8275167: x86 intrinsic for unsignedMultiplyHigh #5933

vamsi-parasa · 2021-10-13T18:55:10Z

Optimize the new Math.unsignedMultiplyHigh using the x86 mul instruction. This change show 1.87X improvement on a micro benchmark.

Progress

Change must not contain extraneous whitespace
Commit message must refer to an issue
Change must be properly reviewed

Issue

JDK-8275167: x86 intrinsic for unsignedMultiplyHigh

Reviewers

Vladimir Kozlov (@vnkozlov - Reviewer)
Sandhya Viswanathan (@sviswa7 - Reviewer)

Reviewing

Using git

Checkout this PR locally:
$ git fetch https://git.openjdk.java.net/jdk pull/5933/head:pull/5933
$ git checkout pull/5933

Update a local copy of the PR:
$ git checkout pull/5933
$ git pull https://git.openjdk.java.net/jdk pull/5933/head

Using Skara CLI tools

Checkout this PR locally:
$ git pr checkout 5933

View PR using the GUI difftool:
$ git pr show -t 5933

Using diff file

Download this PR as a diff file:
https://git.openjdk.java.net/jdk/pull/5933.diff

bridgekeeper · 2021-10-13T18:55:46Z

Hi @vamsi-parasa, welcome to this OpenJDK project and thanks for contributing!

We do not recognize you as Contributor and need to ensure you have signed the Oracle Contributor Agreement (OCA). If you have not signed the OCA, please follow the instructions. Please fill in your GitHub username in the "Username" field of the application. Once you have signed the OCA, please let us know by writing /signed in a comment in this pull request.

If you already are an OpenJDK Author, Committer or Reviewer, please click here to open a new issue so that we can record that fact. Please use "Add GitHub user vamsi-parasa" as summary for the issue.

If you are contributing this work on behalf of your employer and your employer has signed the OCA, please let us know by writing /covered in a comment in this pull request.

vamsi-parasa · 2021-10-13T18:56:31Z

/covered

openjdk · 2021-10-13T18:57:26Z

@vamsi-parasa The following labels will be automatically applied to this pull request:

core-libs
hotspot

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

bridgekeeper · 2021-10-13T18:57:27Z

Thank you! Please allow for a few business days to verify that your employer has signed the OCA. Also, please note that pull requests that are pending an OCA check will not usually be evaluated, so your patience is appreciated!

vamsi-parasa · 2021-10-13T19:00:55Z

/label hotspot-compiler

openjdk · 2021-10-13T19:02:18Z

@vamsi-parasa
The hotspot-compiler label was successfully added.

mlbridge · 2021-10-15T14:08:08Z

Webrevs

01: Full - Incremental (a10a9fbe)
00: Full (cb30b268)

bplb · 2021-10-15T15:53:54Z

The java.lang.Math change looks good, of course. On the rest I cannot comment but it is good to see something being done here.

theRealAph · 2021-10-15T16:14:25Z

src/hotspot/share/opto/mulnode.cpp

+  // It is not worth trying to constant fold this stuff!
+  return TypeLong::LONG;
+}
+
 //=============================================================================


MulHiLNode::Value() and UMulHiLNode::Value() seem to be identical. Perhaps some refactoring would be in order, maybe make a common shared routine.

Sure, will do the refactoring to use a shared routine.

Pushed the refactored code to use a common routine for MulHiLNode::Value() and UMulHiLNode::Value(). Please review...

theRealAph · 2021-10-15T16:56:08Z

test/micro/org/openjdk/bench/java/lang/MathBench.java

+    public long  unsignedMultiplyHighLongLong() {
+        return  Math.unsignedMultiplyHigh(long747, long13);
+    }
+


As far as I can tell, the JMH overhead dominates when trying to measure the latency of events in the nanosecond range. unsignedMultiplyHigh should have a latency of maybe 1.5-2ns. Is that what you saw?

Yes, the JMH overhead was dominating the measurement of latency. The latency observed for unsignedMultiplyHigh was 2.3ns with the intrinsic enabled.

vnkozlov

How you verified correctness of results?
I suggest to extend test/jdk//java/lang/Math/MultiplicationTests.java test to cover unsigned method.

vamsi-parasa · 2021-10-15T19:19:13Z

How you verified correctness of results? I suggest to extend test/jdk//java/lang/Math/MultiplicationTests.java test to cover unsigned method.

