Hi,
Vectorized Query Execution <https://cwiki.apache.org/confluence/display/Hive/Vectorized+Query+Execution > works on ORC files and is supposed to reduce the CPU usage and generally improves the performance of jobs. You can turn it on by using set hive.vectorized.execution.enabled=true; Has anyone done any benchmark on this that are happy to share? Thanks, Mich Talebzadeh LinkedIn <https://www.linkedin.com/profile/view?id=AAEAAAAWh2gBxianrbJd6zP6AcPCCdOABU rV8Pw> https://www.linkedin.com/profile/view?id=AAEAAAAWh2gBxianrbJd6zP6AcPCCdOABUr V8Pw