SQream DB is a modern RDBMS database primarily designed for data warehousing large amounts of data (Big Data) with additional acceleration via graphics processors (GPU). The entire SQream DB database system was built from the beginning, more precisely; no existing system was used as a basis for development, e.g. Hadoop or Postgres. Query execution on graphics processors is a technology similar to the systems used for data mining in cryptocurrencies, and allows massive parallel processing of data on each core of the graphics card processor using a faster frequency of graphics memory than standard RAM on the motherboard.
In standard, frequently used Data Warehouses, all components within the system are closely connected and share hardware resources. With high data throughput and large numbers of users, scaling is difficult and performance problems are created. SQream DB solves this problem with intelligent internal architecture using a separate compiler, executable and data containers to better optimize data flow and processing.
The next step of speeding up the performance within the SQream DB database is achieved by data partitioning in two ways, called hyper – partitioning, intended for maximum data compression and flow which is performed completely automatically.
Another revolutionary approach to data storage with SQream DB is the intelligent use of metadata generated by GPU processing. Metadata data contains descriptive data on the range and values of each chunk, and it is stored separately from the actual data, thus allowing intelligent skipping of unnecessary data ranges in queries, creating the so-called zone maps, which results in a reduction in hardware resources usage.
SQream DB is fully ANSI-92 SQL compatible and easily implemented in all ecosystems due to support for all typical ODBC and JDBC connectors, including Python, C #, .NET, C ++, Java and others. Native support for the SQL language, allows the use of any ETL tool and other applications on top of the database, reducing implementation time to a minimum.
SQream DB can run on most standard server x86-64 hardware with Nvidia graphics cards, and even commercial laptops equipped with such hardware, but for best performance, 2x Nvidia Tesla graphics cards (K80, P40, P100, etc.) are recommended, and for even larger acceleration, IBM POWER9 processors that boost performance by up to 3.7 times as tested.
The database is available as software, which you can install on standard x86-64 or IBM POWER9 architecture with NVIDIA graphics cards, such as cloud service (Amazon P2 / P3 with NVIDIA Tesla, Azure NCv3 with Tesla V100) and IBM Bluemix bare metal systems.