lidavidm opened a new pull request #10294: URL: https://github.com/apache/arrow/pull/10294
This is one of the contributors to the regression in scan times of wide datasets in ARROW-11469 - for every column, we're copying a vector of shared_ptrs of every column, leading to a quadratic number of shared_ptr copies/destructions. And the consuming API expects a reference anyways, so all this copying was pointless. -- 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
