> This PR builds on a concept John Rose told me about some time ago. Instead of > combining memory operations of various sizes, a single large and skewed > memory operation can be made to clean up the tail of remaining bytes. > > This has the effect of simplifying and shortening the code. The number of > branches to evaluate is reduced. > > It should be noted that the performance of the fill operation affects the > allocation of new segments (as they are zeroed out before being returned to > the client code). > > This PR passes tier1, tier2, and tier3 on multiple platforms.
Per Minborg has updated the pull request with a new target base due to a merge or a rebase. The incremental webrev excludes the unrelated changes brought in by the merge/rebase. The pull request contains 18 additional commits since the last revision: - Merge branch 'master' into fill-overlap - Fix inverted logic error - Revert the default value for the fill threshold - Revert the settable fill threshold - Improve performance - Merge branch 'master' into fill-overlap - Use Unsafe directly in benchmarks - Merge branch 'master' into fill-overlap - Use a fixed threashold for fill - Fix benchmark - ... and 8 more: https://git.openjdk.org/jdk/compare/8c025250...bbf08938 ------------- Changes: - all: https://git.openjdk.org/jdk/pull/25383/files - new: https://git.openjdk.org/jdk/pull/25383/files/1f454706..bbf08938 Webrevs: - full: https://webrevs.openjdk.org/?repo=jdk&pr=25383&range=14 - incr: https://webrevs.openjdk.org/?repo=jdk&pr=25383&range=13-14 Stats: 3011 lines in 94 files changed: 1426 ins; 1332 del; 253 mod Patch: https://git.openjdk.org/jdk/pull/25383.diff Fetch: git fetch https://git.openjdk.org/jdk.git pull/25383/head:pull/25383 PR: https://git.openjdk.org/jdk/pull/25383
