-
Type:
Enhancement
-
Resolution: Fixed
-
Priority:
P4
-
Affects Version/s: hs13
-
Component/s: hotspot
-
b02
-
x86
-
solaris_10
| Issue | Fix Version | Assignee | Priority | Status | Resolution | Resolved In Build |
|---|---|---|---|---|---|---|
| JDK-2177140 | 7 | Vladimir Kozlov | P3 | Closed | Fixed | b29 |
| JDK-2174938 | 6u14 | Vladimir Kozlov | P3 | Resolved | Fixed | b01 |
There is ~60% regression in monte_carlo due to not inlining
nextDouble() method and, as result, not (EA) scalarizing Random object.
The method is not inlinined since the size of its compiled
code > 1000 (inlining threshold) because of additional
encoding/decoding instructions.
nextDouble() method and, as result, not (EA) scalarizing Random object.
The method is not inlinined since the size of its compiled
code > 1000 (inlining threshold) because of additional
encoding/decoding instructions.
- backported by
-
JDK-2174938 Compressed Oops: reduce size of compiled methods
-
- Resolved
-
-
JDK-2177140 Compressed Oops: reduce size of compiled methods
-
- Closed
-
- relates to
-
JDK-8076985 Allocation path: biased locking + compressed oops code quality
-
- Resolved
-
-
JDK-6712872 Move some of narrow oops optimizations from final_graph_reshape to igvn
-
- Closed
-