On Wed, 28 Aug 2024 09:28:59 GMT, Per Minborg <pminb...@openjdk.org> wrote:
>> The performance of the `MemorySegment::fil` can be improved by replacing the >> `checkAccess()` method call with calling `checkReadOnly()` instead (as the >> bounds of the segment itself do not need to be checked). >> >> Also, smaller segments can be handled directly by Java code rather than >> transitioning to native code. >> >> Here is how the `MemorySegment::fill` performance is improved by this PR: >> >>  >> >> Operations involving 8 or more bytes are delegated to native code whereas >> smaller segments are handled via a switch rake. >> >> It should be noted that `Arena::allocate` is using `MemorySegment::fil`. >> Hence, this PR will also have a positive effect on memory allocation >> performance. > > Per Minborg has updated the pull request incrementally with one additional > commit since the last revision: > > Switch to bit checking instead of switch statement Added some nit coments - overall, the code looks very clean, and it's nice to see this improvements... now onto copy :-) test/micro/org/openjdk/bench/java/lang/foreign/TestFill.java line 87: > 85: public void buffer_fill() { > 86: // Hopefully, the creation of the intermediate array will be > optimized away. > 87: buffer.clear().put(new byte[ELEM_SIZE]); I think this should use an "absolute" put with explicit offset, so that you can avoid the clear? Otherwise it's not apple to apple... ------------- Marked as reviewed by mcimadamore (Reviewer). PR Review: https://git.openjdk.org/jdk/pull/20712#pullrequestreview-2265840314 PR Review Comment: https://git.openjdk.org/jdk/pull/20712#discussion_r1734415133
