liyafan82 commented on issue #8397: [FLINK-11421][Table SQL/Runtime]Add compilation options to allow comp… URL: https://github.com/apache/flink/pull/8397#issuecomment-493889211 > From all the discussions above, seems we have two conclusions so far: > > 1. JCA only improves vectorized execution codes. > 2. The improvement about vectorization using JCA cannot be reproduced with JMH and can only be observed in cluster environment. > > Am I right about this? Not exactly. For processing time: 1. In cluster environment, the performance improvement is 30% - 40% for vectorization, and about 10% for row-store. 2. In local, the performance improvement is 2% - 7% for row-store, and the improvements for vectorization is unknown. For compilation time: 1. In cluster environment, the compilation time for JCA is more than 10 times longer than that of Janino. 2. In local, the compilation time for JCA is about 3 times longer.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