Tests for unsignedMultiplyHigh were already added in test/jdk//java/lang/Math/MultiplicationTests.java (in July 2021 by Brian Burkhalter). Used that test to verify the correctness of the results.

vnkozlov · 2021-10-15T20:19:31Z

How you verified correctness of results? I suggest to extend test/jdk//java/lang/Math/MultiplicationTests.java test to cover unsigned method.

Tests for unsignedMultiplyHigh were already added in test/jdk//java/lang/Math/MultiplicationTests.java (in July 2021 by Brian Burkhalter). Used that test to verify the correctness of the results.

Good. It seems I have old version of the test.
Did you run it with -Xcomp? How you verified that intrinsic is used?

vamsi-parasa · 2021-10-15T21:04:12Z

How you verified correctness of results? I suggest to extend test/jdk//java/lang/Math/MultiplicationTests.java test to cover unsigned method.

Tests for unsignedMultiplyHigh were already added in test/jdk//java/lang/Math/MultiplicationTests.java (in July 2021 by Brian Burkhalter). Used that test to verify the correctness of the results.

Good. It seems I have old version of the test. Did you run it with -Xcomp? How you verified that intrinsic is used?

The tests were not run with -Xcomp. Looked at the generated x86 code using the disassembler (hsdis) and verified that that correct instruction (mul) instead of (imul, without the intrinsic) was being generated.

…UMulHiLNode and MulHiLNode

vamsi-parasa · 2021-10-19T18:36:55Z

How you verified correctness of results? I suggest to extend test/jdk//java/lang/Math/MultiplicationTests.java test to cover unsigned method.

Tests for unsignedMultiplyHigh were already added in test/jdk//java/lang/Math/MultiplicationTests.java (in July 2021 by Brian Burkhalter). Used that test to verify the correctness of the results.

Good. It seems I have old version of the test. Did you run it with -Xcomp? How you verified that intrinsic is used?

I have verified that the intrinsic is being used by looking at the x86 assembly code generated by using perfasm profiler.

sviswa7 · 2021-10-20T17:32:21Z

The patch looks good to me.

sviswa7 · 2021-10-20T17:33:50Z

@vnkozlov if the patch looks ok to you, could you please run this through your testing?

openjdk · 2021-10-20T17:34:16Z

⚠️ @vamsi-parasa the full name on your profile does not match the author name in this pull requests' HEAD commit. If this pull request gets integrated then the author name from this pull requests' HEAD commit will be used for the resulting commit. If you wish to push a new commit with a different author name, then please run the following commands in a local repository of your personal fork:

$ git checkout umult_high
$ git commit -c user.name='Preferred Full Name' --allow-empty -m 'Update full name'
$ git push

openjdk · 2021-10-20T17:34:20Z

@vamsi-parasa 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:

8275167: x86 intrinsic for unsignedMultiplyHigh

Reviewed-by: kvn, sviswanathan

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 116 new commits pushed to the master branch:

cea3f01: 8275666: serviceability/jvmti/GetObjectSizeClass.java shouldn't have vm.flagless
d1e3ca4: 8233558: [TESTBUG] WindowOwnedByEmbeddedFrameTest.java fails on macos
913f928: 8273507: Convert test/jdk/java/nio/channels/Channels/TransferTo.java to TestNG test
0021a2f: 8275449: Add linux-aarch64-zero build profile
46b5bfb: 8233648: [TESTBUG] DefaultMenuBarTest.java failing on macos
bbc6061: 8272614: Unused parameters in MethodHandleNatives linking methods
7e28bdd: 8275055: Improve HeapRegionRemSet::split_card()
35e5bb5: 8269336: Malformed jdk.serialFilter incorrectly handled
043cde2: 8275319: java.net.NetworkInterface throws java.lang.Error instead of SocketException
a91a0a5: 8233724: Remove -Wc++14-compat warning suppression in operator_new.cpp
... and 106 more: https://git.openjdk.java.net/jdk/compare/124f82377ba93359bc59118ee315ba194080fa92...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.

As you do not have Committer status in this project an existing Committer must agree to sponsor your change. Possible candidates are the reviewers of this PR (@vnkozlov, @sviswa7) but any other Committer may sponsor as well.

➡️ To flag this PR as ready for integration with the above commit message, type /integrate in a new comment. (Afterwards, your sponsor types /sponsor in a new comment to perform the integration).

vnkozlov

Looks good. And I submitted testing.

vnkozlov · 2021-10-20T22:14:33Z

Tests passed. You can integrate changes.

vamsi-parasa · 2021-10-20T22:18:35Z

Tests passed. You can integrate changes.

