The multiyear effort started at Teradata and continued at Starburst is getting close to its final shape. Even though it is in the initial version of cost-based optimizer we were able to see really nice speedups in TPCH and TPCDS benchmarks (up to 10-15x). It is a great foundation for more optimizations in the future. I can’t wait to see it working at production and to get first feedback from Presto users.
Starburst, the enterprise Presto company, announced the public availability of the Starburst Distribution of Presto. The company will provide enterprise-grade support to the rapidly growing Presto user base, while remaining focused on accelerating the development of the Presto engine through continued contributions to the open source Presto project.
There is a new cool feature in Presto that will speed up some inequality joins.
Since couple of months there is a new highly efficient connector for Presto. It works by storing all data in memory on Presto Worker nodes, which allow for extremely fast access times with high throughput while keeping CPU overhead at bare minimum.
I have wanted to experiment with Java for a long time to find out whether or not it can take advantage of Single Instruction, Multiple Data (SIMD) instructions to speed up CPU-intensive computations. I found very little information while I was researching this, so I decided to share my own findings.