Change Description
The OmniRuntime OmniOperator feature of Kunpeng BoostKit for Big Data uses a unified infrastructure to support different engines (such as Spark and openLooKeng), reducing repeated optimization work, fully exploring common and heterogeneous computing power, and promoting the Kunpeng ecosystem.
New Features
- Added support for UDFs.
- Implemented vectorized instruction acceleration in OmniOperator.
- Added support for overflow processing of the decimal type and conversion of the cast type in expressions.
- Enhanced basic Spark functions and the aggregation and Join operators in OmniOperator.
- Adapted to the Spark AQE feature.
- Added support for the Short type in OmniVec.
Modified Features
None
Removed Features
None
Parent topic: V1.1.0