and Topics.