8300109: RISC-V: Improve code generation for MinI/MaxI nodes

[RealFYang]

As described by the issue, code generation for MinI/MaxI nodes on RISC-V could be improved when one of the source register is the same as the destination register. Also the code could be further simplified when that source register is constant 0 making use of the dedicated zero register of the architecture. This adds new match rules for those cases.

Testing:

• Run the new jtreg test added by: JDK-8153837: AArch64: Handle special cases for MaxINode & MinINode #11570
• Tier1-3 tested with release build on HiFive Unmatched board.
• Run non-trivial benchmark workloads (dacapo, specjvm, renaissance, etc) with fastdebug build on HiFive Unmatched board.

---

Progress

• Change must be properly reviewed (1 review required, with at least 1 Reviewer)
• Change must not contain extraneous whitespace
• Commit message must refer to an issue

Issue

• JDK-8300109: RISC-V: Improve code generation for MinI/MaxI nodes

Reviewers

• Feilong Jiang (@feilongjiang - Author) ⚠️ Review applies to a17a391c
• Ludovic Henry (@luhenry - Committer) ⚠️ Review applies to a17a391c
• Aleksey Shipilev (@shipilev - Reviewer) ⚠️ Review applies to a17a391c

Reviewing

Using git

Checkout this PR locally:
$ git fetch https://git.openjdk.org/jdk pull/11988/head:pull/11988
$ git checkout pull/11988

Update a local copy of the PR:
$ git checkout pull/11988
$ git pull https://git.openjdk.org/jdk pull/11988/head

Using Skara CLI tools

Checkout this PR locally:
$ git pr checkout 11988

View PR using the GUI difftool:
$ git pr show -t 11988

Using diff file

Download this PR as a diff file:
https://git.openjdk.org/jdk/pull/11988.diff

[bridgekeeper]

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

[openjdk]

@RealFYang The following label will be automatically applied to this pull request:

• hotspot-compiler

When this pull request is ready to be reviewed, an "RFR" email will be sent to the corresponding mailing list. If you would like to change these labels, use the /label pull request command.

[mlbridge]

Webrevs

• 02: Full - Incremental (1264837c)
• 01: Full - Incremental (a17a391c)
• 00: Full (43cad129)

[luhenry]

I'm curious to see some JMH results on this change.

[shipilev]

Looks okay. I was wondering if it was possible to have multiple match(...)-es per instruct, so we could coalesce the symmetric "compare with zero" cases. But it is fine as it is.

[openjdk]

@RealFYang 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:

8300109: RISC-V: Improve code generation for MinI/MaxI nodes

Reviewed-by: fjiang, luhenry, shade

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 1 new commit pushed to the master branch:

• 319de6a: 8300124: Remove unnecessary assert in GenCollectedHeap::initialize

Please see this link for an up-to-date comparison between the source branch of this pull request and the master branch.
As there are no conflicts, your changes will automatically be rebased on top of these commits when integrating. If you prefer to avoid this automatic rebasing, please check the documentation for the /integrate command for further details.

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

[RealFYang]

Looks okay. I was wondering if it was possible to have multiple match(...)-es per instruct, so we could coalesce the symmetric "compare with zero" cases. But it is fine as it is.

Good suggestion. Fixed in the last commit. Also corrected the pipeline for those nodes as discussed on #11919.

[RealFYang]

I'm curious to see some JMH results on this change.

Well, not that much (%3 at most) when I run the max & min tests in JMH test [1] on my unmatched board:

Before:
Benchmark          (seed)   Mode  Cnt       Score      Error   Units
MathBench.maxInt        0  thrpt    8   97675.352 ± 4081.422  ops/ms
MathBench.maxLong       0  thrpt    8  105212.075 ± 5305.248  ops/ms
MathBench.minInt        0  thrpt    8  104321.539 ± 4342.072  ops/ms
MathBench.minLong       0  thrpt    8   97597.538 ± 3798.621  ops/ms

After:
Benchmark          (seed)   Mode  Cnt       Score      Error   Units
MathBench.maxInt        0  thrpt    8   97890.688 ± 6732.534  ops/ms
MathBench.maxLong       0  thrpt    8  107836.865 ± 3148.886  ops/ms
MathBench.minInt        0  thrpt    8  107521.081 ± 3992.511  ops/ms
MathBench.minLong       0  thrpt    8   97940.617 ± 3876.168  ops/ms

I think it will depend on the micro-architecture implementation. But the code generated should be always simplified in this case.

[1] https://github.com/openjdk/jdk/blob/master/test/micro/org/openjdk/bench/java/lang/MathBench.java#L301

[RealFYang]

Thanks all for the review. I will proceed integrating this if there is no other comments.

[RealFYang]

/integrate

[openjdk]

Going to push as commit f1194dc.
Since your change was applied there have been 34 commits pushed to the master branch:

• 89a032d: 8300002: Performance regression caused by non-inlined hot methods due to post call noop instructions
• 7071397: 8299224: TestReporterStreams.java has bad indentation for legal header
• 1d8b87d: 8300321: Use link tags in javax.sql.rowset package-info
• f9883fc: 8300279: Use generalized see and link tags in core libs in client libs
• 00b6c55: 8300254: ASan build does not correctly propagate ASAN_OPTIONS
• e37078f: 8282664: Unroll by hand StringUTF16 and StringLatin1 polynomial hash loops
• ade08e1: 8300093: Refactor code examples to use @snippet in java.text.MessageFormat
• d7c05d1: 8300011: Refactor code examples to use @snippet in java.util.TimeZone
• 8c12ae8: 8283203: Fix typo in SystemTray.getTrayIconSize javadoc
• e7e3712: 8300010: UnsatisfiedLinkError on calling System.console().readPassword() on Windows
• ... and 24 more: https://git.openjdk.org/jdk/compare/289aed465e9b8449938d4cdb515748e7aca1d070...master

Your commit was automatically rebased without conflicts.

[openjdk]

@RealFYang Pushed as commit f1194dc.

💡 You may see a message that your pull request was closed with unmerged commits. This can be safely ignored.