Commits
Yuqi Gu authored and Wes McKinney committed 1b65c5562fc
ARROW-5458: [C++] Apache Arrow parallel CRC32c computation optimization ARMv8 defines VMULL/PMULL crypto instruction. This patch optimizes crc32c calculate with the instruction when available rather than original linear crc instructions. Author: Yuqi Gu <yuqi.gu@arm.com> Closes #4427 from guyuqi/Arm64-parallel-CRC32c and squashes the following commits: 16e22af03 <Yuqi Gu> Use C++-style casts be0955038 <Yuqi Gu> Re-implemented with the algorithm derived from Intel whitepaper. Remove the useless code of cache prefetching. a3e2bacc1 <Yuqi Gu> Fix code style format-check 349903a8d <Yuqi Gu> Fix style rules 1cdb28380 <Yuqi Gu> ARROW-5458: Apache Arrow parallel CRC32c computation optimization