EMC expands GreenPlum hardware and updates software

EMC has added software and hardware to its Greenplum data processing and warehousing product family.

On Tuesday, it released a high-capacity and a fast-access variant on its existing Greenplum Data Computing Appliance (DCA) for large-scale data warehousing and processing.

It also announced a small hardware module for the Greenplum family, the Data Integration Accelerator, an add-on that promises to speed the loading of data batches into Greenplum DCA hardware.

Greenplum Database has been updated to 4.1, with better Hadoop cluster integration and further analytical functions.

All told, the announcement sees EMC bulk out the Greenplum product portfolio, which it gained with its Greenplum acquisition in July 2010. Customers can now choose hardware for either large or frequently accessed datasets.

In a separate announcement on Tuesday, SAS said it will bring SAS High-Performance Analytics to the Greenplum hardware in the future, but did not give a date. The data analytics software will run in a parallel, shared memory environment on top of the hardware when it comes out, the company said.

Spec-wise, the High Capacity DCA has 3.4 times the uncompressed and compressed storage capacity of the basic DCA appliance, at 124TB and 496TB respectively. However, its data load rate is lower, at 4.8TB per hour, compared with 10 for the standard DCA. Its data scan rate is 8GB lower, at 16GB per second, as well.

Greenplum's High Performance DCA is an improved version of the DCA and High Capacity DCA, with more memory, CPU cores, scan rate and load rates than both. It has more capacity than the DCA but less than the High Capacity DCA.

Unlike the other DCAs, which can both be expanded to six full racks for datasets that require bulk storage, the High Performance DCA only scales between a quarter and a full rack.