8292713: Unsafe.allocateInstance should be intrinsified without UseUnalignedAccesses #9970

shipilev · 2022-08-22T21:04:05Z

See the rationale and references in the bug. I spotted that RISC-V tests are remarkably slow, and profiler shows that Unsafe.allocateInstance is very hot and native. RISC-V and ARM32 systems are UseUnalignedAccess = false, and I believe the _allocateInstance intrinsic is disabled on these paths by mistake. This PR improves the selected tests very considerably, and I think it actually fixes the real performance bug in java.lang.invoke-rich code paths.

Raspberry Pi 4, ARM32 fastdebug build:

$ time make test TEST=java/lang/invoke/VarHandles/VarHandleTestMethodHandleAccessChar.java

# Baseline

real	4m37.970s
user	6m5.490s
sys	0m21.731s

real	4m52.363s
user	6m24.100s
sys	0m21.363s

# Patched

real	2m32.678s ; <--- 1.8x faster
user	4m33.749s
sys	0m22.127s

real	2m38.451s ; <--- 1.8x faster, reproducible
user	4m44.788s
sys	0m22.160s

HiFive Unmatched, RISC-V fastdebug build:

$ time make test TEST=java/lang/invoke/VarHandles/VarHandleTestMethodHandleAccessInt.java

# Baseline

real	19m3.479s
user	27m2.932s
sys	0m27.766s

real	18m52.351s
user	27m23.917s
sys	0m27.682s

# Patched

real	10m5.971s  ; <--- 1.9x faster
user	18m11.538s
sys	0m28.204s

real	10m18.973s ; <--- 1.9x faster, reproducible
user	18m31.067s
sys	0m28.053s

Additional testing:

Linux RISC-V build, timing tests
Linux ARM32 build, timing tests
Linux ARM32 fastdebug tier1

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-8292713: Unsafe.allocateInstance should be intrinsified without UseUnalignedAccesses

Reviewers

Paul Sandoz (@PaulSandoz - Reviewer)
Vladimir Kozlov (@vnkozlov - Reviewer)
Fei Yang (@RealFYang - Reviewer)

Reviewing

Using git

Checkout this PR locally:
$ git fetch https://git.openjdk.org/jdk pull/9970/head:pull/9970
$ git checkout pull/9970

Update a local copy of the PR:
$ git checkout pull/9970
$ git pull https://git.openjdk.org/jdk pull/9970/head

Using Skara CLI tools

Checkout this PR locally:
$ git pr checkout 9970

View PR using the GUI difftool:
$ git pr show -t 9970

Using diff file

Download this PR as a diff file:
https://git.openjdk.org/jdk/pull/9970.diff

bridgekeeper · 2022-08-22T21:05:51Z

👋 Welcome back shade! 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 · 2022-08-22T21:08:25Z

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

hotspot-runtime

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.

shipilev · 2022-08-22T21:08:41Z

@RealFYang, you might want to give it a spin on your RISC-V machines ;)

shipilev · 2022-08-22T21:10:07Z

/label remove hotspot-runtime
/label add hotspot-compiler

openjdk · 2022-08-22T21:10:20Z

@shipilev
The hotspot-runtime label was successfully removed.

openjdk · 2022-08-22T21:12:07Z

@shipilev
The hotspot-compiler label was successfully added.

mlbridge · 2022-08-22T21:15:59Z

Webrevs

00: Full (930baeb1)

VladimirKempik · 2022-08-23T09:39:13Z

1-2 minutes (per test) on thead now, ( was 1-4 before the patch)

PaulSandoz · 2022-08-23T16:02:23Z

I agree that this looks like mistake. Confirmation by another HotSpot member would be useful.

openjdk · 2022-08-23T16:05:09Z

@shipilev 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:

8292713: Unsafe.allocateInstance should be intrinsified without UseUnalignedAccesses