Thanks Vladimir! What are the next steps to integrate the change?

vamsi-parasa · 2021-10-20T22:35:16Z

/integrate

openjdk · 2021-10-20T22:36:07Z

@vamsi-parasa
Your change (at version a10a9fb) is now ready to be sponsored by a Committer.

sviswa7 · 2021-10-20T22:38:46Z

/sponsor

openjdk · 2021-10-20T22:41:04Z

Going to push as commit af7c56b.
Since your change was applied there have been 116 commits pushed to the master branch:

cea3f01: 8275666: serviceability/jvmti/GetObjectSizeClass.java shouldn't have vm.flagless
d1e3ca4: 8233558: [TESTBUG] WindowOwnedByEmbeddedFrameTest.java fails on macos
913f928: 8273507: Convert test/jdk/java/nio/channels/Channels/TransferTo.java to TestNG test
0021a2f: 8275449: Add linux-aarch64-zero build profile
46b5bfb: 8233648: [TESTBUG] DefaultMenuBarTest.java failing on macos
bbc6061: 8272614: Unused parameters in MethodHandleNatives linking methods
7e28bdd: 8275055: Improve HeapRegionRemSet::split_card()
35e5bb5: 8269336: Malformed jdk.serialFilter incorrectly handled
043cde2: 8275319: java.net.NetworkInterface throws java.lang.Error instead of SocketException
a91a0a5: 8233724: Remove -Wc++14-compat warning suppression in operator_new.cpp
... and 106 more: https://git.openjdk.java.net/jdk/compare/124f82377ba93359bc59118ee315ba194080fa92...master

Your commit was automatically rebased without conflicts.

openjdk · 2021-10-20T22:41:25Z

@sviswa7 @vamsi-parasa Pushed as commit af7c56b.

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

ijuma · 2021-10-23T15:13:01Z

src/java.base/share/classes/java/lang/Math.java

@@ -1390,6 +1390,7 @@ public static long multiplyHigh(long x, long y) {
     * @see #multiplyHigh
     * @since 18
     */
+    @IntrinsicCandidate
    public static long unsignedMultiplyHigh(long x, long y) {
        // Compute via multiplyHigh() to leverage the intrinsic


Hi @ijuma, thanks for making a comment in an OpenJDK project!

All comments and discussions in the OpenJDK Community must be made available under the OpenJDK Terms of Use. If you already are an OpenJDK Author, Committer or Reviewer, please click here to open a new issue so that we can record that fact. Please Use "Add GitHub user ijuma for the summary.

If you are not an OpenJDK Author, Committer or Reviewer, simply check the box below to accept the OpenJDK Terms of Use for your comments.

I agree to the OpenJDK Terms of Use for all comments I make in a project in the OpenJDK GitHub organization.

Your comment will be automatically restored once you have accepted the OpenJDK Terms of Use.

Thank you for spotting the stale comment. It will removed in another related commit that will be pushed soon...

8275167: x86 intrinsic for unsignedMultiplyHigh

3bc9591

bridgekeeper bot added the oca Needs verification of OCA signatory status label Oct 13, 2021

bridgekeeper bot added the oca-verify Needs verification of OCA signatory status label Oct 13, 2021

openjdk bot added hotspot hotspot-dev@openjdk.org core-libs core-libs-dev@openjdk.org labels Oct 13, 2021

openjdk bot added the hotspot-compiler hotspot-compiler-dev@openjdk.org label Oct 13, 2021

fix typo in function name

cb30b26

vamsi-parasa marked this pull request as ready for review October 13, 2021 21:30

bridgekeeper bot removed oca Needs verification of OCA signatory status oca-verify Needs verification of OCA signatory status labels Oct 15, 2021

openjdk bot added the rfr Pull request is ready for review label Oct 15, 2021

theRealAph reviewed Oct 15, 2021

View reviewed changes

vnkozlov suggested changes Oct 15, 2021

View reviewed changes

refactoring to remove code duplication by using a common routine for …

a10a9fb

…UMulHiLNode and MulHiLNode

vamsi-parasa closed this Oct 19, 2021

vamsi-parasa reopened this Oct 20, 2021

sviswa7 approved these changes Oct 20, 2021

View reviewed changes

openjdk bot added the ready Pull request is ready to be integrated label Oct 20, 2021

vnkozlov approved these changes Oct 20, 2021

View reviewed changes

openjdk bot added the sponsor Pull request is ready to be sponsored label Oct 20, 2021

openjdk bot closed this Oct 20, 2021

openjdk bot added integrated Pull request has been integrated and removed ready Pull request is ready to be integrated rfr Pull request is ready for review sponsor Pull request is ready to be sponsored labels Oct 20, 2021

ijuma reviewed Oct 23, 2021

View reviewed changes

vamsi-parasa mentioned this pull request Nov 2, 2021

8275821: Optimize random number generators developed in JDK-8248862 using Math.unsignedMultiplyHigh() #6206

