SQream was built to harness the raw brute-force power and high throughput capabilities of the GPU, with MPP-on-chip capabilities and the fully relational SQream DB SQL database. SQream DB comes with automatic tuning, ultra fast performance, class-leading compression, and extreme scalability.
Built for Data at Scale
SQream DB was designed for massive, dynamic workloads. We built our algorithms to handle the most challenging scenarios, and optimized them for the largest datasets, where typical database optimizations fail.
SQream DB’s interface layer is a collection of services that control the data warehouse. It includes concurrency control, access control (object-level permissions), cluster management, and the statement compiler.
The compute layer is where the actual data processing tasks are run. This includes CPU and GPU resources, controlled by the SQream DB software.
The storage layer is split into the metadata layer where all routine database objects are stored, and the persistent columnar bulk data layer which is heavily optimized for raw tablescan performance.
SQream DB has transparent commit, rollback and recovery, with full isolation – which means your data is always safe and consistent.
“We realized the benefits within minutes, we were able to ingest and analyze huge volumes of data to get clear insights on bidding trends, which would have taken hours, if not days through traditional means.”
Vasu Cherlopalle, VP Big Data and Analytics at PubMatic