JDK-8235288 : AVX 512 instructions inadvertently used on Xeon for small vector width operations
Type:Bug
Component:hotspot
Sub-Component:compiler
Affected Version:11.0.6,14
Priority:P3
Status:Resolved
Resolution:Fixed
CPU:x86
Submitted:2019-12-03
Updated:2022-06-27
Resolved:2019-12-04
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.
For vector replicate and reduction operations vinsert and vextract instructions are used. When UseAVX level is set to 3, these instructions are unnecessarily encoded with 512 bit vector width.
Comments
Fix request (13u):
The original change applies cleanly, passes tier1 and tier2 tests.
03-06-2020
Fix request (11u)
Small, minimal risk patch for parity with Oracle 11.0.7, applies cleanly.