V1.5.0
Change Description
The OmniData operator pushdown feature of Kunpeng BoostKit for Big Data pushes operators on compute nodes to storage nodes and transmits the computing results to compute nodes, reducing the amount of data transmitted over the network.
Version 1.5.0 has the following changes:
- Incorporated the documents of this feature into the Kunpeng BoostKit 23.0.RC2 Big Data OmniRuntime Feature Guide.
- Upgraded OmniData to 1.5.0, which supports native accelerated computing using the Filter operator and filtering of Parquet type data using the column index and a bloom filter.
- Supports overlay of operator pushdown and operator acceleration features on the Spark engine, the OmniVec data processing format, selectivity calculation for the string type, and pushdown of some tasks.
Resolved Issues
Redundant tasks can be processed during operator pushdown on the Spark engine.
Known Issues
None
Parent topic: OmniData