> This enhancement makes a change to the ChaCha20 block function intrinsic on > aarch64, moving away from the block parallel implementation and to the > quarter-round parallel implementation that was done on x86_64. Assembly > language profiling yielded an 11% improvement in throughput. When put > together as an intrinsic and hooked into the JCE ChaCha20 cipher, the gains > are more modest, somewhere in the 2-4% range depending on job size, but still > an improvement.
Jamil Nimeh has updated the pull request incrementally with one additional commit since the last revision: Add explanatory comment and reference for quarter round intrinsic ------------- Changes: - all: https://git.openjdk.org/jdk/pull/23397/files - new: https://git.openjdk.org/jdk/pull/23397/files/41817c77..6ba0770b Webrevs: - full: https://webrevs.openjdk.org/?repo=jdk&pr=23397&range=01 - incr: https://webrevs.openjdk.org/?repo=jdk&pr=23397&range=00-01 Stats: 25 lines in 1 file changed: 25 ins; 0 del; 0 mod Patch: https://git.openjdk.org/jdk/pull/23397.diff Fetch: git fetch https://git.openjdk.org/jdk.git pull/23397/head:pull/23397 PR: https://git.openjdk.org/jdk/pull/23397