Closed

3 tasks

vamsi-parasa deleted the umult_high branch December 3, 2021 18:21

8275167: x86 intrinsic for unsignedMultiplyHigh #5933

8275167: x86 intrinsic for unsignedMultiplyHigh #5933

vamsi-parasa commented Oct 13, 2021 •

edited by openjdk bot

bridgekeeper bot commented Oct 13, 2021

vamsi-parasa commented Oct 13, 2021

openjdk bot commented Oct 13, 2021

bridgekeeper bot commented Oct 13, 2021

vamsi-parasa commented Oct 13, 2021

openjdk bot commented Oct 13, 2021

mlbridge bot commented Oct 15, 2021 •

edited

bplb commented Oct 15, 2021

theRealAph Oct 15, 2021

vamsi-parasa Oct 15, 2021

vamsi-parasa Oct 19, 2021

theRealAph Oct 15, 2021

vamsi-parasa Oct 15, 2021

vnkozlov left a comment

vamsi-parasa commented Oct 15, 2021

vnkozlov commented Oct 15, 2021

vamsi-parasa commented Oct 15, 2021

vamsi-parasa commented Oct 19, 2021

sviswa7 commented Oct 20, 2021

sviswa7 commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

openjdk bot commented Oct 20, 2021 •

edited

vnkozlov left a comment

vnkozlov commented Oct 20, 2021

vamsi-parasa commented Oct 20, 2021

vamsi-parasa commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

sviswa7 commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

ijuma Oct 23, 2021 •

edited by bridgekeeper bot

vamsi-parasa Nov 2, 2021

8275167: x86 intrinsic for unsignedMultiplyHigh #5933

8275167: x86 intrinsic for unsignedMultiplyHigh #5933

Conversation

vamsi-parasa commented Oct 13, 2021 • edited by openjdk bot

Progress

Issue

Reviewers

Reviewing

bridgekeeper bot commented Oct 13, 2021

vamsi-parasa commented Oct 13, 2021

openjdk bot commented Oct 13, 2021

bridgekeeper bot commented Oct 13, 2021

vamsi-parasa commented Oct 13, 2021

openjdk bot commented Oct 13, 2021

mlbridge bot commented Oct 15, 2021 • edited

Webrevs

bplb commented Oct 15, 2021

theRealAph Oct 15, 2021

Choose a reason for hiding this comment

vamsi-parasa Oct 15, 2021

Choose a reason for hiding this comment

vamsi-parasa Oct 19, 2021

Choose a reason for hiding this comment

theRealAph Oct 15, 2021

Choose a reason for hiding this comment

vamsi-parasa Oct 15, 2021

Choose a reason for hiding this comment

vnkozlov left a comment

Choose a reason for hiding this comment

vamsi-parasa commented Oct 15, 2021

vnkozlov commented Oct 15, 2021

vamsi-parasa commented Oct 15, 2021

vamsi-parasa commented Oct 19, 2021

sviswa7 commented Oct 20, 2021

sviswa7 commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

openjdk bot commented Oct 20, 2021 • edited

vnkozlov left a comment

Choose a reason for hiding this comment

vnkozlov commented Oct 20, 2021

vamsi-parasa commented Oct 20, 2021

vamsi-parasa commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

sviswa7 commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

openjdk bot commented Oct 20, 2021

ijuma Oct 23, 2021 • edited by bridgekeeper bot

Choose a reason for hiding this comment

vamsi-parasa Nov 2, 2021

Choose a reason for hiding this comment

vamsi-parasa commented Oct 13, 2021 •

edited by openjdk bot

mlbridge bot commented Oct 15, 2021 •

edited

openjdk bot commented Oct 20, 2021 •

edited

ijuma Oct 23, 2021 •

edited by bridgekeeper bot