Reviewed-by: psandoz, kvn, fyang

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 38 new commits pushed to the master branch:

b653b9c: 8291969: Convert LoaderConstraintsTable to ResourceHashtable
0813a47: 8282729: Serial: Move BOT implementation to collector specific directory
fa5cc4c: 8291878: NMT: Malloc limits
ad2e0c4: 8292778: EncodingSupport_md.c convertUtf8ToPlatformString wrong placing of free
13c0369: 8242181: [Linux] Show source information when printing native stack traces in hs_err files
fe0544f: 8292790: Remove hashtable.hpp from other files
926380d: 8292640: C2: Remove unused scratch register usages on x86
f3be673: 8292638: x86: Improve scratch register handling in VM stubs
d24b7b7: 8276651: java/lang/ProcessHandle tests fail with "RuntimeException: Input/output error" in java.lang.ProcessHandleImpl$Info.info0
8a45abd: 8292654: G1 remembered set memory footprint regression after JDK-8286115
... and 28 more: https://git.openjdk.org/jdk/compare/79597f1ea6844f374beeeba219719cd9d5fe7d03...master

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.

vnkozlov

Good.

Originally only 8 get/put*Unaligned intrinsics were guarded by UseUnalignedAccesses.
JDK-8130832 put accidentally additional 3 intrinsics: diff
get/putAddress_raw intrinsics were removed later by JDK-8150921.

RealFYang · 2022-08-24T03:24:53Z

@RealFYang, you might want to give it a spin on your RISC-V machines ;)

Thanks for finding this. And I have launched a Tier1 test with release build on my unmatched board. It should take hours to finish.

RealFYang

Passed tier1 hotspot & jdk test on riscv64-linux unmatched board. Looks good to me.

shipilev · 2022-08-24T12:30:33Z

Passed tier1 hotspot & jdk test on riscv64-linux unmatched board. Looks good to me.

Thanks! Do you know if it passes significantly faster?

RealFYang · 2022-08-24T13:12:47Z

Passed tier1 hotspot & jdk test on riscv64-linux unmatched board. Looks good to me.

Thanks! Do you know if it passes significantly faster?

Well, I was not timing the testing process since it was carried on unmatched board shared with other developers.
But I guess this change will also improve some benchmark numbers. Maybe I can arrange some further tests like specjbb2015 when I can monopolize the board :-)

shipilev · 2022-08-24T13:17:03Z

Passed tier1 hotspot & jdk test on riscv64-linux unmatched board. Looks good to me.

Thanks! Do you know if it passes significantly faster?

Well, I was not timing the testing process since it was carried on unmatched board shared with other developers. But I guess this change will also improve some benchmark numbers. Maybe I can arrange some further tests like specjbb2015 when I can monopolize the board :-)

No need, I was just curious. I'll integrate this then.

/integrate

openjdk · 2022-08-24T13:19:57Z

Going to push as commit c062397.
Since your change was applied there have been 40 commits pushed to the master branch:

a45a4b9: 8292194: G1 nmethod entry barrier disarm value wraps around too early
d3fed12: 8292864: Remove resourceHash.hpp from header files
b653b9c: 8291969: Convert LoaderConstraintsTable to ResourceHashtable
0813a47: 8282729: Serial: Move BOT implementation to collector specific directory
fa5cc4c: 8291878: NMT: Malloc limits
ad2e0c4: 8292778: EncodingSupport_md.c convertUtf8ToPlatformString wrong placing of free
13c0369: 8242181: [Linux] Show source information when printing native stack traces in hs_err files
fe0544f: 8292790: Remove hashtable.hpp from other files
926380d: 8292640: C2: Remove unused scratch register usages on x86
f3be673: 8292638: x86: Improve scratch register handling in VM stubs
... and 30 more: https://git.openjdk.org/jdk/compare/79597f1ea6844f374beeeba219719cd9d5fe7d03...master

Your commit was automatically rebased without conflicts.

openjdk · 2022-08-24T13:20:14Z

@shipilev Pushed as commit c062397.

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

VladimirKempik · 2022-08-24T13:24:59Z

DO we want to backport it to jdk17u as well ?

shipilev · 2022-08-24T13:29:30Z

DO we want to backport it to jdk17u as well ?

