RFR: 8322770: Implement C2 VectorizedHashCode on AArch64 [v5]
Andrew Dinn
adinn at openjdk.org
Thu Aug 22 13:52:07 UTC 2024
On Wed, 21 Aug 2024 16:11:25 GMT, Mikhail Ablakatov <duke at openjdk.org> wrote:
>> Hello,
>>
>> Please review the following PR for [JDK-8322770 Implement C2 VectorizedHashCode on AArch64](https://bugs.openjdk.org/browse/JDK-8322770). It follows previous work done in https://github.com/openjdk/jdk/pull/16629 and https://github.com/openjdk/jdk/pull/10847 for RISC-V and x86 respectively.
>>
>> The code to calculate a hash code consists of two parts: a vectorized loop of Neon instruction that process 4 or 8 elements per iteration depending on the data type and a fully unrolled scalar "loop" that processes up to 7 tail elements.
>>
>> At the time of writing this I don't see potential benefits from providing SVE/SVE2 implementation, but it could be added as a follow-up or independently later if required.
>>
>> # Performance
>>
>> ## Neoverse N1
>>
>>
>> --------------------------------------------------------------------------------------------
>> Version Baseline This patch
>> --------------------------------------------------------------------------------------------
>> Benchmark (size) Mode Cnt Score Error Score Error Units
>> --------------------------------------------------------------------------------------------
>> ArraysHashCode.bytes 1 avgt 15 1.249 ? 0.060 1.247 ? 0.062 ns/op
>> ArraysHashCode.bytes 10 avgt 15 8.754 ? 0.028 4.387 ? 0.015 ns/op
>> ArraysHashCode.bytes 100 avgt 15 98.596 ? 0.051 26.655 ? 0.097 ns/op
>> ArraysHashCode.bytes 10000 avgt 15 10150.578 ? 1.352 2649.962 ? 216.744 ns/op
>> ArraysHashCode.chars 1 avgt 15 1.286 ? 0.062 1.246 ? 0.054 ns/op
>> ArraysHashCode.chars 10 avgt 15 8.731 ? 0.002 5.344 ? 0.003 ns/op
>> ArraysHashCode.chars 100 avgt 15 98.632 ? 0.048 23.023 ? 0.142 ns/op
>> ArraysHashCode.chars 10000 avgt 15 10150.658 ? 3.374 2410.504 ? 8.872 ns/op
>> ArraysHashCode.ints 1 avgt 15 1.189 ? 0.005 1.187 ? 0.001 ns/op
>> ArraysHashCode.ints 10 avgt 15 8.730 ? 0.002 5.676 ? 0.001 ns/op
>> ArraysHashCode.ints 100 avgt 15 98.559 ? 0.016 24.378 ? 0.006 ns/op
>> ArraysHashCode.ints 10000 avgt 15 10148.752 ? 1.336 2419.015 ? 0.492 ns/op
>> ArraysHashCode.multibytes 1 avgt 15 1.037 ? 0.001 1.037 ? 0.001 ...
>
> Mikhail Ablakatov has updated the pull request incrementally with one additional commit since the last revision:
>
> cleanup: use a constexpr function for intpow instead of a templated class
The code here looks very good. Apart from the one bit I highlighted as seriously in need of a comment it is all quite readable.
I think it would be worth adding another comment in the code to document why loop_factor is doubled for bools and bytes. It was not immediately obvious that this was to to do with the available vector load options. A brief comment would stop a maintainer getting sidestepped by that difference and having to do some archaeology to resolve the confusion.
You might also choose to document the reason for choosing 4 for the loop_unroll factor but we have the rationale here on the PR for anyone who needs to know.
Oh, and I should have said: very nice work!
-------------
Marked as reviewed by adinn (Reviewer).
PR Review: https://git.openjdk.org/jdk/pull/18487#pullrequestreview-2254580682
PR Comment: https://git.openjdk.org/jdk/pull/18487#issuecomment-2304723784
More information about the hotspot-dev
mailing list