JDK-8188165 : PPC64: Optimize Unsafe.copyMemory and arraycopy
  • Type: Bug
  • Component: hotspot
  • Sub-Component: compiler
  • Affected Version: 8,9,10,17
  • Priority: P4
  • Status: Open
  • Resolution: Unresolved
  • OS: linux
  • CPU: ppc
  • Submitted: 2017-09-29
  • Updated: 2021-08-17
The Version table provides details related to the release that this issue/RFE will be addressed.

Unresolved : Release in which this issue/RFE will be addressed.
Resolved: Release in which this issue/RFE has been resolved.
Fixed : Release in which this issue/RFE has been fixed. The release containing this fix may be available for download as an Early Access Release or a General Availability Release.

To download the current JDK release, click here.
Other
tbdUnresolved
Related Reports
Relates :  
Description
This is specific to PPC64LE only.

The emphasis in the proposed code is on minimizing branches.  Thus, this code makes no attempt to avoid misaligned accesses and each block is designed to copy as many elements as possible.

As one data point, this yields as much as a 13x improvement in jbyte_disjoint_arraycopy for certain misaligned scenarios.
Comments
Hi Rahul, I'm re-spinning the review for Matt's change (Review thread: http://mail.openjdk.java.net/pipermail/hotspot-dev/2017-October/028629.html). Martin already commented some points to improve and I performed an initial test using SPECjbb2015. I'm not sure if Matt will be able to address it right now. Either way I intend to build upon Matt's first proposal and send a v2. Hence I would like to keep it tagged for OpenJDK 11. Thanks.
24-04-2018

Hi [~mbrandy], Request your help. Are you planning to get the fix in for this bug task, for JDK 11? If not, please change the 'Fix Version' to tbd_feature / tbd_update. Thank you. (JDK 11 Schedule - http://openjdk.java.net/projects/jdk/11/)
24-04-2018

Hi [~mbrandy], Please note targeting this task to 11 for now. Please update Fix Version if this is incorrect. Thanks.
01-12-2017