8296602: RISC-V: improve performance of copy_memory stub

[VladimirKempik]

Please review this backport of JDK-8296602 to jdk17u
This effectively unrolls copy memory loop offering significant perf improvement on real hw platforms. ( data are the same as in original commit)

RISC-V only change, low risk for other platforms.
Testing: TBD.

thead rvb-ice c910
thead

Before ( copy8 only )
Benchmark (size) Mode Cnt Score Error Units
ArrayCopyObject.conjoint_micro 31 thrpt 25 6653.095 ± 251.565 ops/ms
ArrayCopyObject.conjoint_micro 63 thrpt 25 4933.970 ± 77.559 ops/ms
ArrayCopyObject.conjoint_micro 127 thrpt 25 3627.454 ± 34.589 ops/ms
ArrayCopyObject.conjoint_micro 2047 thrpt 25 368.249 ± 0.453 ops/ms
ArrayCopyObject.conjoint_micro 4095 thrpt 25 187.776 ± 0.306 ops/ms
ArrayCopyObject.conjoint_micro 8191 thrpt 25 94.477 ± 0.340 ops/ms

after ( with copy32 )
ArrayCopyObject.conjoint_micro 31 thrpt 25 7620.546 ± 69.756 ops/ms
ArrayCopyObject.conjoint_micro 63 thrpt 25 6677.978 ± 33.112 ops/ms
ArrayCopyObject.conjoint_micro 127 thrpt 25 5206.973 ± 22.612 ops/ms
ArrayCopyObject.conjoint_micro 2047 thrpt 25 653.655 ± 31.494 ops/ms
ArrayCopyObject.conjoint_micro 4095 thrpt 25 352.905 ± 7.390 ops/ms
ArrayCopyObject.conjoint_micro 8191 thrpt 25 165.127 ± 0.832 ops/ms

after ( copy32 with dead code elimination and independent addis )
ArrayCopyObject.conjoint_micro 31 thrpt 25 7576.346 ? 94.487 ops/ms
ArrayCopyObject.conjoint_micro 63 thrpt 25 6475.730 ? 252.590 ops/ms
ArrayCopyObject.conjoint_micro 127 thrpt 25 5221.764 ? 20.415 ops/ms
ArrayCopyObject.conjoint_micro 2047 thrpt 25 691.847 ? 1.102 ops/ms
ArrayCopyObject.conjoint_micro 4095 thrpt 25 360.269 ? 1.091 ops/ms
ArrayCopyObject.conjoint_micro 8191 thrpt 25 179.733 ? 3.012 ops/ms

on hifive unmatched:

before:
Benchmark (size) Mode Cnt Score Error Units
ArrayCopyObject.conjoint_micro 31 thrpt 25 5391.575 ± 152.984 ops/ms
ArrayCopyObject.conjoint_micro 63 thrpt 25 3700.946 ± 43.175 ops/ms
ArrayCopyObject.conjoint_micro 127 thrpt 25 2316.160 ± 24.734 ops/ms
ArrayCopyObject.conjoint_micro 2047 thrpt 25 188.616 ± 0.151 ops/ms
ArrayCopyObject.conjoint_micro 4095 thrpt 25 95.323 ± 0.053 ops/ms
ArrayCopyObject.conjoint_micro 8191 thrpt 25 46.935 ± 0.041 ops/ms

after:
Benchmark (size) Mode Cnt Score Error Units
ArrayCopyObject.conjoint_micro 31 thrpt 25 6136.169 ± 330.409 ops/ms
ArrayCopyObject.conjoint_micro 63 thrpt 25 4924.020 ± 78.529 ops/ms
ArrayCopyObject.conjoint_micro 127 thrpt 25 3732.561 ± 89.606 ops/ms
ArrayCopyObject.conjoint_micro 2047 thrpt 25 431.103 ± 0.505 ops/ms
ArrayCopyObject.conjoint_micro 4095 thrpt 25 221.543 ± 0.363 ops/ms
ArrayCopyObject.conjoint_micro 8191 thrpt 25 100.586 ± 0.197 ops/ms

---

Progress

• Change must not contain extraneous whitespace
• Commit message must refer to an issue

Issue

• JDK-8296602: RISC-V: improve performance of copy_memory stub

Reviewing

Using git

Checkout this PR locally:
$ git fetch https://git.openjdk.org/riscv-port-jdk17u pull/9/head:pull/9
$ git checkout pull/9

Update a local copy of the PR:
$ git checkout pull/9
$ git pull https://git.openjdk.org/riscv-port-jdk17u pull/9/head

Using Skara CLI tools

Checkout this PR locally:
$ git pr checkout 9

View PR using the GUI difftool:
$ git pr show -t 9

Using diff file

Download this PR as a diff file:
https://git.openjdk.org/riscv-port-jdk17u/pull/9.diff

[bridgekeeper]

👋 Welcome back vkempik! A progress list of the required criteria for merging this PR into riscv-port will be added to the body of your pull request. There are additional pull request commands available for use with this pull request.

[openjdk]

This backport pull request has now been updated with issue from the original commit.

[openjdk]

@VladimirKempik This change now passes all automated pre-integration checks.

ℹ️ This project also has non-automated pre-integration requirements. Please see the file CONTRIBUTING.md for details.

After integration, the commit message for the final commit will be:

8296602: RISC-V: improve performance of copy_memory stub

You can use pull request commands such as /summary, /contributor and /issue to adjust it as needed.

At the time when this comment was updated there had been no new commits pushed to the riscv-port branch. If another commit should be pushed before you perform the /integrate command, your PR will be automatically rebased. If you prefer to avoid any potential automatic rebasing, please check the documentation for the /integrate command for further details.

➡️ To integrate this PR with the above commit message to the riscv-port branch, type /integrate in a new comment.

[mlbridge]

Webrevs

• 00: Full (84e4b08c)

[VladimirKempik]

I have filled openjdk/jdk17u-dev#1200 to have more clean tier1 results

[VladimirKempik]

Testing looks good, no new failures in tier1, hotspot:tier2 is clean

I have created PR for backport of JDK-8292407 to jdk17u, it will significantly reduce the amount of failures in tier1, please merge riscv-port branch with master once this backport is integrated.

One strange failure I see before and after the patch is "runtime/8176717/TestInheritFD.java", maybe it's my setup, but unlikely.

Ping @RealFYang for integration

[RealFYang]

Thanks for filing the upstream backporting to fix the failing tests. I will do a merge once that's integrated.
Regarding this performance backporting, I would put off integration for a while after several other nasty bugs are fixed.

[VladimirKempik]

@RealFYang , it's integrated

[RealFYang]

I also tried this test "runtime/8176717/TestInheritFD.java" on my boards, it passed stably for 10 times run.