-
Enhancement
-
Resolution: Fixed
-
P4
-
9, 10, 11, 12, 13
-
b07
Issue | Fix Version | Assignee | Priority | Status | Resolution | Resolved In Build |
---|---|---|---|---|---|---|
JDK-8078643 | 8u60 | Vladimir Ivanov | P4 | Closed | Won't Fix |
If you build the VM with JDK-8058968 included, and run the full suite of Nashorn/Octane with:
~/trunks/jdk9-dev/build/linux-x86_64-normal-server-release/images/j2sdk-image/bin/java -XX:+CITime -jar ~/trunks/jdk9-dev/build/linux-x86_64-normal-server-release/images/j2sdk-image/jre/lib/ext/nashorn.jar -Dnashorn.typeInfo.disabled=false --class-cache-size=0 --persistent-code-cache=false -scripting --log=time test/script/basic/run-octane.js -- --iterations 1
Then you will see this output:
http://cr.openjdk.java.net/~shade/8058968/new-output-2.txt
Notice how much time Incremental Inlining consumes:
Total compilation time : 480.712 s
C2 Compile Time: 376.791 s
Incremental Inline: 84.199 s
IdealLoop: 1.061 s
IGVN: 10.713 s
Inline: 28.659 s
Prune Useless: 43.611 s
Other: 0.155 s
This arguably has an effect on Nashorn warmup, and basically on how fast MH-heavy workloads ramp up.
~/trunks/jdk9-dev/build/linux-x86_64-normal-server-release/images/j2sdk-image/bin/java -XX:+CITime -jar ~/trunks/jdk9-dev/build/linux-x86_64-normal-server-release/images/j2sdk-image/jre/lib/ext/nashorn.jar -Dnashorn.typeInfo.disabled=false --class-cache-size=0 --persistent-code-cache=false -scripting --log=time test/script/basic/run-octane.js -- --iterations 1
Then you will see this output:
http://cr.openjdk.java.net/~shade/8058968/new-output-2.txt
Notice how much time Incremental Inlining consumes:
Total compilation time : 480.712 s
C2 Compile Time: 376.791 s
Incremental Inline: 84.199 s
IdealLoop: 1.061 s
IGVN: 10.713 s
Inline: 28.659 s
Prune Useless: 43.611 s
Other: 0.155 s
This arguably has an effect on Nashorn warmup, and basically on how fast MH-heavy workloads ramp up.
- backported by
-
JDK-8078643 C2: Excessive RemoveUseless passes during incremental inlining
- Closed
- blocks
-
JDK-8059760 VM/JDK fixes for Nashorn performance (warmup/footprint, indy)
- Open
- is blocked by
-
JDK-8217782 Spill detection broken after JDK-8217716
- Resolved
- relates to
-
JDK-8221592 C2 compilation failed with assert(!q->is_MergeMem())
- Closed
-
JDK-8223581 C2 compilation failed with assert(!q->is_MergeMem())
- Closed
-
JDK-8143321 Reduce the C2 compiler's memory usage
- Closed
(1 relates to)