RFR: 8315762: Update subtype check profile collection on s390x following 8308869
Martin Doerr
mdoerr at openjdk.org
Wed Jan 24 14:23:27 UTC 2024
On Wed, 17 Jan 2024 12:06:13 GMT, Amit Kumar <amitkumar at openjdk.org> wrote:
> s390x Implementation for https://github.com/openjdk/jdk/pull/14375
>
> Benchmark Result with patch:
>
> Benchmark (typePollution) (typePollutionNotInternalType) Mode Cnt Score Error Units
> RequireNonNullCheckcastScalability.isDuplicated1 false false thrpt 20 1155.409 ± 43.844 ops/us
> RequireNonNullCheckcastScalability.isDuplicated1 false true thrpt 20 726.923 ± 54.536 ops/us
> RequireNonNullCheckcastScalability.isDuplicated1 true false thrpt 20 676.462 ± 23.503 ops/us
> RequireNonNullCheckcastScalability.isDuplicated1 true true thrpt 20 118.650 ± 2.653 ops/us
>
>
> Without Patch:
>
> Benchmark (typePollution) (typePollutionNotInternalType) Mode Cnt Score Error Units
> RequireNonNullCheckcastScalability.isDuplicated1 false false thrpt 20 1101.248 ± 103.559 ops/us
> RequireNonNullCheckcastScalability.isDuplicated1 false true thrpt 20 109.690 ± 3.312 ops/us
> RequireNonNullCheckcastScalability.isDuplicated1 true false thrpt 20 110.790 ± 7.927 ops/us
> RequireNonNullCheckcastScalability.isDuplicated1 true true thrpt 20 112.244 ± 6.889 ops/us
>
>
> Testing : Fastdebug build + tier1 tests
Looks correct AFAICS. Please make sure it is thoroughly tested before integrating. Especially the C1 code is sensitive to register clashes which may cause errors which are very hard to debug.
-------------
Marked as reviewed by mdoerr (Reviewer).
PR Review: https://git.openjdk.org/jdk/pull/17461#pullrequestreview-1841493258
More information about the hotspot-dev
mailing list