Commits
Antoine Pitrou authored and GitHub committed ca67ec22440
GH-40095: [C++][Parquet] Remove AVX512 variants of BYTE_STREAM_SPLIT encoding (#40127) Two reasons: * the SSE2 and AVX2 variants are already fast enough (on the order of 10 GB/s) * the AVX512 variants do not seem faster, and can even be slower, on tested Intel machines * Closes: #40095 Authored-by: Antoine Pitrou <antoine@python.org> Signed-off-by: Antoine Pitrou <antoine@python.org>