Integrated: 8356869: RISC-V: Improve tail handling of array fill stub
Anjian-Wen
duke at openjdk.org
Wed May 14 08:31:06 UTC 2025
On Tue, 13 May 2025 12:53:40 GMT, Anjian-Wen <duke at openjdk.org> wrote:
> The tail handling after bulk copy in array fill stub may trigger misaligned memory accesses.
> The address is 8-byte aligned after bulk copy and the tail handling copies BYTE, SHORT, and
> INT granules in order. This could trigger misaligned accesses. We should copy the remainings
> in this order: INT, SHORT, and BYTE to avoid such an issue.
>
> JMH data on P550 SBC for reference (@Param("15") private int size):
>
> Before:
> Benchmark (size) Mode Cnt Score Error Units
> ArrayFill.fillByteArray 15 avgt 12 961.604 ± 1.497 ns/op
> ArrayFill.fillIntArray 15 avgt 12 29.355 ± 0.024 ns/op
> ArrayFill.fillShortArray 15 avgt 12 569.499 ± 0.662 ns/op
> ArrayFill.zeroByteArray 15 avgt 12 957.080 ± 5.358 ns/op
> ArrayFill.zeroIntArray 15 avgt 12 29.344 ± 0.006 ns/op
> ArrayFill.zeroShortArray 15 avgt 12 569.730 ± 0.441 ns/op
>
> After:
> Benchmark (size) Mode Cnt Score Error Units
> ArrayFill.fillByteArray 15 avgt 12 32.206 ± 0.005 ns/op
> ArrayFill.fillIntArray 15 avgt 12 29.347 ± 0.007 ns/op
> ArrayFill.fillShortArray 15 avgt 12 31.732 ± 0.451 ns/op
> ArrayFill.zeroByteArray 15 avgt 12 32.208 ± 0.007 ns/op
> ArrayFill.zeroIntArray 15 avgt 12 29.346 ± 0.007 ns/op
> ArrayFill.zeroShortArray 15 avgt 12 31.492 ± 0.006 ns/op
This pull request has now been integrated.
Changeset: b76b6107
Author: Anjian-Wen <wenanjian at bytedance.com>
Committer: Fei Yang <fyang at openjdk.org>
URL: https://git.openjdk.org/jdk/commit/b76b610788cea7149a04faeeba01067272b6e046
Stats: 20 lines in 2 files changed: 5 ins; 5 del; 10 mod
8356869: RISC-V: Improve tail handling of array fill stub
Reviewed-by: fyang, fjiang, mli
-------------
PR: https://git.openjdk.org/jdk/pull/25210
More information about the hotspot-compiler-dev
mailing list