This speeds up multi-threaded CSV reads by removing the serial bottleneck of 
detecting newlines when no newlines can be present in CSV values.

On this machine (8-core AMD processor), the speed of reading a CSV file of text 
column data goes from 600 MB/s (before this patch) to 1.2 GB/s.

[ Full content available at: https://github.com/apache/arrow/pull/2684 ]
This message was relayed via gitbox.apache.org for [email protected]

Reply via email to