Yes, once it gets soaked in mainline for a week or two.

Fix

930baeb

openjdk bot added the rfr Pull request is ready for review label Aug 22, 2022

openjdk bot added the hotspot-runtime hotspot-runtime-dev@openjdk.org label Aug 22, 2022

openjdk bot removed the hotspot-runtime hotspot-runtime-dev@openjdk.org label Aug 22, 2022

openjdk bot added the hotspot-compiler hotspot-compiler-dev@openjdk.org label Aug 22, 2022

shipilev mentioned this pull request Aug 23, 2022

8292407: Improve Weak CAS VarHandle/Unsafe tests resilience under spurious failures #9889

Closed

3 tasks

PaulSandoz approved these changes Aug 23, 2022

View reviewed changes

openjdk bot added the ready Pull request is ready to be integrated label Aug 23, 2022

vnkozlov approved these changes Aug 23, 2022

View reviewed changes

RealFYang approved these changes Aug 24, 2022

View reviewed changes

openjdk bot added the integrated Pull request has been integrated label Aug 24, 2022

openjdk bot closed this Aug 24, 2022

openjdk bot removed ready Pull request is ready to be integrated rfr Pull request is ready for review labels Aug 24, 2022

shipilev deleted the JDK-8292713-unsafe-allocinstance branch September 5, 2022 13:43

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

8292713: Unsafe.allocateInstance should be intrinsified without UseUnalignedAccesses #9970

8292713: Unsafe.allocateInstance should be intrinsified without UseUnalignedAccesses #9970

shipilev commented Aug 22, 2022 •

edited by openjdk bot

Loading

bridgekeeper bot commented Aug 22, 2022

openjdk bot commented Aug 22, 2022

shipilev commented Aug 22, 2022

shipilev commented Aug 22, 2022

openjdk bot commented Aug 22, 2022

openjdk bot commented Aug 22, 2022

mlbridge bot commented Aug 22, 2022

VladimirKempik commented Aug 23, 2022

PaulSandoz commented Aug 23, 2022

openjdk bot commented Aug 23, 2022 •

edited

Loading

vnkozlov left a comment

RealFYang commented Aug 24, 2022

RealFYang left a comment

shipilev commented Aug 24, 2022

RealFYang commented Aug 24, 2022

shipilev commented Aug 24, 2022

openjdk bot commented Aug 24, 2022

openjdk bot commented Aug 24, 2022

VladimirKempik commented Aug 24, 2022

shipilev commented Aug 24, 2022

8292713: Unsafe.allocateInstance should be intrinsified without UseUnalignedAccesses #9970

8292713: Unsafe.allocateInstance should be intrinsified without UseUnalignedAccesses #9970

Conversation

shipilev commented Aug 22, 2022 • edited by openjdk bot Loading

Progress

Issue

Reviewers

Reviewing

bridgekeeper bot commented Aug 22, 2022

openjdk bot commented Aug 22, 2022

shipilev commented Aug 22, 2022

shipilev commented Aug 22, 2022

openjdk bot commented Aug 22, 2022

openjdk bot commented Aug 22, 2022

mlbridge bot commented Aug 22, 2022

Webrevs

VladimirKempik commented Aug 23, 2022

PaulSandoz commented Aug 23, 2022

openjdk bot commented Aug 23, 2022 • edited Loading

vnkozlov left a comment

Choose a reason for hiding this comment

RealFYang commented Aug 24, 2022

RealFYang left a comment

Choose a reason for hiding this comment

shipilev commented Aug 24, 2022

RealFYang commented Aug 24, 2022

shipilev commented Aug 24, 2022

openjdk bot commented Aug 24, 2022

openjdk bot commented Aug 24, 2022

VladimirKempik commented Aug 24, 2022

shipilev commented Aug 24, 2022

shipilev commented Aug 22, 2022 •

edited by openjdk bot

Loading

openjdk bot commented Aug 23, 2022 •

edited

Loading