JDK-8349100 : Regression >3% with J2dBench-vimg_text_aa across all of 24
  • Type: Bug
  • Component: performance
  • Affected Version: 24
  • Priority: P4
  • Status: Open
  • Resolution: Unresolved
  • OS: windows
  • CPU: x86_64
  • Submitted: 2025-01-30
  • Updated: 2025-03-03
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.
JDK 25
25Unresolved
Description
It seems like "death by a thousand cuts" with small regressions in many promo builds. I will keep doing isolation runs, and feel free to assign this back to me, but if anyone in the j2d team has any ideas, please add them. Happens both with -G1 and -ParGC runs.
Comments
I have no idea. These don't map to client changes. People may be trying optimisations elsewhere that look good in some benchmarks but negatively affect these .. or they could be side effects of functional fixes / changes.
03-03-2025