RFR: 8338967: Improve performance for MemorySegment::fill [v10]
Maurizio Cimadamore
mcimadamore at openjdk.org
Fri Aug 30 14:14:21 UTC 2024
On Fri, 30 Aug 2024 10:51:59 GMT, Per Minborg <pminborg at 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 two additional commits since the last revision:
>
> - Revert copyright year
> - Move logic back to AMSI
src/java.base/share/classes/jdk/internal/foreign/AbstractMemorySegmentImpl.java line 200:
> 198: checkReadOnly(false);
> 199: // 0...0X...XXXX implies: 0 <= length < FILL_NATIVE_LIMIT
> 200: if ((length & -FILL_NATIVE_THRESHOLD) == 0) {
Looks great - few notes:
* adding `@ForceInline` here might help
* I'd suggest to move the `length == 0` outside in its own `if` branch (and drop the `return` from there). E.g.
if (length == 0) { ... }
else if (length & -FILL...) { ... }
else { ... }
return this;
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/20712#discussion_r1738755601
More information about the core-libs-dev
mailing list