JDK-8273954 : Regression 8% on Mac and 6% Windows on MonteCarlo
  • Type: Bug
  • Component: hotspot
  • Sub-Component: compiler
  • Affected Version: 17,18
  • Priority: P3
  • Status: Open
  • Resolution: Unresolved
  • CPU: x86
  • Submitted: 2021-09-17
  • Updated: 2021-11-02
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 18
18Unresolved
Related Reports
Relates :  
JDK-8269575 - C2: assert(false) failed: graph should be schedulable after JDK-8252372
Relates :  
JDK-8268883 - C2: assert(false) failed: unscheduable graph
Description
For some reason the variability has not been so bad on Linux, it is a different Intel CPU to Windows, I don't see any specific reason why its different.
Comments
Roland, could you please have a look? Eric's analysis revealed that this was introduced by JDK-8268883 and probably got worse with JDK-8269575.
02-11-2021
ILW = performance regression, one benchmark (MonteCarlo) on Mac and Windows, no workaround = MMH = P3
20-09-2021