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
- Enabled high-performance operator acceleration.
- Provided an efficient data organization mode, OmniVec.
- Enabled connection to the Spark and openLooKeng compute engines.
Modified Features
None
Removed Features
None
Parent topic: V1.0.0