zeroshade opened a new pull request, #13529: URL: https://github.com/apache/arrow/pull/13529
In addition to adding a `DictionaryUnifier` object, and functions for unifying Chunked arrays and Tables, this also adds the necessary SIMD implemented functions to perform the transposition of the integers (along with a benchmark). Calling `TransposeInts` on an array of 1000 8-bit integers across a 50 element mapping took only 30 ns on my laptop as opposed to around 7000 ns for non-SIMD solution. Pure-Go implementations are also provided for the processors that don't have SSE4 or AVX2 or for other architectures than amd64. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
