-
Enhancement
-
Resolution: Fixed
-
P4
-
19
-
b26
-
x86
~20% regression in SPECjvm2008 mpegaudio sub benchmark is observed on Cascade Lake with Default vs -XX:UseAVX=2.
The performance of all the other non-startup sub benchmarks of SPECjvm2008 is within +/- 5%.
The performance regression is due to auto-vectorization of small loops.
We don’t have AVX3Threshold consideration in auto-vectorization.
The performance regression in mpegaudio can be recovered by limiting auto-vectorization to 32-byte vectors.
The performance of all the other non-startup sub benchmarks of SPECjvm2008 is within +/- 5%.
The performance regression is due to auto-vectorization of small loops.
We don’t have AVX3Threshold consideration in auto-vectorization.
The performance regression in mpegaudio can be recovered by limiting auto-vectorization to 32-byte vectors.
- relates to
-
JDK-8287980 Build is broken due to SuperWordMaxVectorSize when C2 is disabled after JDK-8287697
-
- Resolved
-
-
JDK-8311911 C2 Superword does not honor AVX3Threshold
-
- Open
-
-
JDK-8304301 Remove the global option SuperWordMaxVectorSize
-
- Resolved
-